Imported Upstream version 2011.09.14

[youtubedl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index e8b19c8d0a6a90265a17000522e5a4e455bb1149..50d83cf2d5905cb029639604aa78e06ce7227289 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -1,17 +1,26 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-

-# Author: Ricardo Garcia Gonzalez
-# Author: Danny Colligan
-# Author: Benjamin Johnson
-# Author: Vasyl' Vavrychuk
-# Author: Witold Baryluk
-# Author: Paweł Paprota
-# Author: Gergely Imreh
-# 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__ = '2011.09.14'
+
+UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
+

 import cookielib
 import cookielib

-import ctypes

 import datetime
 import datetime

-import email.utils

 import gzip
 import htmlentitydefs
 import httplib
 import gzip
 import htmlentitydefs
 import httplib


@@ -23,20 +32,42 @@ import os.path
 import re
 import socket
 import string
 import re
 import socket
 import string

-import StringIO

 import subprocess
 import sys
 import time
 import urllib
 import urllib2
 import subprocess
 import sys
 import time
 import urllib
 import urllib2

+import warnings

 import zlib
 
 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:
        from urlparse import parse_qs
 except ImportError:
        from cgi import parse_qs
 
 # parse_qs was moved from the cgi module to the urlparse module recently.
 try:
        from urlparse 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
+       pass # Not officially supported, but let it slip
+

 std_headers = {
        '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',
 std_headers = {
        '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',


@@ -47,6 +78,119 @@ std_headers = {
 
 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
 
 
 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.
 


@@ -63,6 +207,7 @@ 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.
 


@@ -89,11 +234,13 @@ 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.
 


@@ -120,13 +267,15 @@ def sanitize_open(filename, open_mode):
                stream = open(filename, open_mode)
                return (stream, filename)
 
                stream = open(filename, open_mode)
                return (stream, filename)
 

+

 def timeconvert(timestr):
 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
+       """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.


@@ -137,6 +286,7 @@ class DownloadError(Exception):
        """
        pass
 
        """
        pass
 

+

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


@@ -145,6 +295,7 @@ class SameFileError(Exception):
        """
        pass
 
        """
        pass
 

+

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


@@ -153,6 +304,7 @@ class PostProcessingError(Exception):
        """
        pass
 
        """
        pass
 

+

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


@@ -161,6 +313,7 @@ class UnavailableVideoError(Exception):
        """
        pass
 
        """
        pass
 

+

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


@@ -176,6 +329,7 @@ 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.
 
 class YoutubeDLHandler(urllib2.HTTPHandler):
        """Handler for HTTP requests and responses.
 


@@ -185,11 +339,11 @@ class YoutubeDLHandler(urllib2.HTTPHandler):
        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.
        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:
 
        Part of this code was copied from:
 

-         http://techknack.net/python-urllib2-handlers/
-         
+       http://techknack.net/python-urllib2-handlers/
+

        Andrew Rowls, the author of that code, agreed to release it to the
        public domain.
        """
        Andrew Rowls, the author of that code, agreed to release it to the
        public domain.
        """


@@ -200,7 +354,7 @@ class YoutubeDLHandler(urllib2.HTTPHandler):
                        return zlib.decompress(data, -zlib.MAX_WBITS)
                except zlib.error:
                        return zlib.decompress(data)
                        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'):
        @staticmethod
        def addinfourl_wrapper(stream, headers, url, code):
                if hasattr(urllib2.addinfourl, 'getcode'):


@@ -208,7 +362,7 @@ class YoutubeDLHandler(urllib2.HTTPHandler):
                ret = urllib2.addinfourl(stream, headers, url)
                ret.code = code
                return ret
                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:
        def http_request(self, req):
                for h in std_headers:
                        if h in req.headers:


@@ -234,6 +388,7 @@ class YoutubeDLHandler(urllib2.HTTPHandler):
                        resp.msg = old_resp.msg
                return resp
 
                        resp.msg = old_resp.msg
                return resp
 

+

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


@@ -286,6 +441,8 @@ class FileDownloader(object):
        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.
        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


@@ -304,16 +461,6 @@ class FileDownloader(object):
                self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
                self.params = params
 
                self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
                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:


@@ -325,7 +472,7 @@ 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


@@ -463,7 +610,7 @@ class FileDownloader(object):
                        os.rename(old_filename, new_filename)
                except (IOError, OSError), err:
                        self.trouble(u'ERROR: unable to rename file')
                        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:
        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:


@@ -477,10 +624,18 @@ class FileDownloader(object):
                if filetime is None:
                        return
                try:
                if filetime is None:
                        return
                try:

-                       os.utime(filename,(time.time(), filetime))
+                       os.utime(filename, (time.time(), filetime))

                except:
                        pass
 
                except:
                        pass
 

+       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."""
                self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
        def report_destination(self, filename):
                """Report destination filename."""
                self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)


@@ -562,11 +717,44 @@ class FileDownloader(object):
                        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(u'ERROR: unable to create directories: %s' % str(err))
+                       self.trouble(u'ERROR: unable to create directory ' + unicode(err))

                        return
 
                        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.dump(info_dict, infof)
+                               finally:
+                                       infof.close()
+                       except (OSError, IOError):
+                               self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
+                               return
+

                try:
                        success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
                except (OSError, IOError), err:
                try:
                        success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
                except (OSError, IOError), err:


@@ -634,7 +822,7 @@ 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', tmpfilename]
+               basic_args = ['rtmpdump'] + [[], ['-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:
                        prevsize = os.path.getsize(tmpfilename)
                retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
                while retval == 2 or retval == 1:
                        prevsize = os.path.getsize(tmpfilename)


@@ -680,7 +868,7 @@ class FileDownloader(object):
                # 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 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)
+                       request.add_header('Range', 'bytes=%d-' % resume_len)

                        open_mode = 'ab'
 
                count = 0
                        open_mode = 'ab'
 
                count = 0


@@ -706,7 +894,7 @@ class FileDownloader(object):
                                        else:
                                                # Examine the reported length
                                                if (content_length is not None and
                                        else:
                                                # Examine the reported length
                                                if (content_length is not None and

-                                                   (resume_len - 100 < long(content_length) < resume_len + 100)):
+                                                               (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,
                                                        # 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,


@@ -751,6 +939,7 @@ class FileDownloader(object):
                        if stream is None:
                                try:
                                        (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
                        if stream is None:
                                try:
                                        (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:
                                        filename = self.undo_temp_name(tmpfilename)
                                        self.report_destination(filename)
                                except (OSError, IOError), err:


@@ -772,6 +961,9 @@ class FileDownloader(object):
                        # Apply rate limit
                        self.slow_down(start, byte_counter - resume_len)
 
                        # Apply rate limit
                        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()
                if data_len is not None and byte_counter != data_len:
                stream.close()
                self.report_finish()
                if data_len is not None and byte_counter != data_len:


@@ -784,6 +976,7 @@ class FileDownloader(object):
 
                return True
 
 
                return True
 

+

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


@@ -855,16 +1048,17 @@ 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'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
+       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'

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

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

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


@@ -1009,7 +1203,7 @@ 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))
+                                       % (video_id, el_type))

                        request = urllib2.Request(video_info_url)
                        try:
                                video_info_webpage = urllib2.urlopen(request).read()
                        request = urllib2.Request(video_info_url)
                        try:
                                video_info_webpage = urllib2.urlopen(request).read()


@@ -1067,11 +1261,19 @@ class YoutubeIE(InfoExtractor):
                                        pass
 
                # description
                                        pass
 
                # 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])
 
                # token
                video_token = urllib.unquote_plus(video_info['token'][0])


@@ -1079,10 +1281,15 @@ class YoutubeIE(InfoExtractor):
                # Decide which formats to download
                req_format = self._downloader.params.get('format', None)
 
                # Decide which formats to download
                req_format = self._downloader.params.get('format', None)
 

-               if 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
+               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_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')

-                       url_data = [dict(pairStr.split('=') for pairStr in uds.split('&')) for uds in url_data_strs]
-                       url_map = dict((ud['itag'], urllib.unquote(ud['url'])) for ud in url_data)
+                       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)
+

                        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):]


@@ -1102,13 +1309,8 @@ class YoutubeIE(InfoExtractor):
                                        self._downloader.trouble(u'ERROR: requested format not available')
                                        return
                                video_url_list = [(req_format, url_map[req_format])] # Specific format
                                        self._downloader.trouble(u'ERROR: requested format not available')
                                        return
                                video_url_list = [(req_format, url_map[req_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])]
-

                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:


@@ -1118,7 +1320,6 @@ 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({
                        try:
                                # Process video information
                                self._downloader.process_info({


@@ -1131,7 +1332,7 @@ class YoutubeIE(InfoExtractor):
                                        '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'),
                                        '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:


@@ -1322,6 +1523,7 @@ 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()


@@ -1331,25 +1533,29 @@ 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)<Attribute name="owner">(.+?)</Attribute>', 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


@@ -1371,6 +1577,7 @@ class DailymotionIE(InfoExtractor):
                except UnavailableVideoError:
                        self._downloader.trouble(u'\nERROR: unable to download video')
 
                except UnavailableVideoError:
                        self._downloader.trouble(u'\nERROR: unable to download video')
 

+

 class GoogleIE(InfoExtractor):
        """Information extractor for video.google.com."""
 
 class GoogleIE(InfoExtractor):
        """Information extractor for video.google.com."""
 


@@ -1464,7 +1671,6 @@ 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({
                try:
                        # Process video information
                        self._downloader.process_info({


@@ -1664,7 +1870,8 @@ 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)


@@ -1685,8 +1892,8 @@ 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()


@@ -1715,13 +1922,128 @@ class YahooIE(InfoExtractor):
                                'thumbnail':    video_thumbnail.decode('utf-8'),
                                'description':  video_description,
                                'thumbnail':    video_thumbnail,
                                'thumbnail':    video_thumbnail.decode('utf-8'),
                                'description':  video_description,
                                'thumbnail':    video_thumbnail,

-                               'description':  video_description,

                                'player_url':   None,
                        })
                except UnavailableVideoError:
                        self._downloader.trouble(u'\nERROR: unable to download video')
 
 
                                'player_url':   None,
                        })
                except UnavailableVideoError:
                        self._downloader.trouble(u'\nERROR: unable to download video')
 
 

+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]+)'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       @staticmethod
+       def suitable(url):
+               return (re.match(VimeoIE._VALID_URL, url) is not None)
+
+       def report_download_webpage(self, video_id):
+               """Report webpage download."""
+               self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
+
+       def _real_initialize(self):
+               return
+
+       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()
+               video_id = mobj.group(1)
+
+               # 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
+
+               # 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:
+                       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 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" % (video_id, sig, sig_exp)
+
+               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."""
 
 class GenericIE(InfoExtractor):
        """Generic last-resort information extractor."""
 


@@ -1779,11 +2101,11 @@ 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


@@ -1856,7 +2178,7 @@ class YoutubeSearchIE(InfoExtractor):
 
                prefix, query = query.split(':')
                prefix = prefix[8:]
 
                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


@@ -1870,7 +2192,7 @@ 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


@@ -1914,6 +2236,7 @@ class YoutubeSearchIE(InfoExtractor):
 
                        pagenum = pagenum + 1
 
 
                        pagenum = pagenum + 1
 

+

 class GoogleSearchIE(InfoExtractor):
        """Information Extractor for Google Video search queries."""
        _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
 class GoogleSearchIE(InfoExtractor):
        """Information Extractor for Google Video search queries."""
        _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'


@@ -1947,7 +2270,7 @@ class GoogleSearchIE(InfoExtractor):
 
                prefix, query = query.split(':')
                prefix = prefix[8:]
 
                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


@@ -1961,7 +2284,7 @@ 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


@@ -2005,6 +2328,7 @@ class GoogleSearchIE(InfoExtractor):
 
                        pagenum = pagenum + 1
 
 
                        pagenum = pagenum + 1
 

+

 class YahooSearchIE(InfoExtractor):
        """Information Extractor for Yahoo! Video search queries."""
        _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
 class YahooSearchIE(InfoExtractor):
        """Information Extractor for Yahoo! Video search queries."""
        _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'


@@ -2038,7 +2362,7 @@ class YahooSearchIE(InfoExtractor):
 
                prefix, query = query.split(':')
                prefix = prefix[8:]
 
                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


@@ -2052,7 +2376,7 @@ 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


@@ -2096,10 +2420,11 @@ 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|artist)\?.*?(p|a)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+       _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([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>'
        _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>'


@@ -2172,6 +2497,7 @@ class YoutubePlaylistIE(InfoExtractor):
                        self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
                return
 
                        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."""
 


@@ -2193,7 +2519,7 @@ class YoutubeUserIE(InfoExtractor):
        def report_download_page(self, username, start_index):
                """Report attempt to download user page."""
                self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
        def report_download_page(self, username, start_index):
                """Report attempt to download user page."""
                self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %

-                                          (username, start_index, start_index + self._GDATA_PAGE_SIZE))
+                               (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()


@@ -2255,9 +2581,9 @@ class YoutubeUserIE(InfoExtractor):
                        video_ids = video_ids[playliststart:]
                else:
                        video_ids = video_ids[playliststart:playlistend]
                        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)" %
                self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %

-                                          (username, all_ids_count, len(video_ids)))
+                               (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)
 
                for video_id in video_ids:
                        self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)


@@ -2342,6 +2668,7 @@ class DepositFilesIE(InfoExtractor):
                except UnavailableVideoError, err:
                        self._downloader.trouble(u'ERROR: unable to download file')
 
                except UnavailableVideoError, err:
                        self._downloader.trouble(u'ERROR: unable to download file')
 

+

 class FacebookIE(InfoExtractor):
        """Information Extractor for Facebook"""
 
 class FacebookIE(InfoExtractor):
        """Information Extractor for Facebook"""
 


@@ -2508,10 +2835,7 @@ class FacebookIE(InfoExtractor):
                                        pass
 
                # description
                                        pass
 
                # description

-               video_description = 'No description available.'
-               if (self._downloader.params.get('forcedescription', False) and
-                   'description' in video_info):
-                       video_description = video_info['description']
+               video_description = video_info.get('description', 'No description available.')

 
                url_map = video_info['video_urls']
                if len(url_map.keys()) > 0:
 
                url_map = video_info['video_urls']
                if len(url_map.keys()) > 0:


@@ -2546,7 +2870,6 @@ class FacebookIE(InfoExtractor):
                        # Extension
                        video_extension = self._video_extensions.get(format_param, 'mp4')
 
                        # Extension
                        video_extension = self._video_extensions.get(format_param, 'mp4')
 

-                       # Find the video URL in fmt_url_map or conn paramters

                        try:
                                # Process video information
                                self._downloader.process_info({
                        try:
                                # Process video information
                                self._downloader.process_info({


@@ -2565,6 +2888,297 @@ class FacebookIE(InfoExtractor):
                        except UnavailableVideoError, err:
                                self._downloader.trouble(u'\nERROR: unable to download video')
 
                        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(/.+)$'
+       _URL_EXT = r'^.*\.([a-z0-9]+)$'
+
+       @staticmethod
+       def suitable(url):
+               return (re.match(BlipTVIE._VALID_URL, url) is not None)
+
+       def report_extraction(self, file_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[blip.tv] %s: Extracting information' % file_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 '?' 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))
+               try:
+                       json_code = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download 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)
+
+                       self._downloader.increment_downloads()
+
+                       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
+
+               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]+)/([^?/]+).*'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+       
+       @staticmethod
+       def suitable(url):
+               return (re.match(MyVideoIE._VALID_URL, url) is not None)
+
+       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:
+                       print(video_url)
+                       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>.*)$'
+
+       @staticmethod
+       def suitable(url):
+               return (re.match(ComedyCentralIE._VALID_URL, url) is not None)
+
+       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_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
+               show_id = mMovieParams[0][2]
+               ACT_COUNT = { # TODO: Detect this dynamically
+                       'thedailyshow.com': 4,
+                       'colbertnation.com': 3,
+               }.get(show_id, 4)
+               OFFSET = {
+                       'thedailyshow.com': 1,
+                       'colbertnation.com': 1,
+               }.get(show_id, 1)
+
+               first_player_url = mMovieParams[0][0]
+               startMediaNum = int(mMovieParams[0][3]) + OFFSET
+               movieId = mMovieParams[0][1]
+
+               playerReq = urllib2.Request(first_player_url)
+               self.report_player_url(epTitle)
+               try:
+                       playerResponse = urllib2.urlopen(playerReq)
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download player: %s' % unicode(err))
+                       return
+               player_url = playerResponse.geturl()
+
+               for actNum in range(ACT_COUNT):
+                       mediaNum = startMediaNum + actNum
+                       mediaId = movieId + str(mediaNum)
+                       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 ' + str(mediaNum) + ': No videos found')
+                               continue
+
+                       # For now, just pick the highest bitrate
+                       format,video_url = turls[-1]
+
+                       self._downloader.increment_downloads()
+
+                       effTitle = show_id.replace('.com', '') + '-' + epTitle
+                       info = {
+                               'id': str(mediaNum),
+                               'url': video_url,
+                               'uploader': show_id,
+                               'upload_date': 'NA',
+                               'title': effTitle,
+                               'stitle': self._simplify_title(effTitle),
+                               'ext': 'mp4',
+                               'format': format,
+                               'thumbnail': None,
+                               'description': 'TODO: Not yet supported',
+                               'player_url': player_url
+                       }
+
+                       try:
+                               self._downloader.process_info(info)
+                       except UnavailableVideoError, err:
+                               self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum))
+                               continue
+
+

 class PostProcessor(object):
        """Post Processor class.
 
 class PostProcessor(object):
        """Post Processor class.
 


@@ -2611,6 +3225,7 @@ class PostProcessor(object):
                """
                return information # by default, do nothing
 
                """
                return information # by default, do nothing
 

+

 class FFmpegExtractAudioPP(PostProcessor):
 
        def __init__(self, downloader=None, preferredcodec=None):
 class FFmpegExtractAudioPP(PostProcessor):
 
        def __init__(self, downloader=None, preferredcodec=None):


@@ -2693,311 +3308,393 @@ class FFmpegExtractAudioPP(PostProcessor):
                information['filepath'] = new_path
                return information
 
                information['filepath'] = new_path
                return information
 

-### MAIN PROGRAM ###
-if __name__ == '__main__':
+
+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()
+               finally:
+                       urlh.close()
+       except (IOError, OSError), err:
+               sys.exit('ERROR: unable to download latest version')
+

        try:
        try:

-               # Modules needed only when running the main program
-               import getpass
-               import optparse
+               outf = open(filename, 'wb')
+               try:
+                       outf.write(newcontent)
+               finally:
+                       outf.close()
+       except (IOError, OSError), err:
+               sys.exit('ERROR: unable to overwrite current version')

 
 

-               # Function to update the program file with the latest version from the repository.
-               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_screen('Updated youtube-dl. Restart to use the new version.')

 
 

-                       downloader.to_screen('Updating to latest stable version...')
-                       try:
-                               latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
-                               latest_version = urllib.urlopen(latest_url).read().strip()
-                               prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
-                               newcontent = urllib.urlopen(prog_url).read()
-                       except (IOError, OSError), err:
-                               sys.exit('ERROR: unable to download latest version')
-                       try:
-                               stream = open(filename, 'w')
-                               stream.write(newcontent)
-                               stream.close()
-                       except (IOError, OSError), err:
-                               sys.exit('ERROR: unable to overwrite current version')
-                       downloader.to_screen('Updated to version %s' % latest_version)
-
-               # Parse command line
-               parser = optparse.OptionParser(
-                       usage='Usage: %prog [options] url...',
-                       version='2011.08.04',
-                       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)
-               parser.add_option('--playlist-start',
-                               dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
-               parser.add_option('--playlist-end',
-                               dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
-               parser.add_option('--dump-user-agent',
-                               action='store_true', dest='dump_user_agent',
-                               help='display the current browser identification', default=False)
-
-               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('--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('--get-filename',
-                               action='store_true', dest='getfilename',
-                               help='simulate, quiet but print output filename', 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)
-               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('-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')
-               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('--cookies',
-                               dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
-               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)
-               parser.add_option_group(filesystem)
-
-               postproc = optparse.OptionGroup(parser, 'Post-processing Options')
-               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" or "mp3"; best by default')
-               parser.add_option_group(postproc)
-
-               (opts, args) = parser.parse_args()
-
-               # 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')
+def parseOpts():
+       # Deferred imports
+       import getpass
+       import optparse

 
 

-               # Dump user agent
-               if opts.dump_user_agent:
-                       print std_headers['User-Agent']
-                       sys.exit(0)
+       def _format_option_string(option):
+               ''' ('-o', '--option') -> -o, --format METAVAR'''

 
 

-               # General configuration
-               cookie_processor = urllib2.HTTPCookieProcessor(jar)
-               urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler()))
-               socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+               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)

 
 

-               # 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
-
-               # 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:
                try:

-                       opts.playliststart = long(opts.playliststart)
-                       if opts.playliststart <= 0:
-                               raise ValueError
-               except (TypeError, ValueError), err:
-                       parser.error(u'invalid playlist start number specified')
+                       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...',
+               'conflict_handler' : 'resolve',
+       }
+
+       parser = optparse.OptionParser(**kw)
+
+       # option groups
+       general        = optparse.OptionGroup(parser, 'General Options')
+       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('--playlist-start',
+                       dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
+       general.add_option('--playlist-end',
+                       dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
+       general.add_option('--dump-user-agent',
+                       action='store_true', dest='dump_user_agent',
+                       help='display the current browser identification', default=False)
+
+       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='-1')
+       video_format.add_option('--max-quality',
+                       action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
+
+
+       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('--get-filename',
+                       action='store_true', dest='getfilename',
+                       help='simulate, quiet but print output filename', 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')
+       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('--cookies',
+                       dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
+       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" or "mp3"; best by default')
+
+
+       parser.add_option_group(general)
+       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 main():
+       parser, opts, args = parseOpts()
+
+       # Open appropriate CookieJar
+       if opts.cookiefile is None:
+               jar = cookielib.CookieJar()
+       else:

                try:
                try:

-                       opts.playlistend = long(opts.playlistend)
-                       if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
-                               raise ValueError
-               except (TypeError, ValueError), err:
-                       parser.error(u'invalid playlist end number specified')
-               if opts.extractaudio:
-                       if opts.audioformat not in ['best', 'aac', 'mp3']:
-                               parser.error(u'invalid audio format 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)
-               deposit_files_ie = DepositFilesIE()
-               facebook_ie = FacebookIE()
-               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 or opts.getfilename),
-                       'forceurl': opts.geturl,
-                       'forcetitle': opts.gettitle,
-                       'forcethumbnail': opts.getthumbnail,
-                       'forcedescription': opts.getdescription,
-                       'forcefilename': opts.getfilename,
-                       'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
-                       '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 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,
-                       })
-               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)
-               fd.add_info_extractor(deposit_files_ie)
-               fd.add_info_extractor(facebook_ie)
-
-               # This must come last since it's the
-               # fallback if none of the others work
-               fd.add_info_extractor(generic_ie)
-
-               # PostProcessors
-               if opts.extractaudio:
-                       fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat))
-
-               # 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')
+                       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)
+
+       # 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)
+
+       # Batch file verification
+       batchurls = []
+       if opts.batchfile is not None:
+               try:
+                       if opts.batchfile == '-':
+                               batchfd = sys.stdin

                        else:
                        else:

-                               sys.exit()
-               retcode = fd.download(all_urls)
+                               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
+
+       # 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']:
+                       parser.error(u'invalid audio format 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)
+       deposit_files_ie = DepositFilesIE()
+       facebook_ie = FacebookIE()
+       bliptv_ie = BlipTVIE()
+       vimeo_ie = VimeoIE()
+       myvideo_ie = MyVideoIE()
+       comedycentral_ie = ComedyCentralIE()
+
+       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 or opts.getfilename),
+               'forceurl': opts.geturl,
+               'forcetitle': opts.gettitle,
+               'forcethumbnail': opts.getthumbnail,
+               'forcedescription': opts.getdescription,
+               'forcefilename': opts.getfilename,
+               'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
+               '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 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,
+               })
+       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)
+       fd.add_info_extractor(deposit_files_ie)
+       fd.add_info_extractor(facebook_ie)
+       fd.add_info_extractor(bliptv_ie)
+       fd.add_info_extractor(vimeo_ie)
+       fd.add_info_extractor(myvideo_ie)
+       fd.add_info_extractor(comedycentral_ie)
+
+       # This must come last since it's the
+       # fallback if none of the others work
+       fd.add_info_extractor(generic_ie)
+
+       # PostProcessors
+       if opts.extractaudio:
+               fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat))
+
+       # 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')
+       # 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)

 
 

-               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')
        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')

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