-# -*- coding: utf-8 -*-
+# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..compat import (
- compat_parse_qs,
- compat_urlparse,
-)
from ..utils import (
determine_ext,
+ ExtractorError,
js_to_json,
strip_jsonp,
unified_strdate,
- ExtractorError,
+ update_url_query,
+ urlhandle_detect_ext,
)
-class WDRIE(InfoExtractor):
- _CURRENT_MAUS_URL = r'https?://www.wdrmaus.de/aktuelle-sendung/(wdr|index).php5'
- _PAGE_REGEX = r'/mediathek/(?P<media_type>[^/]+)/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
+class WDRBaseIE(InfoExtractor):
+ def _extract_wdr_video(self, webpage, display_id):
+ # for wdr.de the data-extension is in a tag with the class "mediaLink"
+ # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
+ # for wdrmaus its in a link to the page in a multiline "videoLink"-tag
+ json_metadata = self._html_search_regex(
+ r'class=(?:"(?:mediaLink|wdrrPlayerPlayBtn)\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
+ webpage, 'media link', default=None, flags=re.MULTILINE)
+
+ if not json_metadata:
+ return
+
+ media_link_obj = self._parse_json(json_metadata, display_id,
+ transform_source=js_to_json)
+ jsonp_url = media_link_obj['mediaObj']['url']
+
+ metadata = self._download_json(
+ jsonp_url, 'metadata', transform_source=strip_jsonp)
+
+ metadata_tracker_data = metadata['trackerData']
+ metadata_media_resource = metadata['mediaResource']
+
+ formats = []
+
+ # check if the metadata contains a direct URL to a file
+ for kind, media_resource in metadata_media_resource.items():
+ if kind not in ('dflt', 'alt'):
+ continue
+
+ for tag_name, medium_url in media_resource.items():
+ if tag_name not in ('videoURL', 'audioURL'):
+ continue
+
+ ext = determine_ext(medium_url)
+ if ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ medium_url, display_id, 'mp4', 'm3u8_native',
+ m3u8_id='hls'))
+ elif ext == 'f4m':
+ manifest_url = update_url_query(
+ medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
+ formats.extend(self._extract_f4m_formats(
+ manifest_url, display_id, f4m_id='hds', fatal=False))
+ elif ext == 'smil':
+ formats.extend(self._extract_smil_formats(
+ medium_url, 'stream', fatal=False))
+ else:
+ a_format = {
+ 'url': medium_url
+ }
+ if ext == 'unknown_video':
+ urlh = self._request_webpage(
+ medium_url, display_id, note='Determining extension')
+ ext = urlhandle_detect_ext(urlh)
+ a_format['ext'] = ext
+ formats.append(a_format)
+
+ self._sort_formats(formats)
+
+ subtitles = {}
+ caption_url = metadata_media_resource.get('captionURL')
+ if caption_url:
+ subtitles['de'] = [{
+ 'url': caption_url,
+ 'ext': 'ttml',
+ }]
+
+ title = metadata_tracker_data['trackerClipTitle']
+
+ return {
+ 'id': metadata_tracker_data.get('trackerClipId', display_id),
+ 'display_id': display_id,
+ 'title': title,
+ 'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
+ 'formats': formats,
+ 'subtitles': subtitles,
+ 'upload_date': unified_strdate(metadata_tracker_data.get('trackerClipAirTime')),
+ }
+
+
+class WDRIE(WDRBaseIE):
+ _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
+ _PAGE_REGEX = r'/(?:mediathek/)?[^/]+/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
_VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
_TESTS = [
{
'url': 'http://www1.wdr.de/mediathek/video/sendungen/doku-am-freitag/video-geheimnis-aachener-dom-100.html',
- 'md5': 'e58c39c3e30077141d258bf588700a7b',
+ # HDS download, MD5 is unstable
'info_dict': {
'id': 'mdb-1058683',
'ext': 'flv',
'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318',
'is_live': False,
'subtitles': {'de': [{
- 'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml'
+ 'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml',
+ 'ext': 'ttml',
}]},
},
- 'skip': 'Page Not Found',
},
{
'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html',
'is_live': False,
'subtitles': {}
},
- 'skip': 'Page Not Found',
},
{
'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
},
{
'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
- 'playlist_mincount': 10,
+ 'playlist_mincount': 8,
'info_dict': {
'id': 'aktuelle-stunde/aktuelle-stunde-120',
},
},
'skip': 'The id changes from week to week because of the new episode'
},
+ {
+ 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5',
+ 'md5': '803138901f6368ee497b4d195bb164f2',
+ 'info_dict': {
+ 'id': 'mdb-186083',
+ 'ext': 'mp4',
+ 'upload_date': '20130919',
+ 'title': 'Sachgeschichte - Achterbahn ',
+ 'description': '- Die Sendung mit der Maus -',
+ },
+ },
+ {
+ 'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html',
+ # Live stream, MD5 unstable
+ 'info_dict': {
+ 'id': 'mdb-869971',
+ 'ext': 'flv',
+ 'title': 'Funkhaus Europa Livestream',
+ 'description': 'md5:2309992a6716c347891c045be50992e4',
+ 'upload_date': '20160101',
+ },
+ }
]
def _real_extract(self, url):
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
- # for wdr.de the data-extension is in a tag with the class "mediaLink"
- # for wdrmaus its in a link to the page in a multiline "videoLink"-tag
- json_metadata = self._html_search_regex(
- r'class=(?:"mediaLink\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
- webpage, 'media link', default=None, flags=re.MULTILINE)
+ info_dict = self._extract_wdr_video(webpage, display_id)
- if not json_metadata:
+ if not info_dict:
entries = [
self.url_result(page_url + href[0], 'WDR')
for href in re.findall(
- r'<a href="(%s)"' % self._PAGE_REGEX,
+ r'<a href="(%s)"[^>]+data-extension=' % self._PAGE_REGEX,
webpage)
]
raise ExtractorError('No downloadable streams found', expected=True)
- media_link_obj = self._parse_json(json_metadata, display_id,
- transform_source=js_to_json)
- jsonp_url = media_link_obj['mediaObj']['url']
-
- metadata = self._download_json(
- jsonp_url, 'metadata', transform_source=strip_jsonp)
-
- metadata_tracker_data = metadata['trackerData']
- metadata_media_resource = metadata['mediaResource']
-
- formats = []
-
- # check if the metadata contains a direct URL to a file
- metadata_media_alt = metadata_media_resource.get('alt')
- if metadata_media_alt:
- for tag_name in ['videoURL', 'audioURL']:
- if tag_name in metadata_media_alt:
- alt_url = metadata_media_alt[tag_name]
- if determine_ext(alt_url) == 'm3u8':
- m3u_fmt = self._extract_m3u8_formats(
- alt_url, display_id, 'mp4', 'm3u8_native',
- m3u8_id='hls')
- formats.extend(m3u_fmt)
- else:
- formats.append({
- 'url': alt_url
- })
-
- # check if there are flash-streams for this video
- if 'dflt' in metadata_media_resource and 'videoURL' in metadata_media_resource['dflt']:
- video_url = metadata_media_resource['dflt']['videoURL']
- if video_url.endswith('.f4m'):
- full_video_url = video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
- formats.extend(self._extract_f4m_formats(full_video_url, display_id, f4m_id='hds', fatal=False))
- elif video_url.endswith('.smil'):
- formats.extend(self._extract_smil_formats(video_url, 'stream', fatal=False))
-
- subtitles = {}
- caption_url = metadata_media_resource.get('captionURL')
- if caption_url:
- subtitles['de'] = [{
- 'url': caption_url
- }]
-
- title = metadata_tracker_data.get('trackerClipTitle')
is_live = url_type == 'live'
if is_live:
- title = self._live_title(title)
- upload_date = None
- elif 'trackerClipAirTime' in metadata_tracker_data:
- upload_date = metadata_tracker_data['trackerClipAirTime']
- else:
- upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
-
- if upload_date:
- upload_date = unified_strdate(upload_date)
-
- self._sort_formats(formats)
+ info_dict.update({
+ 'title': self._live_title(info_dict['title']),
+ 'upload_date': None,
+ })
+ elif 'upload_date' not in info_dict:
+ info_dict['upload_date'] = unified_strdate(self._html_search_meta('DC.Date', webpage, 'upload date'))
- return {
- 'id': metadata_tracker_data.get('trackerClipId', display_id),
- 'display_id': display_id,
- 'title': title,
- 'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
- 'formats': formats,
- 'upload_date': upload_date,
+ info_dict.update({
'description': self._html_search_meta('Description', webpage),
'is_live': is_live,
- 'subtitles': subtitles,
- }
+ })
+
+ return info_dict
class WDRMobileIE(InfoExtractor):
'User-Agent': 'mobile',
},
}
-
-
-class WDRMausIE(InfoExtractor):
- _VALID_URL = 'https?://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)((?<!index)\.php5|/(?:$|[?#]))'
- IE_DESC = 'Sendung mit der Maus'
- _TESTS = [{
- 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5',
- 'md5': '178b432d002162a14ccb3e0876741095',
- 'info_dict': {
- 'id': 'achterbahn',
- 'ext': 'mp4',
- 'thumbnail': 're:^http://.+\.jpg',
- 'upload_date': '20131001',
- 'title': '19.09.2013 - Achterbahn',
- }
- }]
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
-
- webpage = self._download_webpage(url, video_id)
- param_code = self._html_search_regex(
- r'<a href="\?startVideo=1&([^"]+)"', webpage, 'parameters')
-
- title_date = self._search_regex(
- r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
- webpage, 'air date')
- title_str = self._html_search_regex(
- r'<h1>(.*?)</h1>', webpage, 'title')
- title = '%s - %s' % (title_date, title_str)
- upload_date = unified_strdate(
- self._html_search_meta('dc.date', webpage))
-
- fields = compat_parse_qs(param_code)
- video_url = fields['firstVideo'][0]
- thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
-
- formats = [{
- 'format_id': 'rtmp',
- 'url': video_url,
- }]
-
- jscode = self._download_webpage(
- 'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
- video_id, fatal=False,
- note='Downloading URL translation table',
- errnote='Could not download URL translation table')
- if jscode:
- for m in re.finditer(
- r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
- jscode):
- if video_url.startswith(m.group('stream')):
- http_url = video_url.replace(
- m.group('stream'), m.group('dl'))
- formats.append({
- 'format_id': 'http',
- 'url': http_url,
- })
- break
-
- self._sort_formats(formats)
-
- return {
- 'id': video_id,
- 'title': title,
- 'formats': formats,
- 'thumbnail': thumbnail,
- 'upload_date': upload_date,
- }
projects / youtube-dl / blobdiff