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

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import random
   5 import json
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     get_element_by_id,
  10     clean_html,
  11 )
  12
  13
  14 class FKTVIE(InfoExtractor):
  15     IE_NAME = 'fernsehkritik.tv'
  16     _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
  17
  18     _TEST = {
  19         'url': 'http://fernsehkritik.tv/folge-1',
  20         'info_dict': {
  21             'id': '00011',
  22             'ext': 'flv',
  23             'title': 'Folge 1 vom 10. April 2007',
  24             'description': 'md5:fb4818139c7cfe6907d4b83412a6864f',
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         episode = int(mobj.group('ep'))
  31
  32         server = random.randint(2, 4)
  33         video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode
  34         start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode,
  35                                                episode)
  36         playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage,
  37                                       'playlist', flags=re.DOTALL)
  38         files = json.loads(re.sub('{[^{}]*?}', '{}', playlist))
  39         # TODO: return a single multipart video
  40         videos = []
  41         for i, _ in enumerate(files, 1):
  42             video_id = '%04d%d' % (episode, i)
  43             video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i == 1 else '-%d' % i)
  44             videos.append({
  45                 'id': video_id,
  46                 'url': video_url,
  47                 'title': clean_html(get_element_by_id('eptitle', start_webpage)),
  48                 'description': clean_html(get_element_by_id('contentlist', start_webpage)),
  49                 'thumbnail': video_thumbnail
  50             })
  51         return videos
  52
  53
  54 class FKTVPosteckeIE(InfoExtractor):
  55     IE_NAME = 'fernsehkritik.tv:postecke'
  56     _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
  57     _TEST = {
  58         'url': 'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120',
  59         'md5': '262f0adbac80317412f7e57b4808e5c4',
  60         'info_dict': {
  61             'id': '0120',
  62             'ext': 'flv',
  63             'title': 'Postecke 120',
  64         }
  65     }
  66
  67     def _real_extract(self, url):
  68         mobj = re.match(self._VALID_URL, url)
  69         episode = int(mobj.group('ep'))
  70
  71         server = random.randint(2, 4)
  72         video_id = '%04d' % episode
  73         video_url = 'http://dl%d.fernsehkritik.tv/postecke/postecke%d.flv' % (server, episode)
  74         video_title = 'Postecke %d' % episode
  75         return {
  76             'id': video_id,
  77             'url': video_url,
  78             'title': video_title,
  79         }