_ Git - youtube-dl/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 )
  10
  11
  12 class FKTVIE(InfoExtractor):
  13     IE_NAME = 'fernsehkritik.tv'
  14     _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
  15
  16     _TEST = {
  17         'url': 'http://fernsehkritik.tv/folge-1',
  18         'md5': '21f0b0c99bce7d5b524eb1b17b1c6d79',
  19         'info_dict': {
  20             'id': '1',
  21             'ext': 'mp4',
  22             'title': 'Folge 1 vom 10. April 2007',
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         episode = self._match_id(url)
  28
  29         webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/play' % episode, episode)
  30         title = clean_html(self._html_search_regex('<h3>([^<]+?)</h3>', webpage, 'title'))
  31         matches = re.search(r'(?s)<video[^>]*poster="([^"]+)"[^>]*>(.*?)</video>', webpage)
  32         if matches:
  33             poster, sources = matches.groups()
  34             urls = re.findall(r'(?s)<source[^>]*src="([^"]+)"[^>]*>', sources)
  35             if sources:
  36                 formats = [{'url': url, 'format_id': determine_ext(url)} for url in urls]
  37                 return {
  38                     'id': episode,
  39                     'title': title,
  40                     'formats': formats,
  41                     'thumbnail': poster,
  42                 }