cbs.py (4856B)
1 from __future__ import unicode_literals 2 3 from .theplatform import ThePlatformFeedIE 4 from ..utils import ( 5 ExtractorError, 6 int_or_none, 7 find_xpath_attr, 8 xpath_element, 9 xpath_text, 10 update_url_query, 11 ) 12 13 14 class CBSBaseIE(ThePlatformFeedIE): 15 def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'): 16 subtitles = {} 17 for k, ext in [('sMPTE-TTCCURL', 'tt'), ('ClosedCaptionURL', 'ttml'), ('webVTTCaptionURL', 'vtt')]: 18 cc_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', k) 19 if cc_e is not None: 20 cc_url = cc_e.get('value') 21 if cc_url: 22 subtitles.setdefault(subtitles_lang, []).append({ 23 'ext': ext, 24 'url': cc_url, 25 }) 26 return subtitles 27 28 29 class CBSIE(CBSBaseIE): 30 _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:(?:cbs|paramountplus)\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)' 31 32 _TESTS = [{ 33 'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/', 34 'info_dict': { 35 'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_', 36 'ext': 'mp4', 37 'title': 'Connect Chat feat. Garth Brooks', 38 'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!', 39 'duration': 1495, 40 'timestamp': 1385585425, 41 'upload_date': '20131127', 42 'uploader': 'CBSI-NEW', 43 }, 44 'params': { 45 # m3u8 download 46 'skip_download': True, 47 }, 48 '_skip': 'Blocked outside the US', 49 }, { 50 'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/', 51 'only_matching': True, 52 }, { 53 'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/', 54 'only_matching': True, 55 }, { 56 'url': 'https://www.paramountplus.com/shows/all-rise/video/QmR1WhNkh1a_IrdHZrbcRklm176X_rVc/all-rise-space/', 57 'only_matching': True, 58 }] 59 60 def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517): 61 items_data = self._download_xml( 62 'http://can.cbs.com/thunder/player/videoPlayerService.php', 63 content_id, query={'partner': site, 'contentId': content_id}) 64 video_data = xpath_element(items_data, './/item') 65 title = xpath_text(video_data, 'videoTitle', 'title', True) 66 tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id) 67 tp_release_url = 'http://link.theplatform.com/s/' + tp_path 68 69 asset_types = [] 70 subtitles = {} 71 formats = [] 72 last_e = None 73 for item in items_data.findall('.//item'): 74 asset_type = xpath_text(item, 'assetType') 75 if not asset_type or asset_type in asset_types or 'HLS_FPS' in asset_type or 'DASH_CENC' in asset_type: 76 continue 77 asset_types.append(asset_type) 78 query = { 79 'mbr': 'true', 80 'assetTypes': asset_type, 81 } 82 if asset_type.startswith('HLS') or asset_type in ('OnceURL', 'StreamPack'): 83 query['formats'] = 'MPEG4,M3U' 84 elif asset_type in ('RTMP', 'WIFI', '3G'): 85 query['formats'] = 'MPEG4,FLV' 86 try: 87 tp_formats, tp_subtitles = self._extract_theplatform_smil( 88 update_url_query(tp_release_url, query), content_id, 89 'Downloading %s SMIL data' % asset_type) 90 except ExtractorError as e: 91 last_e = e 92 continue 93 formats.extend(tp_formats) 94 subtitles = self._merge_subtitles(subtitles, tp_subtitles) 95 if last_e and not formats: 96 raise last_e 97 self._sort_formats(formats) 98 99 info = self._extract_theplatform_metadata(tp_path, content_id) 100 info.update({ 101 'id': content_id, 102 'title': title, 103 'series': xpath_text(video_data, 'seriesTitle'), 104 'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')), 105 'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')), 106 'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000), 107 'thumbnail': xpath_text(video_data, 'previewImageURL'), 108 'formats': formats, 109 'subtitles': subtitles, 110 }) 111 return info 112 113 def _real_extract(self, url): 114 content_id = self._match_id(url) 115 return self._extract_video_info(content_id)