Merge commit 'upstream/2011.10.19'

[youtubedl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 48c13b701cce6d13382eae08e84b25cf60396600..3a37fae2eb19769886f897090dbd28e397ee3d21 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -1,10 +1,29 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-

-# Author: Ricardo Garcia Gonzalez
-# Author: Danny Colligan
-# Author: Benjamin Johnson
-# License: Public domain code
+
+__author__  = (
+       'Ricardo Garcia Gonzalez',
+       'Danny Colligan',
+       'Benjamin Johnson',
+       'Vasyl\' Vavrychuk',
+       'Witold Baryluk',
+       'Paweł Paprota',
+       'Gergely Imreh',
+       'Rogério Brito',
+       'Philipp Hagemeister',
+       'Sören Schulze',
+       )
+
+__license__ = 'Public Domain'
+__version__ = '2011.10.19'
+
+UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
+
+import cookielib
+import datetime
+import gzip

 import htmlentitydefs
 import htmlentitydefs

+import HTMLParser

 import httplib
 import locale
 import math
 import httplib
 import locale
 import math


@@ -19,6 +38,20 @@ import sys
 import time
 import urllib
 import urllib2
 import time
 import urllib
 import urllib2

+import warnings
+import zlib
+
+if os.name == 'nt':
+       import ctypes
+
+try:
+       import email.utils
+except ImportError: # Python 2.4
+       import email.Utils
+try:
+       import cStringIO as StringIO
+except ImportError:
+       import StringIO

 
 # parse_qs was moved from the cgi module to the urlparse module recently.
 try:
 
 # parse_qs was moved from the cgi module to the urlparse module recently.
 try:


@@ -26,15 +59,139 @@ try:
 except ImportError:
        from cgi import parse_qs
 
 except ImportError:
        from cgi import parse_qs
 

+try:
+       import lxml.etree
+except ImportError:
+       pass # Handled below
+
+try:
+       import xml.etree.ElementTree
+except ImportError: # Python<2.5: Not officially supported, but let it slip
+       warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.')
+

 std_headers = {
 std_headers = {

-       'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.7) Gecko/20100720 Firefox/3.6.7',
+       'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',

        'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
        'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',

+       'Accept-Encoding': 'gzip, deflate',

        'Accept-Language': 'en-us,en;q=0.5',
 }
 
 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
 
        'Accept-Language': 'en-us,en;q=0.5',
 }
 
 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
 

+try:
+       import json
+except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
+       import re
+       class json(object):
+               @staticmethod
+               def loads(s):
+                       s = s.decode('UTF-8')
+                       def raiseError(msg, i):
+                               raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]))
+                       def skipSpace(i, expectMore=True):
+                               while i < len(s) and s[i] in ' \t\r\n':
+                                       i += 1
+                               if expectMore:
+                                       if i >= len(s):
+                                               raiseError('Premature end', i)
+                               return i
+                       def decodeEscape(match):
+                               esc = match.group(1)
+                               _STATIC = {
+                                       '"': '"',
+                                       '\\': '\\',
+                                       '/': '/',
+                                       'b': unichr(0x8),
+                                       'f': unichr(0xc),
+                                       'n': '\n',
+                                       'r': '\r',
+                                       't': '\t',
+                               }
+                               if esc in _STATIC:
+                                       return _STATIC[esc]
+                               if esc[0] == 'u':
+                                       if len(esc) == 1+4:
+                                               return unichr(int(esc[1:5], 16))
+                                       if len(esc) == 5+6 and esc[5:7] == '\\u':
+                                               hi = int(esc[1:5], 16)
+                                               low = int(esc[7:11], 16)
+                                               return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000)
+                               raise ValueError('Unknown escape ' + str(esc))
+                       def parseString(i):
+                               i += 1
+                               e = i
+                               while True:
+                                       e = s.index('"', e)
+                                       bslashes = 0
+                                       while s[e-bslashes-1] == '\\':
+                                               bslashes += 1
+                                       if bslashes % 2 == 1:
+                                               e += 1
+                                               continue
+                                       break
+                               rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)')
+                               stri = rexp.sub(decodeEscape, s[i:e])
+                               return (e+1,stri)
+                       def parseObj(i):
+                               i += 1
+                               res = {}
+                               i = skipSpace(i)
+                               if s[i] == '}': # Empty dictionary
+                                       return (i+1,res)
+                               while True:
+                                       if s[i] != '"':
+                                               raiseError('Expected a string object key', i)
+                                       i,key = parseString(i)
+                                       i = skipSpace(i)
+                                       if i >= len(s) or s[i] != ':':
+                                               raiseError('Expected a colon', i)
+                                       i,val = parse(i+1)
+                                       res[key] = val
+                                       i = skipSpace(i)
+                                       if s[i] == '}':
+                                               return (i+1, res)
+                                       if s[i] != ',':
+                                               raiseError('Expected comma or closing curly brace', i)
+                                       i = skipSpace(i+1)
+                       def parseArray(i):
+                               res = []
+                               i = skipSpace(i+1)
+                               if s[i] == ']': # Empty array
+                                       return (i+1,res)
+                               while True:
+                                       i,val = parse(i)
+                                       res.append(val)
+                                       i = skipSpace(i) # Raise exception if premature end
+                                       if s[i] == ']':
+                                               return (i+1, res)
+                                       if s[i] != ',':
+                                               raiseError('Expected a comma or closing bracket', i)
+                                       i = skipSpace(i+1)
+                       def parseDiscrete(i):
+                               for k,v in {'true': True, 'false': False, 'null': None}.items():
+                                       if s.startswith(k, i):
+                                               return (i+len(k), v)
+                               raiseError('Not a boolean (or null)', i)
+                       def parseNumber(i):
+                               mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:])
+                               if mobj is None:
+                                       raiseError('Not a number', i)
+                               nums = mobj.group(1)
+                               if '.' in nums or 'e' in nums or 'E' in nums:
+                                       return (i+len(nums), float(nums))
+                               return (i+len(nums), int(nums))
+                       CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete}
+                       def parse(i):
+                               i = skipSpace(i)
+                               i,res = CHARMAP.get(s[i], parseNumber)(i)
+                               i = skipSpace(i, False)
+                               return (i,res)
+                       i,res = parse(0)
+                       if i < len(s):
+                               raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')')
+                       return res
+

 def preferredencoding():
        """Get preferred encoding.
 
 def preferredencoding():
        """Get preferred encoding.
 


@@ -51,9 +208,10 @@ def preferredencoding():
                        yield pref
        return yield_preferredencoding().next()
 
                        yield pref
        return yield_preferredencoding().next()
 

+

 def htmlentity_transform(matchobj):
        """Transforms an HTML entity to a Unicode character.
 def htmlentity_transform(matchobj):
        """Transforms an HTML entity to a Unicode character.

-       
+

        This function receives a match object and is intended to be used with
        the re.sub() function.
        """
        This function receives a match object and is intended to be used with
        the re.sub() function.
        """


@@ -77,11 +235,13 @@ def htmlentity_transform(matchobj):
        # Unknown entity in name, return its literal representation
        return (u'&%s;' % entity)
 
        # Unknown entity in name, return its literal representation
        return (u'&%s;' % entity)
 

+

 def sanitize_title(utitle):
        """Sanitizes a video title so it could be used as part of a filename."""
        utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
        return utitle.replace(unicode(os.sep), u'%')
 
 def sanitize_title(utitle):
        """Sanitizes a video title so it could be used as part of a filename."""
        utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
        return utitle.replace(unicode(os.sep), u'%')
 

+

 def sanitize_open(filename, open_mode):
        """Try to open the given filename, and slightly tweak it if this fails.
 
 def sanitize_open(filename, open_mode):
        """Try to open the given filename, and slightly tweak it if this fails.
 


@@ -94,6 +254,9 @@ def sanitize_open(filename, open_mode):
        """
        try:
                if filename == u'-':
        """
        try:
                if filename == u'-':

+                       if sys.platform == 'win32':
+                               import msvcrt
+                               msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)

                        return (sys.stdout, filename)
                stream = open(filename, open_mode)
                return (stream, filename)
                        return (sys.stdout, filename)
                stream = open(filename, open_mode)
                return (stream, filename)


@@ -106,15 +269,25 @@ def sanitize_open(filename, open_mode):
                return (stream, filename)
 
 
                return (stream, filename)
 
 

+def timeconvert(timestr):
+       """Convert RFC 2822 defined time string into system timestamp"""
+       timestamp = None
+       timetuple = email.utils.parsedate_tz(timestr)
+       if timetuple is not None:
+               timestamp = email.utils.mktime_tz(timetuple)
+       return timestamp
+
+

 class DownloadError(Exception):
        """Download Error exception.
 class DownloadError(Exception):
        """Download Error exception.

-       
+

        This exception may be thrown by FileDownloader objects if they are not
        configured to continue on errors. They will contain the appropriate
        error message.
        """
        pass
 
        This exception may be thrown by FileDownloader objects if they are not
        configured to continue on errors. They will contain the appropriate
        error message.
        """
        pass
 

+

 class SameFileError(Exception):
        """Same File exception.
 
 class SameFileError(Exception):
        """Same File exception.
 


@@ -123,6 +296,7 @@ class SameFileError(Exception):
        """
        pass
 
        """
        pass
 

+

 class PostProcessingError(Exception):
        """Post Processing exception.
 
 class PostProcessingError(Exception):
        """Post Processing exception.
 


@@ -131,6 +305,7 @@ class PostProcessingError(Exception):
        """
        pass
 
        """
        pass
 

+

 class UnavailableVideoError(Exception):
        """Unavailable Format exception.
 
 class UnavailableVideoError(Exception):
        """Unavailable Format exception.
 


@@ -139,6 +314,7 @@ class UnavailableVideoError(Exception):
        """
        pass
 
        """
        pass
 

+

 class ContentTooShortError(Exception):
        """Content Too Short exception.
 
 class ContentTooShortError(Exception):
        """Content Too Short exception.
 


@@ -154,6 +330,66 @@ class ContentTooShortError(Exception):
                self.downloaded = downloaded
                self.expected = expected
 
                self.downloaded = downloaded
                self.expected = expected
 

+
+class YoutubeDLHandler(urllib2.HTTPHandler):
+       """Handler for HTTP requests and responses.
+
+       This class, when installed with an OpenerDirector, automatically adds
+       the standard headers to every HTTP request and handles gzipped and
+       deflated responses from web servers. If compression is to be avoided in
+       a particular request, the original request in the program code only has
+       to include the HTTP header "Youtubedl-No-Compression", which will be
+       removed before making the real request.
+
+       Part of this code was copied from:
+
+       http://techknack.net/python-urllib2-handlers/
+
+       Andrew Rowls, the author of that code, agreed to release it to the
+       public domain.
+       """
+
+       @staticmethod
+       def deflate(data):
+               try:
+                       return zlib.decompress(data, -zlib.MAX_WBITS)
+               except zlib.error:
+                       return zlib.decompress(data)
+
+       @staticmethod
+       def addinfourl_wrapper(stream, headers, url, code):
+               if hasattr(urllib2.addinfourl, 'getcode'):
+                       return urllib2.addinfourl(stream, headers, url, code)
+               ret = urllib2.addinfourl(stream, headers, url)
+               ret.code = code
+               return ret
+
+       def http_request(self, req):
+               for h in std_headers:
+                       if h in req.headers:
+                               del req.headers[h]
+                       req.add_header(h, std_headers[h])
+               if 'Youtubedl-no-compression' in req.headers:
+                       if 'Accept-encoding' in req.headers:
+                               del req.headers['Accept-encoding']
+                       del req.headers['Youtubedl-no-compression']
+               return req
+
+       def http_response(self, req, resp):
+               old_resp = resp
+               # gzip
+               if resp.headers.get('Content-encoding', '') == 'gzip':
+                       gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
+                       resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
+                       resp.msg = old_resp.msg
+               # deflate
+               if resp.headers.get('Content-encoding', '') == 'deflate':
+                       gz = StringIO.StringIO(self.deflate(resp.read()))
+                       resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
+                       resp.msg = old_resp.msg
+               return resp
+
+

 class FileDownloader(object):
        """File Downloader class.
 
 class FileDownloader(object):
        """File Downloader class.
 


@@ -181,22 +417,35 @@ class FileDownloader(object):
 
        Available options:
 
 
        Available options:
 

-       username:       Username for authentication purposes.
-       password:       Password for authentication purposes.
-       usenetrc:       Use netrc for authentication instead.
-       quiet:          Do not print messages to stdout.
-       forceurl:       Force printing final URL.
-       forcetitle:     Force printing title.
-       simulate:       Do not download the video files.
-       format:         Video format code.
-       format_limit:   Highest quality format to try.
-       outtmpl:        Template for output names.
-       ignoreerrors:   Do not stop on download errors.
-       ratelimit:      Download speed limit, in bytes/sec.
-       nooverwrites:   Prevent overwriting files.
-       retries:        Number of times to retry for HTTP error 503
-       continuedl:     Try to continue downloads if possible.
-       noprogress:     Do not print the progress bar.
+       username:         Username for authentication purposes.
+       password:         Password for authentication purposes.
+       usenetrc:         Use netrc for authentication instead.
+       quiet:            Do not print messages to stdout.
+       forceurl:         Force printing final URL.
+       forcetitle:       Force printing title.
+       forcethumbnail:   Force printing thumbnail URL.
+       forcedescription: Force printing description.
+       forcefilename:    Force printing final filename.
+       simulate:         Do not download the video files.
+       format:           Video format code.
+       format_limit:     Highest quality format to try.
+       outtmpl:          Template for output names.
+       ignoreerrors:     Do not stop on download errors.
+       ratelimit:        Download speed limit, in bytes/sec.
+       nooverwrites:     Prevent overwriting files.
+       retries:          Number of times to retry for HTTP error 5xx
+       continuedl:       Try to continue downloads if possible.
+       noprogress:       Do not print the progress bar.
+       playliststart:    Playlist item to start at.
+       playlistend:      Playlist item to end at.
+       matchtitle:       Download only matching titles.
+       rejecttitle:      Reject downloads for matching titles.
+       logtostderr:      Log messages to stderr instead of stdout.
+       consoletitle:     Display progress in console window's titlebar.
+       nopart:           Do not use temporary .part files.
+       updatetime:       Use the Last-modified header to set output file timestamps.
+       writedescription: Write the video description to a .description file
+       writeinfojson:    Write the video description to a .info.json file

        """
 
        params = None
        """
 
        params = None


@@ -204,6 +453,7 @@ class FileDownloader(object):
        _pps = []
        _download_retcode = None
        _num_downloads = None
        _pps = []
        _download_retcode = None
        _num_downloads = None

+       _screen_file = None

 
        def __init__(self, params):
                """Create a FileDownloader object with the given options."""
 
        def __init__(self, params):
                """Create a FileDownloader object with the given options."""


@@ -211,18 +461,9 @@ class FileDownloader(object):
                self._pps = []
                self._download_retcode = 0
                self._num_downloads = 0
                self._pps = []
                self._download_retcode = 0
                self._num_downloads = 0

+               self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]

                self.params = params
                self.params = params

-       
-       @staticmethod
-       def pmkdir(filename):
-               """Create directory components in filename. Similar to Unix "mkdir -p"."""
-               components = filename.split(os.sep)
-               aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
-               aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
-               for dir in aggregate:
-                       if not os.path.exists(dir):
-                               os.mkdir(dir)
-       
+

        @staticmethod
        def format_bytes(bytes):
                if bytes is None:
        @staticmethod
        def format_bytes(bytes):
                if bytes is None:


@@ -234,7 +475,7 @@ class FileDownloader(object):
                else:
                        exponent = long(math.log(bytes, 1024.0))
                suffix = 'bkMGTPEZY'[exponent]
                else:
                        exponent = long(math.log(bytes, 1024.0))
                suffix = 'bkMGTPEZY'[exponent]

-               converted = float(bytes) / float(1024**exponent)
+               converted = float(bytes) / float(1024 ** exponent)

                return '%.2f%s' % (converted, suffix)
 
        @staticmethod
                return '%.2f%s' % (converted, suffix)
 
        @staticmethod


@@ -287,40 +528,42 @@ class FileDownloader(object):
                multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
                return long(round(number * multiplier))
 
                multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
                return long(round(number * multiplier))
 

-       @staticmethod
-       def verify_url(url):
-               """Verify a URL is valid and data could be downloaded. Return real data URL."""
-               request = urllib2.Request(url, None, std_headers)
-               data = urllib2.urlopen(request)
-               data.read(1)
-               url = data.geturl()
-               data.close()
-               return url
-

        def add_info_extractor(self, ie):
                """Add an InfoExtractor object to the end of the list."""
                self._ies.append(ie)
                ie.set_downloader(self)
        def add_info_extractor(self, ie):
                """Add an InfoExtractor object to the end of the list."""
                self._ies.append(ie)
                ie.set_downloader(self)

-       
+

        def add_post_processor(self, pp):
                """Add a PostProcessor object to the end of the chain."""
                self._pps.append(pp)
                pp.set_downloader(self)
        def add_post_processor(self, pp):
                """Add a PostProcessor object to the end of the chain."""
                self._pps.append(pp)
                pp.set_downloader(self)

-       
-       def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False):
+
+       def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):

                """Print message to stdout if not in quiet mode."""
                try:
                        if not self.params.get('quiet', False):
                """Print message to stdout if not in quiet mode."""
                try:
                        if not self.params.get('quiet', False):

-                               print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
-                       sys.stdout.flush()
+                               terminator = [u'\n', u''][skip_eol]
+                               print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
+                       self._screen_file.flush()

                except (UnicodeEncodeError), err:
                        if not ignore_encoding_errors:
                                raise
                except (UnicodeEncodeError), err:
                        if not ignore_encoding_errors:
                                raise

-       
+

        def to_stderr(self, message):
                """Print message to stderr."""
                print >>sys.stderr, message.encode(preferredencoding())
        def to_stderr(self, message):
                """Print message to stderr."""
                print >>sys.stderr, message.encode(preferredencoding())

-       
+
+       def to_cons_title(self, message):
+               """Set console/terminal window title to message."""
+               if not self.params.get('consoletitle', False):
+                       return
+               if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
+                       # c_wchar_p() might not be necessary if `message` is
+                       # already of type unicode()
+                       ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
+               elif 'TERM' in os.environ:
+                       sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding()))
+

        def fixed_template(self):
                """Checks if the output template is fixed."""
                return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
        def fixed_template(self):
                """Checks if the output template is fixed."""
                return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)


@@ -351,104 +594,204 @@ class FileDownloader(object):
                if speed > rate_limit:
                        time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
 
                if speed > rate_limit:
                        time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
 

+       def temp_name(self, filename):
+               """Returns a temporary filename for the given filename."""
+               if self.params.get('nopart', False) or filename == u'-' or \
+                               (os.path.exists(filename) and not os.path.isfile(filename)):
+                       return filename
+               return filename + u'.part'
+
+       def undo_temp_name(self, filename):
+               if filename.endswith(u'.part'):
+                       return filename[:-len(u'.part')]
+               return filename
+
+       def try_rename(self, old_filename, new_filename):
+               try:
+                       if old_filename == new_filename:
+                               return
+                       os.rename(old_filename, new_filename)
+               except (IOError, OSError), err:
+                       self.trouble(u'ERROR: unable to rename file')
+
+       def try_utime(self, filename, last_modified_hdr):
+               """Try to set the last-modified time of the given file."""
+               if last_modified_hdr is None:
+                       return
+               if not os.path.isfile(filename):
+                       return
+               timestr = last_modified_hdr
+               if timestr is None:
+                       return
+               filetime = timeconvert(timestr)
+               if filetime is None:
+                       return filetime
+               try:
+                       os.utime(filename, (time.time(), filetime))
+               except:
+                       pass
+               return filetime
+
+       def report_writedescription(self, descfn):
+               """ Report that the description file is being written """
+               self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True)
+
+       def report_writeinfojson(self, infofn):
+               """ Report that the metadata file has been written """
+               self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True)
+

        def report_destination(self, filename):
                """Report destination filename."""
        def report_destination(self, filename):
                """Report destination filename."""

-               self.to_stdout(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
-       
+               self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
+

        def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
                """Report download progress."""
                if self.params.get('noprogress', False):
                        return
        def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
                """Report download progress."""
                if self.params.get('noprogress', False):
                        return

-               self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
+               self.to_screen(u'\r[download] %s of %s at %s ETA %s' %

                                (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
                                (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)

+               self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
+                               (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))

 
        def report_resuming_byte(self, resume_len):
 
        def report_resuming_byte(self, resume_len):

-               """Report attemtp to resume at given byte."""
-               self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
-       
+               """Report attempt to resume at given byte."""
+               self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
+

        def report_retry(self, count, retries):
        def report_retry(self, count, retries):

-               """Report retry in case of HTTP error 503"""
-               self.to_stdout(u'[download] Got HTTP error 503. Retrying (attempt %d of %d)...' % (count, retries))
-       
+               """Report retry in case of HTTP error 5xx"""
+               self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
+

        def report_file_already_downloaded(self, file_name):
                """Report file has already been fully downloaded."""
                try:
        def report_file_already_downloaded(self, file_name):
                """Report file has already been fully downloaded."""
                try:

-                       self.to_stdout(u'[download] %s has already been downloaded' % file_name)
+                       self.to_screen(u'[download] %s has already been downloaded' % file_name)

                except (UnicodeEncodeError), err:
                except (UnicodeEncodeError), err:

-                       self.to_stdout(u'[download] The file has already been downloaded')
-       
+                       self.to_screen(u'[download] The file has already been downloaded')
+

        def report_unable_to_resume(self):
                """Report it was impossible to resume download."""
        def report_unable_to_resume(self):
                """Report it was impossible to resume download."""

-               self.to_stdout(u'[download] Unable to resume')
-       
+               self.to_screen(u'[download] Unable to resume')
+

        def report_finish(self):
                """Report download finished."""
                if self.params.get('noprogress', False):
        def report_finish(self):
                """Report download finished."""
                if self.params.get('noprogress', False):

-                       self.to_stdout(u'[download] Download completed')
+                       self.to_screen(u'[download] Download completed')

                else:
                else:

-                       self.to_stdout(u'')
-       
+                       self.to_screen(u'')
+

        def increment_downloads(self):
                """Increment the ordinal that assigns a number to each file."""
                self._num_downloads += 1
 
        def increment_downloads(self):
                """Increment the ordinal that assigns a number to each file."""
                self._num_downloads += 1
 

+       def prepare_filename(self, info_dict):
+               """Generate the output filename."""
+               try:
+                       template_dict = dict(info_dict)
+                       template_dict['epoch'] = unicode(long(time.time()))
+                       template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
+                       filename = self.params['outtmpl'] % template_dict
+                       return filename
+               except (ValueError, KeyError), err:
+                       self.trouble(u'ERROR: invalid system charset or erroneous output template')
+                       return None
+

        def process_info(self, info_dict):
                """Process a single dictionary returned by an InfoExtractor."""
        def process_info(self, info_dict):
                """Process a single dictionary returned by an InfoExtractor."""

+               filename = self.prepare_filename(info_dict)
+               
+               # Forced printings
+               if self.params.get('forcetitle', False):
+                       print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forceurl', False):
+                       print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
+                       print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forcedescription', False) and 'description' in info_dict:
+                       print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forcefilename', False) and filename is not None:
+                       print filename.encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forceformat', False):
+                       print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')
+

                # Do nothing else if in simulate mode
                if self.params.get('simulate', False):
                # Do nothing else if in simulate mode
                if self.params.get('simulate', False):

-                       # Verify URL if it's an HTTP one
-                       if info_dict['url'].startswith('http'):
-                               try:
-                                       self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
-                               except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
-                                       raise UnavailableVideoError
+                       return

 
 

-                       # Forced printings
-                       if self.params.get('forcetitle', False):
-                               print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
-                       if self.params.get('forceurl', False):
-                               print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
-                       if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
-                               print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
-                       if self.params.get('forcedescription', False) and 'description' in info_dict:
-                               print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if filename is None:
+                       return

 
 

+               matchtitle=self.params.get('matchtitle',False)
+               rejecttitle=self.params.get('rejecttitle',False)
+               title=info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
+                       self.to_screen(u'[download] "%s" title did not match pattern "%s"' % (title, matchtitle))
+                       return
+               if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
+                       self.to_screen(u'[download] "%s" title matched reject pattern "%s"' % (title, rejecttitle))

                        return
                        
                        return
                        

-               try:
-                       template_dict = dict(info_dict)
-                       template_dict['epoch'] = unicode(long(time.time()))
-                       template_dict['ord'] = unicode('%05d' % self._num_downloads)
-                       filename = self.params['outtmpl'] % template_dict
-               except (ValueError, KeyError), err:
-                       self.trouble('ERROR: invalid output template or system charset: %s' % str(err))

                if self.params.get('nooverwrites', False) and os.path.exists(filename):
                if self.params.get('nooverwrites', False) and os.path.exists(filename):

-                       self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
+                       self.to_stderr(u'WARNING: file exists and will be skipped')

                        return
 
                try:
                        return
 
                try:

-                       self.pmkdir(filename)
+                       dn = os.path.dirname(filename)
+                       if dn != '' and not os.path.exists(dn):
+                               os.makedirs(dn)

                except (OSError, IOError), err:
                except (OSError, IOError), err:

-                       self.trouble('ERROR: unable to create directories: %s' % str(err))
+                       self.trouble(u'ERROR: unable to create directory ' + unicode(err))

                        return
 
                        return
 

-               try:
-                       success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
-               except (OSError, IOError), err:
-                       raise UnavailableVideoError
-               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-                       self.trouble('ERROR: unable to download video data: %s' % str(err))
-                       return
-               except (ContentTooShortError, ), err:
-                       self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
-                       return
+               if self.params.get('writedescription', False):
+                       try:
+                               descfn = filename + '.description'
+                               self.report_writedescription(descfn)
+                               descfile = open(descfn, 'wb')
+                               try:
+                                       descfile.write(info_dict['description'].encode('utf-8'))
+                               finally:
+                                       descfile.close()
+                       except (OSError, IOError):
+                               self.trouble(u'ERROR: Cannot write description file ' + descfn)
+                               return
+
+               if self.params.get('writeinfojson', False):
+                       infofn = filename + '.info.json'
+                       self.report_writeinfojson(infofn)
+                       try:
+                               json.dump
+                       except (NameError,AttributeError):
+                               self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
+                               return
+                       try:
+                               infof = open(infofn, 'wb')
+                               try:
+                                       json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
+                                       json.dump(json_info_dict, infof)
+                               finally:
+                                       infof.close()
+                       except (OSError, IOError):
+                               self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
+                               return

 
 

-               if success:
+               if not self.params.get('skip_download', False):

                        try:
                        try:

-                               self.post_process(filename, info_dict)
-                       except (PostProcessingError), err:
-                               self.trouble('ERROR: postprocessing: %s' % str(err))
+                               success = self._do_download(filename, info_dict)
+                       except (OSError, IOError), err:
+                               raise UnavailableVideoError
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self.trouble(u'ERROR: unable to download video data: %s' % str(err))
+                               return
+                       except (ContentTooShortError, ), err:
+                               self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))

                                return
                                return

+       
+                       if success:
+                               try:
+                                       self.post_process(filename, info_dict)
+                               except (PostProcessingError), err:
+                                       self.trouble(u'ERROR: postprocessing: %s' % str(err))
+                                       return

 
        def download(self, url_list):
                """Download a given list of URLs."""
 
        def download(self, url_list):
                """Download a given list of URLs."""


@@ -472,7 +815,7 @@ class FileDownloader(object):
                                break
 
                        if not suitable_found:
                                break
 
                        if not suitable_found:

-                               self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
+                               self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)

 
                return self._download_retcode
 
 
                return self._download_retcode
 


@@ -484,9 +827,10 @@ class FileDownloader(object):
                        info = pp.run(info)
                        if info is None:
                                break
                        info = pp.run(info)
                        if info is None:
                                break

-       
+

        def _download_with_rtmpdump(self, filename, url, player_url):
                self.report_destination(filename)
        def _download_with_rtmpdump(self, filename, url, player_url):
                self.report_destination(filename)

+               tmpfilename = self.temp_name(filename)

 
                # Check for rtmpdump first
                try:
 
                # Check for rtmpdump first
                try:


@@ -498,77 +842,120 @@ class FileDownloader(object):
                # Download using rtmpdump. rtmpdump returns exit code 2 when
                # the connection was interrumpted and resuming appears to be
                # possible. This is part of rtmpdump's normal usage, AFAIK.
                # Download using rtmpdump. rtmpdump returns exit code 2 when
                # the connection was interrumpted and resuming appears to be
                # possible. This is part of rtmpdump's normal usage, AFAIK.

-               basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', filename]
+               basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]

                retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
                while retval == 2 or retval == 1:
                retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
                while retval == 2 or retval == 1:

-                       prevsize = os.path.getsize(filename)
-                       self.to_stdout(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
+                       prevsize = os.path.getsize(tmpfilename)
+                       self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)

                        time.sleep(5.0) # This seems to be needed
                        retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
                        time.sleep(5.0) # This seems to be needed
                        retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])

-                       cursize = os.path.getsize(filename)
+                       cursize = os.path.getsize(tmpfilename)

                        if prevsize == cursize and retval == 1:
                                break
                        if prevsize == cursize and retval == 1:
                                break

+                        # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
+                       if prevsize == cursize and retval == 2 and cursize > 1024:
+                               self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
+                               retval = 0
+                               break

                if retval == 0:
                if retval == 0:

-                       self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
+                       self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
+                       self.try_rename(tmpfilename, filename)

                        return True
                else:
                        return True
                else:

-                       self.trouble('\nERROR: rtmpdump exited with code %d' % retval)
+                       self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)

                        return False
 
                        return False
 

-       def _do_download(self, filename, url, player_url):
+       def _do_download(self, filename, info_dict):
+               url = info_dict['url']
+               player_url = info_dict.get('player_url', None)
+
+               # Check file already present
+               if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
+                       self.report_file_already_downloaded(filename)
+                       return True
+

                # Attempt to download using rtmpdump
                if url.startswith('rtmp'):
                        return self._download_with_rtmpdump(filename, url, player_url)
 
                # Attempt to download using rtmpdump
                if url.startswith('rtmp'):
                        return self._download_with_rtmpdump(filename, url, player_url)
 

+               tmpfilename = self.temp_name(filename)

                stream = None
                stream = None

-               open_mode = 'wb'
-               basic_request = urllib2.Request(url, None, std_headers)
-               request = urllib2.Request(url, None, std_headers)
+
+               # Do not include the Accept-Encoding header
+               headers = {'Youtubedl-no-compression': 'True'}
+               basic_request = urllib2.Request(url, None, headers)
+               request = urllib2.Request(url, None, headers)

 
                # Establish possible resume length
 
                # Establish possible resume length

-               if os.path.isfile(filename):
-                       resume_len = os.path.getsize(filename)
+               if os.path.isfile(tmpfilename):
+                       resume_len = os.path.getsize(tmpfilename)

                else:
                        resume_len = 0
 
                else:
                        resume_len = 0
 

-               # Request parameters in case of being able to resume
-               if self.params.get('continuedl', False) and resume_len != 0:
-                       self.report_resuming_byte(resume_len)
-                       request.add_header('Range','bytes=%d-' % resume_len)
-                       open_mode = 'ab'
+               open_mode = 'wb'
+               if resume_len != 0:
+                       if self.params.get('continuedl', False):
+                               self.report_resuming_byte(resume_len)
+                               request.add_header('Range','bytes=%d-' % resume_len)
+                               open_mode = 'ab'
+                       else:
+                               resume_len = 0

 
                count = 0
                retries = self.params.get('retries', 0)
 
                count = 0
                retries = self.params.get('retries', 0)

-               while True:
+               while count <= retries:

                        # Establish connection
                        try:
                        # Establish connection
                        try:

+                               if count == 0 and 'urlhandle' in info_dict:
+                                       data = info_dict['urlhandle']

                                data = urllib2.urlopen(request)
                                break
                        except (urllib2.HTTPError, ), err:
                                data = urllib2.urlopen(request)
                                break
                        except (urllib2.HTTPError, ), err:

-                               if err.code == 503:
-                                       # Retry in case of HTTP error 503
-                                       count += 1
-                                       if count <= retries:
-                                               self.report_retry(count, retries)
-                                               continue
-                               if err.code != 416: #  416 is 'Requested range not satisfiable'
+                               if (err.code < 500 or err.code >= 600) and err.code != 416:
+                                       # Unexpected HTTP error

                                        raise
                                        raise

-                               # Unable to resume
-                               data = urllib2.urlopen(basic_request)
-                               content_length = data.info()['Content-Length']
-
-                               if content_length is not None and long(content_length) == resume_len:
-                                       # Because the file had already been fully downloaded
-                                       self.report_file_already_downloaded(filename)
-                                       return True
-                               else:
-                                       # Because the server didn't let us
-                                       self.report_unable_to_resume()
-                                       open_mode = 'wb'
+                               elif err.code == 416:
+                                       # Unable to resume (requested range not satisfiable)
+                                       try:
+                                               # Open the connection again without the range header
+                                               data = urllib2.urlopen(basic_request)
+                                               content_length = data.info()['Content-Length']
+                                       except (urllib2.HTTPError, ), err:
+                                               if err.code < 500 or err.code >= 600:
+                                                       raise
+                                       else:
+                                               # Examine the reported length
+                                               if (content_length is not None and
+                                                               (resume_len - 100 < long(content_length) < resume_len + 100)):
+                                                       # The file had already been fully downloaded.
+                                                       # Explanation to the above condition: in issue #175 it was revealed that
+                                                       # YouTube sometimes adds or removes a few bytes from the end of the file,
+                                                       # changing the file size slightly and causing problems for some users. So
+                                                       # I decided to implement a suggested change and consider the file
+                                                       # completely downloaded if the file size differs less than 100 bytes from
+                                                       # the one in the hard drive.
+                                                       self.report_file_already_downloaded(filename)
+                                                       self.try_rename(tmpfilename, filename)
+                                                       return True
+                                               else:
+                                                       # The length does not match, we start the download over
+                                                       self.report_unable_to_resume()
+                                                       open_mode = 'wb'
+                                                       break
+                       # Retry
+                       count += 1
+                       if count <= retries:
+                               self.report_retry(count, retries)
+
+               if count > retries:
+                       self.trouble(u'ERROR: giving up after %s retries' % retries)
+                       return False

 
                data_len = data.info().get('Content-length', None)
 
                data_len = data.info().get('Content-length', None)

+               if data_len is not None:
+                       data_len = long(data_len) + resume_len

                data_len_str = self.format_bytes(data_len)
                data_len_str = self.format_bytes(data_len)

-               byte_counter = 0
+               byte_counter = 0 + resume_len

                block_size = 1024
                start = time.time()
                while True:
                block_size = 1024
                start = time.time()
                while True:


@@ -576,39 +963,55 @@ class FileDownloader(object):
                        before = time.time()
                        data_block = data.read(block_size)
                        after = time.time()
                        before = time.time()
                        data_block = data.read(block_size)
                        after = time.time()

-                       data_block_len = len(data_block)
-                       if data_block_len == 0:
+                       if len(data_block) == 0:

                                break
                                break

-                       byte_counter += data_block_len
+                       byte_counter += len(data_block)

 
                        # Open file just in time
                        if stream is None:
                                try:
 
                        # Open file just in time
                        if stream is None:
                                try:

-                                       (stream, filename) = sanitize_open(filename, open_mode)
+                                       (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
+                                       assert stream is not None
+                                       filename = self.undo_temp_name(tmpfilename)

                                        self.report_destination(filename)
                                except (OSError, IOError), err:
                                        self.report_destination(filename)
                                except (OSError, IOError), err:

-                                       self.trouble('ERROR: unable to open for writing: %s' % str(err))
+                                       self.trouble(u'ERROR: unable to open for writing: %s' % str(err))

                                        return False
                        try:
                                stream.write(data_block)
                        except (IOError, OSError), err:
                                        return False
                        try:
                                stream.write(data_block)
                        except (IOError, OSError), err:

-                               self.trouble('\nERROR: unable to write data: %s' % str(err))
-                       block_size = self.best_block_size(after - before, data_block_len)
+                               self.trouble(u'\nERROR: unable to write data: %s' % str(err))
+                               return False
+                       block_size = self.best_block_size(after - before, len(data_block))

 
                        # Progress message
 
                        # Progress message

-                       percent_str = self.calc_percent(byte_counter, data_len)
-                       eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
-                       speed_str = self.calc_speed(start, time.time(), byte_counter)
-                       self.report_progress(percent_str, data_len_str, speed_str, eta_str)
+                       speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
+                       if data_len is None:
+                               self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
+                       else:
+                               percent_str = self.calc_percent(byte_counter, data_len)
+                               eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
+                               self.report_progress(percent_str, data_len_str, speed_str, eta_str)

 
                        # Apply rate limit
 
                        # Apply rate limit

-                       self.slow_down(start, byte_counter)
+                       self.slow_down(start, byte_counter - resume_len)

 
 

+               if stream is None:
+                       self.trouble(u'\nERROR: Did not get any data blocks')
+                       return False
+               stream.close()

                self.report_finish()
                self.report_finish()

-               if data_len is not None and str(byte_counter) != data_len:
+               if data_len is not None and byte_counter != data_len:

                        raise ContentTooShortError(byte_counter, long(data_len))
                        raise ContentTooShortError(byte_counter, long(data_len))

+               self.try_rename(tmpfilename, filename)
+
+               # Update file modification time
+               if self.params.get('updatetime', True):
+                       info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
+

                return True
 
                return True
 

+

 class InfoExtractor(object):
        """Information Extractor class.
 
 class InfoExtractor(object):
        """Information Extractor class.
 


@@ -639,9 +1042,8 @@ class InfoExtractor(object):
        description:    One-line video description.
 
        Subclasses of this one should re-define the _real_initialize() and
        description:    One-line video description.
 
        Subclasses of this one should re-define the _real_initialize() and

-       _real_extract() methods, as well as the suitable() static method.
-       Probably, they should also be instantiated and added to the main
-       downloader.
+       _real_extract() methods and define a _VALID_URL regexp.
+       Probably, they should also be added to the list of extractors.

        """
 
        _ready = False
        """
 
        _ready = False


@@ -652,10 +1054,9 @@ class InfoExtractor(object):
                self._ready = False
                self.set_downloader(downloader)
 
                self._ready = False
                self.set_downloader(downloader)
 

-       @staticmethod
-       def suitable(url):
+       def suitable(self, url):

                """Receives a URL and returns True if suitable for this IE."""
                """Receives a URL and returns True if suitable for this IE."""

-               return False
+               return re.match(self._VALID_URL, url) is not None

 
        def initialize(self):
                """Initializes an instance (authentication, etc)."""
 
        def initialize(self):
                """Initializes an instance (authentication, etc)."""


@@ -671,7 +1072,7 @@ class InfoExtractor(object):
        def set_downloader(self, downloader):
                """Sets the downloader for this IE."""
                self._downloader = downloader
        def set_downloader(self, downloader):
                """Sets the downloader for this IE."""
                self._downloader = downloader

-       
+

        def _real_initialize(self):
                """Real initialization process. Redefine in subclasses."""
                pass
        def _real_initialize(self):
                """Real initialization process. Redefine in subclasses."""
                pass


@@ -680,16 +1081,17 @@ class InfoExtractor(object):
                """Real extraction process. Redefine in subclasses."""
                pass
 
                """Real extraction process. Redefine in subclasses."""
                pass
 

+

 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 
 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 

-       _VALID_URL = r'^((?:http://)?(?:youtu\.be/|(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?[\?#](?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
+       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'

        _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
        _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'

-       _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
+       _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'

        _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
        _NETRC_MACHINE = 'youtube'
        # Listed in order of quality
        _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
        _NETRC_MACHINE = 'youtube'
        # Listed in order of quality

-       _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13']
+       _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']

        _video_extensions = {
                '13': '3gp',
                '17': 'mp4',
        _video_extensions = {
                '13': '3gp',
                '17': 'mp4',


@@ -698,45 +1100,63 @@ class YoutubeIE(InfoExtractor):
                '37': 'mp4',
                '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
                '43': 'webm',
                '37': 'mp4',
                '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
                '43': 'webm',

+               '44': 'webm',

                '45': 'webm',
        }
                '45': 'webm',
        }

-
-       @staticmethod
-       def suitable(url):
-               return (re.match(YoutubeIE._VALID_URL, url) is not None)
+       _video_dimensions = {
+               '5': '240x400',
+               '6': '???',
+               '13': '???',
+               '17': '144x176',
+               '18': '360x640',
+               '22': '720x1280',
+               '34': '360x640',
+               '35': '480x854',
+               '37': '1080x1920',
+               '38': '3072x4096',
+               '43': '360x640',
+               '44': '480x854',
+               '45': '720x1280',
+       }       
+       IE_NAME = u'youtube'

 
        def report_lang(self):
                """Report attempt to set language."""
 
        def report_lang(self):
                """Report attempt to set language."""

-               self._downloader.to_stdout(u'[youtube] Setting language')
+               self._downloader.to_screen(u'[youtube] Setting language')

 
        def report_login(self):
                """Report attempt to log in."""
 
        def report_login(self):
                """Report attempt to log in."""

-               self._downloader.to_stdout(u'[youtube] Logging in')
-       
+               self._downloader.to_screen(u'[youtube] Logging in')
+

        def report_age_confirmation(self):
                """Report attempt to confirm age."""
        def report_age_confirmation(self):
                """Report attempt to confirm age."""

-               self._downloader.to_stdout(u'[youtube] Confirming age')
-       
+               self._downloader.to_screen(u'[youtube] Confirming age')
+

        def report_video_webpage_download(self, video_id):
                """Report attempt to download video webpage."""
        def report_video_webpage_download(self, video_id):
                """Report attempt to download video webpage."""

-               self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
-       
+               self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
+

        def report_video_info_webpage_download(self, video_id):
                """Report attempt to download video info webpage."""
        def report_video_info_webpage_download(self, video_id):
                """Report attempt to download video info webpage."""

-               self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
-       
+               self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
+

        def report_information_extraction(self, video_id):
                """Report attempt to extract video information."""
        def report_information_extraction(self, video_id):
                """Report attempt to extract video information."""

-               self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
-       
+               self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
+

        def report_unavailable_format(self, video_id, format):
                """Report extracted video URL."""
        def report_unavailable_format(self, video_id, format):
                """Report extracted video URL."""

-               self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
-       
+               self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
+

        def report_rtmp_download(self):
                """Indicate the download will use the RTMP protocol."""
        def report_rtmp_download(self):
                """Indicate the download will use the RTMP protocol."""

-               self._downloader.to_stdout(u'[youtube] RTMP download detected')
-       
+               self._downloader.to_screen(u'[youtube] RTMP download detected')
+
+       def _print_formats(self, formats):
+               print 'Available formats:'
+               for x in formats:
+                       print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))
+

        def _real_initialize(self):
                if self._downloader is None:
                        return
        def _real_initialize(self):
                if self._downloader is None:
                        return


@@ -762,7 +1182,7 @@ class YoutubeIE(InfoExtractor):
                                return
 
                # Set language
                                return
 
                # Set language

-               request = urllib2.Request(self._LANG_URL, None, std_headers)
+               request = urllib2.Request(self._LANG_URL)

                try:
                        self.report_lang()
                        urllib2.urlopen(request).read()
                try:
                        self.report_lang()
                        urllib2.urlopen(request).read()


@@ -782,7 +1202,7 @@ class YoutubeIE(InfoExtractor):
                                'username':     username,
                                'password':     password,
                                }
                                'username':     username,
                                'password':     password,
                                }

-               request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
+               request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))

                try:
                        self.report_login()
                        login_results = urllib2.urlopen(request).read()
                try:
                        self.report_login()
                        login_results = urllib2.urlopen(request).read()


@@ -792,13 +1212,13 @@ class YoutubeIE(InfoExtractor):
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
                        return
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
                        return

-       
+

                # Confirm age
                age_form = {
                                'next_url':             '/',
                                'action_confirm':       'Confirm',
                                }
                # Confirm age
                age_form = {
                                'next_url':             '/',
                                'action_confirm':       'Confirm',
                                }

-               request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
+               request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form))

                try:
                        self.report_age_confirmation()
                        age_results = urllib2.urlopen(request).read()
                try:
                        self.report_age_confirmation()
                        age_results = urllib2.urlopen(request).read()


@@ -816,7 +1236,7 @@ class YoutubeIE(InfoExtractor):
 
                # Get video webpage
                self.report_video_webpage_download(video_id)
 
                # Get video webpage
                self.report_video_webpage_download(video_id)

-               request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers)
+               request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)

                try:
                        video_webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                try:
                        video_webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:


@@ -824,9 +1244,9 @@ class YoutubeIE(InfoExtractor):
                        return
 
                # Attempt to extract SWF player URL
                        return
 
                # Attempt to extract SWF player URL

-               mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage)
+               mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)

                if mobj is not None:
                if mobj is not None:

-                       player_url = mobj.group(1)
+                       player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))

                else:
                        player_url = None
 
                else:
                        player_url = None
 


@@ -834,8 +1254,8 @@ class YoutubeIE(InfoExtractor):
                self.report_video_info_webpage_download(video_id)
                for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
                        video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
                self.report_video_info_webpage_download(video_id)
                for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
                        video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'

-                                          % (video_id, el_type))
-                       request = urllib2.Request(video_info_url, None, std_headers)
+                                       % (video_id, el_type))
+                       request = urllib2.Request(video_info_url)

                        try:
                                video_info_webpage = urllib2.urlopen(request).read()
                                video_info = parse_qs(video_info_webpage)
                        try:
                                video_info_webpage = urllib2.urlopen(request).read()
                                video_info = parse_qs(video_info_webpage)


@@ -844,6 +1264,14 @@ class YoutubeIE(InfoExtractor):
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                                self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
                                return
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                                self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
                                return

+               if 'token' not in video_info:
+                       if 'reason' in video_info:
+                               self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8'))
+                       else:
+                               self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
+                       return
+
+               # Start extracting information

                self.report_information_extraction(video_id)
 
                # uploader
                self.report_information_extraction(video_id)
 
                # uploader


@@ -871,22 +1299,48 @@ class YoutubeIE(InfoExtractor):
                else:   # don't panic if we can't find it
                        video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
 
                else:   # don't panic if we can't find it
                        video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
 

+               # upload date
+               upload_date = u'NA'
+               mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
+               if mobj is not None:
+                       upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
+                       format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
+                       for expression in format_expressions:
+                               try:
+                                       upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
+                               except:
+                                       pass
+

                # description
                # description

-               video_description = 'No description available.'
-               if self._downloader.params.get('forcedescription', False):
-                       mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
-                       if mobj is not None:
-                               video_description = mobj.group(1)
+               try:
+                       lxml.etree
+               except NameError:
+                       video_description = u'No description available.'
+                       if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False):
+                               mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
+                               if mobj is not None:
+                                       video_description = mobj.group(1).decode('utf-8')
+               else:
+                       html_parser = lxml.etree.HTMLParser(encoding='utf-8')
+                       vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser)
+                       video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()'))
+                       # TODO use another parser

 
                # token
                video_token = urllib.unquote_plus(video_info['token'][0])
 
                # Decide which formats to download
 
                # token
                video_token = urllib.unquote_plus(video_info['token'][0])
 
                # Decide which formats to download

-               requested_format = self._downloader.params.get('format', None)
-               get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token)
+               req_format = self._downloader.params.get('format', None)
+
+               if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
+                       self.report_rtmp_download()
+                       video_url_list = [(None, video_info['conn'][0])]
+               elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
+                       url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
+                       url_data = [parse_qs(uds) for uds in url_data_strs]
+                       url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
+                       url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)

 
 

-               if 'fmt_url_map' in video_info:
-                       url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))

                        format_limit = self._downloader.params.get('format_limit', None)
                        if format_limit is not None and format_limit in self._available_formats:
                                format_list = self._available_formats[self._available_formats.index(format_limit):]
                        format_limit = self._downloader.params.get('format_limit', None)
                        if format_limit is not None and format_limit in self._available_formats:
                                format_list = self._available_formats[self._available_formats.index(format_limit):]


@@ -896,19 +1350,29 @@ class YoutubeIE(InfoExtractor):
                        if len(existing_formats) == 0:
                                self._downloader.trouble(u'ERROR: no known formats available for video')
                                return
                        if len(existing_formats) == 0:
                                self._downloader.trouble(u'ERROR: no known formats available for video')
                                return

-                       if requested_format is None:
-                               video_url_list = [(existing_formats[0], get_video_template % existing_formats[0])] # Best quality
-                       elif requested_format == '-1':
-                               video_url_list = [(f, get_video_template % f) for f in existing_formats] # All formats
+                       if self._downloader.params.get('listformats', None):
+                               self._print_formats(existing_formats)
+                               return
+                       if req_format is None or req_format == 'best':
+                               video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
+                       elif req_format == 'worst':
+                               video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
+                       elif req_format in ('-1', 'all'):
+                               video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats

                        else:
                        else:

-                               video_url_list = [(requested_format, get_video_template % requested_format)] # Specific format
-
-               elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
-                       self.report_rtmp_download()
-                       video_url_list = [(None, video_info['conn'][0])]
-
+                               # Specific formats. We pick the first in a slash-delimeted sequence.
+                               # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
+                               req_formats = req_format.split('/')
+                               video_url_list = None
+                               for rf in req_formats:
+                                       if rf in url_map:
+                                               video_url_list = [(rf, url_map[rf])]
+                                               break
+                               if video_url_list is None:
+                                       self._downloader.trouble(u'ERROR: requested format not available')
+                                       return

                else:
                else:

-                       self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
+                       self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')

                        return
 
                for format_param, video_real_url in video_url_list:
                        return
 
                for format_param, video_real_url in video_url_list:


@@ -918,23 +1382,23 @@ class YoutubeIE(InfoExtractor):
                        # Extension
                        video_extension = self._video_extensions.get(format_param, 'flv')
 
                        # Extension
                        video_extension = self._video_extensions.get(format_param, 'flv')
 

-                       # Find the video URL in fmt_url_map or conn paramters

                        try:
                                # Process video information
                                self._downloader.process_info({
                                        'id':           video_id.decode('utf-8'),
                                        'url':          video_real_url.decode('utf-8'),
                                        'uploader':     video_uploader.decode('utf-8'),
                        try:
                                # Process video information
                                self._downloader.process_info({
                                        'id':           video_id.decode('utf-8'),
                                        'url':          video_real_url.decode('utf-8'),
                                        'uploader':     video_uploader.decode('utf-8'),

+                                       'upload_date':  upload_date,

                                        'title':        video_title,
                                        'stitle':       simple_title,
                                        'ext':          video_extension.decode('utf-8'),
                                        'format':       (format_param is None and u'NA' or format_param.decode('utf-8')),
                                        'thumbnail':    video_thumbnail.decode('utf-8'),
                                        'title':        video_title,
                                        'stitle':       simple_title,
                                        'ext':          video_extension.decode('utf-8'),
                                        'format':       (format_param is None and u'NA' or format_param.decode('utf-8')),
                                        'thumbnail':    video_thumbnail.decode('utf-8'),

-                                       'description':  video_description.decode('utf-8'),
+                                       'description':  video_description,

                                        'player_url':   player_url,
                                })
                        except UnavailableVideoError, err:
                                        'player_url':   player_url,
                                })
                        except UnavailableVideoError, err:

-                               self._downloader.trouble(u'ERROR: unable to download video (format may not be available)')
+                               self._downloader.trouble(u'\nERROR: unable to download video')

 
 
 class MetacafeIE(InfoExtractor):
 
 
 class MetacafeIE(InfoExtractor):


@@ -944,34 +1408,31 @@ class MetacafeIE(InfoExtractor):
        _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
        _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
        _youtube_ie = None
        _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
        _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
        _youtube_ie = None

+       IE_NAME = u'metacafe'

 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(MetacafeIE._VALID_URL, url) is not None)
-

        def report_disclaimer(self):
                """Report disclaimer retrieval."""
        def report_disclaimer(self):
                """Report disclaimer retrieval."""

-               self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
+               self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')

 
        def report_age_confirmation(self):
                """Report attempt to confirm age."""
 
        def report_age_confirmation(self):
                """Report attempt to confirm age."""

-               self._downloader.to_stdout(u'[metacafe] Confirming age')
-       
+               self._downloader.to_screen(u'[metacafe] Confirming age')
+

        def report_download_webpage(self, video_id):
                """Report webpage download."""
        def report_download_webpage(self, video_id):
                """Report webpage download."""

-               self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
-       
+               self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
+

        def report_extraction(self, video_id):
                """Report information extraction."""
        def report_extraction(self, video_id):
                """Report information extraction."""

-               self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)

 
        def _real_initialize(self):
                # Retrieve disclaimer
 
        def _real_initialize(self):
                # Retrieve disclaimer

-               request = urllib2.Request(self._DISCLAIMER, None, std_headers)
+               request = urllib2.Request(self._DISCLAIMER)

                try:
                        self.report_disclaimer()
                        disclaimer = urllib2.urlopen(request).read()
                try:
                        self.report_disclaimer()
                        disclaimer = urllib2.urlopen(request).read()


@@ -984,14 +1445,14 @@ class MetacafeIE(InfoExtractor):
                        'filters': '0',
                        'submit': "Continue - I'm over 18",
                        }
                        'filters': '0',
                        'submit': "Continue - I'm over 18",
                        }

-               request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
+               request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form))

                try:
                        self.report_age_confirmation()
                        disclaimer = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
                        return
                try:
                        self.report_age_confirmation()
                        disclaimer = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
                        return

-       
+

        def _real_extract(self, url):
                # Extract id and simplified title from URL
                mobj = re.match(self._VALID_URL, url)
        def _real_extract(self, url):
                # Extract id and simplified title from URL
                mobj = re.match(self._VALID_URL, url)


@@ -1011,7 +1472,6 @@ class MetacafeIE(InfoExtractor):
                self._downloader.increment_downloads()
 
                simple_title = mobj.group(2).decode('utf-8')
                self._downloader.increment_downloads()
 
                simple_title = mobj.group(2).decode('utf-8')

-               video_extension = 'flv'

 
                # Retrieve video webpage to extract further information
                request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
 
                # Retrieve video webpage to extract further information
                request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)


@@ -1025,20 +1485,33 @@ class MetacafeIE(InfoExtractor):
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)
                mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)
                mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)

-               if mobj is None:
-                       self._downloader.trouble(u'ERROR: unable to extract media URL')
-                       return
-               mediaURL = urllib.unquote(mobj.group(1))
-
-               #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
-               #if mobj is None:
-               #       self._downloader.trouble(u'ERROR: unable to extract gdaKey')
-               #       return
-               #gdaKey = mobj.group(1)
-               #
-               #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+               if mobj is not None:
+                       mediaURL = urllib.unquote(mobj.group(1))
+                       video_extension = mediaURL[-3:]

 
 

-               video_url = mediaURL
+                       # Extract gdaKey if available
+                       mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+                       if mobj is None:
+                               video_url = mediaURL
+                       else:
+                               gdaKey = mobj.group(1)
+                               video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+               else:
+                       mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: unable to extract media URL')
+                               return
+                       vardict = parse_qs(mobj.group(1))
+                       if 'mediaData' not in vardict:
+                               self._downloader.trouble(u'ERROR: unable to extract media URL')
+                               return
+                       mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: unable to extract media URL')
+                               return
+                       mediaURL = mobj.group(1).replace('\\/', '/')
+                       video_extension = mediaURL[-3:]
+                       video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))

 
                mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
                if mobj is None:
 
                mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
                if mobj is None:


@@ -1059,6 +1532,7 @@ class MetacafeIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),


@@ -1066,28 +1540,25 @@ class MetacafeIE(InfoExtractor):
                                'player_url':   None,
                        })
                except UnavailableVideoError:
                                'player_url':   None,
                        })
                except UnavailableVideoError:

-                       self._downloader.trouble(u'ERROR: unable to download video')
+                       self._downloader.trouble(u'\nERROR: unable to download video')

 
 
 class DailymotionIE(InfoExtractor):
        """Information Extractor for Dailymotion"""
 
        _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
 
 
 class DailymotionIE(InfoExtractor):
        """Information Extractor for Dailymotion"""
 
        _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'

+       IE_NAME = u'dailymotion'

 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(DailymotionIE._VALID_URL, url) is not None)
-

        def report_download_webpage(self, video_id):
                """Report webpage download."""
        def report_download_webpage(self, video_id):
                """Report webpage download."""

-               self._downloader.to_stdout(u'[dailymotion] %s: Downloading webpage' % video_id)
-       
+               self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
+

        def report_extraction(self, video_id):
                """Report information extraction."""
        def report_extraction(self, video_id):
                """Report information extraction."""

-               self._downloader.to_stdout(u'[dailymotion] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)

 
        def _real_initialize(self):
                return
 
        def _real_initialize(self):
                return


@@ -1108,6 +1579,7 @@ class DailymotionIE(InfoExtractor):
 
                # Retrieve video webpage to extract further information
                request = urllib2.Request(url)
 
                # Retrieve video webpage to extract further information
                request = urllib2.Request(url)

+               request.add_header('Cookie', 'family_filter=off')

                try:
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()
                try:
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()


@@ -1117,25 +1589,29 @@ class DailymotionIE(InfoExtractor):
 
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)
 
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)

-               mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+               mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract media URL')
                        return
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract media URL')
                        return

-               mediaURL = urllib.unquote(mobj.group(1))
+               sequence = urllib.unquote(mobj.group(1))
+               mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')

 
                # if needed add http://www.dailymotion.com/ if relative URL
 
                video_url = mediaURL
 
 
                # if needed add http://www.dailymotion.com/ if relative URL
 
                video_url = mediaURL
 

-               # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
-               mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
+               mobj = re.search(r'(?im)<title>Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?</title>', webpage)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract title')
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
 
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract title')
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
 

-               mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a></div>', webpage)
+               mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return


@@ -1147,6 +1623,7 @@ class DailymotionIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),


@@ -1154,27 +1631,25 @@ class DailymotionIE(InfoExtractor):
                                'player_url':   None,
                        })
                except UnavailableVideoError:
                                'player_url':   None,
                        })
                except UnavailableVideoError:

-                       self._downloader.trouble(u'ERROR: unable to download video')
+                       self._downloader.trouble(u'\nERROR: unable to download video')
+

 
 class GoogleIE(InfoExtractor):
        """Information extractor for video.google.com."""
 
        _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
 
 class GoogleIE(InfoExtractor):
        """Information extractor for video.google.com."""
 
        _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'

+       IE_NAME = u'video.google'

 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(GoogleIE._VALID_URL, url) is not None)
-

        def report_download_webpage(self, video_id):
                """Report webpage download."""
        def report_download_webpage(self, video_id):
                """Report webpage download."""

-               self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
+               self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)

 
        def report_extraction(self, video_id):
                """Report information extraction."""
 
        def report_extraction(self, video_id):
                """Report information extraction."""

-               self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)

 
        def _real_initialize(self):
                return
 
        def _real_initialize(self):
                return


@@ -1249,13 +1724,13 @@ class GoogleIE(InfoExtractor):
                else:   # we need something to pass to process_info
                        video_thumbnail = ''
 
                else:   # we need something to pass to process_info
                        video_thumbnail = ''
 

-

                try:
                        # Process video information
                        self._downloader.process_info({
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     u'NA',
                try:
                        # Process video information
                        self._downloader.process_info({
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     u'NA',

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),


@@ -1263,28 +1738,25 @@ class GoogleIE(InfoExtractor):
                                'player_url':   None,
                        })
                except UnavailableVideoError:
                                'player_url':   None,
                        })
                except UnavailableVideoError:

-                       self._downloader.trouble(u'ERROR: unable to download video')
+                       self._downloader.trouble(u'\nERROR: unable to download video')

 
 
 class PhotobucketIE(InfoExtractor):
        """Information extractor for photobucket.com."""
 
        _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
 
 
 class PhotobucketIE(InfoExtractor):
        """Information extractor for photobucket.com."""
 
        _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'

+       IE_NAME = u'photobucket'

 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(PhotobucketIE._VALID_URL, url) is not None)
-

        def report_download_webpage(self, video_id):
                """Report webpage download."""
        def report_download_webpage(self, video_id):
                """Report webpage download."""

-               self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
+               self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)

 
        def report_extraction(self, video_id):
                """Report information extraction."""
 
        def report_extraction(self, video_id):
                """Report information extraction."""

-               self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)

 
        def _real_initialize(self):
                return
 
        def _real_initialize(self):
                return


@@ -1337,6 +1809,7 @@ class PhotobucketIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),


@@ -1344,7 +1817,7 @@ class PhotobucketIE(InfoExtractor):
                                'player_url':   None,
                        })
                except UnavailableVideoError:
                                'player_url':   None,
                        })
                except UnavailableVideoError:

-                       self._downloader.trouble(u'ERROR: unable to download video')
+                       self._downloader.trouble(u'\nERROR: unable to download video')

 
 
 class YahooIE(InfoExtractor):
 
 
 class YahooIE(InfoExtractor):


@@ -1354,21 +1827,18 @@ class YahooIE(InfoExtractor):
        # _VPAGE_URL matches only the extractable '/watch/' URLs
        _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
        _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
        # _VPAGE_URL matches only the extractable '/watch/' URLs
        _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
        _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'

+       IE_NAME = u'video.yahoo'

 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(YahooIE._VALID_URL, url) is not None)
-

        def report_download_webpage(self, video_id):
                """Report webpage download."""
        def report_download_webpage(self, video_id):
                """Report webpage download."""

-               self._downloader.to_stdout(u'[video.yahoo] %s: Downloading webpage' % video_id)
+               self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)

 
        def report_extraction(self, video_id):
                """Report information extraction."""
 
        def report_extraction(self, video_id):
                """Report information extraction."""

-               self._downloader.to_stdout(u'[video.yahoo] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)

 
        def _real_initialize(self):
                return
 
        def _real_initialize(self):
                return


@@ -1447,7 +1917,8 @@ class YahooIE(InfoExtractor):
                        self._downloader.trouble(u'ERROR: unable to extract video description')
                        return
                video_description = mobj.group(1).decode('utf-8')
                        self._downloader.trouble(u'ERROR: unable to extract video description')
                        return
                video_description = mobj.group(1).decode('utf-8')

-               if not video_description: video_description = 'No description available.'
+               if not video_description:
+                       video_description = 'No description available.'

 
                # Extract video height and width
                mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
 
                # Extract video height and width
                mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)


@@ -1468,8 +1939,8 @@ class YahooIE(InfoExtractor):
                yv_lg = 'R0xx6idZnW2zlrKP8xxAIR'  # not sure what this represents
                yv_bitrate = '700'  # according to Wikipedia this is hard-coded
                request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
                yv_lg = 'R0xx6idZnW2zlrKP8xxAIR'  # not sure what this represents
                yv_bitrate = '700'  # according to Wikipedia this is hard-coded
                request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +

-                                         '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
-                                         '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
+                               '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
+                               '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')

                try:
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()
                try:
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()


@@ -1491,63 +1962,188 @@ class YahooIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url,
                                'uploader':     video_uploader,
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url,
                                'uploader':     video_uploader,

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'thumbnail':    video_thumbnail.decode('utf-8'),
                                'description':  video_description,
                                'thumbnail':    video_thumbnail,
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'thumbnail':    video_thumbnail.decode('utf-8'),
                                'description':  video_description,
                                'thumbnail':    video_thumbnail,

-                               'description':  video_description,

                                'player_url':   None,
                        })
                except UnavailableVideoError:
                                'player_url':   None,
                        })
                except UnavailableVideoError:

-                       self._downloader.trouble(u'ERROR: unable to download video')
+                       self._downloader.trouble(u'\nERROR: unable to download video')

 
 
 
 

-class GenericIE(InfoExtractor):
-       """Generic last-resort information extractor."""
+class VimeoIE(InfoExtractor):
+       """Information extractor for vimeo.com."""
+
+       # _VALID_URL matches Vimeo URLs
+       _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
+       IE_NAME = u'vimeo'

 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return True
-

        def report_download_webpage(self, video_id):
                """Report webpage download."""
        def report_download_webpage(self, video_id):
                """Report webpage download."""

-               self._downloader.to_stdout(u'WARNING: Falling back on generic information extractor.')
-               self._downloader.to_stdout(u'[generic] %s: Downloading webpage' % video_id)
+               self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)

 
        def report_extraction(self, video_id):
                """Report information extraction."""
 
        def report_extraction(self, video_id):
                """Report information extraction."""

-               self._downloader.to_stdout(u'[generic] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)

 
        def _real_initialize(self):
                return
 
 
        def _real_initialize(self):
                return
 

-       def _real_extract(self, url):
+       def _real_extract(self, url, new_video=True):
+               # Extract ID from URL
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+                       return
+

                # At this point we have a new video
                self._downloader.increment_downloads()
                # At this point we have a new video
                self._downloader.increment_downloads()

+               video_id = mobj.group(1)

 
 

-               video_id = url.split('/')[-1]
-               request = urllib2.Request(url)
+               # Retrieve video webpage to extract further information
+               request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers)

                try:
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
                        return
                try:
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
                        return

-               except ValueError, err:
-                       # since this is the last-resort InfoExtractor, if
-                       # this error is thrown, it'll be thrown here
-                       self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
-                       return

 
 

-               # Start with something easy: JW Player in SWFObject
-               mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+               # Now we begin extracting as much information as we can from what we
+               # retrieved. First we extract the information common to all extractors,
+               # and latter we extract those that are Vimeo specific.
+               self.report_extraction(video_id)
+
+               # Extract title
+               mobj = re.search(r'<caption>(.*?)</caption>', webpage)

                if mobj is None:
                if mobj is None:

-                       # Broaden the search a little bit
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_title = mobj.group(1).decode('utf-8')
+               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+               # Extract uploader
+               mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video uploader')
+                       return
+               video_uploader = mobj.group(1).decode('utf-8')
+
+               # Extract video thumbnail
+               mobj = re.search(r'<thumbnail>(.*?)</thumbnail>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+                       return
+               video_thumbnail = mobj.group(1).decode('utf-8')
+
+               # # Extract video description
+               # mobj = re.search(r'<meta property="og:description" content="(.*)" />', webpage)
+               # if mobj is None:
+               #       self._downloader.trouble(u'ERROR: unable to extract video description')
+               #       return
+               # video_description = mobj.group(1).decode('utf-8')
+               # if not video_description: video_description = 'No description available.'
+               video_description = 'Foo.'
+
+               # Vimeo specific: extract request signature
+               mobj = re.search(r'<request_signature>(.*?)</request_signature>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract request signature')
+                       return
+               sig = mobj.group(1).decode('utf-8')
+
+               # Vimeo specific: extract video quality information
+               mobj = re.search(r'<isHD>(\d+)</isHD>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video quality information')
+                       return
+               quality = mobj.group(1).decode('utf-8')
+
+               if int(quality) == 1:
+                       quality = 'hd'
+               else:
+                       quality = 'sd'
+
+               # Vimeo specific: Extract request signature expiration
+               mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract request signature expiration')
+                       return
+               sig_exp = mobj.group(1).decode('utf-8')
+
+               video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=%s" % (video_id, sig, sig_exp, quality)
+
+               try:
+                       # Process video information
+                       self._downloader.process_info({
+                               'id':           video_id.decode('utf-8'),
+                               'url':          video_url,
+                               'uploader':     video_uploader,
+                               'upload_date':  u'NA',
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          u'mp4',
+                               'thumbnail':    video_thumbnail.decode('utf-8'),
+                               'description':  video_description,
+                               'thumbnail':    video_thumbnail,
+                               'description':  video_description,
+                               'player_url':   None,
+                       })
+               except UnavailableVideoError:
+                       self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class GenericIE(InfoExtractor):
+       """Generic last-resort information extractor."""
+
+       _VALID_URL = r'.*'
+       IE_NAME = u'generic'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       def report_download_webpage(self, video_id):
+               """Report webpage download."""
+               self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
+               self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
+
+       def _real_initialize(self):
+               return
+
+       def _real_extract(self, url):
+               # At this point we have a new video
+               self._downloader.increment_downloads()
+
+               video_id = url.split('/')[-1]
+               request = urllib2.Request(url)
+               try:
+                       self.report_download_webpage(video_id)
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+                       return
+               except ValueError, err:
+                       # since this is the last-resort InfoExtractor, if
+                       # this error is thrown, it'll be thrown here
+                       self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+                       return
+
+               self.report_extraction(video_id)
+               # Start with something easy: JW Player in SWFObject
+               mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+               if mobj is None:
+                       # Broaden the search a little bit

                        mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
                        mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)


@@ -1560,11 +2156,11 @@ class GenericIE(InfoExtractor):
                        return
 
                video_url = urllib.unquote(mobj.group(1))
                        return
 
                video_url = urllib.unquote(mobj.group(1))

-               video_id  = os.path.basename(video_url)
+               video_id = os.path.basename(video_url)

 
                # here's a fun little line of code for you:
                video_extension = os.path.splitext(video_id)[1][1:]
 
                # here's a fun little line of code for you:
                video_extension = os.path.splitext(video_id)[1][1:]

-               video_id        = os.path.splitext(video_id)[0]
+               video_id = os.path.splitext(video_id)[0]

 
                # it's tempting to parse this further, but you would
                # have to take into account all the variations like
 
                # it's tempting to parse this further, but you would
                # have to take into account all the variations like


@@ -1593,6 +2189,7 @@ class GenericIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),


@@ -1600,43 +2197,40 @@ class GenericIE(InfoExtractor):
                                'player_url':   None,
                        })
                except UnavailableVideoError, err:
                                'player_url':   None,
                        })
                except UnavailableVideoError, err:

-                       self._downloader.trouble(u'ERROR: unable to download video')
+                       self._downloader.trouble(u'\nERROR: unable to download video')

 
 
 class YoutubeSearchIE(InfoExtractor):
        """Information Extractor for YouTube search queries."""
 
 
 class YoutubeSearchIE(InfoExtractor):
        """Information Extractor for YouTube search queries."""

-       _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
+       _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'

        _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
        _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
        _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
        _youtube_ie = None
        _max_youtube_results = 1000
        _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
        _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
        _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
        _youtube_ie = None
        _max_youtube_results = 1000

+       IE_NAME = u'youtube:search'

 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie

-       
-       @staticmethod
-       def suitable(url):
-               return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)

 
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())
 
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())

-               self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+               self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))

 
        def _real_initialize(self):
                self._youtube_ie.initialize()
 
        def _real_initialize(self):
                self._youtube_ie.initialize()

-       
+

        def _real_extract(self, query):
        def _real_extract(self, query):

-               mobj = re.match(self._VALID_QUERY, query)
+               mobj = re.match(self._VALID_URL, query)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
 
                prefix, query = query.split(':')
                prefix = prefix[8:]
                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
 
                prefix, query = query.split(':')
                prefix = prefix[8:]

-               query  = query.encode('utf-8')
+               query = query.encode('utf-8')

                if prefix == '':
                        self._download_n_results(query, 1)
                        return
                if prefix == '':
                        self._download_n_results(query, 1)
                        return


@@ -1650,7 +2244,7 @@ class YoutubeSearchIE(InfoExtractor):
                                        self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
                                        return
                                elif n > self._max_youtube_results:
                                        self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
                                        return
                                elif n > self._max_youtube_results:

-                                       self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)'  % (self._max_youtube_results, n))
+                                       self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))

                                        n = self._max_youtube_results
                                self._download_n_results(query, n)
                                return
                                        n = self._max_youtube_results
                                self._download_n_results(query, n)
                                return


@@ -1668,7 +2262,7 @@ class YoutubeSearchIE(InfoExtractor):
                while True:
                        self.report_download_page(query, pagenum)
                        result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
                while True:
                        self.report_download_page(query, pagenum)
                        result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)

-                       request = urllib2.Request(result_url, None, std_headers)
+                       request = urllib2.Request(result_url)

                        try:
                                page = urllib2.urlopen(request).read()
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        try:
                                page = urllib2.urlopen(request).read()
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:


@@ -1694,40 +2288,38 @@ class YoutubeSearchIE(InfoExtractor):
 
                        pagenum = pagenum + 1
 
 
                        pagenum = pagenum + 1
 

+

 class GoogleSearchIE(InfoExtractor):
        """Information Extractor for Google Video search queries."""
 class GoogleSearchIE(InfoExtractor):
        """Information Extractor for Google Video search queries."""

-       _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
+       _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'

        _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
        _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
        _MORE_PAGES_INDICATOR = r'<span>Next</span>'
        _google_ie = None
        _max_google_results = 1000
        _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
        _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
        _MORE_PAGES_INDICATOR = r'<span>Next</span>'
        _google_ie = None
        _max_google_results = 1000

+       IE_NAME = u'video.google:search'

 
        def __init__(self, google_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._google_ie = google_ie
 
        def __init__(self, google_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._google_ie = google_ie

-       
-       @staticmethod
-       def suitable(url):
-               return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)

 
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())
 
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())

-               self._downloader.to_stdout(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
+               self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))

 
        def _real_initialize(self):
                self._google_ie.initialize()
 
        def _real_initialize(self):
                self._google_ie.initialize()

-       
+

        def _real_extract(self, query):
        def _real_extract(self, query):

-               mobj = re.match(self._VALID_QUERY, query)
+               mobj = re.match(self._VALID_URL, query)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
 
                prefix, query = query.split(':')
                prefix = prefix[8:]
                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
 
                prefix, query = query.split(':')
                prefix = prefix[8:]

-               query  = query.encode('utf-8')
+               query = query.encode('utf-8')

                if prefix == '':
                        self._download_n_results(query, 1)
                        return
                if prefix == '':
                        self._download_n_results(query, 1)
                        return


@@ -1741,7 +2333,7 @@ class GoogleSearchIE(InfoExtractor):
                                        self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
                                        return
                                elif n > self._max_google_results:
                                        self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
                                        return
                                elif n > self._max_google_results:

-                                       self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)'  % (self._max_google_results, n))
+                                       self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))

                                        n = self._max_google_results
                                self._download_n_results(query, n)
                                return
                                        n = self._max_google_results
                                self._download_n_results(query, n)
                                return


@@ -1759,7 +2351,7 @@ class GoogleSearchIE(InfoExtractor):
                while True:
                        self.report_download_page(query, pagenum)
                        result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
                while True:
                        self.report_download_page(query, pagenum)
                        result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)

-                       request = urllib2.Request(result_url, None, std_headers)
+                       request = urllib2.Request(result_url)

                        try:
                                page = urllib2.urlopen(request).read()
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        try:
                                page = urllib2.urlopen(request).read()
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:


@@ -1785,40 +2377,38 @@ class GoogleSearchIE(InfoExtractor):
 
                        pagenum = pagenum + 1
 
 
                        pagenum = pagenum + 1
 

+

 class YahooSearchIE(InfoExtractor):
        """Information Extractor for Yahoo! Video search queries."""
 class YahooSearchIE(InfoExtractor):
        """Information Extractor for Yahoo! Video search queries."""

-       _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
+       _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'

        _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
        _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
        _MORE_PAGES_INDICATOR = r'\s*Next'
        _yahoo_ie = None
        _max_yahoo_results = 1000
        _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
        _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
        _MORE_PAGES_INDICATOR = r'\s*Next'
        _yahoo_ie = None
        _max_yahoo_results = 1000

+       IE_NAME = u'video.yahoo:search'

 
        def __init__(self, yahoo_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._yahoo_ie = yahoo_ie
 
        def __init__(self, yahoo_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._yahoo_ie = yahoo_ie

-       
-       @staticmethod
-       def suitable(url):
-               return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)

 
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())
 
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())

-               self._downloader.to_stdout(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
+               self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))

 
        def _real_initialize(self):
                self._yahoo_ie.initialize()
 
        def _real_initialize(self):
                self._yahoo_ie.initialize()

-       
+

        def _real_extract(self, query):
        def _real_extract(self, query):

-               mobj = re.match(self._VALID_QUERY, query)
+               mobj = re.match(self._VALID_URL, query)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
 
                prefix, query = query.split(':')
                prefix = prefix[8:]
                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
 
                prefix, query = query.split(':')
                prefix = prefix[8:]

-               query  = query.encode('utf-8')
+               query = query.encode('utf-8')

                if prefix == '':
                        self._download_n_results(query, 1)
                        return
                if prefix == '':
                        self._download_n_results(query, 1)
                        return


@@ -1832,7 +2422,7 @@ class YahooSearchIE(InfoExtractor):
                                        self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
                                        return
                                elif n > self._max_yahoo_results:
                                        self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
                                        return
                                elif n > self._max_yahoo_results:

-                                       self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)'  % (self._max_yahoo_results, n))
+                                       self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))

                                        n = self._max_yahoo_results
                                self._download_n_results(query, n)
                                return
                                        n = self._max_yahoo_results
                                self._download_n_results(query, n)
                                return


@@ -1850,7 +2440,7 @@ class YahooSearchIE(InfoExtractor):
                while True:
                        self.report_download_page(query, pagenum)
                        result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
                while True:
                        self.report_download_page(query, pagenum)
                        result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)

-                       request = urllib2.Request(result_url, None, std_headers)
+                       request = urllib2.Request(result_url)

                        try:
                                page = urllib2.urlopen(request).read()
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        try:
                                page = urllib2.urlopen(request).read()
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:


@@ -1876,30 +2466,28 @@ class YahooSearchIE(InfoExtractor):
 
                        pagenum = pagenum + 1
 
 
                        pagenum = pagenum + 1
 

+

 class YoutubePlaylistIE(InfoExtractor):
        """Information Extractor for YouTube playlists."""
 
 class YoutubePlaylistIE(InfoExtractor):
        """Information Extractor for YouTube playlists."""
 

-       _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*'
-       _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
+       _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+       _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'

        _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
        _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
        _youtube_ie = None
        _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
        _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
        _youtube_ie = None

+       IE_NAME = u'youtube:playlist'

 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie

-       
-       @staticmethod
-       def suitable(url):
-               return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)

 
        def report_download_page(self, playlist_id, pagenum):
                """Report attempt to download playlist page with given number."""
 
        def report_download_page(self, playlist_id, pagenum):
                """Report attempt to download playlist page with given number."""

-               self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+               self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))

 
        def _real_initialize(self):
                self._youtube_ie.initialize()
 
        def _real_initialize(self):
                self._youtube_ie.initialize()

-       
+

        def _real_extract(self, url):
                # Extract playlist id
                mobj = re.match(self._VALID_URL, url)
        def _real_extract(self, url):
                # Extract playlist id
                mobj = re.match(self._VALID_URL, url)


@@ -1907,14 +2495,26 @@ class YoutubePlaylistIE(InfoExtractor):
                        self._downloader.trouble(u'ERROR: invalid url: %s' % url)
                        return
 
                        self._downloader.trouble(u'ERROR: invalid url: %s' % url)
                        return
 

+               # Single video case
+               if mobj.group(3) is not None:
+                       self._youtube_ie.extract(mobj.group(3))
+                       return
+

                # Download playlist pages
                # Download playlist pages

-               playlist_id = mobj.group(1)
+               # prefix is 'p' as default for playlists but there are other types that need extra care
+               playlist_prefix = mobj.group(1)
+               if playlist_prefix == 'a':
+                       playlist_access = 'artist'
+               else:
+                       playlist_prefix = 'p'
+                       playlist_access = 'view_play_list'
+               playlist_id = mobj.group(2)

                video_ids = []
                pagenum = 1
 
                while True:
                        self.report_download_page(playlist_id, pagenum)
                video_ids = []
                pagenum = 1
 
                while True:
                        self.report_download_page(playlist_id, pagenum)

-                       request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
+                       request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))

                        try:
                                page = urllib2.urlopen(request).read()
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        try:
                                page = urllib2.urlopen(request).read()
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:


@@ -1932,33 +2532,38 @@ class YoutubePlaylistIE(InfoExtractor):
                                break
                        pagenum = pagenum + 1
 
                                break
                        pagenum = pagenum + 1
 

+               playliststart = self._downloader.params.get('playliststart', 1) - 1
+               playlistend = self._downloader.params.get('playlistend', -1)
+               video_ids = video_ids[playliststart:playlistend]
+

                for id in video_ids:
                        self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
                return
 
                for id in video_ids:
                        self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
                return
 

+

 class YoutubeUserIE(InfoExtractor):
        """Information Extractor for YouTube users."""
 
 class YoutubeUserIE(InfoExtractor):
        """Information Extractor for YouTube users."""
 

-       _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)'
+       _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'

        _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
        _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'

-       _VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this.
+       _GDATA_PAGE_SIZE = 50
+       _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
+       _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'

        _youtube_ie = None
        _youtube_ie = None

+       IE_NAME = u'youtube:user'

 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie

-       
-       @staticmethod
-       def suitable(url):
-               return (re.match(YoutubeUserIE._VALID_URL, url) is not None)

 
 

-       def report_download_page(self, username):
+       def report_download_page(self, username, start_index):

                """Report attempt to download user page."""
                """Report attempt to download user page."""

-               self._downloader.to_stdout(u'[youtube] user %s: Downloading page ' % (username))
+               self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
+                               (username, start_index, start_index + self._GDATA_PAGE_SIZE))

 
        def _real_initialize(self):
                self._youtube_ie.initialize()
 
        def _real_initialize(self):
                self._youtube_ie.initialize()

-       
+

        def _real_extract(self, url):
                # Extract username
                mobj = re.match(self._VALID_URL, url)
        def _real_extract(self, url):
                # Extract username
                mobj = re.match(self._VALID_URL, url)


@@ -1966,289 +2571,1485 @@ class YoutubeUserIE(InfoExtractor):
                        self._downloader.trouble(u'ERROR: invalid url: %s' % url)
                        return
 
                        self._downloader.trouble(u'ERROR: invalid url: %s' % url)
                        return
 

-               # Download user page

                username = mobj.group(1)
                username = mobj.group(1)

+
+               # Download video ids using YouTube Data API. Result size per
+               # query is limited (currently to 50 videos) so we need to query
+               # page by page until there are no video ids - it means we got
+               # all of them.
+

                video_ids = []
                video_ids = []

-               pagenum = 1
+               pagenum = 0
+
+               while True:
+                       start_index = pagenum * self._GDATA_PAGE_SIZE + 1
+                       self.report_download_page(username, start_index)
+
+                       request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
+
+                       try:
+                               page = urllib2.urlopen(request).read()
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+                               return
+
+                       # Extract video identifiers
+                       ids_in_page = []
+
+                       for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+                               if mobj.group(1) not in ids_in_page:
+                                       ids_in_page.append(mobj.group(1))
+
+                       video_ids.extend(ids_in_page)
+
+                       # A little optimization - if current page is not
+                       # "full", ie. does not contain PAGE_SIZE video ids then
+                       # we can assume that this page is the last one - there
+                       # are no more ids on further pages - no need to query
+                       # again.
+
+                       if len(ids_in_page) < self._GDATA_PAGE_SIZE:
+                               break
+
+                       pagenum += 1
+
+               all_ids_count = len(video_ids)
+               playliststart = self._downloader.params.get('playliststart', 1) - 1
+               playlistend = self._downloader.params.get('playlistend', -1)
+
+               if playlistend == -1:
+                       video_ids = video_ids[playliststart:]
+               else:
+                       video_ids = video_ids[playliststart:playlistend]
+
+               self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
+                               (username, all_ids_count, len(video_ids)))
+
+               for video_id in video_ids:
+                       self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
+
+
+class DepositFilesIE(InfoExtractor):
+       """Information extractor for depositfiles.com"""
+
+       _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
+       IE_NAME = u'DepositFiles'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       def report_download_webpage(self, file_id):
+               """Report webpage download."""
+               self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
+
+       def report_extraction(self, file_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
+
+       def _real_initialize(self):
+               return
+
+       def _real_extract(self, url):
+               # At this point we have a new file
+               self._downloader.increment_downloads()
+
+               file_id = url.split('/')[-1]
+               # Rebuild url in english locale
+               url = 'http://depositfiles.com/en/files/' + file_id

 
 

-               self.report_download_page(username)
-               request = urllib2.Request(self._TEMPLATE_URL % (username), None, std_headers)
+               # Retrieve file webpage with 'Free download' button pressed
+               free_download_indication = { 'gateway_result' : '1' }
+               request = urllib2.Request(url, urllib.urlencode(free_download_indication))

                try:
                try:

-                       page = urllib2.urlopen(request).read()
+                       self.report_download_webpage(file_id)
+                       webpage = urllib2.urlopen(request).read()

                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:

-                       self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+                       self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))

                        return
 
                        return
 

-               # Extract video identifiers
-               ids_in_page = []
-
-               for mobj in re.finditer(self._VIDEO_INDICATOR, page):
-                       if mobj.group(1) not in ids_in_page:
-                               ids_in_page.append(mobj.group(1))
-               video_ids.extend(ids_in_page)
+               # Search for the real file URL
+               mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
+               if (mobj is None) or (mobj.group(1) is None):
+                       # Try to figure out reason of the error.
+                       mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
+                       if (mobj is not None) and (mobj.group(1) is not None):
+                               restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
+                               self._downloader.trouble(u'ERROR: %s' % restriction_message)
+                       else:
+                               self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url)
+                       return

 
 

-               for id in video_ids:
-                       self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
-               return
+               file_url = mobj.group(1)
+               file_extension = os.path.splitext(file_url)[1][1:]

 
 

-class PostProcessor(object):
-       """Post Processor class.
+               # Search for file title
+               mobj = re.search(r'<b title="(.*?)">', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract title')
+                       return
+               file_title = mobj.group(1).decode('utf-8')

 
 

-       PostProcessor objects can be added to downloaders with their
-       add_post_processor() method. When the downloader has finished a
-       successful download, it will take its internal chain of PostProcessors
-       and start calling the run() method on each one of them, first with
-       an initial argument and then with the returned value of the previous
-       PostProcessor.
+               try:
+                       # Process file information
+                       self._downloader.process_info({
+                               'id':           file_id.decode('utf-8'),
+                               'url':          file_url.decode('utf-8'),
+                               'uploader':     u'NA',
+                               'upload_date':  u'NA',
+                               'title':        file_title,
+                               'stitle':       file_title,
+                               'ext':          file_extension.decode('utf-8'),
+                               'format':       u'NA',
+                               'player_url':   None,
+                       })
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'ERROR: unable to download file')

 
 

-       The chain will be stopped if one of them ever returns None or the end
-       of the chain is reached.

 
 

-       PostProcessor objects follow a "mutual registration" process similar
-       to InfoExtractor objects.
-       """
+class FacebookIE(InfoExtractor):
+       """Information Extractor for Facebook"""

 
 

-       _downloader = None
+       _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/video/video\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+       _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
+       _NETRC_MACHINE = 'facebook'
+       _available_formats = ['highqual', 'lowqual']
+       _video_extensions = {
+               'highqual': 'mp4',
+               'lowqual': 'mp4',
+       }
+       IE_NAME = u'facebook'

 
        def __init__(self, downloader=None):
 
        def __init__(self, downloader=None):

-               self._downloader = downloader
+               InfoExtractor.__init__(self, downloader)

 
 

-       def set_downloader(self, downloader):
-               """Sets the downloader for this PP."""
-               self._downloader = downloader
-       
-       def run(self, information):
-               """Run the PostProcessor.
+       def _reporter(self, message):
+               """Add header and report message."""
+               self._downloader.to_screen(u'[facebook] %s' % message)

 
 

-               The "information" argument is a dictionary like the ones
-               composed by InfoExtractors. The only difference is that this
-               one has an extra field called "filepath" that points to the
-               downloaded file.
+       def report_login(self):
+               """Report attempt to log in."""
+               self._reporter(u'Logging in')

 
 

-               When this method returns None, the postprocessing chain is
-               stopped. However, this method may return an information
-               dictionary that will be passed to the next postprocessing
-               object in the chain. It can be the one it received after
-               changing some fields.
+       def report_video_webpage_download(self, video_id):
+               """Report attempt to download video webpage."""
+               self._reporter(u'%s: Downloading video webpage' % video_id)

 
 

-               In addition, this method may raise a PostProcessingError
-               exception that will be taken into account by the downloader
-               it was called from.
-               """
-               return information # by default, do nothing
-       
-### MAIN PROGRAM ###
-if __name__ == '__main__':
-       try:
-               # Modules needed only when running the main program
-               import getpass
-               import optparse
-
-               # Function to update the program file with the latest version from bitbucket.org
-               def update_self(downloader, filename):
-                       # Note: downloader only used for options
-                       if not os.access (filename, os.W_OK):
-                               sys.exit('ERROR: no write permissions on %s' % filename)
-
-                       downloader.to_stdout('Updating to latest stable version...')
-                       latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION'
-                       latest_version = urllib.urlopen(latest_url).read().strip()
-                       prog_url = 'http://bitbucket.org/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
-                       newcontent = urllib.urlopen(prog_url).read()
-                       stream = open(filename, 'w')
-                       stream.write(newcontent)
-                       stream.close()
-                       downloader.to_stdout('Updated to version %s' % latest_version)
-
-               # General configuration
-               urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
-               urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
-               socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
-
-               # Parse command line
-               parser = optparse.OptionParser(
-                       usage='Usage: %prog [options] url...',
-                       version='2010.07.24',
-                       conflict_handler='resolve',
-               )
-
-               parser.add_option('-h', '--help',
-                               action='help', help='print this help text and exit')
-               parser.add_option('-v', '--version',
-                               action='version', help='print program version and exit')
-               parser.add_option('-U', '--update',
-                               action='store_true', dest='update_self', help='update this program to latest stable version')
-               parser.add_option('-i', '--ignore-errors',
-                               action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
-               parser.add_option('-r', '--rate-limit',
-                               dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
-               parser.add_option('-R', '--retries',
-                               dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
-
-               authentication = optparse.OptionGroup(parser, 'Authentication Options')
-               authentication.add_option('-u', '--username',
-                               dest='username', metavar='USERNAME', help='account username')
-               authentication.add_option('-p', '--password',
-                               dest='password', metavar='PASSWORD', help='account password')
-               authentication.add_option('-n', '--netrc',
-                               action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
-               parser.add_option_group(authentication)
-
-               video_format = optparse.OptionGroup(parser, 'Video Format Options')
-               video_format.add_option('-f', '--format',
-                               action='store', dest='format', metavar='FORMAT', help='video format code')
-               video_format.add_option('-m', '--mobile-version',
-                               action='store_const', dest='format', help='alias for -f 17', const='17')
-               video_format.add_option('--all-formats',
-                               action='store_const', dest='format', help='download all available video formats', const='-1')
-               video_format.add_option('--max-quality',
-                               action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
-               parser.add_option_group(video_format)
-
-               verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
-               verbosity.add_option('-q', '--quiet',
-                               action='store_true', dest='quiet', help='activates quiet mode', default=False)
-               verbosity.add_option('-s', '--simulate',
-                               action='store_true', dest='simulate', help='do not download video', default=False)
-               verbosity.add_option('-g', '--get-url',
-                               action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
-               verbosity.add_option('-e', '--get-title',
-                               action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
-               verbosity.add_option('--get-thumbnail',
-                               action='store_true', dest='getthumbnail', help='simulate, quiet but print thumbnail URL', default=False)
-               verbosity.add_option('--get-description',
-                               action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False)
-               verbosity.add_option('--no-progress',
-                               action='store_true', dest='noprogress', help='do not print progress bar', default=False)
-               parser.add_option_group(verbosity)
-
-               filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
-               filesystem.add_option('-t', '--title',
-                               action='store_true', dest='usetitle', help='use title in file name', default=False)
-               filesystem.add_option('-l', '--literal',
-                               action='store_true', dest='useliteral', help='use literal title in file name', default=False)
-               filesystem.add_option('-o', '--output',
-                               dest='outtmpl', metavar='TEMPLATE', help='output filename template')
-               filesystem.add_option('-a', '--batch-file',
-                               dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
-               filesystem.add_option('-w', '--no-overwrites',
-                               action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
-               filesystem.add_option('-c', '--continue',
-                               action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
-               parser.add_option_group(filesystem)
-
-               (opts, args) = parser.parse_args()
-
-               # Batch file verification
-               batchurls = []
-               if opts.batchfile is not None:
+       def report_information_extraction(self, video_id):
+               """Report attempt to extract video information."""
+               self._reporter(u'%s: Extracting video information' % video_id)
+
+       def _parse_page(self, video_webpage):
+               """Extract video information from page"""
+               # General data
+               data = {'title': r'class="video_title datawrap">(.*?)</',
+                       'description': r'<div class="datawrap">(.*?)</div>',
+                       'owner': r'\("video_owner_name", "(.*?)"\)',
+                       'upload_date': r'data-date="(.*?)"',
+                       'thumbnail':  r'\("thumb_url", "(?P<THUMB>.*?)"\)',
+                       }
+               video_info = {}
+               for piece in data.keys():
+                       mobj = re.search(data[piece], video_webpage)
+                       if mobj is not None:
+                               video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
+
+               # Video urls
+               video_urls = {}
+               for fmt in self._available_formats:
+                       mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
+                       if mobj is not None:
+                               # URL is in a Javascript segment inside an escaped Unicode format within
+                               # the generally utf-8 page
+                               video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
+               video_info['video_urls'] = video_urls
+
+               return video_info
+
+       def _real_initialize(self):
+               if self._downloader is None:
+                       return
+
+               useremail = None
+               password = None
+               downloader_params = self._downloader.params
+
+               # Attempt to use provided username and password or .netrc data
+               if downloader_params.get('username', None) is not None:
+                       useremail = downloader_params['username']
+                       password = downloader_params['password']
+               elif downloader_params.get('usenetrc', False):

                        try:
                        try:

-                               if opts.batchfile == '-':
-                                       batchfd = sys.stdin
+                               info = netrc.netrc().authenticators(self._NETRC_MACHINE)
+                               if info is not None:
+                                       useremail = info[0]
+                                       password = info[2]

                                else:
                                else:

-                                       batchfd = open(opts.batchfile, 'r')
-                               batchurls = batchfd.readlines()
-                               batchurls = [x.strip() for x in batchurls]
-                               batchurls = [x for x in batchurls if len(x) > 0]
-                       except IOError:
-                               sys.exit(u'ERROR: batch file could not be read')
-               all_urls = batchurls + args
-
-               # Conflicting, missing and erroneous options
-               if opts.usenetrc and (opts.username is not None or opts.password is not None):
-                       parser.error(u'using .netrc conflicts with giving username/password')
-               if opts.password is not None and opts.username is None:
-                       parser.error(u'account username missing')
-               if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
-                       parser.error(u'using output template conflicts with using title or literal title')
-               if opts.usetitle and opts.useliteral:
-                       parser.error(u'using title conflicts with using literal title')
-               if opts.username is not None and opts.password is None:
-                       opts.password = getpass.getpass(u'Type account password and press return:')
-               if opts.ratelimit is not None:
-                       numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
-                       if numeric_limit is None:
-                               parser.error(u'invalid rate limit specified')
-                       opts.ratelimit = numeric_limit
-               if opts.retries is not None:
-                       try:
-                               opts.retries = long(opts.retries)
-                       except (TypeError, ValueError), err:
-                               parser.error(u'invalid retry count specified')
-
-               # Information extractors
-               youtube_ie = YoutubeIE()
-               metacafe_ie = MetacafeIE(youtube_ie)
-               dailymotion_ie = DailymotionIE()
-               youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
-               youtube_user_ie = YoutubeUserIE(youtube_ie)
-               youtube_search_ie = YoutubeSearchIE(youtube_ie)
-               google_ie = GoogleIE()
-               google_search_ie = GoogleSearchIE(google_ie)
-               photobucket_ie = PhotobucketIE()
-               yahoo_ie = YahooIE()
-               yahoo_search_ie = YahooSearchIE(yahoo_ie)
-               generic_ie = GenericIE()
-
-               # File downloader
-               fd = FileDownloader({
-                       'usenetrc': opts.usenetrc,
-                       'username': opts.username,
-                       'password': opts.password,
-                       'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
-                       'forceurl': opts.geturl,
-                       'forcetitle': opts.gettitle,
-                       'forcethumbnail': opts.getthumbnail,
-                       'forcedescription': opts.getdescription,
-                       'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
-                       'format': opts.format,
-                       'format_limit': opts.format_limit,
-                       'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
-                               or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
-                               or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
-                               or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
-                               or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
-                               or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
-                               or u'%(id)s.%(ext)s'),
-                       'ignoreerrors': opts.ignoreerrors,
-                       'ratelimit': opts.ratelimit,
-                       'nooverwrites': opts.nooverwrites,
-                       'retries': opts.retries,
-                       'continuedl': opts.continue_dl,
-                       'noprogress': opts.noprogress,
-                       })
-               fd.add_info_extractor(youtube_search_ie)
-               fd.add_info_extractor(youtube_pl_ie)
-               fd.add_info_extractor(youtube_user_ie)
-               fd.add_info_extractor(metacafe_ie)
-               fd.add_info_extractor(dailymotion_ie)
-               fd.add_info_extractor(youtube_ie)
-               fd.add_info_extractor(google_ie)
-               fd.add_info_extractor(google_search_ie)
-               fd.add_info_extractor(photobucket_ie)
-               fd.add_info_extractor(yahoo_ie)
-               fd.add_info_extractor(yahoo_search_ie)
-
-               # This must come last since it's the
-               # fallback if none of the others work
-               fd.add_info_extractor(generic_ie)
-
-               # Update version
-               if opts.update_self:
-                       update_self(fd, sys.argv[0])
-
-               # Maybe do nothing
-               if len(all_urls) < 1:
-                       if not opts.update_self:
-                               parser.error(u'you must provide at least one URL')
-                       else:
-                               sys.exit()
-               retcode = fd.download(all_urls)
-               sys.exit(retcode)
+                                       raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
+                       except (IOError, netrc.NetrcParseError), err:
+                               self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+                               return

 
 

-       except DownloadError:
-               sys.exit(1)
-       except SameFileError:
+               if useremail is None:
+                       return
+
+               # Log in
+               login_form = {
+                       'email': useremail,
+                       'pass': password,
+                       'login': 'Log+In'
+                       }
+               request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
+               try:
+                       self.report_login()
+                       login_results = urllib2.urlopen(request).read()
+                       if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
+                               self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
+                               return
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+                       return
+
+       def _real_extract(self, url):
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               video_id = mobj.group('ID')
+
+               # Get video webpage
+               self.report_video_webpage_download(video_id)
+               request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
+               try:
+                       page = urllib2.urlopen(request)
+                       video_webpage = page.read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+                       return
+
+               # Start extracting information
+               self.report_information_extraction(video_id)
+
+               # Extract information
+               video_info = self._parse_page(video_webpage)
+
+               # uploader
+               if 'owner' not in video_info:
+                       self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+                       return
+               video_uploader = video_info['owner']
+
+               # title
+               if 'title' not in video_info:
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_title = video_info['title']
+               video_title = video_title.decode('utf-8')
+               video_title = sanitize_title(video_title)
+
+               # simplified title
+               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+               simple_title = simple_title.strip(ur'_')
+
+               # thumbnail image
+               if 'thumbnail' not in video_info:
+                       self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
+                       video_thumbnail = ''
+               else:
+                       video_thumbnail = video_info['thumbnail']
+
+               # upload date
+               upload_date = u'NA'
+               if 'upload_date' in video_info:
+                       upload_time = video_info['upload_date']
+                       timetuple = email.utils.parsedate_tz(upload_time)
+                       if timetuple is not None:
+                               try:
+                                       upload_date = time.strftime('%Y%m%d', timetuple[0:9])
+                               except:
+                                       pass
+
+               # description
+               video_description = video_info.get('description', 'No description available.')
+
+               url_map = video_info['video_urls']
+               if len(url_map.keys()) > 0:
+                       # Decide which formats to download
+                       req_format = self._downloader.params.get('format', None)
+                       format_limit = self._downloader.params.get('format_limit', None)
+
+                       if format_limit is not None and format_limit in self._available_formats:
+                               format_list = self._available_formats[self._available_formats.index(format_limit):]
+                       else:
+                               format_list = self._available_formats
+                       existing_formats = [x for x in format_list if x in url_map]
+                       if len(existing_formats) == 0:
+                               self._downloader.trouble(u'ERROR: no known formats available for video')
+                               return
+                       if req_format is None:
+                               video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
+                       elif req_format == 'worst':
+                               video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
+                       elif req_format == '-1':
+                               video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
+                       else:
+                               # Specific format
+                               if req_format not in url_map:
+                                       self._downloader.trouble(u'ERROR: requested format not available')
+                                       return
+                               video_url_list = [(req_format, url_map[req_format])] # Specific format
+
+               for format_param, video_real_url in video_url_list:
+
+                       # At this point we have a new video
+                       self._downloader.increment_downloads()
+
+                       # Extension
+                       video_extension = self._video_extensions.get(format_param, 'mp4')
+
+                       try:
+                               # Process video information
+                               self._downloader.process_info({
+                                       'id':           video_id.decode('utf-8'),
+                                       'url':          video_real_url.decode('utf-8'),
+                                       'uploader':     video_uploader.decode('utf-8'),
+                                       'upload_date':  upload_date,
+                                       'title':        video_title,
+                                       'stitle':       simple_title,
+                                       'ext':          video_extension.decode('utf-8'),
+                                       'format':       (format_param is None and u'NA' or format_param.decode('utf-8')),
+                                       'thumbnail':    video_thumbnail.decode('utf-8'),
+                                       'description':  video_description.decode('utf-8'),
+                                       'player_url':   None,
+                               })
+                       except UnavailableVideoError, err:
+                               self._downloader.trouble(u'\nERROR: unable to download video')
+
+class BlipTVIE(InfoExtractor):
+       """Information extractor for blip.tv"""
+
+       _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
+       _URL_EXT = r'^.*\.([a-z0-9]+)$'
+       IE_NAME = u'blip.tv'
+
+       def report_extraction(self, file_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
+
+       def report_direct_download(self, title):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
+
+       def _simplify_title(self, title):
+               res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+               res = res.strip(ur'_')
+               return res
+
+       def _real_extract(self, url):
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+               if '?' in url:
+                       cchar = '&'
+               else:
+                       cchar = '?'
+               json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
+               request = urllib2.Request(json_url)
+               self.report_extraction(mobj.group(1))
+               info = None
+               try:
+                       urlh = urllib2.urlopen(request)
+                       if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
+                               basename = url.split('/')[-1]
+                               title,ext = os.path.splitext(basename)
+                               ext = ext.replace('.', '')
+                               self.report_direct_download(title)
+                               info = {
+                                       'id': title,
+                                       'url': url,
+                                       'title': title,
+                                       'stitle': self._simplify_title(title),
+                                       'ext': ext,
+                                       'urlhandle': urlh
+                               }
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+                       return
+               if info is None: # Regular URL
+                       try:
+                               json_code = urlh.read()
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err))
+                               return
+
+                       try:
+                               json_data = json.loads(json_code)
+                               if 'Post' in json_data:
+                                       data = json_data['Post']
+                               else:
+                                       data = json_data
+       
+                               upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+                               video_url = data['media']['url']
+                               umobj = re.match(self._URL_EXT, video_url)
+                               if umobj is None:
+                                       raise ValueError('Can not determine filename extension')
+                               ext = umobj.group(1)
+       
+                               info = {
+                                       'id': data['item_id'],
+                                       'url': video_url,
+                                       'uploader': data['display_name'],
+                                       'upload_date': upload_date,
+                                       'title': data['title'],
+                                       'stitle': self._simplify_title(data['title']),
+                                       'ext': ext,
+                                       'format': data['media']['mimeType'],
+                                       'thumbnail': data['thumbnailUrl'],
+                                       'description': data['description'],
+                                       'player_url': data['embedUrl']
+                               }
+                       except (ValueError,KeyError), err:
+                               self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
+                               return
+
+               self._downloader.increment_downloads()
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class MyVideoIE(InfoExtractor):
+       """Information Extractor for myvideo.de."""
+
+       _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
+       IE_NAME = u'myvideo'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+       
+       def report_download_webpage(self, video_id):
+               """Report webpage download."""
+               self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
+
+       def _real_initialize(self):
+               return
+
+       def _real_extract(self,url):
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._download.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+               video_id = mobj.group(1)
+               simple_title = mobj.group(2).decode('utf-8')
+               # should actually not be necessary
+               simple_title = sanitize_title(simple_title)
+               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title)
+
+               # Get video webpage
+               request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
+               try:
+                       self.report_download_webpage(video_id)
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+                       return
+
+               self.report_extraction(video_id)
+               mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />',
+                                webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               video_url = mobj.group(1) + ('/%s.flv' % video_id)
+
+               mobj = re.search('<title>([^<]+)</title>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract title')
+                       return
+
+               video_title = mobj.group(1)
+               video_title = sanitize_title(video_title)
+
+               try:
+                       self._downloader.process_info({
+                               'id':           video_id,
+                               'url':          video_url,
+                               'uploader':     u'NA',
+                               'upload_date':  u'NA',
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          u'flv',
+                               'format':       u'NA',
+                               'player_url':   None,
+                       })
+               except UnavailableVideoError:
+                       self._downloader.trouble(u'\nERROR: Unable to download video')
+
+class ComedyCentralIE(InfoExtractor):
+       """Information extractor for The Daily Show and Colbert Report """
+
+       _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
+       IE_NAME = u'comedycentral'
+
+       def report_extraction(self, episode_id):
+               self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
+       
+       def report_config_download(self, episode_id):
+               self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
+
+       def report_index_download(self, episode_id):
+               self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id)
+
+       def report_player_url(self, episode_id):
+               self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
+
+       def _simplify_title(self, title):
+               res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+               res = res.strip(ur'_')
+               return res
+
+       def _real_extract(self, url):
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+               if mobj.group('shortname'):
+                       if mobj.group('shortname') in ('tds', 'thedailyshow'):
+                               url = 'http://www.thedailyshow.com/full-episodes/'
+                       else:
+                               url = 'http://www.colbertnation.com/full-episodes/'
+                       mobj = re.match(self._VALID_URL, url)
+                       assert mobj is not None
+
+               dlNewest = not mobj.group('episode')
+               if dlNewest:
+                       epTitle = mobj.group('showname')
+               else:
+                       epTitle = mobj.group('episode')
+
+               req = urllib2.Request(url)
+               self.report_extraction(epTitle)
+               try:
+                       htmlHandle = urllib2.urlopen(req)
+                       html = htmlHandle.read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+                       return
+               if dlNewest:
+                       url = htmlHandle.geturl()
+                       mobj = re.match(self._VALID_URL, url)
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
+                               return
+                       if mobj.group('episode') == '':
+                               self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
+                               return
+                       epTitle = mobj.group('episode')
+
+               mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"/>', html)
+               if len(mMovieParams) == 0:
+                       self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
+                       return
+
+               playerUrl_raw = mMovieParams[0][0]
+               self.report_player_url(epTitle)
+               try:
+                       urlHandle = urllib2.urlopen(playerUrl_raw)
+                       playerUrl = urlHandle.geturl()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err))
+                       return
+
+               uri = mMovieParams[0][1]
+               indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + urllib.urlencode({'uri': uri})
+               self.report_index_download(epTitle)
+               try:
+                       indexXml = urllib2.urlopen(indexUrl).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err))
+                       return
+
+               idoc = xml.etree.ElementTree.fromstring(indexXml)
+               itemEls = idoc.findall('.//item')
+               for itemEl in itemEls:
+                       mediaId = itemEl.findall('./guid')[0].text
+                       shortMediaId = mediaId.split(':')[-1]
+                       showId = mediaId.split(':')[-2].replace('.com', '')
+                       officialTitle = itemEl.findall('./title')[0].text
+                       officialDate = itemEl.findall('./pubDate')[0].text
+
+                       configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
+                                               urllib.urlencode({'uri': mediaId}))
+                       configReq = urllib2.Request(configUrl)
+                       self.report_config_download(epTitle)
+                       try:
+                               configXml = urllib2.urlopen(configReq).read()
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+                               return
+
+                       cdoc = xml.etree.ElementTree.fromstring(configXml)
+                       turls = []
+                       for rendition in cdoc.findall('.//rendition'):
+                               finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
+                               turls.append(finfo)
+
+                       if len(turls) == 0:
+                               self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
+                               continue
+
+                       # For now, just pick the highest bitrate
+                       format,video_url = turls[-1]
+
+                       self._downloader.increment_downloads()
+
+                       effTitle = showId + '-' + epTitle
+                       info = {
+                               'id': shortMediaId,
+                               'url': video_url,
+                               'uploader': showId,
+                               'upload_date': officialDate,
+                               'title': effTitle,
+                               'stitle': self._simplify_title(effTitle),
+                               'ext': 'mp4',
+                               'format': format,
+                               'thumbnail': None,
+                               'description': officialTitle,
+                               'player_url': playerUrl
+                       }
+
+                       try:
+                               self._downloader.process_info(info)
+                       except UnavailableVideoError, err:
+                               self._downloader.trouble(u'\nERROR: unable to download ' + mediaId)
+                               continue
+
+
+class EscapistIE(InfoExtractor):
+       """Information extractor for The Escapist """
+
+       _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+       IE_NAME = u'escapist'
+
+       def report_extraction(self, showName):
+               self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
+
+       def report_config_download(self, showName):
+               self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
+
+       def _simplify_title(self, title):
+               res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+               res = res.strip(ur'_')
+               return res
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               showName = mobj.group('showname')
+               videoId = mobj.group('episode')
+
+               self.report_extraction(showName)
+               try:
+                       webPage = urllib2.urlopen(url).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
+                       return
+
+               descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
+               description = htmlParser.unescape(descMatch.group(1))
+               imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
+               imgUrl = htmlParser.unescape(imgMatch.group(1))
+               playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
+               playerUrl = htmlParser.unescape(playerUrlMatch.group(1))
+               configUrlMatch = re.search('config=(.*)$', playerUrl)
+               configUrl = urllib2.unquote(configUrlMatch.group(1))
+
+               self.report_config_download(showName)
+               try:
+                       configJSON = urllib2.urlopen(configUrl).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err))
+                       return
+
+               # Technically, it's JavaScript, not JSON
+               configJSON = configJSON.replace("'", '"')
+
+               try:
+                       config = json.loads(configJSON)
+               except (ValueError,), err:
+                       self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err))
+                       return
+
+               playlist = config['playlist']
+               videoUrl = playlist[1]['url']
+
+               self._downloader.increment_downloads()
+               info = {
+                       'id': videoId,
+                       'url': videoUrl,
+                       'uploader': showName,
+                       'upload_date': None,
+                       'title': showName,
+                       'stitle': self._simplify_title(showName),
+                       'ext': 'flv',
+                       'format': 'flv',
+                       'thumbnail': imgUrl,
+                       'description': description,
+                       'player_url': playerUrl,
+               }
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download ' + videoId)
+
+
+class CollegeHumorIE(InfoExtractor):
+       """Information extractor for collegehumor.com"""
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
+       IE_NAME = u'collegehumor'
+
+       def report_webpage(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+       def _simplify_title(self, title):
+               res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+               res = res.strip(ur'_')
+               return res
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               video_id = mobj.group('videoid')
+
+               self.report_webpage(video_id)
+               request = urllib2.Request(url)
+               try:
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+                       return
+
+               m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
+               if m is None:
+                       self._downloader.trouble(u'ERROR: Cannot extract internal video ID')
+                       return
+               internal_video_id = m.group('internalvideoid')
+
+               info = {
+                       'id': video_id,
+                       'internal_id': internal_video_id,
+               }
+
+               self.report_extraction(video_id)
+               xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id
+               try:
+                       metaXml = urllib2.urlopen(xmlUrl).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err))
+                       return
+
+               mdoc = xml.etree.ElementTree.fromstring(metaXml)
+               try:
+                       videoNode = mdoc.findall('./video')[0]
+                       info['description'] = videoNode.findall('./description')[0].text
+                       info['title'] = videoNode.findall('./caption')[0].text
+                       info['stitle'] = self._simplify_title(info['title'])
+                       info['url'] = videoNode.findall('./file')[0].text
+                       info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
+                       info['ext'] = info['url'].rpartition('.')[2]
+                       info['format'] = info['ext']
+               except IndexError:
+                       self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
+                       return
+
+               self._downloader.increment_downloads()
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class XVideosIE(InfoExtractor):
+       """Information extractor for xvideos.com"""
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
+       IE_NAME = u'xvideos'
+
+       def report_webpage(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+       def _simplify_title(self, title):
+               res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+               res = res.strip(ur'_')
+               return res
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               video_id = mobj.group(1).decode('utf-8')
+
+               self.report_webpage(video_id)
+
+               request = urllib2.Request(r'http://www.xvideos.com/video' + video_id)
+               try:
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+                       return
+
+               self.report_extraction(video_id)
+
+
+               # Extract video URL
+               mobj = re.search(r'flv_url=(.+?)&', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video url')
+                       return
+               video_url = urllib2.unquote(mobj.group(1).decode('utf-8'))
+
+
+               # Extract title
+               mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_title = mobj.group(1).decode('utf-8')
+
+
+               # Extract video thumbnail
+               mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+                       return
+               video_thumbnail = mobj.group(1).decode('utf-8')
+
+
+
+               self._downloader.increment_downloads()
+               info = {
+                       'id': video_id,
+                       'url': video_url,
+                       'uploader': None,
+                       'upload_date': None,
+                       'title': video_title,
+                       'stitle': self._simplify_title(video_title),
+                       'ext': 'flv',
+                       'format': 'flv',
+                       'thumbnail': video_thumbnail,
+                       'description': None,
+                       'player_url': None,
+               }
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
+
+
+class PostProcessor(object):
+       """Post Processor class.
+
+       PostProcessor objects can be added to downloaders with their
+       add_post_processor() method. When the downloader has finished a
+       successful download, it will take its internal chain of PostProcessors
+       and start calling the run() method on each one of them, first with
+       an initial argument and then with the returned value of the previous
+       PostProcessor.
+
+       The chain will be stopped if one of them ever returns None or the end
+       of the chain is reached.
+
+       PostProcessor objects follow a "mutual registration" process similar
+       to InfoExtractor objects.
+       """
+
+       _downloader = None
+
+       def __init__(self, downloader=None):
+               self._downloader = downloader
+
+       def set_downloader(self, downloader):
+               """Sets the downloader for this PP."""
+               self._downloader = downloader
+
+       def run(self, information):
+               """Run the PostProcessor.
+
+               The "information" argument is a dictionary like the ones
+               composed by InfoExtractors. The only difference is that this
+               one has an extra field called "filepath" that points to the
+               downloaded file.
+
+               When this method returns None, the postprocessing chain is
+               stopped. However, this method may return an information
+               dictionary that will be passed to the next postprocessing
+               object in the chain. It can be the one it received after
+               changing some fields.
+
+               In addition, this method may raise a PostProcessingError
+               exception that will be taken into account by the downloader
+               it was called from.
+               """
+               return information # by default, do nothing
+
+
+class FFmpegExtractAudioPP(PostProcessor):
+
+       def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False):
+               PostProcessor.__init__(self, downloader)
+               if preferredcodec is None:
+                       preferredcodec = 'best'
+               self._preferredcodec = preferredcodec
+               self._preferredquality = preferredquality
+               self._keepvideo = keepvideo
+
+       @staticmethod
+       def get_audio_codec(path):
+               try:
+                       cmd = ['ffprobe', '-show_streams', '--', path]
+                       handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
+                       output = handle.communicate()[0]
+                       if handle.wait() != 0:
+                               return None
+               except (IOError, OSError):
+                       return None
+               audio_codec = None
+               for line in output.split('\n'):
+                       if line.startswith('codec_name='):
+                               audio_codec = line.split('=')[1].strip()
+                       elif line.strip() == 'codec_type=audio' and audio_codec is not None:
+                               return audio_codec
+               return None
+
+       @staticmethod
+       def run_ffmpeg(path, out_path, codec, more_opts):
+               try:
+                       cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path]
+                       ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT)
+                       return (ret == 0)
+               except (IOError, OSError):
+                       return False
+
+       def run(self, information):
+               path = information['filepath']
+
+               filecodec = self.get_audio_codec(path)
+               if filecodec is None:
+                       self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe')
+                       return None
+
+               more_opts = []
+               if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
+                       if filecodec in ['aac', 'mp3', 'vorbis']:
+                               # Lossless if possible
+                               acodec = 'copy'
+                               extension = filecodec
+                               if filecodec == 'aac':
+                                       more_opts = ['-f', 'adts']
+                               if filecodec == 'vorbis':
+                                       extension = 'ogg'
+                       else:
+                               # MP3 otherwise.
+                               acodec = 'libmp3lame'
+                               extension = 'mp3'
+                               more_opts = []
+                               if self._preferredquality is not None:
+                                       more_opts += ['-ab', self._preferredquality]
+               else:
+                       # We convert the audio (lossy)
+                       acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'vorbis': 'libvorbis'}[self._preferredcodec]
+                       extension = self._preferredcodec
+                       more_opts = []
+                       if self._preferredquality is not None:
+                               more_opts += ['-ab', self._preferredquality]
+                       if self._preferredcodec == 'aac':
+                               more_opts += ['-f', 'adts']
+                       if self._preferredcodec == 'vorbis':
+                               extension = 'ogg'
+
+               (prefix, ext) = os.path.splitext(path)
+               new_path = prefix + '.' + extension
+               self._downloader.to_screen(u'[ffmpeg] Destination: %s' % new_path)
+               status = self.run_ffmpeg(path, new_path, acodec, more_opts)
+
+               if not status:
+                       self._downloader.to_stderr(u'WARNING: error running ffmpeg')
+                       return None
+
+               # Try to update the date time for extracted audio file.
+               if information.get('filetime') is not None:
+                       try:
+                               os.utime(new_path, (time.time(), information['filetime']))
+                       except:
+                               self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
+
+               if not self._keepvideo:
+                       try:
+                               os.remove(path)
+                       except (IOError, OSError):
+                               self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
+                               return None
+
+               information['filepath'] = new_path
+               return information
+
+
+def updateSelf(downloader, filename):
+       ''' Update the program file with the latest version from the repository '''
+       # Note: downloader only used for options
+       if not os.access(filename, os.W_OK):
+               sys.exit('ERROR: no write permissions on %s' % filename)
+
+       downloader.to_screen('Updating to latest version...')
+
+       try:
+               try:
+                       urlh = urllib.urlopen(UPDATE_URL)
+                       newcontent = urlh.read()
+                       
+                       vmatch = re.search("__version__ = '([^']+)'", newcontent)
+                       if vmatch is not None and vmatch.group(1) == __version__:
+                               downloader.to_screen('youtube-dl is up-to-date (' + __version__ + ')')
+                               return
+               finally:
+                       urlh.close()
+       except (IOError, OSError), err:
+               sys.exit('ERROR: unable to download latest version')
+
+       try:
+               outf = open(filename, 'wb')
+               try:
+                       outf.write(newcontent)
+               finally:
+                       outf.close()
+       except (IOError, OSError), err:
+               sys.exit('ERROR: unable to overwrite current version')
+
+       downloader.to_screen('Updated youtube-dl. Restart youtube-dl to use the new version.')
+
+def parseOpts():
+       # Deferred imports
+       import getpass
+       import optparse
+
+       def _format_option_string(option):
+               ''' ('-o', '--option') -> -o, --format METAVAR'''
+
+               opts = []
+
+               if option._short_opts: opts.append(option._short_opts[0])
+               if option._long_opts: opts.append(option._long_opts[0])
+               if len(opts) > 1: opts.insert(1, ', ')
+
+               if option.takes_value(): opts.append(' %s' % option.metavar)
+
+               return "".join(opts)
+
+       def _find_term_columns():
+               columns = os.environ.get('COLUMNS', None)
+               if columns:
+                       return int(columns)
+
+               try:
+                       sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+                       out,err = sp.communicate()
+                       return int(out.split()[1])
+               except:
+                       pass
+               return None
+
+       max_width = 80
+       max_help_position = 80
+
+       # No need to wrap help messages if we're on a wide console
+       columns = _find_term_columns()
+       if columns: max_width = columns
+
+       fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
+       fmt.format_option_strings = _format_option_string
+
+       kw = {
+               'version'   : __version__,
+               'formatter' : fmt,
+               'usage' : '%prog [options] url [url...]',
+               'conflict_handler' : 'resolve',
+       }
+
+       parser = optparse.OptionParser(**kw)
+
+       # option groups
+       general        = optparse.OptionGroup(parser, 'General Options')
+       selection      = optparse.OptionGroup(parser, 'Video Selection')
+       authentication = optparse.OptionGroup(parser, 'Authentication Options')
+       video_format   = optparse.OptionGroup(parser, 'Video Format Options')
+       postproc       = optparse.OptionGroup(parser, 'Post-processing Options')
+       filesystem     = optparse.OptionGroup(parser, 'Filesystem Options')
+       verbosity      = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
+
+       general.add_option('-h', '--help',
+                       action='help', help='print this help text and exit')
+       general.add_option('-v', '--version',
+                       action='version', help='print program version and exit')
+       general.add_option('-U', '--update',
+                       action='store_true', dest='update_self', help='update this program to latest version')
+       general.add_option('-i', '--ignore-errors',
+                       action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
+       general.add_option('-r', '--rate-limit',
+                       dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
+       general.add_option('-R', '--retries',
+                       dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
+       general.add_option('--dump-user-agent',
+                       action='store_true', dest='dump_user_agent',
+                       help='display the current browser identification', default=False)
+       general.add_option('--list-extractors',
+                       action='store_true', dest='list_extractors',
+                       help='List all supported extractors and the URLs they would handle', default=False)
+
+       selection.add_option('--playlist-start',
+                       dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
+       selection.add_option('--playlist-end',
+                       dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
+       selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
+       selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
+
+       authentication.add_option('-u', '--username',
+                       dest='username', metavar='USERNAME', help='account username')
+       authentication.add_option('-p', '--password',
+                       dest='password', metavar='PASSWORD', help='account password')
+       authentication.add_option('-n', '--netrc',
+                       action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
+
+
+       video_format.add_option('-f', '--format',
+                       action='store', dest='format', metavar='FORMAT', help='video format code')
+       video_format.add_option('--all-formats',
+                       action='store_const', dest='format', help='download all available video formats', const='all')
+       video_format.add_option('--max-quality',
+                       action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
+       video_format.add_option('-F', '--list-formats',
+                       action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
+
+
+       verbosity.add_option('-q', '--quiet',
+                       action='store_true', dest='quiet', help='activates quiet mode', default=False)
+       verbosity.add_option('-s', '--simulate',
+                       action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False)
+       verbosity.add_option('--skip-download',
+                       action='store_true', dest='skip_download', help='do not download the video', default=False)
+       verbosity.add_option('-g', '--get-url',
+                       action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
+       verbosity.add_option('-e', '--get-title',
+                       action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
+       verbosity.add_option('--get-thumbnail',
+                       action='store_true', dest='getthumbnail',
+                       help='simulate, quiet but print thumbnail URL', default=False)
+       verbosity.add_option('--get-description',
+                       action='store_true', dest='getdescription',
+                       help='simulate, quiet but print video description', default=False)
+       verbosity.add_option('--get-filename',
+                       action='store_true', dest='getfilename',
+                       help='simulate, quiet but print output filename', default=False)
+       verbosity.add_option('--get-format',
+                       action='store_true', dest='getformat',
+                       help='simulate, quiet but print output format', default=False)
+       verbosity.add_option('--no-progress',
+                       action='store_true', dest='noprogress', help='do not print progress bar', default=False)
+       verbosity.add_option('--console-title',
+                       action='store_true', dest='consoletitle',
+                       help='display progress in console titlebar', default=False)
+
+
+       filesystem.add_option('-t', '--title',
+                       action='store_true', dest='usetitle', help='use title in file name', default=False)
+       filesystem.add_option('-l', '--literal',
+                       action='store_true', dest='useliteral', help='use literal title in file name', default=False)
+       filesystem.add_option('-A', '--auto-number',
+                       action='store_true', dest='autonumber',
+                       help='number downloaded files starting from 00000', default=False)
+       filesystem.add_option('-o', '--output',
+                       dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, and %% for a literal percent')
+       filesystem.add_option('-a', '--batch-file',
+                       dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
+       filesystem.add_option('-w', '--no-overwrites',
+                       action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
+       filesystem.add_option('-c', '--continue',
+                       action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
+       filesystem.add_option('--no-continue',
+                       action='store_false', dest='continue_dl',
+                       help='do not resume partially downloaded files (restart from beginning)')
+       filesystem.add_option('--cookies',
+                       dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
+       filesystem.add_option('--no-part',
+                       action='store_true', dest='nopart', help='do not use .part files', default=False)
+       filesystem.add_option('--no-mtime',
+                       action='store_false', dest='updatetime',
+                       help='do not use the Last-modified header to set the file modification time', default=True)
+       filesystem.add_option('--write-description',
+                       action='store_true', dest='writedescription',
+                       help='write video description to a .description file', default=False)
+       filesystem.add_option('--write-info-json',
+                       action='store_true', dest='writeinfojson',
+                       help='write video metadata to a .info.json file', default=False)
+
+
+       postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
+                       help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
+       postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
+                       help='"best", "aac", "vorbis" or "mp3"; best by default')
+       postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
+                       help='ffmpeg audio bitrate specification, 128k by default')
+       postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
+                       help='keeps the video file on disk after the post-processing; the video is erased by default')
+
+
+       parser.add_option_group(general)
+       parser.add_option_group(selection)
+       parser.add_option_group(filesystem)
+       parser.add_option_group(verbosity)
+       parser.add_option_group(video_format)
+       parser.add_option_group(authentication)
+       parser.add_option_group(postproc)
+
+       opts, args = parser.parse_args()
+
+       return parser, opts, args
+
+def gen_extractors():
+       """ Return a list of an instance of every supported extractor.
+       The order does matter; the first extractor matched is the one handling the URL.
+       """
+       youtube_ie = YoutubeIE()
+       google_ie = GoogleIE()
+       yahoo_ie = YahooIE()
+       return [
+               YoutubePlaylistIE(youtube_ie),
+               YoutubeUserIE(youtube_ie),
+               YoutubeSearchIE(youtube_ie),
+               youtube_ie,
+               MetacafeIE(youtube_ie),
+               DailymotionIE(),
+               google_ie,
+               GoogleSearchIE(google_ie),
+               PhotobucketIE(),
+               yahoo_ie,
+               YahooSearchIE(yahoo_ie),
+               DepositFilesIE(),
+               FacebookIE(),
+               BlipTVIE(),
+               VimeoIE(),
+               MyVideoIE(),
+               ComedyCentralIE(),
+               EscapistIE(),
+               CollegeHumorIE(),
+               XVideosIE(),
+
+               GenericIE()
+       ]
+
+def main():
+       parser, opts, args = parseOpts()
+
+       # Open appropriate CookieJar
+       if opts.cookiefile is None:
+               jar = cookielib.CookieJar()
+       else:
+               try:
+                       jar = cookielib.MozillaCookieJar(opts.cookiefile)
+                       if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
+                               jar.load()
+               except (IOError, OSError), err:
+                       sys.exit(u'ERROR: unable to open cookie file')
+
+       # Dump user agent
+       if opts.dump_user_agent:
+               print std_headers['User-Agent']
+               sys.exit(0)
+
+       # Batch file verification
+       batchurls = []
+       if opts.batchfile is not None:
+               try:
+                       if opts.batchfile == '-':
+                               batchfd = sys.stdin
+                       else:
+                               batchfd = open(opts.batchfile, 'r')
+                       batchurls = batchfd.readlines()
+                       batchurls = [x.strip() for x in batchurls]
+                       batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
+               except IOError:
+                       sys.exit(u'ERROR: batch file could not be read')
+       all_urls = batchurls + args
+
+       # General configuration
+       cookie_processor = urllib2.HTTPCookieProcessor(jar)
+       opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())
+       urllib2.install_opener(opener)
+       socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
+       extractors = gen_extractors()
+
+       if opts.list_extractors:
+               for ie in extractors:
+                       print(ie.IE_NAME)
+                       matchedUrls = filter(lambda url: ie.suitable(url), all_urls)
+                       all_urls = filter(lambda url: url not in matchedUrls, all_urls)
+                       for mu in matchedUrls:
+                               print(u'  ' + mu)
+               sys.exit(0)
+
+       # Conflicting, missing and erroneous options
+       if opts.usenetrc and (opts.username is not None or opts.password is not None):
+               parser.error(u'using .netrc conflicts with giving username/password')
+       if opts.password is not None and opts.username is None:
+               parser.error(u'account username missing')
+       if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber):
+               parser.error(u'using output template conflicts with using title, literal title or auto number')
+       if opts.usetitle and opts.useliteral:
+               parser.error(u'using title conflicts with using literal title')
+       if opts.username is not None and opts.password is None:
+               opts.password = getpass.getpass(u'Type account password and press return:')
+       if opts.ratelimit is not None:
+               numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
+               if numeric_limit is None:
+                       parser.error(u'invalid rate limit specified')
+               opts.ratelimit = numeric_limit
+       if opts.retries is not None:
+               try:
+                       opts.retries = long(opts.retries)
+               except (TypeError, ValueError), err:
+                       parser.error(u'invalid retry count specified')
+       try:
+               opts.playliststart = int(opts.playliststart)
+               if opts.playliststart <= 0:
+                       raise ValueError(u'Playlist start must be positive')
+       except (TypeError, ValueError), err:
+               parser.error(u'invalid playlist start number specified')
+       try:
+               opts.playlistend = int(opts.playlistend)
+               if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
+                       raise ValueError(u'Playlist end must be greater than playlist start')
+       except (TypeError, ValueError), err:
+               parser.error(u'invalid playlist end number specified')
+       if opts.extractaudio:
+               if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis']:
+                       parser.error(u'invalid audio format specified')
+
+       # File downloader
+       fd = FileDownloader({
+               'usenetrc': opts.usenetrc,
+               'username': opts.username,
+               'password': opts.password,
+               'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+               'forceurl': opts.geturl,
+               'forcetitle': opts.gettitle,
+               'forcethumbnail': opts.getthumbnail,
+               'forcedescription': opts.getdescription,
+               'forcefilename': opts.getfilename,
+               'forceformat': opts.getformat,
+               'simulate': opts.simulate,
+               'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+               'format': opts.format,
+               'format_limit': opts.format_limit,
+               'listformats': opts.listformats,
+               'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
+                       or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
+                       or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
+                       or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
+                       or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s')
+                       or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
+                       or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
+                       or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
+                       or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
+                       or u'%(id)s.%(ext)s'),
+               'ignoreerrors': opts.ignoreerrors,
+               'ratelimit': opts.ratelimit,
+               'nooverwrites': opts.nooverwrites,
+               'retries': opts.retries,
+               'continuedl': opts.continue_dl,
+               'noprogress': opts.noprogress,
+               'playliststart': opts.playliststart,
+               'playlistend': opts.playlistend,
+               'logtostderr': opts.outtmpl == '-',
+               'consoletitle': opts.consoletitle,
+               'nopart': opts.nopart,
+               'updatetime': opts.updatetime,
+               'writedescription': opts.writedescription,
+               'writeinfojson': opts.writeinfojson,
+               'matchtitle': opts.matchtitle,
+               'rejecttitle': opts.rejecttitle,
+               })
+       for extractor in extractors:
+               fd.add_info_extractor(extractor)
+
+       # PostProcessors
+       if opts.extractaudio:
+               fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo))
+
+       # Update version
+       if opts.update_self:
+               updateSelf(fd, sys.argv[0])
+
+       # Maybe do nothing
+       if len(all_urls) < 1:
+               if not opts.update_self:
+                       parser.error(u'you must provide at least one URL')
+               else:
+                       sys.exit()
+       retcode = fd.download(all_urls)
+
+       # Dump cookie jar if requested
+       if opts.cookiefile is not None:
+               try:
+                       jar.save()
+               except (IOError, OSError), err:
+                       sys.exit(u'ERROR: unable to save cookie jar')
+
+       sys.exit(retcode)
+
+
+if __name__ == '__main__':
+       try:
+               main()
+       except DownloadError:
+               sys.exit(1)
+       except SameFileError:

                sys.exit(u'ERROR: fixed output name but more than one file to download')
        except KeyboardInterrupt:
                sys.exit(u'\nERROR: Interrupted by user')
                sys.exit(u'ERROR: fixed output name but more than one file to download')
        except KeyboardInterrupt:
                sys.exit(u'\nERROR: Interrupted by user')

+
+# vim: set ts=4 sw=4 sts=4 noet ai si filetype=python: