yt_dlp/extractor/xinpianchang.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     try_get,
   8     update_url_query,
   9     url_or_none,
  10 )
  11
  12
  13 class XinpianchangIE(InfoExtractor):
  14     _VALID_URL = r'https?://www\.xinpianchang\.com/(?P<id>[^/]+?)(?:\D|$)'
  15     IE_NAME = 'xinpianchang'
  16     IE_DESC = 'xinpianchang.com'
  17     _TESTS = [{
  18         'url': 'https://www.xinpianchang.com/a11766551',
  19         'info_dict': {
  20             'id': 'a11766551',
  21             'ext': 'mp4',
  22             'title': '北京2022冬奥会闭幕式再见短片-冰墩墩下班了',
  23             'description': 'md5:4a730c10639a82190fabe921c0fa4b87',
  24             'duration': 151,
  25             'thumbnail': r're:^https?://oss-xpc0\.xpccdn\.com.+/assets/',
  26             'uploader': '正时文创',
  27             'uploader_id': 10357277,
  28             'categories': ['宣传片', '国家城市', '广告', '其他'],
  29             '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']
  30         },
  31     }, {
  32         'url': 'https://www.xinpianchang.com/a11762904',
  33         'info_dict': {
  34             'id': 'a11762904',
  35             'ext': 'mp4',
  36             'title': '冬奥会决胜时刻《法国派出三只鸡？》',
  37             'description': 'md5:55cb139ef8f48f0c877932d1f196df8b',
  38             'duration': 136,
  39             'thumbnail': r're:^https?://oss-xpc0\.xpccdn\.com.+/assets/',
  40             'uploader': '精品动画',
  41             'uploader_id': 10858927,
  42             'categories': ['动画', '三维CG'],
  43             'keywords': ['France Télévisions', '法国3台', '蠢萌', '冬奥会']
  44         },
  45     }, {
  46         'url': 'https://www.xinpianchang.com/a11779743?from=IndexPick&part=%E7%BC%96%E8%BE%91%E7%B2%BE%E9%80%89&index=2',
  47         'only_matching': True,
  48     }]
  49
  50     def _real_extract(self, url):
  51         video_id = self._match_id(url)
  52         webpage = self._download_webpage(url, video_id=video_id)
  53         domain = self.find_value_with_regex(var='requireNewDomain', webpage=webpage)
  54         vid = self.find_value_with_regex(var='vid', webpage=webpage)
  55         app_key = self.find_value_with_regex(var='modeServerAppKey', webpage=webpage)
  56         api = update_url_query(f'{domain}/mod/api/v2/media/{vid}', {'appKey': app_key})
  57         data = self._download_json(api, video_id=video_id)['data']
  58         formats, subtitles = [], {}
  59         for k, v in data.get('resource').items():
  60             if k in ('dash', 'hls'):
  61                 v_url = v.get('url')
  62                 if not v_url:
  63                     continue
  64                 if k == 'dash':
  65                     fmts, subs = self._extract_mpd_formats_and_subtitles(v_url, video_id=video_id)
  66                 elif k == 'hls':
  67                     fmts, subs = self._extract_m3u8_formats_and_subtitles(v_url, video_id=video_id)
  68                 formats.extend(fmts)
  69                 subtitles = self._merge_subtitles(subtitles, subs)
  70             elif k == 'progressive':
  71                 formats.extend([{
  72                     'url': url_or_none(prog.get('url')),
  73                     'width': int_or_none(prog.get('width')),
  74                     'height': int_or_none(prog.get('height')),
  75                     'ext': 'mp4',
  76                 } for prog in v if prog.get('url') or []])
  77
  78         self._sort_formats(formats)
  79
  80         return {
  81             'id': video_id,
  82             'title': data.get('title'),
  83             'description': data.get('description'),
  84             'duration': int_or_none(data.get('duration')),
  85             'categories': data.get('categories'),
  86             'keywords': data.get('keywords'),
  87             'thumbnail': data.get('cover'),
  88             'uploader': try_get(data, lambda x: x['owner']['username']),
  89             'uploader_id': try_get(data, lambda x: x['owner']['id']),
  90             'formats': formats,
  91             'subtitles': subtitles,
  92         }
  93
  94     def find_value_with_regex(self, var, webpage):
  95         return self._search_regex(rf'var\s{var}\s=\s\"(?P<vid>[^\"]+)\"', webpage, name=var)