X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/16bc3ce7c4083ef5aada74702570833b8014f4d4..be922f81528dd4ec718dc2486d305f6be6cc76af:/youtube-dl
diff --git a/youtube-dl b/youtube-dl
index 6cb58f1..818a3a7 100755
--- a/youtube-dl
+++ b/youtube-dl
@@ -1,7 +1,7 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
-__author__ = (
+__authors__ = (
'Ricardo Garcia Gonzalez',
'Danny Colligan',
'Benjamin Johnson',
@@ -12,10 +12,13 @@ __author__ = (
'Rogério Brito',
'Philipp Hagemeister',
'Sören Schulze',
+ 'Kevin Ngo',
+ 'Ori Avtalion',
+ 'shizeeg',
)
__license__ = 'Public Domain'
-__version__ = '2011.09.27'
+__version__ = '2012.01.05'
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
@@ -77,8 +80,6 @@ std_headers = {
'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):
@@ -277,6 +278,26 @@ def timeconvert(timestr):
timestamp = email.utils.mktime_tz(timetuple)
return timestamp
+def _simplify_title(title):
+ expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
+ return expr.sub(u'_', title).strip(u'_')
+
+def _orderedSet(iterable):
+ """ Remove all duplicates from the input iterable """
+ res = []
+ for el in iterable:
+ if el not in res:
+ res.append(el)
+ return res
+
+def _unescapeHTML(s):
+ """
+ @param s a string (of type unicode)
+ """
+ assert type(s) == type(u'')
+
+ htmlParser = HTMLParser.HTMLParser()
+ return htmlParser.unescape(s)
class DownloadError(Exception):
"""Download Error exception.
@@ -305,6 +326,10 @@ class PostProcessingError(Exception):
"""
pass
+class MaxDownloadsReached(Exception):
+ """ --max-downloads limit has been reached. """
+ pass
+
class UnavailableVideoError(Exception):
"""Unavailable Format exception.
@@ -695,8 +720,31 @@ class FileDownloader(object):
self.trouble(u'ERROR: invalid system charset or erroneous output template')
return None
+ def _match_entry(self, info_dict):
+ """ Returns None iff the file should be downloaded """
+
+ title = info_dict['title']
+ matchtitle = self.params.get('matchtitle', False)
+ if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
+ return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
+ rejecttitle = self.params.get('rejecttitle', False)
+ if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
+ return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
+ return None
+
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
+
+ reason = self._match_entry(info_dict)
+ if reason is not None:
+ self.to_screen(u'[download] ' + reason)
+ return
+
+ max_downloads = self.params.get('max_downloads')
+ if max_downloads is not None:
+ if self._num_downloads > int(max_downloads):
+ raise MaxDownloadsReached()
+
filename = self.prepare_filename(info_dict)
# Forced printings
@@ -720,20 +768,6 @@ class FileDownloader(object):
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
-
- if self.params.get('nooverwrites', False) and os.path.exists(filename):
- self.to_stderr(u'WARNING: file exists and will be skipped')
- return
-
try:
dn = os.path.dirname(filename)
if dn != '' and not os.path.exists(dn):
@@ -775,16 +809,19 @@ class FileDownloader(object):
return
if not self.params.get('skip_download', False):
- try:
- 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 self.params.get('nooverwrites', False) and os.path.exists(filename):
+ success = True
+ else:
+ try:
+ 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:
@@ -1092,6 +1129,7 @@ class YoutubeIE(InfoExtractor):
_NETRC_MACHINE = 'youtube'
# Listed in order of quality
_available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
+ _available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
@@ -1103,6 +1141,21 @@ class YoutubeIE(InfoExtractor):
'44': 'webm',
'45': 'webm',
}
+ _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):
@@ -1137,6 +1190,11 @@ class YoutubeIE(InfoExtractor):
"""Indicate the download will use the RTMP protocol."""
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
@@ -1216,7 +1274,7 @@ class YoutubeIE(InfoExtractor):
# 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)
+ 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:
@@ -1269,8 +1327,7 @@ class YoutubeIE(InfoExtractor):
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'_')
+ simple_title = _simplify_title(video_title)
# thumbnail image
if 'thumbnail_url' not in video_info:
@@ -1322,14 +1379,18 @@ class YoutubeIE(InfoExtractor):
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):]
+ available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
+ if format_limit is not None and format_limit in available_formats:
+ format_list = available_formats[available_formats.index(format_limit):]
else:
- format_list = self._available_formats
+ format_list = available_formats
existing_formats = [x for x in format_list if x in url_map]
if len(existing_formats) == 0:
self._downloader.trouble(u'ERROR: no known formats available for video')
return
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(existing_formats)
+ return
if req_format is None or req_format == 'best':
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
elif req_format == 'worst':
@@ -1537,9 +1598,6 @@ class DailymotionIE(InfoExtractor):
"""Report information extraction."""
self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
@@ -1551,7 +1609,6 @@ class DailymotionIE(InfoExtractor):
self._downloader.increment_downloads()
video_id = mobj.group(1)
- simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv'
# Retrieve video webpage to extract further information
@@ -1581,12 +1638,13 @@ class DailymotionIE(InfoExtractor):
video_url = mediaURL
- mobj = re.search(r'(?im)
Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?', webpage)
+ 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 = _unescapeHTML(mobj.group('title').decode('utf-8'))
video_title = sanitize_title(video_title)
+ simple_title = _simplify_title(video_title)
mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage)
if mobj is None:
@@ -1628,9 +1686,6 @@ class GoogleIE(InfoExtractor):
"""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)
@@ -1674,7 +1729,7 @@ class GoogleIE(InfoExtractor):
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)
+ simple_title = _simplify_title(video_title)
# Extract video description
mobj = re.search(r'([^<]*)', webpage)
@@ -1735,9 +1790,6 @@ class PhotobucketIE(InfoExtractor):
"""Report information extraction."""
self._downloader.to_screen(u'[photobucket] %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)
@@ -1776,7 +1828,7 @@ class PhotobucketIE(InfoExtractor):
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)
+ simple_title = _simplify_title(vide_title)
video_uploader = mobj.group(2).decode('utf-8')
@@ -1817,9 +1869,6 @@ class YahooIE(InfoExtractor):
"""Report information extraction."""
self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url, new_video=True):
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
@@ -1873,7 +1922,7 @@ class YahooIE(InfoExtractor):
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)
+ simple_title = _simplify_title(video_title)
mobj = re.search(r'', webpage)
if mobj is None:
@@ -1970,9 +2019,6 @@ class VimeoIE(InfoExtractor):
"""Report information extraction."""
self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url, new_video=True):
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
@@ -2004,7 +2050,7 @@ class VimeoIE(InfoExtractor):
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)
+ simple_title = _simplify_title(video_title)
# Extract uploader
mobj = re.search(r'http://vimeo.com/(.*?)', webpage)
@@ -2036,6 +2082,18 @@ class VimeoIE(InfoExtractor):
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:
@@ -2043,7 +2101,7 @@ class VimeoIE(InfoExtractor):
return
sig_exp = mobj.group(1).decode('utf-8')
- video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp)
+ video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=%s" % (video_id, sig, sig_exp, quality)
try:
# Process video information
@@ -2083,9 +2141,6 @@ class GenericIE(InfoExtractor):
"""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()
@@ -2139,7 +2194,7 @@ class GenericIE(InfoExtractor):
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)
+ simple_title = _simplify_title(video_title)
# video uploader is domain name
mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
@@ -2435,7 +2490,7 @@ class YahooSearchIE(InfoExtractor):
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+ _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*'
@@ -2479,7 +2534,8 @@ class YoutubePlaylistIE(InfoExtractor):
while True:
self.report_download_page(playlist_id, pagenum)
- request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
+ url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
+ request = urllib2.Request(url)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@@ -2513,7 +2569,7 @@ class YoutubeUserIE(InfoExtractor):
_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=(.+?)&'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
_youtube_ie = None
IE_NAME = u'youtube:user'
@@ -2611,9 +2667,6 @@ class DepositFilesIE(InfoExtractor):
"""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()
@@ -2674,11 +2727,12 @@ class DepositFilesIE(InfoExtractor):
class FacebookIE(InfoExtractor):
"""Information Extractor for Facebook"""
- _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/video/video\.php\?(?:.*?)v=(?P\d+)(?:.*)'
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P\d+)(?:.*)'
_LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
_NETRC_MACHINE = 'facebook'
- _available_formats = ['highqual', 'lowqual']
+ _available_formats = ['video', 'highqual', 'lowqual']
_video_extensions = {
+ 'video': 'mp4',
'highqual': 'mp4',
'lowqual': 'mp4',
}
@@ -2706,10 +2760,9 @@ class FacebookIE(InfoExtractor):
def _parse_page(self, video_webpage):
"""Extract video information from page"""
# General data
- data = {'title': r'class="video_title datawrap">(.*?)',
+ data = {'title': r'\("video_title", "(.*?)"\)',
'description': r'(.*?)
',
'owner': r'\("video_owner_name", "(.*?)"\)',
- 'upload_date': r'data-date="(.*?)"',
'thumbnail': r'\("thumb_url", "(?P.*?)"\)',
}
video_info = {}
@@ -2811,9 +2864,7 @@ class FacebookIE(InfoExtractor):
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'_')
+ simple_title = _simplify_title(video_title)
# thumbnail image
if 'thumbnail' not in video_info:
@@ -2904,11 +2955,6 @@ class BlipTVIE(InfoExtractor):
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
@@ -2928,13 +2974,14 @@ class BlipTVIE(InfoExtractor):
if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
basename = url.split('/')[-1]
title,ext = os.path.splitext(basename)
+ title = title.decode('UTF-8')
ext = ext.replace('.', '')
self.report_direct_download(title)
info = {
'id': title,
'url': url,
'title': title,
- 'stitle': self._simplify_title(title),
+ 'stitle': _simplify_title(title),
'ext': ext,
'urlhandle': urlh
}
@@ -2968,7 +3015,7 @@ class BlipTVIE(InfoExtractor):
'uploader': data['display_name'],
'upload_date': upload_date,
'title': data['title'],
- 'stitle': self._simplify_title(data['title']),
+ 'stitle': _simplify_title(data['title']),
'ext': ext,
'format': data['media']['mimeType'],
'thumbnail': data['thumbnailUrl'],
@@ -3004,9 +3051,6 @@ class MyVideoIE(InfoExtractor):
"""Report information extraction."""
self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
@@ -3014,10 +3058,6 @@ class MyVideoIE(InfoExtractor):
return
video_id = mobj.group(1)
- simple_title = mobj.group(2).decode('utf-8')
- # should actually not be necessary
- simple_title = sanitize_title(simple_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title)
# Get video webpage
request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
@@ -3044,6 +3084,8 @@ class MyVideoIE(InfoExtractor):
video_title = mobj.group(1)
video_title = sanitize_title(video_title)
+ simple_title = _simplify_title(video_title)
+
try:
self._downloader.process_info({
'id': video_id,
@@ -3077,11 +3119,6 @@ class ComedyCentralIE(InfoExtractor):
def report_player_url(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
@@ -3090,9 +3127,9 @@ class ComedyCentralIE(InfoExtractor):
if mobj.group('shortname'):
if mobj.group('shortname') in ('tds', 'thedailyshow'):
- url = 'http://www.thedailyshow.com/full-episodes/'
+ url = u'http://www.thedailyshow.com/full-episodes/'
else:
- url = 'http://www.colbertnation.com/full-episodes/'
+ url = u'http://www.colbertnation.com/full-episodes/'
mobj = re.match(self._VALID_URL, url)
assert mobj is not None
@@ -3121,7 +3158,7 @@ class ComedyCentralIE(InfoExtractor):
return
epTitle = mobj.group('episode')
- mMovieParams = re.findall('', html)
+ mMovieParams = re.findall('(?:[0-9]+)/(?P.*)$'
+ IE_NAME = u'collegehumor'
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
+
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+ video_id = mobj.group('videoid')
+
+ self.report_webpage(video_id)
+ request = urllib2.Request(url)
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
+
+ m = re.search(r'id="video:(?P[0-9]+)"', webpage)
+ if m is None:
+ self._downloader.trouble(u'ERROR: Cannot extract internal video ID')
+ return
+ internal_video_id = m.group('internalvideoid')
+
+ info = {
+ 'id': video_id,
+ 'internal_id': internal_video_id,
+ }
+
+ self.report_extraction(video_id)
+ xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id
+ try:
+ metaXml = urllib2.urlopen(xmlUrl).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err))
+ return
+
+ mdoc = xml.etree.ElementTree.fromstring(metaXml)
+ try:
+ videoNode = mdoc.findall('./video')[0]
+ info['description'] = videoNode.findall('./description')[0].text
+ info['title'] = videoNode.findall('./caption')[0].text
+ info['stitle'] = _simplify_title(info['title'])
+ info['url'] = videoNode.findall('./file')[0].text
+ info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
+ info['ext'] = info['url'].rpartition('.')[2]
+ info['format'] = info['ext']
+ except IndexError:
+ self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
+ return
+
+ self._downloader.increment_downloads()
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class XVideosIE(InfoExtractor):
+ """Information extractor for xvideos.com"""
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
+ IE_NAME = u'xvideos'
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
+
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+ video_id = mobj.group(1).decode('utf-8')
+
+ self.report_webpage(video_id)
+
+ request = urllib2.Request(r'http://www.xvideos.com/video' + video_id)
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
+
+ self.report_extraction(video_id)
+
+
+ # Extract video URL
+ mobj = re.search(r'flv_url=(.+?)&', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video url')
+ return
+ video_url = urllib2.unquote(mobj.group(1).decode('utf-8'))
+
+
+ # Extract title
+ mobj = re.search(r'(.*?)\s+-\s+XVID', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+
+
+ # Extract video thumbnail
+ mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1).decode('utf-8')
+
+
+
+ self._downloader.increment_downloads()
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'stitle': _simplify_title(video_title),
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'thumbnail': video_thumbnail,
+ 'description': None,
+ 'player_url': None,
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
+
+
+class SoundcloudIE(InfoExtractor):
+ """Information extractor for soundcloud.com
+ To access the media, the uid of the song and a stream token
+ must be extracted from the page source and the script must make
+ a request to media.soundcloud.com/crossdomain.xml. Then
+ the media can be grabbed by requesting from an url composed
+ of the stream token and uid
+ """
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
+ IE_NAME = u'soundcloud'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
+
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ # extract uploader (which is in the url)
+ uploader = mobj.group(1).decode('utf-8')
+ # extract simple title (uploader + slug of song title)
+ slug_title = mobj.group(2).decode('utf-8')
+ simple_title = uploader + '-' + slug_title
+
+ self.report_webpage('%s/%s' % (uploader, slug_title))
+
+ request = urllib2.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title))
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
+
+ self.report_extraction('%s/%s' % (uploader, slug_title))
+
+ # extract uid and stream token that soundcloud hands out for access
+ mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage)
+ if mobj:
+ video_id = mobj.group(1)
+ stream_token = mobj.group(2)
+
+ # extract unsimplified title
+ mobj = re.search('"title":"(.*?)",', webpage)
+ if mobj:
+ title = mobj.group(1)
+
+ # construct media url (with uid/token)
+ mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s"
+ mediaURL = mediaURL % (video_id, stream_token)
+
+ # description
+ description = u'No description available'
+ mobj = re.search('track-description-value">(.*?)
', webpage)
+ if mobj:
+ description = mobj.group(1)
+
+ # upload date
+ upload_date = None
+ mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)", webpage)
+ if mobj:
+ try:
+ upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
+ except Exception, e:
+ print str(e)
+
+ # for soundcloud, a request to a cross domain is required for cookies
+ request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
+
+ try:
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': mediaURL,
+ 'uploader': uploader.decode('utf-8'),
+ 'upload_date': upload_date,
+ 'title': simple_title.decode('utf-8'),
+ 'stitle': simple_title.decode('utf-8'),
+ 'ext': u'mp3',
+ 'format': u'NA',
+ 'player_url': None,
+ 'description': description.decode('utf-8')
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class InfoQIE(InfoExtractor):
+ """Information extractor for infoq.com"""
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
+ IE_NAME = u'infoq'
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
+
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ self.report_webpage(url)
+
+ request = urllib2.Request(url)
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
+
+ self.report_extraction(url)
+
+
+ # Extract video URL
+ mobj = re.search(r"jsclassref='([^']*)'", webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video url')
+ return
+ video_url = 'rtmpe://video.infoq.com/cfx/st/' + urllib2.unquote(mobj.group(1).decode('base64'))
+
+
+ # Extract title
+ mobj = re.search(r'contentTitle = "(.*?)";', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+
+ # Extract description
+ video_description = u'No description available.'
+ mobj = re.search(r'', webpage)
+ if mobj is not None:
+ video_description = mobj.group(1).decode('utf-8')
+
+ video_filename = video_url.split('/')[-1]
+ video_id, extension = video_filename.split('.')
+
+ self._downloader.increment_downloads()
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'stitle': _simplify_title(video_title),
+ 'ext': extension,
+ 'format': extension, # Extension is always(?) mp4, but seems to be flv
+ 'thumbnail': None,
+ 'description': video_description,
+ 'player_url': None,
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
+
+class MixcloudIE(InfoExtractor):
+ """Information extractor for www.mixcloud.com"""
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
+ IE_NAME = u'mixcloud'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_json(self, file_id):
+ """Report JSON download."""
+ self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME)
+
+ def report_extraction(self, file_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
+
+ def get_urls(self, jsonData, fmt, bitrate='best'):
+ """Get urls from 'audio_formats' section in json"""
+ file_url = None
+ try:
+ bitrate_list = jsonData[fmt]
+ if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
+ bitrate = max(bitrate_list) # select highest
+
+ url_list = jsonData[fmt][bitrate]
+ except TypeError: # we have no bitrate info.
+ url_list = jsonData[fmt]
+
+ return url_list
+
+ def check_urls(self, url_list):
+ """Returns 1st active url from list"""
+ for url in url_list:
+ try:
+ urllib2.urlopen(url)
+ return url
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ url = None
+
+ return None
+
+ def _print_formats(self, formats):
+ print 'Available formats:'
+ for fmt in formats.keys():
+ for b in formats[fmt]:
+ try:
+ ext = formats[fmt][b][0]
+ print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])
+ except TypeError: # we have no bitrate info
+ ext = formats[fmt][0]
+ print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])
+ break
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+ # extract uploader & filename from url
+ uploader = mobj.group(1).decode('utf-8')
+ file_id = uploader + "-" + mobj.group(2).decode('utf-8')
+
+ # construct API request
+ file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
+ # retrieve .json file with links to files
+ request = urllib2.Request(file_url)
+ try:
+ self.report_download_json(file_url)
+ jsonData = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err))
+ return
+
+ # parse JSON
+ json_data = json.loads(jsonData)
+ player_url = json_data['player_swf_url']
+ formats = dict(json_data['audio_formats'])
+
+ req_format = self._downloader.params.get('format', None)
+ bitrate = None
+
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(formats)
+ return
+
+ if req_format is None or req_format == 'best':
+ for format_param in formats.keys():
+ url_list = self.get_urls(formats, format_param)
+ # check urls
+ file_url = self.check_urls(url_list)
+ if file_url is not None:
+ break # got it!
+ else:
+ if req_format not in formats.keys():
+ self._downloader.trouble(u'ERROR: format is not available')
+ return
+
+ url_list = self.get_urls(formats, req_format)
+ file_url = self.check_urls(url_list)
+ format_param = req_format
+
+ # We have audio
+ self._downloader.increment_downloads()
+ try:
+ # Process file information
+ self._downloader.process_info({
+ 'id': file_id.decode('utf-8'),
+ 'url': file_url.decode('utf-8'),
+ 'uploader': uploader.decode('utf-8'),
+ 'upload_date': u'NA',
+ 'title': json_data['name'],
+ 'stitle': _simplify_title(json_data['name']),
+ 'ext': file_url.split('.')[-1].decode('utf-8'),
+ 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+ 'thumbnail': json_data['thumbnail_url'],
+ 'description': json_data['description'],
+ 'player_url': player_url.decode('utf-8'),
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'ERROR: unable to download file')
+
+class StanfordOpenClassroomIE(InfoExtractor):
+ """Information extractor for Stanford's Open ClassRoom"""
+
+ _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P[^&]+)(&video=(?P