X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffktv.py;h=2958452f470bca7f7322fa9dcdccca66f525cee0;hb=ec85ded83cbfa652ba94cb080aab52d8b270212a;hp=239d9df38190536633f214795f2a8ad12ce89eb6;hpb=6c36d8d6fb39b686ae5b475868de3523b6c76f76;p=youtube-dl diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py index 239d9df38..2958452f4 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -1,58 +1,51 @@ -import re,random +from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( + clean_html, determine_ext, + js_to_json, ) + class FKTVIE(InfoExtractor): - """Information Extractor for Fernsehkritik-TV""" - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/folge-(?P[0-9]+)(?:/.*)?' - - def _real_extract(self,url): - mobj = re.match(self._VALID_URL, url) - episode = int(mobj.group('ep')) - - server = random.randint(2,4) - video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode - videos = [] - # Download all three parts - for i in range(1,4): - video_id = '%04d%d' % (episode, i) - video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i==1 else '-%d'%i) - video_title = 'Fernsehkritik %d.%d' % (episode, i) - videos.append({ - 'id': video_id, - 'url': video_url, - 'ext': determine_ext(video_url), - 'title': video_title, - 'thumbnail': video_thumbnail - }) - return videos - -class FKTVPosteckeIE(InfoExtractor): - """Information Extractor for Fernsehkritik-TV Postecke""" - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/inline-video/postecke.php\?(.*&)?ep=(?P[0-9]+)(&|$)' + IE_NAME = 'fernsehkritik.tv' + _VALID_URL = r'https?://(?:www\.)?fernsehkritik\.tv/folge-(?P[0-9]+)(?:/.*)?' + _TEST = { - u'url': u'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120', - u'file': u'0120.flv', - u'md5': u'262f0adbac80317412f7e57b4808e5c4', - u'info_dict': { - u"title": u"Postecke 120" - } + 'url': 'http://fernsehkritik.tv/folge-1', + 'md5': '21f0b0c99bce7d5b524eb1b17b1c6d79', + 'info_dict': { + 'id': '1', + 'ext': 'mp4', + 'title': 'Folge 1 vom 10. April 2007', + 'thumbnail': r're:^https?://.*\.jpg$', + }, } - def _real_extract(self,url): - mobj = re.match(self._VALID_URL, url) - episode = int(mobj.group('ep')) - - server = random.randint(2,4) - video_id = '%04d' % episode - video_url = 'http://dl%d.fernsehkritik.tv/postecke/postecke%d.flv' % (server, episode) - video_title = 'Postecke %d' % episode - return[{ - 'id': video_id, - 'url': video_url, - 'ext': determine_ext(video_url), - 'title': video_title, - }] + def _real_extract(self, url): + episode = self._match_id(url) + + webpage = self._download_webpage( + 'http://fernsehkritik.tv/folge-%s/play' % episode, episode) + title = clean_html(self._html_search_regex( + '

([^<]+)

', webpage, 'title')) + thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False) + sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json) + + formats = [] + for source in sources: + furl = source.get('src') + if furl: + formats.append({ + 'url': furl, + 'format_id': determine_ext(furl), + }) + self._sort_formats(formats) + + return { + 'id': episode, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + }