Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mojvideo.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     ExtractorError,
   9     parse_duration,
  10 )
  11
  12
  13 class MojvideoIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-(?P<display_id>[^/]+)/(?P<id>[a-f0-9]+)'
  15     _TEST = {
  16         'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906',
  17         'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7',
  18         'info_dict': {
  19             'id': '3d1ed4497707730b2906',
  20             'display_id': 'v-avtu-pred-mano-rdecelaska-alfi-nipic',
  21             'ext': 'mp4',
  22             'title': 'V avtu pred mano rdečelaska - Alfi Nipič',
  23             'thumbnail': r're:^http://.*\.jpg$',
  24             'duration': 242,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31         display_id = mobj.group('display_id')
  32
  33         # XML is malformed
  34         playerapi = self._download_webpage(
  35             'http://www.mojvideo.com/playerapi.php?v=%s&t=1' % video_id, display_id)
  36
  37         if '<error>true</error>' in playerapi:
  38             error_desc = self._html_search_regex(
  39                 r'<errordesc>([^<]*)</errordesc>', playerapi, 'error description', fatal=False)
  40             raise ExtractorError('%s said: %s' % (self.IE_NAME, error_desc), expected=True)
  41
  42         title = self._html_search_regex(
  43             r'<title>([^<]+)</title>', playerapi, 'title')
  44         video_url = self._html_search_regex(
  45             r'<file>([^<]+)</file>', playerapi, 'video URL')
  46         thumbnail = self._html_search_regex(
  47             r'<preview>([^<]+)</preview>', playerapi, 'thumbnail', fatal=False)
  48         duration = parse_duration(self._html_search_regex(
  49             r'<duration>([^<]+)</duration>', playerapi, 'duration', fatal=False))
  50
  51         return {
  52             'id': video_id,
  53             'display_id': display_id,
  54             'url': video_url,
  55             'title': title,
  56             'thumbnail': thumbnail,
  57             'duration': duration,
  58         }