_ Git - youtube-dl/blob - youtube_dl/extractor/megavideoz.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     float_or_none,
   9     xpath_text,
  10 )
  11
  12
  13 class MegaVideozIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?megavideoz\.eu/video/(?P<id>[^/]+)(?:/(?P<display_id>[^/]+))?'
  15     _TEST = {
  16         'url': 'http://megavideoz.eu/video/WM6UB919XMXH/SMPTE-Universal-Film-Leader',
  17         'info_dict': {
  18             'id': '48723',
  19             'display_id': 'SMPTE-Universal-Film-Leader',
  20             'ext': 'mp4',
  21             'title': 'SMPTE Universal Film Leader',
  22             'thumbnail': 're:https?://.*?\.jpg',
  23             'duration': 10.93,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30         display_id = mobj.group('display_id') or video_id
  31
  32         webpage = self._download_webpage(url, display_id)
  33
  34         config = self._download_xml(
  35             self._search_regex(
  36                 r"var\s+cnf\s*=\s*'([^']+)'", webpage, 'cnf url'),
  37             display_id)
  38
  39         video_url = xpath_text(config, './file', 'video url', fatal=True)
  40         title = xpath_text(config, './title', 'title', fatal=True)
  41         thumbnail = xpath_text(config, './image', 'thumbnail')
  42         duration = float_or_none(xpath_text(config, './duration', 'duration'))
  43         video_id = xpath_text(config, './mediaid', 'video id') or video_id
  44
  45         return {
  46             'id': video_id,
  47             'display_id': display_id,
  48             'url': video_url,
  49             'title': title,
  50             'thumbnail': thumbnail,
  51             'duration': duration
  52         }