import re
from .common import InfoExtractor
-from ..compat import (
- compat_parse_qs,
- compat_urlparse,
-)
from ..utils import (
+ determine_ext,
+ js_to_json,
+ strip_jsonp,
unified_strdate,
ExtractorError,
)
class WDRIE(InfoExtractor):
- _CURRENT_MAUS_URL = r'https?://www.wdrmaus.de/aktuelle-sendung/(wdr|index).php5'
+ _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
_PAGE_REGEX = r'/mediathek/(?P<media_type>[^/]+)/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
- _VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + "|" + _CURRENT_MAUS_URL
-
- _JS_URL_REGEX = r'(https?://deviceids-medp.wdr.de/ondemand/\d+/\d+\.js)'
+ _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/live/index.html',
'info_dict': {
'id': 'mdb-103364',
- 'ext': 'flv',
+ 'ext': 'mp4',
'display_id': 'index',
'title': r're:^WDR Fernsehen im Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'alt_title': 'WDR Fernsehen Live',
'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
'is_live': True,
'subtitles': {}
- }
+ },
+ 'params': {
+ 'skip_download': True, # m3u8 download
+ },
},
{
'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': 'ca365705551e4bd5217490f3b0591290',
+ 'info_dict': {
+ 'id': 'mdb-186083',
+ 'ext': 'flv',
+ 'upload_date': '20130919',
+ 'title': 'Sachgeschichte - Achterbahn ',
+ 'description': '- Die Sendung mit der Maus -',
+ },
+ 'params': {
+ 'skip_download': True, # the file has different versions :(
+ },
+ },
]
def _real_extract(self, url):
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
- js_url = self._search_regex(self._JS_URL_REGEX, webpage, 'js_url', default=None)
+ # 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)
- if not js_url:
+ if not json_metadata:
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)
- js_data = self._download_webpage(js_url, 'metadata')
- json_data = self._search_regex(r'\(({.*})\)', js_data, 'json')
- metadata = self._parse_json(json_data, display_id)
+ 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"]
+ 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")
+ metadata_media_alt = metadata_media_resource.get('alt')
if metadata_media_alt:
- for tag_name in ["videoURL", 'audioURL']:
+ for tag_name in ['videoURL', 'audioURL']:
if tag_name in metadata_media_alt:
- formats.append({
- 'url': metadata_media_alt[tag_name]
- })
+ 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 '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))
formats.extend(self._extract_smil_formats(video_url, 'stream', fatal=False))
subtitles = {}
- caption_url = metadata_media_resource.get("captionURL")
+ caption_url = metadata_media_resource.get('captionURL')
if caption_url:
subtitles['de'] = [{
'url': caption_url
}]
- title = metadata_tracker_data.get("trackerClipTitle")
+ title = metadata_tracker_data.get('trackerClipTitle')
is_live = url_type == 'live'
if is_live:
self._sort_formats(formats)
return {
- 'id': metadata_tracker_data.get("trackerClipId", display_id),
+ 'id': metadata_tracker_data.get('trackerClipId', display_id),
'display_id': display_id,
'title': title,
- 'alt_title': metadata_tracker_data.get("trackerClipSubcategory"),
+ 'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
'formats': formats,
'upload_date': upload_date,
- 'description': self._html_search_meta("Description", webpage),
+ 'description': self._html_search_meta('Description', webpage),
'is_live': is_live,
'subtitles': subtitles,
}
'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