2 from __future__ import unicode_literals
7 from .common import InfoExtractor
20 class ZDFIE(InfoExtractor):
21 _VALID_URL = r'(?:zdf:|zdf:video:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/(.*beitrag/(?:video/)?))(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
24 'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt',
28 'title': 'ZDFspezial - Ende des Machtpokers',
29 '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".',
31 'uploader': 'spezial',
32 'uploader_id': '225948',
33 'upload_date': '20131127',
35 'skip': 'Videos on ZDF.de are depublicised in short order',
38 def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
40 for param_group in smil.findall(self._xpath_ns('./head/paramGroup', namespace)):
41 group_id = param_group.attrib.get(self._xpath_ns('id', 'http://www.w3.org/XML/1998/namespace'))
43 for param in param_group:
44 params[param.get('name')] = param.get('value')
45 param_groups[group_id] = params
48 for video in smil.findall(self._xpath_ns('.//video', namespace)):
49 src = video.get('src')
52 bitrate = float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
53 group_id = video.get('paramGroup')
54 param_group = param_groups[group_id]
55 for proto in param_group['protocols'].split(','):
57 'url': '%s://%s' % (proto, param_group['host']),
58 'app': param_group['app'],
61 'format_id': '%s-%d' % (proto, bitrate),
64 self._sort_formats(formats)
67 def extract_from_xml_url(self, video_id, xml_url):
68 doc = self._download_xml(
70 note='Downloading video info',
71 errnote='Failed to download video info')
73 status_code = doc.find('./status/statuscode')
74 if status_code is not None and status_code.text != 'ok':
75 code = status_code.text
76 if code == 'notVisibleAnymore':
77 message = 'Video %s is not available' % video_id
79 message = '%s returned error: %s' % (self.IE_NAME, code)
80 raise ExtractorError(message, expected=True)
82 title = doc.find('.//information/title').text
83 description = xpath_text(doc, './/information/detail', 'description')
84 duration = int_or_none(xpath_text(doc, './/details/lengthSec', 'duration'))
85 uploader = xpath_text(doc, './/details/originChannelTitle', 'uploader')
86 uploader_id = xpath_text(doc, './/details/originChannelId', 'uploader id')
87 upload_date = unified_strdate(xpath_text(doc, './/details/airtime', 'upload date'))
89 def xml_to_thumbnails(fnode):
92 thumbnail_url = node.text
98 if 'key' in node.attrib:
99 m = re.match('^([0-9]+)x([0-9]+)$', node.attrib['key'])
101 thumbnail['width'] = int(m.group(1))
102 thumbnail['height'] = int(m.group(2))
103 thumbnails.append(thumbnail)
106 thumbnails = xml_to_thumbnails(doc.findall('.//teaserimages/teaserimage'))
108 format_nodes = doc.findall('.//formitaeten/formitaet')
109 quality = qualities(['veryhigh', 'high', 'med', 'low'])
111 def get_quality(elem):
112 return quality(xpath_text(elem, 'quality'))
113 format_nodes.sort(key=get_quality)
116 for fnode in format_nodes:
117 video_url = fnode.find('url').text
118 is_available = 'http://www.metafilegenerator' not in video_url
121 format_id = fnode.attrib['basetype']
122 quality = xpath_text(fnode, './quality', 'quality')
123 format_m = re.match(r'''(?x)
124 (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
125 (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
128 ext = determine_ext(video_url, None) or format_m.group('container')
129 if ext not in ('smil', 'f4m', 'm3u8'):
130 format_id = format_id + '-' + quality
131 if format_id in format_ids:
137 formats.extend(self._extract_smil_formats(
138 video_url, video_id, fatal=False))
140 formats.extend(self._extract_m3u8_formats(
141 video_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
143 formats.extend(self._extract_f4m_formats(
144 video_url, video_id, f4m_id=format_id, fatal=False))
146 proto = format_m.group('proto').lower()
148 abr = int_or_none(xpath_text(fnode, './audioBitrate', 'abr'), 1000)
149 vbr = int_or_none(xpath_text(fnode, './videoBitrate', 'vbr'), 1000)
151 width = int_or_none(xpath_text(fnode, './width', 'width'))
152 height = int_or_none(xpath_text(fnode, './height', 'height'))
154 filesize = int_or_none(xpath_text(fnode, './filesize', 'filesize'))
161 'format_id': format_id,
164 'acodec': format_m.group('acodec'),
165 'vcodec': format_m.group('vcodec'),
170 'filesize': filesize,
171 'format_note': format_note,
173 '_available': is_available,
175 format_ids.append(format_id)
177 self._sort_formats(formats)
182 'description': description,
183 'duration': duration,
184 'thumbnails': thumbnails,
185 'uploader': uploader,
186 'uploader_id': uploader_id,
187 'upload_date': upload_date,
191 def _real_extract(self, url):
192 video_id = self._match_id(url)
193 xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
194 return self.extract_from_xml_url(video_id, xml_url)
197 class ZDFChannelIE(InfoExtractor):
198 _VALID_URL = r'(?:zdf:topic:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/.*kanaluebersicht/(?:[^/]+/)?)(?P<id>[0-9]+)'
200 'url': 'http://www.zdf.de/ZDFmediathek#/kanaluebersicht/1586442/sendung/Titanic',
206 'url': 'http://www.zdf.de/ZDFmediathek/kanaluebersicht/aktuellste/332',
207 'only_matching': True,
209 'url': 'http://www.zdf.de/ZDFmediathek/kanaluebersicht/meist-gesehen/332',
210 'only_matching': True,
212 'url': 'http://www.zdf.de/ZDFmediathek/kanaluebersicht/_/1798716?bc=nrt;nrm?flash=off',
213 'only_matching': True,
217 def _fetch_page(self, channel_id, page):
218 offset = page * self._PAGE_SIZE
220 'http://www.zdf.de/ZDFmediathek/xmlservice/web/aktuellste?ak=web&offset=%d&maxLength=%d&id=%s'
221 % (offset, self._PAGE_SIZE, channel_id))
222 doc = self._download_xml(
224 note='Downloading channel info',
225 errnote='Failed to download channel info')
227 title = doc.find('.//information/title').text
228 description = doc.find('.//information/detail').text
229 for asset in doc.findall('.//teasers/teaser'):
230 a_type = asset.find('./type').text
231 a_id = asset.find('./details/assetId').text
232 if a_type not in ('video', 'topic'):
236 'playlist_title': title,
237 'playlist_description': description,
238 'url': 'zdf:%s:%s' % (a_type, a_id),
241 def _real_extract(self, url):
242 channel_id = self._match_id(url)
243 entries = OnDemandPagedList(
244 functools.partial(self._fetch_page, channel_id), self._PAGE_SIZE)