X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fclipfish.py;h=bb52e0c6ff75178626f83cd0a6d2de6607e861ad;hb=8b1aeadc33cdb1eef8079e67d522d8a39676bb53;hp=09dfaac6022782c248df0ce80d7ddcfc49bc8288;hpb=be612d9e0c485915f12b8165fc1a0187f29afda8;p=youtube-dl diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py index 09dfaac60..bb52e0c6f 100644 --- a/youtube_dl/extractor/clipfish.py +++ b/youtube_dl/extractor/clipfish.py @@ -1,54 +1,67 @@ +# coding: utf-8 from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - ExtractorError, int_or_none, - js_to_json, - determine_ext, + unified_strdate, ) class ClipfishIE(InfoExtractor): - IE_NAME = 'clipfish' - - _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P[0-9]+)/' + _VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P[0-9]+)' _TEST = { - 'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/', - 'md5': '79bc922f3e8a9097b3d68a93780fd475', + 'url': 'http://www.clipfish.de/special/ugly-americans/video/4343170/s01-e01-ugly-americans-date-in-der-hoelle/', + 'md5': '720563e467b86374c194bdead08d207d', 'info_dict': { - 'id': '3966754', + 'id': '4343170', 'ext': 'mp4', - 'title': 'FIFA 14 - E3 2013 Trailer', - 'duration': 82, + 'title': 'S01 E01 - Ugly Americans - Date in der Hölle', + 'description': 'Mark Lilly arbeitet im Sozialdienst der Stadt New York und soll Immigranten bei ihrer Einbürgerung in die USA zur Seite stehen.', + 'upload_date': '20161005', + 'duration': 1291, + 'view_count': int, } } def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - video_info = self._parse_json( - js_to_json(self._html_search_regex('var videoObject = ({[^}]+?})', webpage, 'videoObject')), - video_id - ) - info_url = self._parse_json( - js_to_json(self._html_search_regex('var globalFlashvars = ({[^}]+?})', webpage, 'globalFlashvars')), - video_id - )['data'] - - doc = self._download_xml( - info_url, video_id, note='Downloading info page') - title = doc.find('title').text - video_url = doc.find('filename').text - thumbnail = doc.find('imageurl').text - duration = int_or_none(video_info['length']) - formats = [{'url': video_info['videourl']},{'url': video_url}] - self._sort_formats(formats) + + video_info = self._download_json( + 'http://www.clipfish.de/devapi/id/%s?format=json&apikey=hbbtv' % video_id, + video_id)['items'][0] + + formats = [] + + m3u8_url = video_info.get('media_videourl_hls') + if m3u8_url: + formats.append({ + 'url': m3u8_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'), + 'ext': 'mp4', + 'format_id': 'hls', + }) + + mp4_url = video_info.get('media_videourl') + if mp4_url: + formats.append({ + 'url': mp4_url, + 'format_id': 'mp4', + 'width': int_or_none(video_info.get('width')), + 'height': int_or_none(video_info.get('height')), + 'tbr': int_or_none(video_info.get('bitrate')), + }) + + descr = video_info.get('descr') + if descr: + descr = descr.strip() return { 'id': video_id, - 'title': title, + 'title': video_info['title'], + 'description': descr, 'formats': formats, - 'thumbnail': thumbnail, - 'duration': duration, + 'thumbnail': video_info.get('media_content_thumbnail_large') or video_info.get('media_thumbnail'), + 'duration': int_or_none(video_info.get('media_length')), + 'upload_date': unified_strdate(video_info.get('pubDate')), + 'view_count': int_or_none(video_info.get('media_views')) }