- mobj = re.match(self._VALID_URL, url)
- prog_name = mobj.group(1)
- webpage = self._download_webpage(url, prog_name)
- video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
-
- title = self._html_search_regex(
- r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')
- description = self._og_search_description(webpage)
-
- info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
- data_json = self._download_webpage(
- info_url, video_id, 'Downloading video info')
- data = json.loads(data_json)
-
- url = unescapeHTML(data['video']['files'][0]['path']['#text'])
-
- return {
- 'id': video_id,
- 'title': title,
- 'url': url,
- 'description': description,
- 'thumbnail': self._og_search_thumbnail(webpage),
- }
+ video_id = self._match_id(url)
+ video_type = None
+ webpage = self._download_webpage(url, video_id)
+
+ ustream_url = UstreamIE._extract_url(webpage)
+ if ustream_url:
+ return self.url_result(ustream_url, UstreamIE.ie_key())
+
+ if '&vod' not in url:
+ bc = self._search_regex(
+ r"(<[^>]+id='brightcove-player-embed'[^>]+>)",
+ webpage, 'brightcove embed', default=None)
+ if bc:
+ bc_attr = extract_attributes(bc)
+ bc_url = self.BRIGHTCOVE_URL_TEMPLATE % (
+ bc_attr.get('data-bcaccountid', '3162030207001'),
+ bc_attr.get('data-noprebcplayerid', 'SyGGpuJy3g'),
+ bc_attr.get('data-newbcplayerid', 'default'),
+ bc_attr['data-bcid'])
+ return self.url_result(smuggle_url(bc_url, {'source_url': url}))
+
+ # We first look for clipid, because clipprog always appears before
+ patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
+ results = list(filter(None, (re.search(p, webpage) for p in patterns)))
+ if results:
+ matches = results[0]
+ video_type, video_id = matches.groups()
+ video_type = 'clip' if video_type == 'id' else 'program'
+ else:
+ m = re.search(r'data-(?P<type>clip|prog)id=["\'](?P<id>\d+)', webpage)
+ if m:
+ video_id = m.group('id')
+ video_type = 'program' if m.group('type') == 'prog' else 'clip'
+ else:
+ senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+ if senate_isvp_url:
+ title = self._og_search_title(webpage)
+ surl = smuggle_url(senate_isvp_url, {'force_title': title})
+ return self.url_result(surl, 'SenateISVP', video_id, title)
+ if video_type is None or video_id is None:
+ raise ExtractorError('unable to find video id and type')
+
+ def get_text_attr(d, attr):
+ return d.get(attr, {}).get('#text')
+
+ data = self._download_json(
+ 'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
+ video_id)['video']
+ if data['@status'] != 'Success':
+ raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True)
+
+ doc = self._download_xml(
+ 'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
+ video_id)
+
+ description = self._html_search_meta('description', webpage)
+
+ title = find_xpath_attr(doc, './/string', 'name', 'title').text
+ thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
+
+ files = data['files']
+ capfile = get_text_attr(data, 'capfile')
+
+ entries = []
+ for partnum, f in enumerate(files):
+ formats = []
+ for quality in f['qualities']:
+ formats.append({
+ 'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
+ 'url': unescapeHTML(get_text_attr(quality, 'file')),
+ 'height': int_or_none(get_text_attr(quality, 'height')),
+ 'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
+ })
+ if not formats:
+ path = unescapeHTML(get_text_attr(f, 'path'))
+ if not path:
+ continue
+ formats = self._extract_m3u8_formats(
+ path, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }]
+ self._sort_formats(formats)
+ entries.append({
+ 'id': '%s_%d' % (video_id, partnum + 1),
+ 'title': (
+ title if len(files) == 1 else
+ '%s part %d' % (title, partnum + 1)),
+ 'formats': formats,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': int_or_none(get_text_attr(f, 'length')),
+ 'subtitles': {
+ 'en': [{
+ 'url': capfile,
+ 'ext': determine_ext(capfile, 'dfxp')
+ }],
+ } if capfile else None,
+ })
+
+ if len(entries) == 1:
+ entry = dict(entries[0])
+ entry['id'] = 'c' + video_id if video_type == 'clip' else video_id
+ return entry
+ else:
+ return {
+ '_type': 'playlist',
+ 'entries': entries,
+ 'title': title,
+ 'id': 'c' + video_id if video_type == 'clip' else video_id,
+ }
Rapsys Git / youtubedl / blobdiff