2 from __future__ import unicode_literals
7 from .common import InfoExtractor
15 def extract_from_xml_url(ie, video_id, xml_url):
16 doc = ie._download_xml(
18 note='Downloading video info',
19 errnote='Failed to download video info')
21 title = doc.find('.//information/title').text
22 description = doc.find('.//information/detail').text
23 duration = int(doc.find('.//details/lengthSec').text)
24 uploader_node = doc.find('.//details/originChannelTitle')
25 uploader = None if uploader_node is None else uploader_node.text
26 uploader_id_node = doc.find('.//details/originChannelId')
27 uploader_id = None if uploader_id_node is None else uploader_id_node.text
28 upload_date = unified_strdate(doc.find('.//details/airtime').text)
30 def xml_to_format(fnode):
31 video_url = fnode.find('url').text
32 is_available = 'http://www.metafilegenerator' not in video_url
34 format_id = fnode.attrib['basetype']
35 format_m = re.match(r'''(?x)
36 (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
37 (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
40 ext = format_m.group('container')
41 proto = format_m.group('proto').lower()
43 quality = fnode.find('./quality').text
44 abr = int(fnode.find('./audioBitrate').text) // 1000
45 vbr_node = fnode.find('./videoBitrate')
46 vbr = None if vbr_node is None else int(vbr_node.text) // 1000
48 width_node = fnode.find('./width')
49 width = None if width_node is None else int_or_none(width_node.text)
50 height_node = fnode.find('./height')
51 height = None if height_node is None else int_or_none(height_node.text)
58 'format_id': format_id + '-' + quality,
61 'acodec': format_m.group('acodec'),
62 'vcodec': format_m.group('vcodec'),
67 'filesize': int_or_none(fnode.find('./filesize').text),
68 'format_note': format_note,
70 '_available': is_available,
73 def xml_to_thumbnails(fnode):
76 thumbnail = {'url': node.text}
77 if 'key' in node.attrib:
78 width_x_height = node.attrib['key']
79 thumbnail['width'] = int_or_none(width_x_height.split('x')[0])
80 thumbnail['height'] = int_or_none(width_x_height.split('x')[1])
81 thumbnails.append(thumbnail)
85 thumbnail_nodes = doc.findall('.//teaserimages/teaserimage')
86 thumbnails = xml_to_thumbnails(thumbnail_nodes)
88 format_nodes = doc.findall('.//formitaeten/formitaet')
89 formats = list(filter(
90 lambda f: f['_available'],
91 map(xml_to_format, format_nodes)))
92 ie._sort_formats(formats)
97 'description': description,
99 'thumbnails': thumbnails,
100 'uploader': uploader,
101 'uploader_id': uploader_id,
102 'upload_date': upload_date,
107 class ZDFIE(InfoExtractor):
108 _VALID_URL = r'(?:zdf:|zdf:video:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/(.*beitrag/(?:video/)?))(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
111 'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt',
115 'title': 'ZDFspezial - Ende des Machtpokers',
116 '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".',
118 'uploader': 'spezial',
119 'uploader_id': '225948',
120 'upload_date': '20131127',
122 'skip': 'Videos on ZDF.de are depublicised in short order',
125 def _real_extract(self, url):
126 video_id = self._match_id(url)
127 xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
128 return extract_from_xml_url(self, video_id, xml_url)
131 class ZDFChannelIE(InfoExtractor):
132 _VALID_URL = r'(?:zdf:topic:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/.*kanaluebersicht/)(?P<id>[0-9]+)'
134 'url': 'http://www.zdf.de/ZDFmediathek#/kanaluebersicht/1586442/sendung/Titanic',
142 def _fetch_page(self, channel_id, page):
143 offset = page * self._PAGE_SIZE
145 'http://www.zdf.de/ZDFmediathek/xmlservice/web/aktuellste?ak=web&offset=%d&maxLength=%d&id=%s'
146 % (offset, self._PAGE_SIZE, channel_id))
147 doc = self._download_xml(
149 note='Downloading channel info',
150 errnote='Failed to download channel info')
152 title = doc.find('.//information/title').text
153 description = doc.find('.//information/detail').text
154 for asset in doc.findall('.//teasers/teaser'):
155 a_type = asset.find('./type').text
156 a_id = asset.find('./details/assetId').text
157 if a_type not in ('video', 'topic'):
161 'playlist_title': title,
162 'playlist_description': description,
163 'url': 'zdf:%s:%s' % (a_type, a_id),
166 def _real_extract(self, url):
167 channel_id = self._match_id(url)
168 entries = OnDemandPagedList(
169 functools.partial(self._fetch_page, channel_id), self._PAGE_SIZE)