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     determine_ext,
  10     get_element_by_id,
  11     clean_html,
  12 )
  13
  14
  15 class FKTVIE(InfoExtractor):
  16     IE_NAME = 'fernsehkritik.tv'
  17     _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
  18
  19     _TEST = {
  20         'url': 'http://fernsehkritik.tv/folge-1',
  21         'info_dict': {
  22             'id': '00011',
  23             'ext': 'flv',
  24             'title': 'Folge 1 vom 10. April 2007',
  25             'description': 'md5:fb4818139c7cfe6907d4b83412a6864f',
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         episode = int(mobj.group('ep'))
  32
  33         server = random.randint(2, 4)
  34         video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode
  35         start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode,
  36             episode)
  37         playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage,
  38             'playlist', flags=re.DOTALL)
  39         files = json.loads(re.sub('{[^{}]*?}', '{}', playlist))
  40         # TODO: return a single multipart video
  41         videos = []
  42         for i, _ in enumerate(files, 1):
  43             video_id = '%04d%d' % (episode, i)
  44             video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i == 1 else '-%d' % i)
  45             videos.append({
  46                 'id': video_id,
  47                 'url': video_url,
  48                 'title': clean_html(get_element_by_id('eptitle', start_webpage)),
  49                 'description': clean_html(get_element_by_id('contentlist', start_webpage)),
  50                 'thumbnail': video_thumbnail
  51             })
  52         return videos
  53
  54
  55 class FKTVPosteckeIE(InfoExtractor):
  56     IE_NAME = 'fernsehkritik.tv:postecke'
  57     _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
  58     _TEST = {
  59         'url': 'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120',
  60         'md5': '262f0adbac80317412f7e57b4808e5c4',
  61         'info_dict': {
  62             'id': '0120',
  63             'ext': 'flv',
  64             'title': 'Postecke 120',
  65         }
  66     }
  67
  68     def _real_extract(self, url):
  69         mobj = re.match(self._VALID_URL, url)
  70         episode = int(mobj.group('ep'))
  71
  72         server = random.randint(2, 4)
  73         video_id = '%04d' % episode
  74         video_url = 'http://dl%d.fernsehkritik.tv/postecke/postecke%d.flv' % (server, episode)
  75         video_title = 'Postecke %d' % episode
  76         return {
  77             'id': video_id,
  78             'url': video_url,
  79             'title': video_title,
  80         }