X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/c14c8740bfc1b94d4ec18f886c6e001acf171999..97d9ce777ddbef73838c06e34e5f81e35d50a47b:/youtube-dl?ds=sidebyside
diff --git a/youtube-dl b/youtube-dl
index 9e28621..3a37fae 100755
--- a/youtube-dl
+++ b/youtube-dl
@@ -1,10 +1,29 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
-# Author: Ricardo Garcia Gonzalez
-# Author: Danny Colligan
-# Author: Benjamin Johnson
-# License: Public domain code
+
+__author__ = (
+ 'Ricardo Garcia Gonzalez',
+ 'Danny Colligan',
+ 'Benjamin Johnson',
+ 'Vasyl\' Vavrychuk',
+ 'Witold Baryluk',
+ 'PaweÅ Paprota',
+ 'Gergely Imreh',
+ 'Rogério Brito',
+ 'Philipp Hagemeister',
+ 'Sören Schulze',
+ )
+
+__license__ = 'Public Domain'
+__version__ = '2011.10.19'
+
+UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
+
+import cookielib
+import datetime
+import gzip
import htmlentitydefs
+import HTMLParser
import httplib
import locale
import math
@@ -19,6 +38,20 @@ import sys
import time
import urllib
import urllib2
+import warnings
+import zlib
+
+if os.name == 'nt':
+ import ctypes
+
+try:
+ import email.utils
+except ImportError: # Python 2.4
+ import email.Utils
+try:
+ import cStringIO as StringIO
+except ImportError:
+ import StringIO
# parse_qs was moved from the cgi module to the urlparse module recently.
try:
@@ -26,15 +59,139 @@ try:
except ImportError:
from cgi import parse_qs
+try:
+ import lxml.etree
+except ImportError:
+ pass # Handled below
+
+try:
+ import xml.etree.ElementTree
+except ImportError: # Python<2.5: Not officially supported, but let it slip
+ warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.')
+
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2',
+ 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
- 'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
+ 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+ 'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'en-us,en;q=0.5',
}
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
+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.
@@ -51,15 +208,86 @@ def preferredencoding():
yield pref
return yield_preferredencoding().next()
+
+def htmlentity_transform(matchobj):
+ """Transforms an HTML entity to a Unicode character.
+
+ This function receives a match object and is intended to be used with
+ the re.sub() function.
+ """
+ entity = matchobj.group(1)
+
+ # Known non-numeric HTML entity
+ if entity in htmlentitydefs.name2codepoint:
+ return unichr(htmlentitydefs.name2codepoint[entity])
+
+ # Unicode character
+ mobj = re.match(ur'(?u)#(x?\d+)', entity)
+ if mobj is not None:
+ numstr = mobj.group(1)
+ if numstr.startswith(u'x'):
+ base = 16
+ numstr = u'0%s' % numstr
+ else:
+ base = 10
+ return unichr(long(numstr, base))
+
+ # 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_open(filename, open_mode):
+ """Try to open the given filename, and slightly tweak it if this fails.
+
+ Attempts to open the given filename. If this fails, it tries to change
+ the filename slightly, step by step, until it's either able to open it
+ or it fails and raises a final exception, like the standard open()
+ function.
+
+ It returns the tuple (stream, definitive_file_name).
+ """
+ try:
+ if filename == u'-':
+ if sys.platform == 'win32':
+ import msvcrt
+ msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
+ return (sys.stdout, filename)
+ stream = open(filename, open_mode)
+ return (stream, filename)
+ except (IOError, OSError), err:
+ # In case of error, try to remove win32 forbidden chars
+ filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
+
+ # An exception here should be caught in the caller
+ stream = open(filename, open_mode)
+ return (stream, filename)
+
+
+def timeconvert(timestr):
+ """Convert RFC 2822 defined time string into system timestamp"""
+ timestamp = None
+ timetuple = email.utils.parsedate_tz(timestr)
+ if timetuple is not None:
+ timestamp = email.utils.mktime_tz(timetuple)
+ return timestamp
+
+
class DownloadError(Exception):
"""Download Error exception.
-
+
This exception may be thrown by FileDownloader objects if they are not
configured to continue on errors. They will contain the appropriate
error message.
"""
pass
+
class SameFileError(Exception):
"""Same File exception.
@@ -68,6 +296,7 @@ class SameFileError(Exception):
"""
pass
+
class PostProcessingError(Exception):
"""Post Processing exception.
@@ -76,7 +305,8 @@ class PostProcessingError(Exception):
"""
pass
-class UnavailableFormatError(Exception):
+
+class UnavailableVideoError(Exception):
"""Unavailable Format exception.
This exception will be thrown when a video is requested
@@ -84,6 +314,7 @@ class UnavailableFormatError(Exception):
"""
pass
+
class ContentTooShortError(Exception):
"""Content Too Short exception.
@@ -99,6 +330,66 @@ class ContentTooShortError(Exception):
self.downloaded = downloaded
self.expected = expected
+
+class YoutubeDLHandler(urllib2.HTTPHandler):
+ """Handler for HTTP requests and responses.
+
+ This class, when installed with an OpenerDirector, automatically adds
+ the standard headers to every HTTP request and handles gzipped and
+ deflated responses from web servers. If compression is to be avoided in
+ a particular request, the original request in the program code only has
+ to include the HTTP header "Youtubedl-No-Compression", which will be
+ removed before making the real request.
+
+ Part of this code was copied from:
+
+ http://techknack.net/python-urllib2-handlers/
+
+ Andrew Rowls, the author of that code, agreed to release it to the
+ public domain.
+ """
+
+ @staticmethod
+ def deflate(data):
+ try:
+ return zlib.decompress(data, -zlib.MAX_WBITS)
+ except zlib.error:
+ return zlib.decompress(data)
+
+ @staticmethod
+ def addinfourl_wrapper(stream, headers, url, code):
+ if hasattr(urllib2.addinfourl, 'getcode'):
+ return urllib2.addinfourl(stream, headers, url, code)
+ ret = urllib2.addinfourl(stream, headers, url)
+ ret.code = code
+ return ret
+
+ def http_request(self, req):
+ for h in std_headers:
+ if h in req.headers:
+ del req.headers[h]
+ req.add_header(h, std_headers[h])
+ if 'Youtubedl-no-compression' in req.headers:
+ if 'Accept-encoding' in req.headers:
+ del req.headers['Accept-encoding']
+ del req.headers['Youtubedl-no-compression']
+ return req
+
+ def http_response(self, req, resp):
+ old_resp = resp
+ # gzip
+ if resp.headers.get('Content-encoding', '') == 'gzip':
+ gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
+ resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
+ resp.msg = old_resp.msg
+ # deflate
+ if resp.headers.get('Content-encoding', '') == 'deflate':
+ gz = StringIO.StringIO(self.deflate(resp.read()))
+ resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
+ resp.msg = old_resp.msg
+ return resp
+
+
class FileDownloader(object):
"""File Downloader class.
@@ -126,43 +417,53 @@ class FileDownloader(object):
Available options:
- username: Username for authentication purposes.
- password: Password for authentication purposes.
- usenetrc: Use netrc for authentication instead.
- quiet: Do not print messages to stdout.
- forceurl: Force printing final URL.
- forcetitle: Force printing title.
- simulate: Do not download the video files.
- format: Video format code.
- outtmpl: Template for output names.
- ignoreerrors: Do not stop on download errors.
- ratelimit: Download speed limit, in bytes/sec.
- nooverwrites: Prevent overwriting files.
- continuedl: Try to continue downloads if possible.
+ username: Username for authentication purposes.
+ password: Password for authentication purposes.
+ usenetrc: Use netrc for authentication instead.
+ quiet: Do not print messages to stdout.
+ forceurl: Force printing final URL.
+ forcetitle: Force printing title.
+ forcethumbnail: Force printing thumbnail URL.
+ forcedescription: Force printing description.
+ forcefilename: Force printing final filename.
+ simulate: Do not download the video files.
+ format: Video format code.
+ format_limit: Highest quality format to try.
+ outtmpl: Template for output names.
+ ignoreerrors: Do not stop on download errors.
+ ratelimit: Download speed limit, in bytes/sec.
+ nooverwrites: Prevent overwriting files.
+ retries: Number of times to retry for HTTP error 5xx
+ continuedl: Try to continue downloads if possible.
+ noprogress: Do not print the progress bar.
+ playliststart: Playlist item to start at.
+ playlistend: Playlist item to end at.
+ matchtitle: Download only matching titles.
+ rejecttitle: Reject downloads for matching titles.
+ logtostderr: Log messages to stderr instead of stdout.
+ consoletitle: Display progress in console window's titlebar.
+ nopart: Do not use temporary .part files.
+ updatetime: Use the Last-modified header to set output file timestamps.
+ writedescription: Write the video description to a .description file
+ writeinfojson: Write the video description to a .info.json file
"""
params = None
_ies = []
_pps = []
_download_retcode = None
+ _num_downloads = None
+ _screen_file = None
def __init__(self, params):
"""Create a FileDownloader object with the given options."""
self._ies = []
self._pps = []
self._download_retcode = 0
+ self._num_downloads = 0
+ 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:
@@ -174,7 +475,7 @@ class FileDownloader(object):
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
@@ -227,36 +528,42 @@ class FileDownloader(object):
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
return long(round(number * multiplier))
- @staticmethod
- def verify_url(url):
- """Verify a URL is valid and data could be downloaded. Return real data URL."""
- request = urllib2.Request(url, None, std_headers)
- data = urllib2.urlopen(request)
- data.read(1)
- url = data.geturl()
- data.close()
- return url
-
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
ie.set_downloader(self)
-
+
def add_post_processor(self, pp):
"""Add a PostProcessor object to the end of the chain."""
self._pps.append(pp)
pp.set_downloader(self)
-
- def to_stdout(self, message, skip_eol=False):
+
+ def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):
"""Print message to stdout if not in quiet mode."""
- if not self.params.get('quiet', False):
- print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
- sys.stdout.flush()
-
+ try:
+ if not self.params.get('quiet', False):
+ terminator = [u'\n', u''][skip_eol]
+ print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
+ self._screen_file.flush()
+ except (UnicodeEncodeError), err:
+ if not ignore_encoding_errors:
+ raise
+
def to_stderr(self, message):
"""Print message to stderr."""
print >>sys.stderr, message.encode(preferredencoding())
-
+
+ def to_cons_title(self, message):
+ """Set console/terminal window title to message."""
+ if not self.params.get('consoletitle', False):
+ return
+ if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
+ # c_wchar_p() might not be necessary if `message` is
+ # already of type unicode()
+ ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
+ elif 'TERM' in os.environ:
+ sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding()))
+
def fixed_template(self):
"""Checks if the output template is fixed."""
return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
@@ -287,83 +594,204 @@ class FileDownloader(object):
if speed > rate_limit:
time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
+ def temp_name(self, filename):
+ """Returns a temporary filename for the given filename."""
+ if self.params.get('nopart', False) or filename == u'-' or \
+ (os.path.exists(filename) and not os.path.isfile(filename)):
+ return filename
+ return filename + u'.part'
+
+ def undo_temp_name(self, filename):
+ if filename.endswith(u'.part'):
+ return filename[:-len(u'.part')]
+ return filename
+
+ def try_rename(self, old_filename, new_filename):
+ try:
+ if old_filename == new_filename:
+ return
+ os.rename(old_filename, new_filename)
+ except (IOError, OSError), err:
+ self.trouble(u'ERROR: unable to rename file')
+
+ def try_utime(self, filename, last_modified_hdr):
+ """Try to set the last-modified time of the given file."""
+ if last_modified_hdr is None:
+ return
+ if not os.path.isfile(filename):
+ return
+ timestr = last_modified_hdr
+ if timestr is None:
+ return
+ filetime = timeconvert(timestr)
+ if filetime is None:
+ return filetime
+ try:
+ os.utime(filename, (time.time(), filetime))
+ except:
+ pass
+ return filetime
+
+ def report_writedescription(self, descfn):
+ """ Report that the description file is being written """
+ self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True)
+
+ def report_writeinfojson(self, infofn):
+ """ Report that the metadata file has been written """
+ self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True)
+
def report_destination(self, filename):
"""Report destination filename."""
- self.to_stdout(u'[download] Destination: %s' % filename)
-
+ self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
+
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
"""Report download progress."""
- self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
+ if self.params.get('noprogress', False):
+ return
+ self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
+ self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
+ (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
def report_resuming_byte(self, resume_len):
- """Report attemtp to resume at given byte."""
- self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
-
+ """Report attempt to resume at given byte."""
+ self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
+
+ def report_retry(self, count, retries):
+ """Report retry in case of HTTP error 5xx"""
+ self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
+
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
- self.to_stdout(u'[download] %s has already been downloaded' % file_name)
-
+ try:
+ self.to_screen(u'[download] %s has already been downloaded' % file_name)
+ except (UnicodeEncodeError), err:
+ self.to_screen(u'[download] The file has already been downloaded')
+
def report_unable_to_resume(self):
"""Report it was impossible to resume download."""
- self.to_stdout(u'[download] Unable to resume')
-
+ self.to_screen(u'[download] Unable to resume')
+
def report_finish(self):
"""Report download finished."""
- self.to_stdout(u'')
+ if self.params.get('noprogress', False):
+ self.to_screen(u'[download] Download completed')
+ else:
+ self.to_screen(u'')
+
+ def increment_downloads(self):
+ """Increment the ordinal that assigns a number to each file."""
+ self._num_downloads += 1
+
+ def prepare_filename(self, info_dict):
+ """Generate the output filename."""
+ try:
+ template_dict = dict(info_dict)
+ template_dict['epoch'] = unicode(long(time.time()))
+ template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
+ filename = self.params['outtmpl'] % template_dict
+ return filename
+ except (ValueError, KeyError), err:
+ self.trouble(u'ERROR: invalid system charset or erroneous output template')
+ return None
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
+ filename = self.prepare_filename(info_dict)
+
+ # Forced printings
+ if self.params.get('forcetitle', False):
+ print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forceurl', False):
+ print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
+ print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forcedescription', False) and 'description' in info_dict:
+ print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forcefilename', False) and filename is not None:
+ print filename.encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forceformat', False):
+ print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')
+
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
- # Verify URL if it's an HTTP one
- if info_dict['url'].startswith('http'):
- try:
- info_dict['url'] = self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
- except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
- raise UnavailableFormatError
+ return
- # Forced printings
- if self.params.get('forcetitle', False):
- print info_dict['title'].encode(preferredencoding())
- if self.params.get('forceurl', False):
- print info_dict['url'].encode(preferredencoding())
+ if filename is None:
+ return
+ matchtitle=self.params.get('matchtitle',False)
+ rejecttitle=self.params.get('rejecttitle',False)
+ title=info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
+ self.to_screen(u'[download] "%s" title did not match pattern "%s"' % (title, matchtitle))
+ return
+ if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
+ self.to_screen(u'[download] "%s" title matched reject pattern "%s"' % (title, rejecttitle))
return
- try:
- template_dict = dict(info_dict)
- template_dict['epoch'] = unicode(long(time.time()))
- filename = self.params['outtmpl'] % template_dict
- except (ValueError, KeyError), err:
- self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
if self.params.get('nooverwrites', False) and os.path.exists(filename):
- self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
+ self.to_stderr(u'WARNING: file exists and will be skipped')
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:
- self.trouble('ERROR: unable to create directories: %s' % str(err))
+ self.trouble(u'ERROR: unable to create directory ' + unicode(err))
return
- try:
- success = self._do_download(filename, info_dict['url'].encode('utf-8'))
- except (OSError, IOError), err:
- raise UnavailableFormatError
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.trouble('ERROR: unable to download video data: %s' % str(err))
- return
- except (ContentTooShortError, ), err:
- self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
- return
+ if self.params.get('writedescription', False):
+ try:
+ descfn = filename + '.description'
+ self.report_writedescription(descfn)
+ descfile = open(descfn, 'wb')
+ try:
+ descfile.write(info_dict['description'].encode('utf-8'))
+ finally:
+ descfile.close()
+ except (OSError, IOError):
+ self.trouble(u'ERROR: Cannot write description file ' + descfn)
+ return
+
+ if self.params.get('writeinfojson', False):
+ infofn = filename + '.info.json'
+ self.report_writeinfojson(infofn)
+ try:
+ json.dump
+ except (NameError,AttributeError):
+ self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
+ return
+ try:
+ infof = open(infofn, 'wb')
+ try:
+ json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
+ json.dump(json_info_dict, infof)
+ finally:
+ infof.close()
+ except (OSError, IOError):
+ self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
+ return
- if success:
+ if not self.params.get('skip_download', False):
try:
- self.post_process(filename, info_dict)
- except (PostProcessingError), err:
- self.trouble('ERROR: postprocessing: %s' % str(err))
+ success = self._do_download(filename, info_dict)
+ except (OSError, IOError), err:
+ raise UnavailableVideoError
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.trouble(u'ERROR: unable to download video data: %s' % str(err))
+ return
+ except (ContentTooShortError, ), err:
+ self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
+
+ if success:
+ try:
+ self.post_process(filename, info_dict)
+ except (PostProcessingError), err:
+ self.trouble(u'ERROR: postprocessing: %s' % str(err))
+ return
def download(self, url_list):
"""Download a given list of URLs."""
@@ -387,7 +815,7 @@ class FileDownloader(object):
break
if not suitable_found:
- self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
+ self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
return self._download_retcode
@@ -399,9 +827,10 @@ class FileDownloader(object):
info = pp.run(info)
if info is None:
break
-
- def _download_with_rtmpdump(self, filename, url):
+
+ def _download_with_rtmpdump(self, filename, url, player_url):
self.report_destination(filename)
+ tmpfilename = self.temp_name(filename)
# Check for rtmpdump first
try:
@@ -413,63 +842,120 @@ class FileDownloader(object):
# Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrumpted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK.
- basic_args = ['rtmpdump', '-q', '-r', url, '-o', filename]
+ basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
while retval == 2 or retval == 1:
- self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename), skip_eol=True)
- time.sleep(2.0) # This seems to be needed
+ prevsize = os.path.getsize(tmpfilename)
+ self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
+ time.sleep(5.0) # This seems to be needed
retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
+ cursize = os.path.getsize(tmpfilename)
+ if prevsize == cursize and retval == 1:
+ break
+ # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
+ if prevsize == cursize and retval == 2 and cursize > 1024:
+ self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
+ retval = 0
+ break
if retval == 0:
- self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
+ self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
+ self.try_rename(tmpfilename, filename)
return True
else:
- self.trouble('ERROR: rtmpdump exited with code %d' % retval)
+ self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
return False
- def _do_download(self, filename, url):
+ def _do_download(self, filename, info_dict):
+ url = info_dict['url']
+ player_url = info_dict.get('player_url', None)
+
+ # Check file already present
+ if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
+ self.report_file_already_downloaded(filename)
+ return True
+
# Attempt to download using rtmpdump
if url.startswith('rtmp'):
- return self._download_with_rtmpdump(filename, url)
+ return self._download_with_rtmpdump(filename, url, player_url)
+ tmpfilename = self.temp_name(filename)
stream = None
- open_mode = 'wb'
- basic_request = urllib2.Request(url, None, std_headers)
- request = urllib2.Request(url, None, std_headers)
+
+ # Do not include the Accept-Encoding header
+ headers = {'Youtubedl-no-compression': 'True'}
+ basic_request = urllib2.Request(url, None, headers)
+ request = urllib2.Request(url, None, headers)
# Establish possible resume length
- if os.path.isfile(filename):
- resume_len = os.path.getsize(filename)
+ if os.path.isfile(tmpfilename):
+ resume_len = os.path.getsize(tmpfilename)
else:
resume_len = 0
- # Request parameters in case of being able to resume
- if self.params.get('continuedl', False) and resume_len != 0:
- self.report_resuming_byte(resume_len)
- request.add_header('Range','bytes=%d-' % resume_len)
- open_mode = 'ab'
-
- # Establish connection
- try:
- data = urllib2.urlopen(request)
- except (urllib2.HTTPError, ), err:
- if err.code != 416: # 416 is 'Requested range not satisfiable'
- raise
- # Unable to resume
- data = urllib2.urlopen(basic_request)
- content_length = data.info()['Content-Length']
-
- if content_length is not None and long(content_length) == resume_len:
- # Because the file had already been fully downloaded
- self.report_file_already_downloaded(filename)
- return True
+ open_mode = 'wb'
+ if resume_len != 0:
+ if self.params.get('continuedl', False):
+ self.report_resuming_byte(resume_len)
+ request.add_header('Range','bytes=%d-' % resume_len)
+ open_mode = 'ab'
else:
- # Because the server didn't let us
- self.report_unable_to_resume()
- open_mode = 'wb'
+ resume_len = 0
+
+ count = 0
+ retries = self.params.get('retries', 0)
+ while count <= retries:
+ # Establish connection
+ try:
+ if count == 0 and 'urlhandle' in info_dict:
+ data = info_dict['urlhandle']
+ data = urllib2.urlopen(request)
+ break
+ except (urllib2.HTTPError, ), err:
+ if (err.code < 500 or err.code >= 600) and err.code != 416:
+ # Unexpected HTTP error
+ raise
+ elif err.code == 416:
+ # Unable to resume (requested range not satisfiable)
+ try:
+ # Open the connection again without the range header
+ data = urllib2.urlopen(basic_request)
+ content_length = data.info()['Content-Length']
+ except (urllib2.HTTPError, ), err:
+ if err.code < 500 or err.code >= 600:
+ raise
+ else:
+ # Examine the reported length
+ if (content_length is not None and
+ (resume_len - 100 < long(content_length) < resume_len + 100)):
+ # The file had already been fully downloaded.
+ # Explanation to the above condition: in issue #175 it was revealed that
+ # YouTube sometimes adds or removes a few bytes from the end of the file,
+ # changing the file size slightly and causing problems for some users. So
+ # I decided to implement a suggested change and consider the file
+ # completely downloaded if the file size differs less than 100 bytes from
+ # the one in the hard drive.
+ self.report_file_already_downloaded(filename)
+ self.try_rename(tmpfilename, filename)
+ return True
+ else:
+ # The length does not match, we start the download over
+ self.report_unable_to_resume()
+ open_mode = 'wb'
+ break
+ # Retry
+ count += 1
+ if count <= retries:
+ self.report_retry(count, retries)
+
+ if count > retries:
+ self.trouble(u'ERROR: giving up after %s retries' % retries)
+ return False
data_len = data.info().get('Content-length', None)
+ if data_len is not None:
+ data_len = long(data_len) + resume_len
data_len_str = self.format_bytes(data_len)
- byte_counter = 0
+ byte_counter = 0 + resume_len
block_size = 1024
start = time.time()
while True:
@@ -477,36 +963,55 @@ class FileDownloader(object):
before = time.time()
data_block = data.read(block_size)
after = time.time()
- data_block_len = len(data_block)
- if data_block_len == 0:
+ if len(data_block) == 0:
break
- byte_counter += data_block_len
+ byte_counter += len(data_block)
# Open file just in time
if stream is None:
try:
- stream = open(filename, open_mode)
+ (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
+ assert stream is not None
+ filename = self.undo_temp_name(tmpfilename)
self.report_destination(filename)
except (OSError, IOError), err:
- self.trouble('ERROR: unable to open for writing: %s' % str(err))
+ self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
return False
- stream.write(data_block)
- block_size = self.best_block_size(after - before, data_block_len)
+ try:
+ stream.write(data_block)
+ except (IOError, OSError), err:
+ self.trouble(u'\nERROR: unable to write data: %s' % str(err))
+ return False
+ block_size = self.best_block_size(after - before, len(data_block))
# Progress message
- percent_str = self.calc_percent(byte_counter, data_len)
- eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
- speed_str = self.calc_speed(start, time.time(), byte_counter)
- self.report_progress(percent_str, data_len_str, speed_str, eta_str)
+ speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
+ if data_len is None:
+ self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
+ else:
+ percent_str = self.calc_percent(byte_counter, data_len)
+ eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
+ self.report_progress(percent_str, data_len_str, speed_str, eta_str)
# Apply rate limit
- self.slow_down(start, byte_counter)
+ self.slow_down(start, byte_counter - resume_len)
+ if stream is None:
+ self.trouble(u'\nERROR: Did not get any data blocks')
+ return False
+ stream.close()
self.report_finish()
- if data_len is not None and str(byte_counter) != data_len:
+ if data_len is not None and byte_counter != data_len:
raise ContentTooShortError(byte_counter, long(data_len))
+ self.try_rename(tmpfilename, filename)
+
+ # Update file modification time
+ if self.params.get('updatetime', True):
+ info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
+
return True
+
class InfoExtractor(object):
"""Information Extractor class.
@@ -525,11 +1030,20 @@ class InfoExtractor(object):
title: Literal title.
stitle: Simplified title.
ext: Video filename extension.
+ format: Video format.
+ player_url: SWF Player URL (may be None).
+
+ The following fields are optional. Their primary purpose is to allow
+ youtube-dl to serve as the backend for a video search function, such
+ as the one in youtube2mp3. They are only used when their respective
+ forced printing functions are called:
+
+ thumbnail: Full URL to a video thumbnail image.
+ description: One-line video description.
Subclasses of this one should re-define the _real_initialize() and
- _real_extract() methods, as well as the suitable() static method.
- Probably, they should also be instantiated and added to the main
- downloader.
+ _real_extract() methods and define a _VALID_URL regexp.
+ Probably, they should also be added to the list of extractors.
"""
_ready = False
@@ -540,10 +1054,9 @@ class InfoExtractor(object):
self._ready = False
self.set_downloader(downloader)
- @staticmethod
- def suitable(url):
+ def suitable(self, url):
"""Receives a URL and returns True if suitable for this IE."""
- return False
+ return re.match(self._VALID_URL, url) is not None
def initialize(self):
"""Initializes an instance (authentication, etc)."""
@@ -559,7 +1072,7 @@ class InfoExtractor(object):
def set_downloader(self, downloader):
"""Sets the downloader for this IE."""
self._downloader = downloader
-
+
def _real_initialize(self):
"""Real initialization process. Redefine in subclasses."""
pass
@@ -568,78 +1081,82 @@ class InfoExtractor(object):
"""Real extraction process. Redefine in subclasses."""
pass
+
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
- _LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
- _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
+ _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
+ _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'
- _available_formats = ['37', '22', '35', '18', '5', '17', '13', None] # listed in order of priority for -b flag
+ # Listed in order of quality
+ _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
'18': 'mp4',
'22': 'mp4',
'37': 'mp4',
+ '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
+ '43': 'webm',
+ '44': 'webm',
+ '45': 'webm',
}
-
- @staticmethod
- def suitable(url):
- return (re.match(YoutubeIE._VALID_URL, url) is not None)
-
- @staticmethod
- def htmlentity_transform(matchobj):
- """Transforms an HTML entity to a Unicode character."""
- entity = matchobj.group(1)
-
- # Known non-numeric HTML entity
- if entity in htmlentitydefs.name2codepoint:
- return unichr(htmlentitydefs.name2codepoint[entity])
-
- # Unicode character
- mobj = re.match(ur'(?u)#(x?\d+)', entity)
- if mobj is not None:
- numstr = mobj.group(1)
- if numstr.startswith(u'x'):
- base = 16
- numstr = u'0%s' % numstr
- else:
- base = 10
- return unichr(long(numstr, base))
-
- # Unknown entity in name, return its literal representation
- return (u'&%s;' % entity)
+ _video_dimensions = {
+ '5': '240x400',
+ '6': '???',
+ '13': '???',
+ '17': '144x176',
+ '18': '360x640',
+ '22': '720x1280',
+ '34': '360x640',
+ '35': '480x854',
+ '37': '1080x1920',
+ '38': '3072x4096',
+ '43': '360x640',
+ '44': '480x854',
+ '45': '720x1280',
+ }
+ IE_NAME = u'youtube'
def report_lang(self):
"""Report attempt to set language."""
- self._downloader.to_stdout(u'[youtube] Setting language')
+ self._downloader.to_screen(u'[youtube] Setting language')
def report_login(self):
"""Report attempt to log in."""
- self._downloader.to_stdout(u'[youtube] Logging in')
-
+ self._downloader.to_screen(u'[youtube] Logging in')
+
def report_age_confirmation(self):
"""Report attempt to confirm age."""
- self._downloader.to_stdout(u'[youtube] Confirming age')
-
+ self._downloader.to_screen(u'[youtube] Confirming age')
+
+ def report_video_webpage_download(self, video_id):
+ """Report attempt to download video webpage."""
+ self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
+
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
- self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
-
+ self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
+
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
- self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
-
+ self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
+
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
- self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
-
+ self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
+
def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol."""
- self._downloader.to_stdout(u'[youtube] RTMP download detected')
-
+ self._downloader.to_screen(u'[youtube] RTMP download detected')
+
+ def _print_formats(self, formats):
+ print 'Available formats:'
+ for x in formats:
+ print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))
+
def _real_initialize(self):
if self._downloader is None:
return
@@ -665,7 +1182,7 @@ class YoutubeIE(InfoExtractor):
return
# Set language
- request = urllib2.Request(self._LANG_URL, None, std_headers)
+ request = urllib2.Request(self._LANG_URL)
try:
self.report_lang()
urllib2.urlopen(request).read()
@@ -685,7 +1202,7 @@ class YoutubeIE(InfoExtractor):
'username': username,
'password': password,
}
- request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
+ request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
try:
self.report_login()
login_results = urllib2.urlopen(request).read()
@@ -695,13 +1212,13 @@ class YoutubeIE(InfoExtractor):
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
return
-
+
# Confirm age
age_form = {
'next_url': '/',
'action_confirm': 'Confirm',
}
- request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
+ request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form))
try:
self.report_age_confirmation()
age_results = urllib2.urlopen(request).read()
@@ -717,73 +1234,153 @@ class YoutubeIE(InfoExtractor):
return
video_id = mobj.group(2)
- # Downloader parameters
- best_quality = False
- format_param = None
- quality_index = 0
- if self._downloader is not None:
- params = self._downloader.params
- format_param = params.get('format', None)
- if format_param == '0':
- format_param = self._available_formats[quality_index]
- best_quality = True
-
- while True:
- # Extension
- video_extension = self._video_extensions.get(format_param, 'flv')
+ # Get video webpage
+ self.report_video_webpage_download(video_id)
+ request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
+ try:
+ video_webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
- # Get video info
- video_info_url = 'http://www.youtube.com/get_video_info?&video_id=%s&el=detailpage&ps=default&eurl=&gl=US&hl=en' % video_id
- request = urllib2.Request(video_info_url, None, std_headers)
+ # Attempt to extract SWF player URL
+ mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
+ if mobj is not None:
+ player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
+ else:
+ player_url = None
+
+ # Get video info
+ self.report_video_info_webpage_download(video_id)
+ for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
+ video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
+ % (video_id, el_type))
+ request = urllib2.Request(video_info_url)
try:
- self.report_video_info_webpage_download(video_id)
video_info_webpage = urllib2.urlopen(request).read()
video_info = parse_qs(video_info_webpage)
+ if 'token' in video_info:
+ break
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
return
- self.report_information_extraction(video_id)
-
- # "t" param
- if 'token' not in video_info:
- # Attempt to see if YouTube has issued an error message
- if 'reason' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason')
- stream = open('reportme-ydl-%s.dat' % time.time(), 'wb')
- stream.write(video_info_webpage)
- stream.close()
- else:
- reason = urllib.unquote_plus(video_info['reason'][0])
- self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8'))
+ if 'token' not in video_info:
+ if 'reason' in video_info:
+ self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8'))
+ else:
+ self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
+ return
+
+ # Start extracting information
+ self.report_information_extraction(video_id)
+
+ # uploader
+ if 'author' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = urllib.unquote_plus(video_info['author'][0])
+
+ # title
+ if 'title' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = urllib.unquote_plus(video_info['title'][0])
+ video_title = video_title.decode('utf-8')
+ video_title = sanitize_title(video_title)
+
+ # simplified title
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = simple_title.strip(ur'_')
+
+ # thumbnail image
+ if 'thumbnail_url' not in video_info:
+ self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
+ video_thumbnail = ''
+ else: # don't panic if we can't find it
+ video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
+
+ # upload date
+ upload_date = u'NA'
+ mobj = re.search(r'id="eow-date.*?>(.*?)', video_webpage, re.DOTALL)
+ if mobj is not None:
+ upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
+ format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
+ for expression in format_expressions:
+ try:
+ upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
+ except:
+ pass
+
+ # description
+ 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'', video_webpage)
+ if mobj is not None:
+ video_description = mobj.group(1).decode('utf-8')
+ else:
+ html_parser = lxml.etree.HTMLParser(encoding='utf-8')
+ vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser)
+ video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()'))
+ # TODO use another parser
+
+ # token
+ video_token = urllib.unquote_plus(video_info['token'][0])
+
+ # Decide which formats to download
+ req_format = self._downloader.params.get('format', None)
+
+ if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
+ self.report_rtmp_download()
+ video_url_list = [(None, video_info['conn'][0])]
+ elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
+ url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
+ url_data = [parse_qs(uds) for uds in url_data_strs]
+ url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
+ url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
+
+ format_limit = self._downloader.params.get('format_limit', None)
+ if format_limit is not None and format_limit in self._available_formats:
+ format_list = self._available_formats[self._available_formats.index(format_limit):]
+ else:
+ format_list = self._available_formats
+ existing_formats = [x for x in format_list if x in url_map]
+ if len(existing_formats) == 0:
+ self._downloader.trouble(u'ERROR: no known formats available for video')
return
- token = urllib.unquote_plus(video_info['token'][0])
- video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token)
- if format_param is not None:
- video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
-
- # Check possible RTMP download
- if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
- self.report_rtmp_download()
- video_real_url = video_info['conn'][0]
-
- # uploader
- if 'author' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(existing_formats)
return
- video_uploader = urllib.unquote_plus(video_info['author'][0])
+ if req_format is None or req_format == 'best':
+ video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
+ elif req_format == 'worst':
+ video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
+ elif req_format in ('-1', 'all'):
+ video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
+ else:
+ # Specific formats. We pick the first in a slash-delimeted sequence.
+ # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
+ req_formats = req_format.split('/')
+ video_url_list = None
+ for rf in req_formats:
+ if rf in url_map:
+ video_url_list = [(rf, url_map[rf])]
+ break
+ if video_url_list is None:
+ self._downloader.trouble(u'ERROR: requested format not available')
+ return
+ else:
+ self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
+ return
- # title
- if 'title' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = urllib.unquote_plus(video_info['title'][0])
- video_title = video_title.decode('utf-8')
- video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
- video_title = video_title.replace(os.sep, u'%')
+ for format_param, video_real_url in video_url_list:
+ # At this point we have a new video
+ self._downloader.increment_downloads()
- # simplified title
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- simple_title = simple_title.strip(ur'_')
+ # Extension
+ video_extension = self._video_extensions.get(format_param, 'flv')
try:
# Process video information
@@ -791,27 +1388,17 @@ class YoutubeIE(InfoExtractor):
'id': video_id.decode('utf-8'),
'url': video_real_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
+ 'upload_date': upload_date,
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
+ 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+ 'thumbnail': video_thumbnail.decode('utf-8'),
+ 'description': video_description,
+ 'player_url': player_url,
})
-
- return
-
- except UnavailableFormatError, err:
- if best_quality:
- if quality_index == len(self._available_formats) - 1:
- # I don't ever expect this to happen
- self._downloader.trouble(u'ERROR: no known formats available for video')
- return
- else:
- self.report_unavailable_format(video_id, format_param)
- quality_index += 1
- format_param = self._available_formats[quality_index]
- continue
- else:
- self._downloader.trouble('ERROR: format not available for video')
- return
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
class MetacafeIE(InfoExtractor):
@@ -821,34 +1408,31 @@ class MetacafeIE(InfoExtractor):
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
_youtube_ie = None
+ IE_NAME = u'metacafe'
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie
- @staticmethod
- def suitable(url):
- return (re.match(MetacafeIE._VALID_URL, url) is not None)
-
def report_disclaimer(self):
"""Report disclaimer retrieval."""
- self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
+ self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
- self._downloader.to_stdout(u'[metacafe] Confirming age')
-
+ self._downloader.to_screen(u'[metacafe] Confirming age')
+
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
-
+ self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
+
def report_extraction(self, video_id):
"""Report information extraction."""
- self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
+ self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
def _real_initialize(self):
# Retrieve disclaimer
- request = urllib2.Request(self._DISCLAIMER, None, std_headers)
+ request = urllib2.Request(self._DISCLAIMER)
try:
self.report_disclaimer()
disclaimer = urllib2.urlopen(request).read()
@@ -861,14 +1445,14 @@ class MetacafeIE(InfoExtractor):
'filters': '0',
'submit': "Continue - I'm over 18",
}
- request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
+ request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form))
try:
self.report_age_confirmation()
disclaimer = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
return
-
+
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
@@ -884,8 +1468,10 @@ class MetacafeIE(InfoExtractor):
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
return
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
simple_title = mobj.group(2).decode('utf-8')
- video_extension = 'flv'
# Retrieve video webpage to extract further information
request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
@@ -899,26 +1485,40 @@ class MetacafeIE(InfoExtractor):
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = urllib.unquote(mobj.group(1))
-
- #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
- #if mobj is None:
- # self._downloader.trouble(u'ERROR: unable to extract gdaKey')
- # return
- #gdaKey = mobj.group(1)
- #
- #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+ if mobj is not None:
+ mediaURL = urllib.unquote(mobj.group(1))
+ video_extension = mediaURL[-3:]
- video_url = mediaURL
+ # Extract gdaKey if available
+ mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+ if mobj is None:
+ video_url = mediaURL
+ else:
+ gdaKey = mobj.group(1)
+ video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+ else:
+ mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ vardict = parse_qs(mobj.group(1))
+ if 'mediaData' not in vardict:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = mobj.group(1).replace('\\/', '/')
+ video_extension = mediaURL[-3:]
+ video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
mobj = re.search(r'(?im)(.*) - Video', 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)
mobj = re.search(r'(?ms)By:\s*(.+?)<', webpage)
if mobj is None:
@@ -932,50 +1532,143 @@ class MetacafeIE(InfoExtractor):
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
+ 'upload_date': u'NA',
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
})
- except UnavailableFormatError:
- self._downloader.trouble(u'ERROR: format not available for video')
+ except UnavailableVideoError:
+ self._downloader.trouble(u'\nERROR: unable to download video')
-class GoogleIE(InfoExtractor):
- """Information extractor for video.google.com."""
+class DailymotionIE(InfoExtractor):
+ """Information Extractor for Dailymotion"""
- _VALID_URL = r'(?:http://)?video\.google\.com/videoplay\?docid=([^\&]+).*'
+ _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
+ IE_NAME = u'dailymotion'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- @staticmethod
- def suitable(url):
- return (re.match(GoogleIE._VALID_URL, url) is not None)
-
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
+ self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
+ self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
def _real_initialize(self):
return
def _real_extract(self, url):
- # Extract id from URL
+ # Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ 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)
- video_extension = 'mp4'
+ simple_title = mobj.group(2).decode('utf-8')
+ video_extension = 'flv'
# Retrieve video webpage to extract further information
- request = urllib2.Request('http://video.google.com/videoplay?docid=%s' % video_id)
+ request = urllib2.Request(url)
+ request.add_header('Cookie', 'family_filter=off')
+ 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 retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract URL, uploader and title from webpage
+ self.report_extraction(video_id)
+ 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
+ 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
+
+ mobj = re.search(r'(?im)Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?', 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)
+
+ mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = mobj.group(1)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class GoogleIE(InfoExtractor):
+ """Information extractor for video.google.com."""
+
+ _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
+ IE_NAME = u'video.google'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # 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)
+
+ video_extension = 'mp4'
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
@@ -985,7 +1678,10 @@ class GoogleIE(InfoExtractor):
# Extract URL, uploader, and title from webpage
self.report_extraction(video_id)
- mobj = re.search(r"download_url:'(.*)'", webpage)
+ mobj = re.search(r"download_url:'([^']+)'", webpage)
+ if mobj is None:
+ video_extension = 'flv'
+ mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
@@ -1000,43 +1696,67 @@ class GoogleIE(InfoExtractor):
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ # Extract video description
+ mobj = re.search(r'([^<]*)', 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.'
- # Google Video doesn't show uploader nicknames?
- video_uploader = 'uploader'
+ # Extract video thumbnail
+ if self._downloader.params.get('forcethumbnail', False):
+ request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
+ try:
+ 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
+ mobj = re.search(r'![]()
', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1)
+ else: # we need something to pass to process_info
+ video_thumbnail = ''
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'title': video_title.decode('utf-8'),
- 'stitle': video_title.decode('utf-8'),
+ 'uploader': u'NA',
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
})
- except UnavailableFormatError:
- self._downloader.trouble(u'ERROR: format not available for video')
+ except UnavailableVideoError:
+ self._downloader.trouble(u'\nERROR: unable to download video')
class PhotobucketIE(InfoExtractor):
"""Information extractor for photobucket.com."""
_VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+ IE_NAME = u'photobucket'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- @staticmethod
- def suitable(url):
- return (re.match(PhotobucketIE._VALID_URL, url) is not None)
-
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
+ self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
+ self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
def _real_initialize(self):
return
@@ -1048,6 +1768,8 @@ class PhotobucketIE(InfoExtractor):
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)
video_extension = 'flv'
@@ -1076,6 +1798,8 @@ class PhotobucketIE(InfoExtractor):
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
video_uploader = mobj.group(2).decode('utf-8')
@@ -1084,218 +1808,1678 @@ class PhotobucketIE(InfoExtractor):
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'title': video_title.decode('utf-8'),
- 'stitle': video_title.decode('utf-8'),
+ 'uploader': video_uploader,
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
})
- except UnavailableFormatError:
- self._downloader.trouble(u'ERROR: format not available for video')
+ except UnavailableVideoError:
+ self._downloader.trouble(u'\nERROR: unable to download video')
-class YoutubeSearchIE(InfoExtractor):
- """Information Extractor for YouTube search queries."""
- _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
- _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
- _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*'
- _youtube_ie = None
- _max_youtube_results = 1000
+class YahooIE(InfoExtractor):
+ """Information extractor for video.yahoo.com."""
- def __init__(self, youtube_ie, downloader=None):
+ # _VALID_URL matches all Yahoo! Video URLs
+ # _VPAGE_URL matches only the extractable '/watch/' URLs
+ _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
+ _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
+ IE_NAME = u'video.yahoo'
+
+ def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- self._youtube_ie = youtube_ie
-
- @staticmethod
- def suitable(url):
- return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
def _real_initialize(self):
- self._youtube_ie.initialize()
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_QUERY, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
+ return
- prefix, query = query.split(':')
- prefix = prefix[8:]
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_youtube_results)
+ 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
- else:
- try:
- n = long(prefix)
- if n <= 0:
- 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))
- n = self._max_youtube_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
- video_ids = []
- already_seen = set()
- pagenum = 1
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+ video_id = mobj.group(2)
+ video_extension = 'flv'
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
- request = urllib2.Request(result_url, None, std_headers)
+ # Rewrite valid but non-extractable URLs as
+ # extractable English language /watch/ URLs
+ if re.match(self._VPAGE_URL, url) is None:
+ request = urllib2.Request(url)
try:
- page = urllib2.urlopen(request).read()
+ webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
- # Extract video identifiers
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
- if video_id not in already_seen:
- video_ids.append(video_id)
- already_seen.add(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
- return
+ mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Unable to extract id field')
+ return
+ yahoo_id = mobj.group(1)
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Unable to extract vid field')
return
+ yahoo_vid = mobj.group(1)
- pagenum = pagenum + 1
+ url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
+ return self._real_extract(url, new_video=False)
-class YoutubePlaylistIE(InfoExtractor):
- """Information Extractor for YouTube playlists."""
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
- _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:view_play_list|my_playlists)\?.*?p=([^&]+).*'
- _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
- _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
- _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
- _youtube_ie = None
+ # Extract uploader and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'', 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)
- def __init__(self, youtube_ie, downloader=None):
- InfoExtractor.__init__(self, downloader)
- self._youtube_ie = youtube_ie
-
- @staticmethod
- def suitable(url):
- return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
+ mobj = re.search(r'', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video uploader')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
- def report_download_page(self, playlist_id, pagenum):
- """Report attempt to download playlist page with given number."""
- self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+ # Extract video thumbnail
+ mobj = re.search(r'', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1).decode('utf-8')
- def _real_initialize(self):
- self._youtube_ie.initialize()
-
- def _real_extract(self, url):
- # Extract playlist id
- mobj = re.match(self._VALID_URL, url)
+ # Extract video description
+ mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ 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.'
- # Download playlist pages
- playlist_id = mobj.group(1)
- video_ids = []
- pagenum = 1
+ # Extract video height and width
+ mobj = re.search(r'', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video height')
+ return
+ yv_video_height = mobj.group(1)
- while True:
- self.report_download_page(playlist_id, pagenum)
- request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
- try:
- page = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
+ mobj = re.search(r'', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video width')
+ return
+ yv_video_width = mobj.group(1)
+
+ # Retrieve video playlist to extract media URL
+ # I'm not completely sure what all these options are, but we
+ # seem to need most of them, otherwise the server sends a 401.
+ 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')
+ 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
- # Extract video identifiers
- ids_in_page = []
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- video_ids.extend(ids_in_page)
+ # Extract media URL from playlist XML
+ mobj = re.search(r'(.*?)', 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'http://vimeo.com/(.*?)', 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'(.*?)', 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'', 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'(.*?)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract request signature')
+ return
+ sig = mobj.group(1).decode('utf-8')
+
+ # Vimeo specific: extract video quality information
+ mobj = re.search(r'(\d+)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video quality information')
+ return
+ quality = mobj.group(1).decode('utf-8')
+
+ if int(quality) == 1:
+ quality = 'hd'
+ else:
+ quality = 'sd'
+
+ # Vimeo specific: Extract request signature expiration
+ mobj = re.search(r'(.*?)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract request signature expiration')
+ return
+ sig_exp = mobj.group(1).decode('utf-8')
+
+ video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=%s" % (video_id, sig, sig_exp, quality)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': u'mp4',
+ 'thumbnail': video_thumbnail.decode('utf-8'),
+ 'description': video_description,
+ 'thumbnail': video_thumbnail,
+ 'description': video_description,
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class GenericIE(InfoExtractor):
+ """Generic last-resort information extractor."""
+
+ _VALID_URL = r'.*'
+ IE_NAME = u'generic'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
+ self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
+ video_id = url.split('/')[-1]
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+ except ValueError, err:
+ # since this is the last-resort InfoExtractor, if
+ # this error is thrown, it'll be thrown here
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ self.report_extraction(video_id)
+ # Start with something easy: JW Player in SWFObject
+ mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ # Broaden the search a little bit
+ mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # It's possible that one of the regexes
+ # matched, but returned an empty group:
+ if mobj.group(1) is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ video_url = urllib.unquote(mobj.group(1))
+ 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:]
+ 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
+ # Video Title - Site Name
+ # Site Name | Video Title
+ # Video Title - Tagline | Site Name
+ # and so on and so forth; it's just not practical
+ mobj = re.search(r'(.*)', 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)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ # video uploader is domain name
+ mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader,
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class YoutubeSearchIE(InfoExtractor):
+ """Information Extractor for YouTube search queries."""
+ _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
+ _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
+ _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*'
+ _youtube_ie = None
+ _max_youtube_results = 1000
+ IE_NAME = u'youtube:search'
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_URL, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_youtube_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ 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))
+ n = self._max_youtube_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+
+class GoogleSearchIE(InfoExtractor):
+ """Information Extractor for Google Video search queries."""
+ _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
+ _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
+ _MORE_PAGES_INDICATOR = r'Next'
+ _google_ie = None
+ _max_google_results = 1000
+ IE_NAME = u'video.google:search'
+
+ def __init__(self, google_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._google_ie = google_ie
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._google_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_URL, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_google_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ 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))
+ n = self._max_google_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = mobj.group(1)
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ for id in video_ids:
+ self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+
+class YahooSearchIE(InfoExtractor):
+ """Information Extractor for Yahoo! Video search queries."""
+ _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
+ _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
+ _MORE_PAGES_INDICATOR = r'\s*Next'
+ _yahoo_ie = None
+ _max_yahoo_results = 1000
+ IE_NAME = u'video.yahoo:search'
+
+ def __init__(self, yahoo_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._yahoo_ie = yahoo_ie
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._yahoo_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_URL, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_yahoo_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ 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))
+ n = self._max_yahoo_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = mobj.group(1)
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ for id in video_ids:
+ self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+
+class YoutubePlaylistIE(InfoExtractor):
+ """Information Extractor for YouTube playlists."""
+
+ _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+ _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
+ _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*'
+ _youtube_ie = None
+ IE_NAME = u'youtube:playlist'
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ def report_download_page(self, playlist_id, pagenum):
+ """Report attempt to download playlist page with given number."""
+ self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, url):
+ # Extract playlist id
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ # Single video case
+ if mobj.group(3) is not None:
+ self._youtube_ie.extract(mobj.group(3))
+ return
+
+ # Download playlist pages
+ # prefix is 'p' as default for playlists but there are other types that need extra care
+ playlist_prefix = mobj.group(1)
+ if playlist_prefix == 'a':
+ playlist_access = 'artist'
+ else:
+ playlist_prefix = 'p'
+ playlist_access = 'view_play_list'
+ playlist_id = mobj.group(2)
+ video_ids = []
+ pagenum = 1
+
+ while True:
+ self.report_download_page(playlist_id, pagenum)
+ request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ ids_in_page = []
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+ video_ids.extend(ids_in_page)
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ break
+ pagenum = pagenum + 1
+
+ playliststart = self._downloader.params.get('playliststart', 1) - 1
+ playlistend = self._downloader.params.get('playlistend', -1)
+ video_ids = video_ids[playliststart:playlistend]
+
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+
+class YoutubeUserIE(InfoExtractor):
+ """Information Extractor for YouTube users."""
+
+ _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
+ _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
+ _GDATA_PAGE_SIZE = 50
+ _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
+ _youtube_ie = None
+ IE_NAME = u'youtube:user'
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ 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))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, url):
+ # Extract username
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ username = mobj.group(1)
+
+ # Download video ids using YouTube Data API. Result size per
+ # query is limited (currently to 50 videos) so we need to query
+ # page by page until there are no video ids - it means we got
+ # all of them.
+
+ video_ids = []
+ pagenum = 0
+
+ while True:
+ start_index = pagenum * self._GDATA_PAGE_SIZE + 1
+ self.report_download_page(username, start_index)
+
+ request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
+
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ ids_in_page = []
+
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+
+ video_ids.extend(ids_in_page)
+
+ # A little optimization - if current page is not
+ # "full", ie. does not contain PAGE_SIZE video ids then
+ # we can assume that this page is the last one - there
+ # are no more ids on further pages - no need to query
+ # again.
+
+ if len(ids_in_page) < self._GDATA_PAGE_SIZE:
+ break
+
+ pagenum += 1
+
+ all_ids_count = len(video_ids)
+ playliststart = self._downloader.params.get('playliststart', 1) - 1
+ playlistend = self._downloader.params.get('playlistend', -1)
+
+ if playlistend == -1:
+ video_ids = video_ids[playliststart:]
+ else:
+ video_ids = video_ids[playliststart:playlistend]
+
+ self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
+ (username, all_ids_count, len(video_ids)))
+
+ for video_id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
+
+
+class DepositFilesIE(InfoExtractor):
+ """Information extractor for depositfiles.com"""
+
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
+ IE_NAME = u'DepositFiles'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, file_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
+
+ def report_extraction(self, file_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # At this point we have a new file
+ self._downloader.increment_downloads()
+
+ file_id = url.split('/')[-1]
+ # Rebuild url in english locale
+ url = 'http://depositfiles.com/en/files/' + file_id
+
+ # Retrieve file webpage with 'Free download' button pressed
+ free_download_indication = { 'gateway_result' : '1' }
+ request = urllib2.Request(url, urllib.urlencode(free_download_indication))
+ try:
+ self.report_download_webpage(file_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))
+ return
+
+ # Search for the real file URL
+ mobj = re.search(r'