X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdreisat.py;h=8ac8587be6af564af3674c8ff7e7754364bc311e;hb=c3124c3085e6a9a83ee31ace3a7d528a324c42da;hp=cb7226f82a6af167569286918a56cce64e796150;hpb=304cbe981e9f3b62288abc54bd84b0eaef286795;p=youtube-dl diff --git a/youtube_dl/extractor/dreisat.py b/youtube_dl/extractor/dreisat.py index cb7226f82..8ac8587be 100644 --- a/youtube_dl/extractor/dreisat.py +++ b/youtube_dl/extractor/dreisat.py @@ -1,40 +1,55 @@ -# coding: utf-8 +from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( - determine_ext, + ExtractorError, unified_strdate, ) class DreiSatIE(InfoExtractor): IE_NAME = '3sat' - _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/index\.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P[0-9]+)$' - _TEST = { - u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983", - u'file': u'36983.webm', - u'md5': u'57c97d0469d71cf874f6815aa2b7c944', - u'info_dict': { - u"title": u"Kaffeeland Schweiz", - u"description": u"Über 80 Kaffeeröstereien liefern in der Schweiz das Getränk, in das das Land so vernarrt ist: Mehr als 1000 Tassen trinkt ein Schweizer pro Jahr. SCHWEIZWEIT nimmt die Kaffeekultur unter die...", - u"uploader": u"3sat", - u"upload_date": u"20130622" - } - } - + _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php|mediathek\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P[0-9]+)$' + _TESTS = [ + { + 'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918', + 'md5': 'be37228896d30a88f315b638900a026e', + 'info_dict': { + 'id': '45918', + 'ext': 'mp4', + 'title': 'Waidmannsheil', + 'description': 'md5:cce00ca1d70e21425e72c86a98a56817', + 'uploader': '3sat', + 'upload_date': '20140913' + } + }, + { + 'url': 'http://www.3sat.de/mediathek/mediathek.php?mode=play&obj=51066', + 'only_matching': True, + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id - details_doc = self._download_xml(details_url, video_id, note=u'Downloading video details') + details_doc = self._download_xml(details_url, video_id, 'Downloading video details') + + status_code = details_doc.find('./status/statuscode') + if status_code is not None and status_code.text != 'ok': + code = status_code.text + if code == 'notVisibleAnymore': + message = 'Video %s is not available' % video_id + else: + message = '%s returned error: %s' % (self.IE_NAME, code) + raise ExtractorError(message, expected=True) thumbnail_els = details_doc.findall('.//teaserimage') thumbnails = [{ - 'width': te.attrib['key'].partition('x')[0], - 'height': te.attrib['key'].partition('x')[2], + 'width': int(te.attrib['key'].partition('x')[0]), + 'height': int(te.attrib['key'].partition('x')[2]), 'url': te.text, } for te in thumbnail_els] @@ -52,18 +67,12 @@ class DreiSatIE(InfoExtractor): 'width': int(fe.find('./width').text), 'height': int(fe.find('./height').text), 'url': fe.find('./url').text, - 'ext': determine_ext(fe.find('./url').text), 'filesize': int(fe.find('./filesize').text), 'video_bitrate': int(fe.find('./videoBitrate').text), - '3sat_qualityname': fe.find('./quality').text, } for fe in format_els if not fe.find('./url').text.startswith('http://www.metafilegenerator.de/')] - def _sortkey(format): - qidx = ['low', 'med', 'high', 'veryhigh'].index(format['3sat_qualityname']) - prefer_http = 1 if 'rtmp' in format['url'] else 0 - return (qidx, prefer_http, format['video_bitrate']) - formats.sort(key=_sortkey) + self._sort_formats(formats) return { '_type': 'video',