Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rudo.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     js_to_json,
   9     get_element_by_class,
  10     unified_strdate,
  11 )
  12
  13
  14 class RudoIE(InfoExtractor):
  15     _VALID_URL = r'https?://rudo\.video/vod/(?P<id>[0-9a-zA-Z]+)'
  16
  17     _TEST = {
  18         'url': 'http://rudo.video/vod/oTzw0MGnyG',
  19         'md5': '2a03a5b32dd90a04c83b6d391cf7b415',
  20         'info_dict': {
  21             'id': 'oTzw0MGnyG',
  22             'ext': 'mp4',
  23             'title': 'Comentario Tomás Mosciatti',
  24             'upload_date': '20160617',
  25         },
  26     }
  27
  28     @classmethod
  29     def _extract_url(cls, webpage):
  30         mobj = re.search(
  31             r'<iframe[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)',
  32             webpage)
  33         if mobj:
  34             return mobj.group('url')
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38
  39         webpage = self._download_webpage(url, video_id, encoding='iso-8859-1')
  40
  41         jwplayer_data = self._parse_json(self._search_regex(
  42             r'(?s)playerInstance\.setup\(({.+?})\)', webpage, 'jwplayer data'), video_id,
  43             transform_source=lambda s: js_to_json(re.sub(r'encodeURI\([^)]+\)', '""', s)))
  44
  45         info_dict = self._parse_jwplayer_data(
  46             jwplayer_data, video_id, require_title=False, m3u8_id='hls', mpd_id='dash')
  47
  48         info_dict.update({
  49             'title': self._og_search_title(webpage),
  50             'upload_date': unified_strdate(get_element_by_class('date', webpage)),
  51         })
  52
  53         return info_dict