youtube_dl/extractor/moevideo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     clean_html,
   9     int_or_none,
  10 )
  11
  12
  13 class MoeVideoIE(InfoExtractor):
  14     IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net'
  15     _VALID_URL = r'''(?x)
  16         https?://(?P<host>(?:www\.)?
  17         (?:(?:moevideo|playreplay|videochart)\.net|thesame\.tv))/
  18         (?:video|framevideo|embed)/(?P<id>[0-9a-z]+\.[0-9A-Za-z]+)'''
  19     _API_URL = 'http://api.letitbit.net/'
  20     _API_KEY = 'tVL0gjqo5'
  21     _TESTS = [
  22         {
  23             'url': 'http://moevideo.net/video/00297.0036103fe3d513ef27915216fd29',
  24             'md5': '129f5ae1f6585d0e9bb4f38e774ffb3a',
  25             'info_dict': {
  26                 'id': '00297.0036103fe3d513ef27915216fd29',
  27                 'ext': 'flv',
  28                 'title': 'Sink cut out machine',
  29                 'description': 'md5:f29ff97b663aefa760bf7ca63c8ca8a8',
  30                 'thumbnail': r're:^https?://.*\.jpg$',
  31                 'width': 540,
  32                 'height': 360,
  33                 'duration': 179,
  34                 'filesize': 17822500,
  35             },
  36             'skip': 'Video has been removed',
  37         },
  38         {
  39             'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',
  40             'md5': '74f0a014d5b661f0f0e2361300d1620e',
  41             'info_dict': {
  42                 'id': '77107.7f325710a627383d40540d8e991a',
  43                 'ext': 'flv',
  44                 'title': 'Operacion Condor.',
  45                 'description': 'md5:7e68cb2fcda66833d5081c542491a9a3',
  46                 'thumbnail': r're:^https?://.*\.jpg$',
  47                 'width': 480,
  48                 'height': 296,
  49                 'duration': 6027,
  50                 'filesize': 588257923,
  51             },
  52             'skip': 'Video has been removed',
  53         },
  54     ]
  55
  56     def _real_extract(self, url):
  57         host, video_id = re.match(self._VALID_URL, url).groups()
  58
  59         webpage = self._download_webpage(
  60             'http://%s/video/%s' % (host, video_id),
  61             video_id, 'Downloading webpage')
  62
  63         title = self._og_search_title(webpage)
  64
  65         embed_webpage = self._download_webpage(
  66             'http://%s/embed/%s' % (host, video_id),
  67             video_id, 'Downloading embed webpage')
  68         video = self._parse_json(self._search_regex(
  69             r'mvplayer\("#player"\s*,\s*({.+})',
  70             embed_webpage, 'mvplayer'), video_id)['video']
  71
  72         return {
  73             'id': video_id,
  74             'title': title,
  75             'thumbnail': video.get('poster') or self._og_search_thumbnail(webpage),
  76             'description': clean_html(self._og_search_description(webpage)),
  77             'duration': int_or_none(self._og_search_property('video:duration', webpage)),
  78             'url': video['ourUrl'],
  79         }