yt_dlp/extractor/meipai.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     parse_duration,
   5     unified_timestamp,
   6 )
   7
   8
   9 class MeipaiIE(InfoExtractor):
  10     IE_DESC = '美拍'
  11     _VALID_URL = r'https?://(?:www\.)?meipai\.com/media/(?P<id>[0-9]+)'
  12     _TESTS = [{
  13         # regular uploaded video
  14         'url': 'http://www.meipai.com/media/531697625',
  15         'md5': 'e3e9600f9e55a302daecc90825854b4f',
  16         'info_dict': {
  17             'id': '531697625',
  18             'ext': 'mp4',
  19             'title': '#葉子##阿桑##余姿昀##超級女聲#',
  20             'description': '#葉子##阿桑##余姿昀##超級女聲#',
  21             'thumbnail': r're:^https?://.*\.jpg$',
  22             'duration': 152,
  23             'timestamp': 1465492420,
  24             'upload_date': '20160609',
  25             'view_count': 35511,
  26             'creator': '她她-TATA',
  27             'tags': ['葉子', '阿桑', '余姿昀', '超級女聲'],
  28         },
  29     }, {
  30         # record of live streaming
  31         'url': 'http://www.meipai.com/media/585526361',
  32         'md5': 'ff7d6afdbc6143342408223d4f5fb99a',
  33         'info_dict': {
  34             'id': '585526361',
  35             'ext': 'mp4',
  36             'title': '姿昀和善願 練歌練琴啦😁😁😁',
  37             'description': '姿昀和善願 練歌練琴啦😁😁😁',
  38             'thumbnail': r're:^https?://.*\.jpg$',
  39             'duration': 5975,
  40             'timestamp': 1474311799,
  41             'upload_date': '20160919',
  42             'view_count': 1215,
  43             'creator': '她她-TATA',
  44         },
  45     }]
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49         webpage = self._download_webpage(url, video_id)
  50
  51         title = self._generic_title('', webpage)
  52
  53         formats = []
  54
  55         # recorded playback of live streaming
  56         m3u8_url = self._html_search_regex(
  57             r'file:\s*encodeURIComponent\((["\'])(?P<url>(?:(?!\1).)+)\1\)',
  58             webpage, 'm3u8 url', group='url', default=None)
  59         if m3u8_url:
  60             formats.extend(self._extract_m3u8_formats(
  61                 m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
  62                 m3u8_id='hls', fatal=False))
  63
  64         if not formats:
  65             # regular uploaded video
  66             video_url = self._search_regex(
  67                 r'data-video=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'video url',
  68                 group='url', default=None)
  69             if video_url:
  70                 formats.append({
  71                     'url': video_url,
  72                     'format_id': 'http',
  73                 })
  74
  75         timestamp = unified_timestamp(self._og_search_property(
  76             'video:release_date', webpage, 'release date', fatal=False))
  77
  78         tags = self._og_search_property(
  79             'video:tag', webpage, 'tags', default='').split(',')
  80
  81         view_count = int_or_none(self._html_search_meta(
  82             'interactionCount', webpage, 'view count'))
  83         duration = parse_duration(self._html_search_meta(
  84             'duration', webpage, 'duration'))
  85         creator = self._og_search_property(
  86             'video:director', webpage, 'creator', fatal=False)
  87
  88         return {
  89             'id': video_id,
  90             'title': title,
  91             'description': self._og_search_description(webpage),
  92             'thumbnail': self._og_search_thumbnail(webpage),
  93             'duration': duration,
  94             'timestamp': timestamp,
  95             'view_count': view_count,
  96             'creator': creator,
  97             'tags': tags,
  98             'formats': formats,
  99         }