Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/fktv.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     clean_html,
   8     determine_ext,
   9     ExtractorError,
  10 )
  11
  12
  13 class FKTVIE(InfoExtractor):
  14     IE_NAME = 'fernsehkritik.tv'
  15     _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
  16
  17     _TEST = {
  18         'url': 'http://fernsehkritik.tv/folge-1',
  19         'md5': '21f0b0c99bce7d5b524eb1b17b1c6d79',
  20         'info_dict': {
  21             'id': '1',
  22             'ext': 'mp4',
  23             'title': 'Folge 1 vom 10. April 2007',
  24             'thumbnail': 're:^https?://.*\.jpg$',
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         episode = self._match_id(url)
  30
  31         webpage = self._download_webpage(
  32             'http://fernsehkritik.tv/folge-%s/play' % episode, episode)
  33         title = clean_html(self._html_search_regex(
  34             '<h3>([^<]+)</h3>', webpage, 'title'))
  35         matches = re.search(
  36             r'(?s)<video(?:(?!poster)[^>])+(?:poster="([^"]+)")?[^>]*>(.*)</video>',
  37             webpage)
  38         if matches is None:
  39             raise ExtractorError('Unable to extract the video')
  40
  41         poster, sources = matches.groups()
  42         if poster is None:
  43             self.report_warning('unable to extract thumbnail')
  44
  45         urls = re.findall(r'<source[^>]+src="([^"]+)"', sources)
  46         formats = [{
  47             'url': furl,
  48             'format_id': determine_ext(furl),
  49         } for furl in urls]
  50         return {
  51             'id': episode,
  52             'title': title,
  53             'formats': formats,
  54             'thumbnail': poster,
  55         }