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

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