X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fzdf.py;h=3b1ac4e9f5246e268e0c0b49d64249196270e9d4;hb=f07a9f6f4347facde15a0cca9560119f0b6f8a94;hp=a8d899883f900a524bb8740559440a9d8bc21aac;hpb=02dbf93f0e98a56ed04b4a9e6a6d62efd6d801f9;p=youtube-dl diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index a8d899883..3b1ac4e9f 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -1,50 +1,55 @@ -import operator +# coding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor from ..utils import ( - parse_xml_doc, + int_or_none, unified_strdate, ) class ZDFIE(InfoExtractor): - _VALID_URL = r'^http://www\.zdf\.de\/ZDFmediathek(?P#)?\/(.*beitrag\/video\/)(?P[^/\?]+)(?:\?.*)?' + _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P#)?/(.*beitrag/(?:video/)?)(?P[0-9]+)(?:/[^/?]+)?(?:\?.*)?' + + _TEST = { + 'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt', + 'info_dict': { + 'id': '2037704', + 'ext': 'webm', + 'title': 'ZDFspezial - Ende des Machtpokers', + 'description': 'Union und SPD haben sich auf einen Koalitionsvertrag geeinigt. Aber was bedeutet das für die Bürger? Sehen Sie hierzu das ZDFspezial "Ende des Machtpokers - Große Koalition für Deutschland".', + 'duration': 1022, + 'uploader': 'spezial', + 'uploader_id': '225948', + 'upload_date': '20131127', + }, + 'skip': 'Videos on ZDF.de are depublicised in short order', + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') - xml_url = u'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id - info_xml = self._download_webpage( - xml_url, video_id, note=u'Downloading video info') - doc = parse_xml_doc(info_xml) + xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id + doc = self._download_xml( + xml_url, video_id, + note='Downloading video info', + errnote='Failed to download video info') title = doc.find('.//information/title').text description = doc.find('.//information/detail').text + duration = int(doc.find('.//details/lengthSec').text) uploader_node = doc.find('.//details/originChannelTitle') uploader = None if uploader_node is None else uploader_node.text - duration_str = doc.find('.//details/length').text - duration_m = re.match(r'''(?x)^ - (?P[0-9]{2}) - :(?P[0-9]{2}) - :(?P[0-9]{2}) - (?:\.(?P[0-9]+)?) - ''', duration_str) - duration = ( - ( - (int(duration_m.group('hours')) * 60 * 60) + - (int(duration_m.group('minutes')) * 60) + - int(duration_m.group('seconds')) - ) - if duration_m - else None - ) + uploader_id_node = doc.find('.//details/originChannelId') + uploader_id = None if uploader_id_node is None else uploader_id_node.text upload_date = unified_strdate(doc.find('.//details/airtime').text) def xml_to_format(fnode): video_url = fnode.find('url').text - is_available = u'http://www.metafilegenerator' not in video_url + is_available = 'http://www.metafilegenerator' not in video_url format_id = fnode.attrib['basetype'] format_m = re.match(r'''(?x) @@ -52,49 +57,53 @@ class ZDFIE(InfoExtractor): (?P[^_]+)_(?P[^_]+)_(?P[^_]+) ''', format_id) - PROTO_ORDER = ['http', 'rtmp', 'rtsp'] - try: - proto_pref = -PROTO_ORDER.index(format_m.group('proto')) - except ValueError: - proto_pref = 999 + ext = format_m.group('container') + proto = format_m.group('proto').lower() quality = fnode.find('./quality').text - QUALITY_ORDER = ['veryhigh', '300', 'high', 'med', 'low'] - try: - quality_pref = -QUALITY_ORDER.index(quality) - except ValueError: - quality_pref = 999 - abr = int(fnode.find('./audioBitrate').text) // 1000 - vbr = int(fnode.find('./videoBitrate').text) // 1000 - pref = (is_available, proto_pref, quality_pref, vbr, abr) + vbr_node = fnode.find('./videoBitrate') + vbr = None if vbr_node is None else int(vbr_node.text) // 1000 + + width_node = fnode.find('./width') + width = None if width_node is None else int_or_none(width_node.text) + height_node = fnode.find('./height') + height = None if height_node is None else int_or_none(height_node.text) + + format_note = '' + if not format_note: + format_note = None return { - 'format_id': format_id, + 'format_id': format_id + '-' + quality, 'url': video_url, - 'ext': format_m.group('container'), + 'ext': ext, 'acodec': format_m.group('acodec'), 'vcodec': format_m.group('vcodec'), 'abr': abr, 'vbr': vbr, - 'width': int(fnode.find('./width').text), - 'height': int(fnode.find('./height').text), - 'quality_name': quality, - 'filesize': int(fnode.find('./filesize').text), - 'format_note': None if is_available else u'(unavailable)', - '_pref': pref, + 'width': width, + 'height': height, + 'filesize': int_or_none(fnode.find('./filesize').text), + 'format_note': format_note, + 'protocol': proto, + '_available': is_available, } format_nodes = doc.findall('.//formitaeten/formitaet') - formats = sorted(map(xml_to_format, format_nodes), - key=operator.itemgetter('_pref')) + formats = list(filter( + lambda f: f['_available'], + map(xml_to_format, format_nodes))) + + self._sort_formats(formats) return { 'id': video_id, 'title': title, - 'formats': formats, 'description': description, - 'uploader': uploader, 'duration': duration, + 'uploader': uploader, + 'uploader_id': uploader_id, 'upload_date': upload_date, - } + 'formats': formats, + } \ No newline at end of file