X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Frtl2.py;h=721ee733ce38c7e4a95c7806b10bbbd346166451;hb=96d315c2be1c00339b4cb77e80b3d5f63770a735;hp=2bdbf2ec221db7372f7ba0f4788a22cfb81fb7f6;hpb=8011fba3ae4301995f77c64ac63a4a467ef73b7e;p=youtube-dl diff --git a/youtube_dl/extractor/rtl2.py b/youtube_dl/extractor/rtl2.py index 2bdbf2ec2..721ee733c 100644 --- a/youtube_dl/extractor/rtl2.py +++ b/youtube_dl/extractor/rtl2.py @@ -1,98 +1,100 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re -import json from .common import InfoExtractor -from ..utils import ( - ExtractorError, - clean_html, - unified_strdate, - int_or_none, -) +from ..utils import int_or_none class RTL2IE(InfoExtractor): - """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW""" - _VALID_URL = r'http?://(?P(?P(www\.)?rtl2\.de)/.*/(?P.*))' - _TEST = { + _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P[^?#/]*?)(?:$|/(?:$|[?#]))' + _TESTS = [{ 'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0', - 'md5': 'dsadasdada', 'info_dict': { 'id': 'folge-203-0', 'ext': 'f4v', - 'title': 'GRIP sucht den Sommerk\xf6nig', - 'description' : 'Matthias, Det und Helge treten gegeneinander an.' - # TODO more properties, either as: - # * A value - # * MD5 checksum; start the string with md5: - # * A regular expression; start the string with re: - # * Any Python type (for example int or float) + 'title': 'GRIP sucht den Sommerkönig', + 'description': 'md5:e3adbb940fd3c6e76fa341b8748b562f' }, - #'params': { - # rtmp download - # 'skip_download': True, - #}, - } + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + 'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/', + 'info_dict': { + 'id': '21040-anna-erwischt-alex', + 'ext': 'mp4', + 'title': 'Anna erwischt Alex!', + 'description': 'Anna nimmt ihrem Vater nicht ab, dass er nicht spielt. Und tatsächlich erwischt sie ihn auf frischer Tat.' + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_page_url = 'http://%s/' % mobj.group('domain') - video_id = mobj.group('video_id') - - webpage = self._download_webpage('http://' + mobj.group('url'), video_id) - - vico_id = self._html_search_regex(r'vico_id: ([0-9]+)', webpage, '%s'); - vivi_id = self._html_search_regex(r'vivi_id: ([0-9]+)', webpage, '%s'); - - info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id - webpage = self._download_webpage(info_url, '') - - video_info = json.loads(webpage.decode("latin1")) - print video_info - - - #self._download_webpage('http://cp108781.edgefcs.net/crossdomain.xml', '') - - download_url = video_info["video"]["streamurl"] # self._html_search_regex(r'streamurl\":\"(.*?)\"', webpage, '%s'); - title = video_info["video"]["titel"] # self._html_search_regex(r'titel\":\"(.*?)\"', webpage, '%s'); - description = video_info["video"]["beschreibung"] # self._html_search_regex(r'beschreibung\":\"(.*?)\"', webpage, '%s'); - #ext = self._html_search_regex(r'streamurl\":\".*?(\..{2,4})\"', webpage, '%s'); - - thumbnail = video_info["video"]["image"] - - download_url = download_url.replace("\\", "") - - stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, '%s'); - - #upload_date = self._html_search_regex(r'property=\"dc:date\".*?datatype=\"xsd:dateTime\".*?content=\"(.*?)\"', webpage, 'title') - #download_url += " -y " + stream_url - - #print stream_url - #print download_url - #print description - #print title - #print ext - - formats = [] - - fmt = { - 'url' : download_url, - #'app': 'ondemand?_fcs_vhost=cp108781.edgefcs.net', - 'play_path': stream_url, - #'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf', - #'page_url': 'http://www.cbsnews.com', - #'ext': ext, - } - - formats.append(fmt) - + # Some rtl2 urls have no slash at the end, so append it. + if not url.endswith('/'): + url += '/' + + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + mobj = re.search( + r']+data-collection="(?P\d+)"[^>]+data-video="(?P\d+)"', + webpage) + if mobj: + vico_id = mobj.group('vico_id') + vivi_id = mobj.group('vivi_id') + else: + vico_id = self._html_search_regex( + r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id') + vivi_id = self._html_search_regex( + r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id') + + info = self._download_json( + 'http://www.rtl2.de/sites/default/modules/rtl2/mediathek/php/get_video_jw.php', + video_id, query={ + 'vico_id': vico_id, + 'vivi_id': vivi_id, + }) + video_info = info['video'] + title = video_info['titel'] + + formats = [] + + rtmp_url = video_info.get('streamurl') + if rtmp_url: + rtmp_url = rtmp_url.replace('\\', '') + stream_url = 'mp4:' + self._html_search_regex(r'/ondemand/(.+)', rtmp_url, 'stream URL') + rtmp_conn = ['S:connect', 'O:1', 'NS:pageUrl:' + url, 'NB:fpad:0', 'NN:videoFunction:1', 'O:0'] + + formats.append({ + 'format_id': 'rtmp', + 'url': rtmp_url, + 'play_path': stream_url, + 'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf', + 'page_url': url, + 'flash_version': 'LNX 11,2,202,429', + 'rtmp_conn': rtmp_conn, + 'no_resume': True, + 'preference': 1, + }) + + m3u8_url = video_info.get('streamurl_hls') + if m3u8_url: + formats.extend(self._extract_akamai_formats(m3u8_url, video_id)) + + self._sort_formats(formats) return { - 'id': video_id, + 'id': video_id, 'title': title, - 'thumbnail' : thumbnail, - 'description' : description, + 'thumbnail': video_info.get('image'), + 'description': video_info.get('beschreibung'), + 'duration': int_or_none(video_info.get('duration')), 'formats': formats, }