X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fspiegeltv.py;h=e1cfb869834cf0d50b04a11c5fc137d7c9afcad8;hb=ec85ded83cbfa652ba94cb080aab52d8b270212a;hp=06838f78d91d607ce0ee48327e9450a3ea26eca3;hpb=89c15fe0b3044d39caf1c97df523acc33107f399;p=youtube-dl diff --git a/youtube_dl/extractor/spiegeltv.py b/youtube_dl/extractor/spiegeltv.py index 06838f78d..e1cfb8698 100644 --- a/youtube_dl/extractor/spiegeltv.py +++ b/youtube_dl/extractor/spiegeltv.py @@ -2,11 +2,15 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import float_or_none +from ..compat import compat_urllib_parse_urlparse +from ..utils import ( + determine_ext, + float_or_none, +) class SpiegeltvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P[\-a-z0-9]+)' + _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/(?:#/)?filme/(?P[\-a-z0-9]+)' _TESTS = [{ 'url': 'http://www.spiegel.tv/filme/flug-mh370/', 'info_dict': { @@ -14,15 +18,20 @@ class SpiegeltvIE(InfoExtractor): 'ext': 'm4v', 'title': 'Flug MH370', 'description': 'Das Rätsel um die Boeing 777 der Malaysia-Airlines', - 'thumbnail': 're:http://.*\.jpg$', + 'thumbnail': r're:http://.*\.jpg$', }, 'params': { - # rtmp download + # m3u8 download 'skip_download': True, } + }, { + 'url': 'http://www.spiegel.tv/#/filme/alleskino-die-wahrheit-ueber-maenner/', + 'only_matching': True, }] def _real_extract(self, url): + if '/#/' in url: + url = url.replace('/#/', '/') video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._html_search_regex(r'(.*?)', webpage, 'title') @@ -46,9 +55,43 @@ class SpiegeltvIE(InfoExtractor): is_wide = media_json['is_wide'] server_json = self._download_json( - 'http://www.spiegel.tv/streaming_servers/', video_id, - note='Downloading server information') - server = server_json[0]['endpoint'] + 'http://spiegeltv-prod-static.s3.amazonaws.com/projectConfigs/projectConfig.json', + video_id, note='Downloading server information') + + format = '16x9' if is_wide else '4x3' + + formats = [] + for streamingserver in server_json['streamingserver']: + endpoint = streamingserver.get('endpoint') + if not endpoint: + continue + play_path = 'mp4:%s_spiegeltv_0500_%s.m4v' % (uuid, format) + if endpoint.startswith('rtmp'): + formats.append({ + 'url': endpoint, + 'format_id': 'rtmp', + 'app': compat_urllib_parse_urlparse(endpoint).path[1:], + 'play_path': play_path, + 'player_path': 'http://prod-static.spiegel.tv/frontend-076.swf', + 'ext': 'flv', + 'rtmp_live': True, + }) + elif determine_ext(endpoint) == 'm3u8': + formats.append({ + 'url': endpoint.replace('[video]', play_path), + 'ext': 'm4v', + 'format_id': 'hls', # Prefer hls since it allows to workaround georestriction + 'protocol': 'm3u8', + 'preference': 1, + 'http_headers': { + 'Accept-Encoding': 'deflate', # gzip causes trouble on the server side + }, + }) + else: + formats.append({ + 'url': endpoint, + }) + self._check_formats(formats, video_id) thumbnails = [] for image in media_json['images']: @@ -60,16 +103,12 @@ class SpiegeltvIE(InfoExtractor): description = media_json['subtitle'] duration = float_or_none(media_json.get('duration_in_ms'), scale=1000) - format = '16x9' if is_wide else '4x3' - - url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v' return { 'id': video_id, 'title': title, - 'url': url, - 'ext': 'm4v', 'description': description, 'duration': duration, - 'thumbnails': thumbnails - } \ No newline at end of file + 'thumbnails': thumbnails, + 'formats': formats, + }