youtube_dl/extractor/cctv.py

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