[zdf] update for the completely new video portal launched Oct 28
This commit is contained in:
Paul Hartmann
parent
f3517569f6
commit
dbc591b194
@ -6,207 +6,98 @@ import re
|
|||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
int_or_none,
|
|
||||||
unified_strdate,
|
|
||||||
OnDemandPagedList,
|
OnDemandPagedList,
|
||||||
xpath_text,
|
|
||||||
determine_ext,
|
determine_ext,
|
||||||
qualities,
|
|
||||||
float_or_none,
|
|
||||||
ExtractorError,
|
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class ZDFIE(InfoExtractor):
|
class ZDFIE(InfoExtractor):
|
||||||
_VALID_URL = r'(?:zdf:|zdf:video:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/(.*beitrag/(?:video/)?))(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
|
_VALID_URL = r'https?://www\.zdf\.de/.*?/(?P<id>[^/?]*?)\.html'
|
||||||
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt',
|
'url': 'https://www.zdf.de/service-und-hilfe/die-neue-zdf-mediathek/zdfmediathek-trailer-100.html',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '2037704',
|
'id': 'zdfmediathek-trailer-100',
|
||||||
'ext': 'webm',
|
'ext': 'mp4',
|
||||||
'title': 'ZDFspezial - Ende des Machtpokers',
|
'title': 'Trailer ZDFmediathek Supermarkt',
|
||||||
'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 _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
|
|
||||||
param_groups = {}
|
|
||||||
for param_group in smil.findall(self._xpath_ns('./head/paramGroup', namespace)):
|
|
||||||
group_id = param_group.attrib.get(self._xpath_ns('id', 'http://www.w3.org/XML/1998/namespace'))
|
|
||||||
params = {}
|
|
||||||
for param in param_group:
|
|
||||||
params[param.get('name')] = param.get('value')
|
|
||||||
param_groups[group_id] = params
|
|
||||||
|
|
||||||
formats = []
|
|
||||||
for video in smil.findall(self._xpath_ns('.//video', namespace)):
|
|
||||||
src = video.get('src')
|
|
||||||
if not src:
|
|
||||||
continue
|
|
||||||
bitrate = float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
|
|
||||||
group_id = video.get('paramGroup')
|
|
||||||
param_group = param_groups[group_id]
|
|
||||||
for proto in param_group['protocols'].split(','):
|
|
||||||
formats.append({
|
|
||||||
'url': '%s://%s' % (proto, param_group['host']),
|
|
||||||
'app': param_group['app'],
|
|
||||||
'play_path': src,
|
|
||||||
'ext': 'flv',
|
|
||||||
'format_id': '%s-%d' % (proto, bitrate),
|
|
||||||
'tbr': bitrate,
|
|
||||||
})
|
|
||||||
self._sort_formats(formats)
|
|
||||||
return formats
|
|
||||||
|
|
||||||
def extract_from_xml_url(self, video_id, xml_url):
|
|
||||||
doc = self._download_xml(
|
|
||||||
xml_url, video_id,
|
|
||||||
note='Downloading video info',
|
|
||||||
errnote='Failed to download video info')
|
|
||||||
|
|
||||||
status_code = 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)
|
|
||||||
|
|
||||||
title = doc.find('.//information/title').text
|
|
||||||
description = xpath_text(doc, './/information/detail', 'description')
|
|
||||||
duration = int_or_none(xpath_text(doc, './/details/lengthSec', 'duration'))
|
|
||||||
uploader = xpath_text(doc, './/details/originChannelTitle', 'uploader')
|
|
||||||
uploader_id = xpath_text(doc, './/details/originChannelId', 'uploader id')
|
|
||||||
upload_date = unified_strdate(xpath_text(doc, './/details/airtime', 'upload date'))
|
|
||||||
subtitles = {}
|
|
||||||
captions_url = doc.find('.//caption/url')
|
|
||||||
if captions_url is not None:
|
|
||||||
subtitles['de'] = [{
|
|
||||||
'url': captions_url.text,
|
|
||||||
'ext': 'ttml',
|
|
||||||
}]
|
|
||||||
|
|
||||||
def xml_to_thumbnails(fnode):
|
|
||||||
thumbnails = []
|
|
||||||
for node in fnode:
|
|
||||||
thumbnail_url = node.text
|
|
||||||
if not thumbnail_url:
|
|
||||||
continue
|
|
||||||
thumbnail = {
|
|
||||||
'url': thumbnail_url,
|
|
||||||
}
|
}
|
||||||
if 'key' in node.attrib:
|
}]
|
||||||
m = re.match('^([0-9]+)x([0-9]+)$', node.attrib['key'])
|
|
||||||
if m:
|
|
||||||
thumbnail['width'] = int(m.group(1))
|
|
||||||
thumbnail['height'] = int(m.group(2))
|
|
||||||
thumbnails.append(thumbnail)
|
|
||||||
return thumbnails
|
|
||||||
|
|
||||||
thumbnails = xml_to_thumbnails(doc.findall('.//teaserimages/teaserimage'))
|
def _real_extract(self, url):
|
||||||
|
video_id = self._match_id(url)
|
||||||
|
print('video_id: {}'.format(video_id))
|
||||||
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
|
||||||
format_nodes = doc.findall('.//formitaeten/formitaet')
|
jsb = self._search_regex(r"data-zdfplayer-jsb='([^']*)'", webpage, 'zdfplayer jsb data', flags=re.DOTALL)
|
||||||
quality = qualities(['veryhigh', 'high', 'med', 'low'])
|
jsb_json = self._parse_json(jsb, video_id)
|
||||||
|
|
||||||
|
configuration_url = 'https://www.zdf.de' + jsb_json['config']
|
||||||
|
configuration_json = self._download_json(configuration_url, video_id, note='Downloading player configuration')
|
||||||
|
api_token = configuration_json['apiToken']
|
||||||
|
|
||||||
|
player_js = self._download_webpage('https://www.zdf.de/ZDFplayer/latest-v2/skins/zdf/zdf-player.js', video_id, note='Downloading player script')
|
||||||
|
player_id = self._search_regex(r'this\.ptmd_player_id="([^"]*)"', player_js, 'player id')
|
||||||
|
|
||||||
|
content_json = self._download_json(jsb_json['content'], video_id, headers={'Api-Auth': 'Bearer {}'.format(api_token)}, note='Downloading content description')
|
||||||
|
main_video_content = content_json['mainVideoContent']['http://zdf.de/rels/target']
|
||||||
|
meta_data_url_template = main_video_content['http://zdf.de/rels/streams/ptmd-template']
|
||||||
|
meta_data_url = 'https://api.zdf.de' + meta_data_url_template.replace('{playerId}', player_id)
|
||||||
|
|
||||||
|
title = main_video_content['title']
|
||||||
|
|
||||||
|
meta_data = self._download_json(meta_data_url, video_id, note='Downloading meta data')
|
||||||
|
|
||||||
def get_quality(elem):
|
|
||||||
return quality(xpath_text(elem, 'quality'))
|
|
||||||
format_nodes.sort(key=get_quality)
|
|
||||||
format_ids = []
|
|
||||||
formats = []
|
formats = []
|
||||||
for fnode in format_nodes:
|
for p_list_entry in meta_data['priorityList']:
|
||||||
video_url = fnode.find('url').text
|
for formitaet in p_list_entry['formitaeten']:
|
||||||
is_available = 'http://www.metafilegenerator' not in video_url
|
# mime = formitaet.get('mimeType')
|
||||||
if not is_available:
|
facets = formitaet.get('facets') or []
|
||||||
|
add = ''
|
||||||
|
if formitaet.get('isAdaptive'):
|
||||||
|
add += 'a'
|
||||||
|
facets.append('adaptive')
|
||||||
|
if 'restriction_useragent' in facets:
|
||||||
|
add += 'b'
|
||||||
|
if 'progressive' in facets:
|
||||||
|
add += 'p'
|
||||||
|
type_ = formitaet['type']
|
||||||
|
for entry in formitaet['qualities']:
|
||||||
|
tracks = entry['audio']['tracks']
|
||||||
|
if not tracks:
|
||||||
continue
|
continue
|
||||||
format_id = fnode.attrib['basetype']
|
if len(tracks) > 1:
|
||||||
quality = xpath_text(fnode, './quality', 'quality')
|
self._downloader.report_warning('unexpected input: multiple tracks')
|
||||||
format_m = re.match(r'''(?x)
|
track = tracks[0]
|
||||||
(?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
|
video_url = track['uri']
|
||||||
(?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
|
format_id = type_ + '-'
|
||||||
''', format_id)
|
if add:
|
||||||
|
format_id += add + '-'
|
||||||
ext = determine_ext(video_url, None) or format_m.group('container')
|
# named qualities are not very useful for sorting the formats:
|
||||||
if ext not in ('smil', 'f4m', 'm3u8'):
|
# a 'high' m3u8 entry can be better quality than a 'veryhigh' direct mp4 download
|
||||||
format_id = format_id + '-' + quality
|
format_id += entry['quality']
|
||||||
if format_id in format_ids:
|
ext = determine_ext(video_url, None)
|
||||||
continue
|
|
||||||
|
|
||||||
if ext == 'meta':
|
if ext == 'meta':
|
||||||
continue
|
continue
|
||||||
elif ext == 'smil':
|
if ext == 'm3u8':
|
||||||
formats.extend(self._extract_smil_formats(
|
|
||||||
video_url, video_id, fatal=False))
|
|
||||||
elif ext == 'm3u8':
|
|
||||||
# the certificates are misconfigured (see
|
|
||||||
# https://github.com/rg3/youtube-dl/issues/8665)
|
|
||||||
if video_url.startswith('https://'):
|
|
||||||
continue
|
|
||||||
formats.extend(self._extract_m3u8_formats(
|
formats.extend(self._extract_m3u8_formats(
|
||||||
video_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
|
video_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
|
||||||
elif ext == 'f4m':
|
elif ext == 'f4m':
|
||||||
formats.extend(self._extract_f4m_formats(
|
formats.extend(self._extract_f4m_formats(
|
||||||
video_url, video_id, f4m_id=format_id, fatal=False))
|
video_url, video_id, f4m_id=format_id, fatal=False))
|
||||||
else:
|
else:
|
||||||
proto = format_m.group('proto').lower()
|
|
||||||
|
|
||||||
abr = int_or_none(xpath_text(fnode, './audioBitrate', 'abr'), 1000)
|
|
||||||
vbr = int_or_none(xpath_text(fnode, './videoBitrate', 'vbr'), 1000)
|
|
||||||
|
|
||||||
width = int_or_none(xpath_text(fnode, './width', 'width'))
|
|
||||||
height = int_or_none(xpath_text(fnode, './height', 'height'))
|
|
||||||
|
|
||||||
filesize = int_or_none(xpath_text(fnode, './filesize', 'filesize'))
|
|
||||||
|
|
||||||
format_note = ''
|
|
||||||
if not format_note:
|
|
||||||
format_note = None
|
|
||||||
|
|
||||||
formats.append({
|
formats.append({
|
||||||
'format_id': format_id,
|
'format_id': format_id,
|
||||||
'url': video_url,
|
'url': video_url,
|
||||||
'ext': ext,
|
'format_note': ', '.join(facets)
|
||||||
'acodec': format_m.group('acodec'),
|
|
||||||
'vcodec': format_m.group('vcodec'),
|
|
||||||
'abr': abr,
|
|
||||||
'vbr': vbr,
|
|
||||||
'width': width,
|
|
||||||
'height': height,
|
|
||||||
'filesize': filesize,
|
|
||||||
'format_note': format_note,
|
|
||||||
'protocol': proto,
|
|
||||||
'_available': is_available,
|
|
||||||
})
|
})
|
||||||
format_ids.append(format_id)
|
|
||||||
|
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': title,
|
'title': title,
|
||||||
'description': description,
|
'formats': formats
|
||||||
'duration': duration,
|
|
||||||
'thumbnails': thumbnails,
|
|
||||||
'uploader': uploader,
|
|
||||||
'uploader_id': uploader_id,
|
|
||||||
'upload_date': upload_date,
|
|
||||||
'formats': formats,
|
|
||||||
'subtitles': subtitles,
|
|
||||||
}
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
|
||||||
video_id = self._match_id(url)
|
|
||||||
xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
|
|
||||||
return self.extract_from_xml_url(video_id, xml_url)
|
|
||||||
|
|
||||||
|
|
||||||
class ZDFChannelIE(InfoExtractor):
|
class ZDFChannelIE(InfoExtractor):
|
||||||
|
_WORKING = False
|
||||||
_VALID_URL = r'(?:zdf:topic:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/.*kanaluebersicht/(?:[^/]+/)?)(?P<id>[0-9]+)'
|
_VALID_URL = r'(?:zdf:topic:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/.*kanaluebersicht/(?:[^/]+/)?)(?P<id>[0-9]+)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://www.zdf.de/ZDFmediathek#/kanaluebersicht/1586442/sendung/Titanic',
|
'url': 'http://www.zdf.de/ZDFmediathek#/kanaluebersicht/1586442/sendung/Titanic',
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user