yt_dlp/extractor/cctv.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     float_or_none,
   6     try_get,
   7     unified_timestamp,
   8 )
   9
  10
  11 class CCTVIE(InfoExtractor):
  12     IE_DESC = '央视网'
  13     _VALID_URL = r'https?://(?:(?:[^/]+)\.(?:cntv|cctv)\.(?:com|cn)|(?:www\.)?ncpa-classic\.com)/(?:[^/]+/)*?(?P<id>[^/?#&]+?)(?:/index)?(?:\.s?html|[?#&]|$)'
  14     _TESTS = [{
  15         # fo.addVariable("videoCenterId","id")
  16         'url': 'http://sports.cntv.cn/2016/02/12/ARTIaBRxv4rTT1yWf1frW2wi160212.shtml',
  17         'md5': 'd61ec00a493e09da810bf406a078f691',
  18         'info_dict': {
  19             'id': '5ecdbeab623f4973b40ff25f18b174e8',
  20             'ext': 'mp4',
  21             'title': '[NBA]二少联手砍下46分 雷霆主场击败鹈鹕（快讯）',
  22             'description': 'md5:7e14a5328dc5eb3d1cd6afbbe0574e95',
  23             'duration': 98,
  24             'uploader': 'songjunjie',
  25             'timestamp': 1455279956,
  26             'upload_date': '20160212',
  27         },
  28     }, {
  29         # var guid = "id"
  30         'url': 'http://tv.cctv.com/2016/02/05/VIDEUS7apq3lKrHG9Dncm03B160205.shtml',
  31         'info_dict': {
  32             'id': 'efc5d49e5b3b4ab2b34f3a502b73d3ae',
  33             'ext': 'mp4',
  34             'title': '[赛车]“车王”舒马赫恢复情况成谜（快讯）',
  35             'description': '2月4日，蒙特泽莫罗透露了关于“车王”舒马赫恢复情况，但情况是否属实遭到了质疑。',
  36             'duration': 37,
  37             'uploader': 'shujun',
  38             'timestamp': 1454677291,
  39             'upload_date': '20160205',
  40         },
  41         'params': {
  42             'skip_download': True,
  43         },
  44     }, {
  45         # changePlayer('id')
  46         'url': 'http://english.cntv.cn/special/four_comprehensives/index.shtml',
  47         'info_dict': {
  48             'id': '4bb9bb4db7a6471ba85fdeda5af0381e',
  49             'ext': 'mp4',
  50             'title': 'NHnews008 ANNUAL POLITICAL SEASON',
  51             'description': 'Four Comprehensives',
  52             'duration': 60,
  53             'uploader': 'zhangyunlei',
  54             'timestamp': 1425385521,
  55             'upload_date': '20150303',
  56         },
  57         'params': {
  58             'skip_download': True,
  59         },
  60     }, {
  61         # loadvideo('id')
  62         'url': 'http://cctv.cntv.cn/lm/tvseries_russian/yilugesanghua/index.shtml',
  63         'info_dict': {
  64             'id': 'b15f009ff45c43968b9af583fc2e04b2',
  65             'ext': 'mp4',
  66             'title': 'Путь，усыпанный космеями Серия 1',
  67             'description': 'Путь, усыпанный космеями',
  68             'duration': 2645,
  69             'uploader': 'renxue',
  70             'timestamp': 1477479241,
  71             'upload_date': '20161026',
  72         },
  73         'params': {
  74             'skip_download': True,
  75         },
  76     }, {
  77         # var initMyAray = 'id'
  78         'url': 'http://www.ncpa-classic.com/2013/05/22/VIDE1369219508996867.shtml',
  79         'info_dict': {
  80             'id': 'a194cfa7f18c426b823d876668325946',
  81             'ext': 'mp4',
  82             'title': '小泽征尔音乐塾 音乐梦想无国界',
  83             'duration': 2173,
  84             'timestamp': 1369248264,
  85             'upload_date': '20130522',
  86         },
  87         'params': {
  88             'skip_download': True,
  89         },
  90     }, {
  91         # videoCenterId: "id"
  92         'url': 'http://news.cctv.com/2024/02/21/ARTIcU5tKIOIF2myEGCATkLo240221.shtml',
  93         'info_dict': {
  94             'id': '5c846c0518444308ba32c4159df3b3e0',
  95             'ext': 'mp4',
  96             'title': '《平“语”近人——习近平喜欢的典故》第三季 第5集：风物长宜放眼量',
  97             'uploader': 'yangjuan',
  98             'timestamp': 1708554940,
  99             'upload_date': '20240221',
 100         },
 101         'params': {
 102             'skip_download': True,
 103         },
 104     }, {
 105         # var ids = ["id"]
 106         'url': 'http://www.ncpa-classic.com/clt/more/416/index.shtml',
 107         'info_dict': {
 108             'id': 'a8606119a4884588a79d81c02abecc16',
 109             'ext': 'mp3',
 110             'title': '来自维也纳的新年贺礼',
 111             'description': 'md5:f13764ae8dd484e84dd4b39d5bcba2a7',
 112             'duration': 1578,
 113             'uploader': 'djy',
 114             'timestamp': 1482942419,
 115             'upload_date': '20161228',
 116         },
 117         'params': {
 118             'skip_download': True,
 119         },
 120         'expected_warnings': ['Failed to download m3u8 information'],
 121     }, {
 122         'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml',
 123         'only_matching': True,
 124     }, {
 125         'url': 'http://tv.cntv.cn/video/C39296/e0210d949f113ddfb38d31f00a4e5c44',
 126         'only_matching': True,
 127     }, {
 128         'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
 129         'only_matching': True,
 130     }, {
 131         'url': 'http://tv.cctv.com/2016/09/07/VIDE5C1FnlX5bUywlrjhxXOV160907.shtml',
 132         'only_matching': True,
 133     }, {
 134         'url': 'http://tv.cntv.cn/video/C39296/95cfac44cabd3ddc4a9438780a4e5c44',
 135         'only_matching': True,
 136     }]
 137
 138     def _real_extract(self, url):
 139         video_id = self._match_id(url)
 140         webpage = self._download_webpage(url, video_id)
 141
 142         video_id = self._search_regex(
 143             [r'var\s+guid\s*=\s*["\']([\da-fA-F]+)',
 144              r'videoCenterId(?:["\']\s*,|:)\s*["\']([\da-fA-F]+)',
 145              r'changePlayer\s*\(\s*["\']([\da-fA-F]+)',
 146              r'load[Vv]ideo\s*\(\s*["\']([\da-fA-F]+)',
 147              r'var\s+initMyAray\s*=\s*["\']([\da-fA-F]+)',
 148              r'var\s+ids\s*=\s*\[["\']([\da-fA-F]+)'],
 149             webpage, 'video id')
 150
 151         data = self._download_json(
 152             'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do', video_id,
 153             query={
 154                 'pid': video_id,
 155                 'url': url,
 156                 'idl': 32,
 157                 'idlr': 32,
 158                 'modifyed': 'false',
 159             })
 160
 161         title = data['title']
 162
 163         formats = []
 164
 165         video = data.get('video')
 166         if isinstance(video, dict):
 167             for quality, chapters_key in enumerate(('lowChapters', 'chapters')):
 168                 video_url = try_get(
 169                     video, lambda x: x[chapters_key][0]['url'], str)
 170                 if video_url:
 171                     formats.append({
 172                         'url': video_url,
 173                         'format_id': 'http',
 174                         'quality': quality,
 175                         # Sample clip
 176                         'preference': -10,
 177                     })
 178
 179         hls_url = try_get(data, lambda x: x['hls_url'], str)
 180         if hls_url:
 181             hls_url = re.sub(r'maxbr=\d+&?', '', hls_url)
 182             formats.extend(self._extract_m3u8_formats(
 183                 hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
 184                 m3u8_id='hls', fatal=False))
 185
 186         uploader = data.get('editer_name')
 187         description = self._html_search_meta(
 188             'description', webpage, default=None)
 189         timestamp = unified_timestamp(data.get('f_pgmtime'))
 190         duration = float_or_none(try_get(video, lambda x: x['totalLength']))
 191
 192         return {
 193             'id': video_id,
 194             'title': title,
 195             'description': description,
 196             'uploader': uploader,
 197             'timestamp': timestamp,
 198             'duration': duration,
 199             'formats': formats,
 200         }