yt_dlp/extractor/xinpianchang.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     try_get,
   5     update_url_query,
   6     url_or_none,
   7 )
   8
   9
  10 class XinpianchangIE(InfoExtractor):
  11     _VALID_URL = r'https?://www\.xinpianchang\.com/(?P<id>[^/]+?)(?:\D|$)'
  12     IE_NAME = 'xinpianchang'
  13     IE_DESC = 'xinpianchang.com'
  14     _TESTS = [{
  15         'url': 'https://www.xinpianchang.com/a11766551',
  16         'info_dict': {
  17             'id': 'a11766551',
  18             'ext': 'mp4',
  19             'title': '北京2022冬奥会闭幕式再见短片-冰墩墩下班了',
  20             'description': 'md5:4a730c10639a82190fabe921c0fa4b87',
  21             'duration': 151,
  22             'thumbnail': r're:^https?://oss-xpc0\.xpccdn\.com.+/assets/',
  23             'uploader': '正时文创',
  24             'uploader_id': 10357277,
  25             'categories': ['宣传片', '国家城市', '广告', '其他'],
  26             'keywords': ['北京冬奥会', '冰墩墩', '再见', '告别', '冰墩墩哭了', '感动', '闭幕式', '熄火']
  27         },
  28     }, {
  29         'url': 'https://www.xinpianchang.com/a11762904',
  30         'info_dict': {
  31             'id': 'a11762904',
  32             'ext': 'mp4',
  33             'title': '冬奥会决胜时刻《法国派出三只鸡？》',
  34             'description': 'md5:55cb139ef8f48f0c877932d1f196df8b',
  35             'duration': 136,
  36             'thumbnail': r're:^https?://oss-xpc0\.xpccdn\.com.+/assets/',
  37             'uploader': '精品动画',
  38             'uploader_id': 10858927,
  39             'categories': ['动画', '三维CG'],
  40             'keywords': ['France Télévisions', '法国3台', '蠢萌', '冬奥会']
  41         },
  42     }, {
  43         'url': 'https://www.xinpianchang.com/a11779743?from=IndexPick&part=%E7%BC%96%E8%BE%91%E7%B2%BE%E9%80%89&index=2',
  44         'only_matching': True,
  45     }]
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49         webpage = self._download_webpage(url, video_id=video_id)
  50         domain = self.find_value_with_regex(var='requireNewDomain', webpage=webpage)
  51         vid = self.find_value_with_regex(var='vid', webpage=webpage)
  52         app_key = self.find_value_with_regex(var='modeServerAppKey', webpage=webpage)
  53         api = update_url_query(f'{domain}/mod/api/v2/media/{vid}', {'appKey': app_key})
  54         data = self._download_json(api, video_id=video_id)['data']
  55         formats, subtitles = [], {}
  56         for k, v in data.get('resource').items():
  57             if k in ('dash', 'hls'):
  58                 v_url = v.get('url')
  59                 if not v_url:
  60                     continue
  61                 if k == 'dash':
  62                     fmts, subs = self._extract_mpd_formats_and_subtitles(v_url, video_id=video_id)
  63                 elif k == 'hls':
  64                     fmts, subs = self._extract_m3u8_formats_and_subtitles(v_url, video_id=video_id)
  65                 formats.extend(fmts)
  66                 subtitles = self._merge_subtitles(subtitles, subs)
  67             elif k == 'progressive':
  68                 formats.extend([{
  69                     'url': url_or_none(prog.get('url')),
  70                     'width': int_or_none(prog.get('width')),
  71                     'height': int_or_none(prog.get('height')),
  72                     'ext': 'mp4',
  73                 } for prog in v if prog.get('url') or []])
  74
  75         return {
  76             'id': video_id,
  77             'title': data.get('title'),
  78             'description': data.get('description'),
  79             'duration': int_or_none(data.get('duration')),
  80             'categories': data.get('categories'),
  81             'keywords': data.get('keywords'),
  82             'thumbnail': data.get('cover'),
  83             'uploader': try_get(data, lambda x: x['owner']['username']),
  84             'uploader_id': try_get(data, lambda x: x['owner']['id']),
  85             'formats': formats,
  86             'subtitles': subtitles,
  87         }
  88
  89     def find_value_with_regex(self, var, webpage):
  90         return self._search_regex(rf'var\s{var}\s=\s\"(?P<vid>[^\"]+)\"', webpage, name=var)