yt_dlp/extractor/cctv.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_str
   5 from ..utils import (
   6     float_or_none,
   7     try_get,
   8     unified_timestamp,
   9 )
  10
  11
  12 class CCTVIE(InfoExtractor):
  13     IE_DESC = '央视网'
  14     _VALID_URL = r'https?://(?:(?:[^/]+)\.(?:cntv|cctv)\.(?:com|cn)|(?:www\.)?ncpa-classic\.com)/(?:[^/]+/)*?(?P<id>[^/?#&]+?)(?:/index)?(?:\.s?html|[?#&]|$)'
  15     _TESTS = [{
  16         # fo.addVariable("videoCenterId","id")
  17         'url': 'http://sports.cntv.cn/2016/02/12/ARTIaBRxv4rTT1yWf1frW2wi160212.shtml',
  18         'md5': 'd61ec00a493e09da810bf406a078f691',
  19         'info_dict': {
  20             'id': '5ecdbeab623f4973b40ff25f18b174e8',
  21             'ext': 'mp4',
  22             'title': '[NBA]二少联手砍下46分 雷霆主场击败鹈鹕（快讯）',
  23             'description': 'md5:7e14a5328dc5eb3d1cd6afbbe0574e95',
  24             'duration': 98,
  25             'uploader': 'songjunjie',
  26             'timestamp': 1455279956,
  27             'upload_date': '20160212',
  28         },
  29     }, {
  30         # var guid = "id"
  31         'url': 'http://tv.cctv.com/2016/02/05/VIDEUS7apq3lKrHG9Dncm03B160205.shtml',
  32         'info_dict': {
  33             'id': 'efc5d49e5b3b4ab2b34f3a502b73d3ae',
  34             'ext': 'mp4',
  35             'title': '[赛车]“车王”舒马赫恢复情况成谜（快讯）',
  36             '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。',
  37             'duration': 37,
  38             'uploader': 'shujun',
  39             'timestamp': 1454677291,
  40             'upload_date': '20160205',
  41         },
  42         'params': {
  43             'skip_download': True,
  44         },
  45     }, {
  46         # changePlayer('id')
  47         'url': 'http://english.cntv.cn/special/four_comprehensives/index.shtml',
  48         'info_dict': {
  49             'id': '4bb9bb4db7a6471ba85fdeda5af0381e',
  50             'ext': 'mp4',
  51             'title': 'NHnews008 ANNUAL POLITICAL SEASON',
  52             'description': 'Four Comprehensives',
  53             'duration': 60,
  54             'uploader': 'zhangyunlei',
  55             'timestamp': 1425385521,
  56             'upload_date': '20150303',
  57         },
  58         'params': {
  59             'skip_download': True,
  60         },
  61     }, {
  62         # loadvideo('id')
  63         'url': 'http://cctv.cntv.cn/lm/tvseries_russian/yilugesanghua/index.shtml',
  64         'info_dict': {
  65             'id': 'b15f009ff45c43968b9af583fc2e04b2',
  66             'ext': 'mp4',
  67             'title': 'Путь，усыпанный космеями Серия 1',
  68             'description': 'Путь, усыпанный космеями',
  69             'duration': 2645,
  70             'uploader': 'renxue',
  71             'timestamp': 1477479241,
  72             'upload_date': '20161026',
  73         },
  74         'params': {
  75             'skip_download': True,
  76         },
  77     }, {
  78         # var initMyAray = 'id'
  79         'url': 'http://www.ncpa-classic.com/2013/05/22/VIDE1369219508996867.shtml',
  80         'info_dict': {
  81             'id': 'a194cfa7f18c426b823d876668325946',
  82             'ext': 'mp4',
  83             'title': '小泽征尔音乐塾 音乐梦想无国界',
  84             'duration': 2173,
  85             'timestamp': 1369248264,
  86             'upload_date': '20130522',
  87         },
  88         'params': {
  89             'skip_download': True,
  90         },
  91     }, {
  92         # videoCenterId: "id"
  93         'url': 'http://news.cctv.com/2024/02/21/ARTIcU5tKIOIF2myEGCATkLo240221.shtml',
  94         'info_dict': {
  95             'id': '5c846c0518444308ba32c4159df3b3e0',
  96             'ext': 'mp4',
  97             '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',
  98             'uploader': 'yangjuan',
  99             'timestamp': 1708554940,
 100             'upload_date': '20240221',
 101         },
 102         'params': {
 103             'skip_download': True,
 104         },
 105     }, {
 106         # var ids = ["id"]
 107         'url': 'http://www.ncpa-classic.com/clt/more/416/index.shtml',
 108         'info_dict': {
 109             'id': 'a8606119a4884588a79d81c02abecc16',
 110             'ext': 'mp3',
 111             'title': '来自维也纳的新年贺礼',
 112             'description': 'md5:f13764ae8dd484e84dd4b39d5bcba2a7',
 113             'duration': 1578,
 114             'uploader': 'djy',
 115             'timestamp': 1482942419,
 116             'upload_date': '20161228',
 117         },
 118         'params': {
 119             'skip_download': True,
 120         },
 121         'expected_warnings': ['Failed to download m3u8 information'],
 122     }, {
 123         'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml',
 124         'only_matching': True,
 125     }, {
 126         'url': 'http://tv.cntv.cn/video/C39296/e0210d949f113ddfb38d31f00a4e5c44',
 127         'only_matching': True,
 128     }, {
 129         'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
 130         'only_matching': True,
 131     }, {
 132         'url': 'http://tv.cctv.com/2016/09/07/VIDE5C1FnlX5bUywlrjhxXOV160907.shtml',
 133         'only_matching': True,
 134     }, {
 135         'url': 'http://tv.cntv.cn/video/C39296/95cfac44cabd3ddc4a9438780a4e5c44',
 136         'only_matching': True,
 137     }]
 138
 139     def _real_extract(self, url):
 140         video_id = self._match_id(url)
 141         webpage = self._download_webpage(url, video_id)
 142
 143         video_id = self._search_regex(
 144             [r'var\s+guid\s*=\s*["\']([\da-fA-F]+)',
 145              r'videoCenterId(?:["\']\s*,|:)\s*["\']([\da-fA-F]+)',
 146              r'changePlayer\s*\(\s*["\']([\da-fA-F]+)',
 147              r'load[Vv]ideo\s*\(\s*["\']([\da-fA-F]+)',
 148              r'var\s+initMyAray\s*=\s*["\']([\da-fA-F]+)',
 149              r'var\s+ids\s*=\s*\[["\']([\da-fA-F]+)'],
 150             webpage, 'video id')
 151
 152         data = self._download_json(
 153             'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do', video_id,
 154             query={
 155                 'pid': video_id,
 156                 'url': url,
 157                 'idl': 32,
 158                 'idlr': 32,
 159                 'modifyed': 'false',
 160             })
 161
 162         title = data['title']
 163
 164         formats = []
 165
 166         video = data.get('video')
 167         if isinstance(video, dict):
 168             for quality, chapters_key in enumerate(('lowChapters', 'chapters')):
 169                 video_url = try_get(
 170                     video, lambda x: x[chapters_key][0]['url'], compat_str)
 171                 if video_url:
 172                     formats.append({
 173                         'url': video_url,
 174                         'format_id': 'http',
 175                         'quality': quality,
 176                         # Sample clip
 177                         'preference': -10
 178                     })
 179
 180         hls_url = try_get(data, lambda x: x['hls_url'], compat_str)
 181         if hls_url:
 182             hls_url = re.sub(r'maxbr=\d+&?', '', hls_url)
 183             formats.extend(self._extract_m3u8_formats(
 184                 hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
 185                 m3u8_id='hls', fatal=False))
 186
 187         uploader = data.get('editer_name')
 188         description = self._html_search_meta(
 189             'description', webpage, default=None)
 190         timestamp = unified_timestamp(data.get('f_pgmtime'))
 191         duration = float_or_none(try_get(video, lambda x: x['totalLength']))
 192
 193         return {
 194             'id': video_id,
 195             'title': title,
 196             'description': description,
 197             'uploader': uploader,
 198             'timestamp': timestamp,
 199             'duration': duration,
 200             'formats': formats,
 201         }