X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/782e271dfe61ed8d5dbf100286ad876068ea585c..0433503f78928c1f0c76a8d66ef236dc35ff23df:/youtube_dl/extractor/fktv.py?ds=inline diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py index 9c89362..2958452 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -1,79 +1,51 @@ -import re -import random -import json +from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - determine_ext, - get_element_by_id, clean_html, + determine_ext, + js_to_json, ) class FKTVIE(InfoExtractor): - IE_NAME = u'fernsehkritik.tv' - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/folge-(?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/folge-1', - u'file': u'00011.flv', - u'info_dict': { - u'title': u'Folge 1 vom 10. April 2007', - u'description': u'md5:fb4818139c7cfe6907d4b83412a6864f', + '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_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode - start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode, - episode) - playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage, - u'playlist', flags=re.DOTALL) - files = json.loads(re.sub('{[^{}]*?}', '{}', playlist)) - # TODO: return a single multipart video - videos = [] - for i, _ in enumerate(files, 1): - 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': clean_html(get_element_by_id('eptitle', start_webpage)), - 'description': clean_html(get_element_by_id('contentlist', start_webpage)), - 'thumbnail': video_thumbnail - }) - return videos - - -class FKTVPosteckeIE(InfoExtractor): - IE_NAME = u'fernsehkritik.tv:postecke' - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/inline-video/postecke.php\?(.*&)?ep=(?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" - } - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - episode = int(mobj.group('ep')) + 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) - 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, + 'id': episode, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, }