}]
+class ArteTvIE(InfoExtractor):
+ """arte.tv information extractor."""
+
+ _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
+ _LIVE_URL = r'index-[0-9]+\.html$'
+
+ IE_NAME = u'arte.tv'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id)
+
+ def fetch_webpage(self, url):
+ self._downloader.increment_downloads()
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(url)
+ 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:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+ return webpage
+
+ def grep_webpage(self, url, regex, regexFlags, matchTuples):
+ page = self.fetch_webpage(url)
+ mobj = re.search(regex, page, regexFlags)
+ info = {}
+
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ for (i, key, err) in matchTuples:
+ if mobj.group(i) is None:
+ self._downloader.trouble(err)
+ return
+ else:
+ info[key] = mobj.group(i)
+
+ return info
+
+ def extractLiveStream(self, url):
+ video_lang = url.split('/')[-4]
+ info = self.grep_webpage(
+ url,
+ r'src="(.*?/videothek_js.*?\.js)',
+ 0,
+ [
+ (1, 'url', u'ERROR: Invalid URL: %s' % url)
+ ]
+ )
+ http_host = url.split('/')[2]
+ next_url = 'http://%s%s' % (http_host, urllib.unquote(info.get('url')))
+ info = self.grep_webpage(
+ next_url,
+ r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
+ '(http://.*?\.swf).*?' +
+ '(rtmp://.*?)\'',
+ re.DOTALL,
+ [
+ (1, 'path', u'ERROR: could not extract video path: %s' % url),
+ (2, 'player', u'ERROR: could not extract video player: %s' % url),
+ (3, 'url', u'ERROR: could not extract video url: %s' % url)
+ ]
+ )
+ video_url = u'%s/%s' % (info.get('url'), info.get('path'))
+
+ def extractPlus7Stream(self, url):
+ video_lang = url.split('/')[-3]
+ info = self.grep_webpage(
+ url,
+ r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
+ 0,
+ [
+ (1, 'url', u'ERROR: Invalid URL: %s' % url)
+ ]
+ )
+ next_url = urllib.unquote(info.get('url'))
+ info = self.grep_webpage(
+ next_url,
+ r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
+ 0,
+ [
+ (1, 'url', u'ERROR: Could not find <video> tag: %s' % url)
+ ]
+ )
+ next_url = urllib.unquote(info.get('url'))
+
+ info = self.grep_webpage(
+ next_url,
+ r'<video id="(.*?)".*?>.*?' +
+ '<name>(.*?)</name>.*?' +
+ '<dateVideo>(.*?)</dateVideo>.*?' +
+ '<url quality="hd">(.*?)</url>',
+ re.DOTALL,
+ [
+ (1, 'id', u'ERROR: could not extract video id: %s' % url),
+ (2, 'title', u'ERROR: could not extract video title: %s' % url),
+ (3, 'date', u'ERROR: could not extract video date: %s' % url),
+ (4, 'url', u'ERROR: could not extract video url: %s' % url)
+ ]
+ )
+
+ return {
+ 'id': info.get('id'),
+ 'url': urllib.unquote(info.get('url')),
+ 'uploader': u'arte.tv',
+ 'upload_date': info.get('date'),
+ 'title': info.get('title'),
+ 'ext': u'mp4',
+ 'format': u'NA',
+ 'player_url': None,
+ }
+
+ def _real_extract(self, url):
+ video_id = url.split('/')[-1]
+ self.report_extraction(video_id)
+
+ if re.search(self._LIVE_URL, video_id) is not None:
+ self.extractLiveStream(url)
+ return
+ else:
+ info = self.extractPlus7Stream(url)
+
+ return [info]
+
+
class GenericIE(InfoExtractor):
"""Generic last-resort information extractor."""
_VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
IE_NAME = u'comedycentral'
+ _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
+
+ _video_extensions = {
+ '3500': 'mp4',
+ '2200': 'mp4',
+ '1700': 'mp4',
+ '1200': 'mp4',
+ '750': 'mp4',
+ '400': 'mp4',
+ }
+ _video_dimensions = {
+ '3500': '1280x720',
+ '2200': '960x540',
+ '1700': '768x432',
+ '1200': '640x360',
+ '750': '512x288',
+ '400': '384x216',
+ }
+
def report_extraction(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
def report_player_url(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
+
+ 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, 'mp4'), self._video_dimensions.get(x, '???')))
+
+
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
epTitle = mobj.group('episode')
mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html)
+
if len(mMovieParams) == 0:
- self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
- return
+ # The Colbert Report embeds the information in a without
+ # a URL prefix; so extract the alternate reference
+ # and then add the URL prefix manually.
+ altMovieParams = re.findall('data-mgid="([^"]*episode.*?:.*?)"', html)
+ if len(altMovieParams) == 0:
+ self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
+ return
+ else:
+ mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
+
playerUrl_raw = mMovieParams[0][0]
self.report_player_url(epTitle)
try:
if len(turls) == 0:
self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
continue
+
+ if self._downloader.params.get('listformats', None):
+ self._print_formats([i[0] for i in turls])
+ return
# For now, just pick the highest bitrate
format,video_url = turls[-1]
- # Patch to download from alternative CDN, which does not
- # break on current RTMPDump builds
-
+ # Get the format arg from the arg stream
+ req_format = self._downloader.params.get('format', None)
+
+ # Select format if we can find one
+ for f,v in turls:
+ if f == req_format:
+ format, video_url = f, v
+ break
+ # Patch to download from alternative CDN, which does not
+ # break on current RTMPDump builds
broken_cdn = "rtmpe://viacomccstrmfs.fplive.net/viacomccstrm/gsp.comedystor/"
better_cdn = "rtmpe://cp10740.edgefcs.net/ondemand/mtvnorigin/gsp.comedystor/"
-
+
if video_url.startswith(broken_cdn):
- video_url = video_url.replace(broken_cdn, better_cdn)
-
+ video_url = video_url.replace(broken_cdn, better_cdn)
effTitle = showId + u'-' + epTitle
info = {
projects / youtube-dl / blobdiff