)
__license__ = 'Public Domain'
-__version__ = '2011.09.06-phihag'
+__version__ = '2011.09.14'
-UPDATE_URL = 'https://raw.github.com/phihag/youtube-dl/master/youtube-dl'
+UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
import cookielib
import datetime
# Retrieve video webpage to extract further information
request = urllib2.Request(url)
+ request.add_header('Cookie', 'family_filter=off')
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
- mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+ mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
- mediaURL = urllib.unquote(mobj.group(1))
+ sequence = urllib.unquote(mobj.group(1))
+ mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
# if needed add http://www.dailymotion.com/ if relative URL
video_url = mediaURL
- # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
- mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
+ mobj = re.search(r'(?im)<title>Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?</title>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage)
+ mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
'thumbnail': video_thumbnail,
- 'description': video_description,
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'\nERROR: Unable to download video')
class ComedyCentralIE(InfoExtractor):
- """Information extractor for blip.tv"""
+ """Information extractor for The Daily Show and Colbert Report """
- _VALID_URL = r'^(?:https?://)?(www\.)?(thedailyshow|colbertnation)\.com/full-episodes/(.*)$'
+ _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
@staticmethod
def suitable(url):
def report_config_download(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
+ def report_player_url(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
+
def _simplify_title(self, title):
res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
res = res.strip(ur'_')
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
- epTitle = mobj.group(3)
+
+ if mobj.group('shortname'):
+ if mobj.group('shortname') in ('tds', 'thedailyshow'):
+ url = 'http://www.thedailyshow.com/full-episodes/'
+ else:
+ url = 'http://www.colbertnation.com/full-episodes/'
+ mobj = re.match(self._VALID_URL, url)
+ assert mobj is not None
+
+ dlNewest = not mobj.group('episode')
+ if dlNewest:
+ epTitle = mobj.group('showname')
+ else:
+ epTitle = mobj.group('episode')
req = urllib2.Request(url)
self.report_extraction(epTitle)
try:
- html = urllib2.urlopen(req).read()
+ htmlHandle = urllib2.urlopen(req)
+ html = htmlHandle.read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
return
+ if dlNewest:
+ url = htmlHandle.geturl()
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
+ return
+ if mobj.group('episode') == '':
+ self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
+ return
+ epTitle = mobj.group('episode')
- mMovieParams = re.findall('<param name="movie" value="http://media.mtvnservices.com/(.*?:episode:.*?:)(.*?)"/>', html)
+ mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/(.*?:episode:([^:]*):)(.*?))"/>', html)
if len(mMovieParams) == 0:
self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
return
- ACT_COUNT = 4
- mediaNum = int(mMovieParams[0][1]) - ACT_COUNT
+ show_id = mMovieParams[0][2]
+ ACT_COUNT = { # TODO: Detect this dynamically
+ 'thedailyshow.com': 4,
+ 'colbertnation.com': 3,
+ }.get(show_id, 4)
+ OFFSET = {
+ 'thedailyshow.com': 1,
+ 'colbertnation.com': 1,
+ }.get(show_id, 1)
+
+ first_player_url = mMovieParams[0][0]
+ startMediaNum = int(mMovieParams[0][3]) + OFFSET
+ movieId = mMovieParams[0][1]
+
+ playerReq = urllib2.Request(first_player_url)
+ self.report_player_url(epTitle)
+ try:
+ playerResponse = urllib2.urlopen(playerReq)
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download player: %s' % unicode(err))
+ return
+ player_url = playerResponse.geturl()
for actNum in range(ACT_COUNT):
- mediaId = mMovieParams[0][0] + str(mediaNum + actNum)
+ mediaNum = startMediaNum + actNum
+ mediaId = movieId + str(mediaNum)
configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
urllib.urlencode({'uri': mediaId}))
configReq = urllib2.Request(configUrl)
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
return
-
+
cdoc = xml.etree.ElementTree.fromstring(configXml)
turls = []
for rendition in cdoc.findall('.//rendition'):
finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
turls.append(finfo)
+ if len(turls) == 0:
+ self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum) + ': No videos found')
+ continue
+
# For now, just pick the highest bitrate
format,video_url = turls[-1]
self._downloader.increment_downloads()
- actTitle = epTitle + '-act' + str(actNum+1)
+
+ effTitle = show_id.replace('.com', '') + '-' + epTitle
info = {
- 'id': epTitle,
+ 'id': str(mediaNum),
'url': video_url,
- 'uploader': 'NA',
+ 'uploader': show_id,
'upload_date': 'NA',
- 'title': actTitle,
- 'stitle': self._simplify_title(actTitle),
+ 'title': effTitle,
+ 'stitle': self._simplify_title(effTitle),
'ext': 'mp4',
'format': format,
'thumbnail': None,
'description': 'TODO: Not yet supported',
- 'player_url': None
+ 'player_url': player_url
}
-
+
try:
self._downloader.process_info(info)
except UnavailableVideoError, err:
- self._downloader.trouble(u'\nERROR: unable to download video')
+ self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum))
+ continue
class PostProcessor(object):