yt_dlp/extractor/xinpianchang.py

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