yt_dlp/extractor/moevideo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     clean_html,
   8     int_or_none,
   9 )
  10
  11
  12 class MoeVideoIE(InfoExtractor):
  13     IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net'
  14     _VALID_URL = r'''(?x)
  15         https?://(?P<host>(?:www\.)?
  16         (?:(?:moevideo|playreplay|videochart)\.net|thesame\.tv))/
  17         (?:video|framevideo|embed)/(?P<id>[0-9a-z]+\.[0-9A-Za-z]+)'''
  18     _API_URL = 'http://api.letitbit.net/'
  19     _API_KEY = 'tVL0gjqo5'
  20     _TESTS = [
  21         {
  22             'url': 'http://moevideo.net/video/00297.0036103fe3d513ef27915216fd29',
  23             'md5': '129f5ae1f6585d0e9bb4f38e774ffb3a',
  24             'info_dict': {
  25                 'id': '00297.0036103fe3d513ef27915216fd29',
  26                 'ext': 'flv',
  27                 'title': 'Sink cut out machine',
  28                 'description': 'md5:f29ff97b663aefa760bf7ca63c8ca8a8',
  29                 'thumbnail': r're:^https?://.*\.jpg$',
  30                 'width': 540,
  31                 'height': 360,
  32                 'duration': 179,
  33                 'filesize': 17822500,
  34             },
  35             'skip': 'Video has been removed',
  36         },
  37         {
  38             'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',
  39             'md5': '74f0a014d5b661f0f0e2361300d1620e',
  40             'info_dict': {
  41                 'id': '77107.7f325710a627383d40540d8e991a',
  42                 'ext': 'flv',
  43                 'title': 'Operacion Condor.',
  44                 'description': 'md5:7e68cb2fcda66833d5081c542491a9a3',
  45                 'thumbnail': r're:^https?://.*\.jpg$',
  46                 'width': 480,
  47                 'height': 296,
  48                 'duration': 6027,
  49                 'filesize': 588257923,
  50             },
  51             'skip': 'Video has been removed',
  52         },
  53     ]
  54
  55     def _real_extract(self, url):
  56         host, video_id = self._match_valid_url(url).groups()
  57
  58         webpage = self._download_webpage(
  59             'http://%s/video/%s' % (host, video_id),
  60             video_id, 'Downloading webpage')
  61
  62         title = self._og_search_title(webpage)
  63
  64         embed_webpage = self._download_webpage(
  65             'http://%s/embed/%s' % (host, video_id),
  66             video_id, 'Downloading embed webpage')
  67         video = self._parse_json(self._search_regex(
  68             r'mvplayer\("#player"\s*,\s*({.+})',
  69             embed_webpage, 'mvplayer'), video_id)['video']
  70
  71         return {
  72             'id': video_id,
  73             'title': title,
  74             'thumbnail': video.get('poster') or self._og_search_thumbnail(webpage),
  75             'description': clean_html(self._og_search_description(webpage)),
  76             'duration': int_or_none(self._og_search_property('video:duration', webpage)),
  77             'url': video['ourUrl'],
  78         }