yt_dlp/extractor/moevideo.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     int_or_none,
   5 )
   6
   7
   8 class MoeVideoIE(InfoExtractor):
   9     IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net'
  10     _VALID_URL = r'''(?x)
  11         https?://(?P<host>(?:www\.)?
  12         (?:(?:moevideo|playreplay|videochart)\.net|thesame\.tv))/
  13         (?:video|framevideo|embed)/(?P<id>[0-9a-z]+\.[0-9A-Za-z]+)'''
  14     _API_URL = 'http://api.letitbit.net/'
  15     _API_KEY = 'tVL0gjqo5'
  16     _TESTS = [
  17         {
  18             'url': 'http://moevideo.net/video/00297.0036103fe3d513ef27915216fd29',
  19             'md5': '129f5ae1f6585d0e9bb4f38e774ffb3a',
  20             'info_dict': {
  21                 'id': '00297.0036103fe3d513ef27915216fd29',
  22                 'ext': 'flv',
  23                 'title': 'Sink cut out machine',
  24                 'description': 'md5:f29ff97b663aefa760bf7ca63c8ca8a8',
  25                 'thumbnail': r're:^https?://.*\.jpg$',
  26                 'width': 540,
  27                 'height': 360,
  28                 'duration': 179,
  29                 'filesize': 17822500,
  30             },
  31             'skip': 'Video has been removed',
  32         },
  33         {
  34             'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',
  35             'md5': '74f0a014d5b661f0f0e2361300d1620e',
  36             'info_dict': {
  37                 'id': '77107.7f325710a627383d40540d8e991a',
  38                 'ext': 'flv',
  39                 'title': 'Operacion Condor.',
  40                 'description': 'md5:7e68cb2fcda66833d5081c542491a9a3',
  41                 'thumbnail': r're:^https?://.*\.jpg$',
  42                 'width': 480,
  43                 'height': 296,
  44                 'duration': 6027,
  45                 'filesize': 588257923,
  46             },
  47             'skip': 'Video has been removed',
  48         },
  49     ]
  50
  51     def _real_extract(self, url):
  52         host, video_id = self._match_valid_url(url).groups()
  53
  54         webpage = self._download_webpage(
  55             'http://%s/video/%s' % (host, video_id),
  56             video_id, 'Downloading webpage')
  57
  58         title = self._og_search_title(webpage)
  59
  60         embed_webpage = self._download_webpage(
  61             'http://%s/embed/%s' % (host, video_id),
  62             video_id, 'Downloading embed webpage')
  63         video = self._parse_json(self._search_regex(
  64             r'mvplayer\("#player"\s*,\s*({.+})',
  65             embed_webpage, 'mvplayer'), video_id)['video']
  66
  67         return {
  68             'id': video_id,
  69             'title': title,
  70             'thumbnail': video.get('poster') or self._og_search_thumbnail(webpage),
  71             'description': clean_html(self._og_search_description(webpage)),
  72             'duration': int_or_none(self._og_search_property('video:duration', webpage)),
  73             'url': video['ourUrl'],
  74         }