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)/(?:[^/]+/)*?(?P<id>[^/?#&]+?)(?:/index)?\.s?html'
  18     _TESTS = [{
  19         'url': 'http://sports.cntv.cn/2016/02/12/ARTIaBRxv4rTT1yWf1frW2wi160212.shtml',
  20         'md5': 'd61ec00a493e09da810bf406a078f691',
  21         'info_dict': {
  22             'id': '5ecdbeab623f4973b40ff25f18b174e8',
  23             'ext': 'mp4',
  24             'title': '[NBA]二少联手砍下46分 雷霆主场击败鹈鹕（快讯）',
  25             'description': 'md5:7e14a5328dc5eb3d1cd6afbbe0574e95',
  26             'duration': 98,
  27             'uploader': 'songjunjie',
  28             'timestamp': 1455279956,
  29             'upload_date': '20160212',
  30         },
  31     }, {
  32         'url': 'http://tv.cctv.com/2016/02/05/VIDEUS7apq3lKrHG9Dncm03B160205.shtml',
  33         'info_dict': {
  34             'id': 'efc5d49e5b3b4ab2b34f3a502b73d3ae',
  35             'ext': 'mp4',
  36             'title': '[赛车]“车王”舒马赫恢复情况成谜（快讯）',
  37             '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。',
  38             'duration': 37,
  39             'uploader': 'shujun',
  40             'timestamp': 1454677291,
  41             'upload_date': '20160205',
  42         },
  43         'params': {
  44             'skip_download': True,
  45         },
  46     }, {
  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         '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         'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml',
  78         'only_matching': True,
  79     }, {
  80         'url': 'http://tv.cntv.cn/video/C39296/e0210d949f113ddfb38d31f00a4e5c44',
  81         'only_matching': True,
  82     }, {
  83         'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
  84         'only_matching': True,
  85     }, {
  86         'url': 'http://tv.cctv.com/2016/09/07/VIDE5C1FnlX5bUywlrjhxXOV160907.shtml',
  87         'only_matching': True,
  88     }, {
  89         'url': 'http://tv.cntv.cn/video/C39296/95cfac44cabd3ddc4a9438780a4e5c44',
  90         'only_matching': True
  91     }]
  92
  93     def _real_extract(self, url):
  94         video_id = self._match_id(url)
  95         webpage = self._download_webpage(url, video_id)
  96
  97         video_id = self._search_regex(
  98             [r'var\s+guid\s*=\s*["\']([\da-fA-F]+)',
  99              r'videoCenterId["\']\s*,\s*["\']([\da-fA-F]+)',
 100              r'"changePlayer\s*\(\s*["\']([\da-fA-F]+)',
 101              r'"load[Vv]ideo\s*\(\s*["\']([\da-fA-F]+)'],
 102             webpage, 'video id', default=video_id)
 103
 104         data = self._download_json(
 105             'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do', video_id,
 106             query={
 107                 'pid': video_id,
 108                 'url': url,
 109                 'idl': 32,
 110                 'idlr': 32,
 111                 'modifyed': 'false',
 112             })
 113
 114         title = data['title']
 115
 116         formats = []
 117
 118         video = data.get('video')
 119         if isinstance(video, dict):
 120             for quality, chapters_key in enumerate(('lowChapters', 'chapters')):
 121                 video_url = try_get(
 122                     video, lambda x: x[chapters_key][0]['url'], compat_str)
 123                 if video_url:
 124                     formats.append({
 125                         'url': video_url,
 126                         'format_id': 'http',
 127                         'quality': quality,
 128                         'preference': -1,
 129                     })
 130
 131         hls_url = try_get(data, lambda x: x['hls_url'], compat_str)
 132         if hls_url:
 133             hls_url = re.sub(r'maxbr=\d+&?', '', hls_url)
 134             formats.extend(self._extract_m3u8_formats(
 135                 hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
 136                 m3u8_id='hls', fatal=False))
 137
 138         self._sort_formats(formats)
 139
 140         uploader = data.get('editer_name')
 141         description = self._html_search_meta('description', webpage)
 142         timestamp = unified_timestamp(data.get('f_pgmtime'))
 143         duration = float_or_none(try_get(video, lambda x: x['totalLength']))
 144
 145         return {
 146             'id': video_id,
 147             'title': title,
 148             'description': description,
 149             'uploader': uploader,
 150             'timestamp': timestamp,
 151             'duration': duration,
 152             'formats': formats,
 153         }