diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index ed4e39574..d107080f5 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -967,7 +967,6 @@ from .watchindianporn import WatchIndianPornIE from .wdr import ( WDRIE, WDRMobileIE, - WDRMausIE, ) from .webofstories import ( WebOfStoriesIE, diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index 31c904303..1e729cb7c 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -1,214 +1,205 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import itertools 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, - qualities, + ExtractorError, ) class WDRIE(InfoExtractor): - _PLAYER_REGEX = '-(?:video|audio)player(?:_size-[LMS])?' - _VALID_URL = r'(?Phttps?://www\d?\.(?:wdr\d?|funkhauseuropa)\.de/)(?P.+?)(?P%s)?\.html' % _PLAYER_REGEX + _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5' + _PAGE_REGEX = r'/mediathek/(?P[^/]+)/(?P[^/]+)/(?P.+)\.html' + _VALID_URL = r'(?Phttps?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL _TESTS = [ { - 'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html', + 'url': 'http://www1.wdr.de/mediathek/video/sendungen/doku-am-freitag/video-geheimnis-aachener-dom-100.html', + 'md5': 'e58c39c3e30077141d258bf588700a7b', 'info_dict': { - 'id': 'mdb-362427', + 'id': 'mdb-1058683', 'ext': 'flv', - 'title': 'Servicezeit', - 'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb', - 'upload_date': '20140310', - 'is_live': False - }, - 'params': { - 'skip_download': True, + 'display_id': 'doku-am-freitag/video-geheimnis-aachener-dom-100', + 'title': 'Geheimnis Aachener Dom', + 'alt_title': 'Doku am Freitag', + 'upload_date': '20160304', + 'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318', + 'is_live': False, + 'subtitles': {'de': [{ + 'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml' + }]}, }, 'skip': 'Page Not Found', }, { - 'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html', + 'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html', + 'md5': 'f4c1f96d01cf285240f53ea4309663d8', 'info_dict': { - 'id': 'mdb-363194', - 'ext': 'flv', - 'title': 'Marga Spiegel ist tot', - 'description': 'md5:2309992a6716c347891c045be50992e4', - 'upload_date': '20140311', - 'is_live': False - }, - 'params': { - 'skip_download': True, + 'id': 'mdb-1072000', + 'ext': 'mp3', + 'display_id': 'wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100', + 'title': 'Schriftstellerin Juli Zeh', + 'alt_title': 'WDR 3 Gespräch am Samstag', + 'upload_date': '20160312', + 'description': 'md5:e127d320bc2b1f149be697ce044a3dd7', + 'is_live': False, + 'subtitles': {} }, 'skip': 'Page Not Found', }, { - 'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html', - 'md5': '83e9e8fefad36f357278759870805898', + 'url': 'http://www1.wdr.de/mediathek/video/live/index.html', 'info_dict': { - 'id': 'mdb-194332', - 'ext': 'mp3', - 'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)', - 'description': 'md5:2309992a6716c347891c045be50992e4', - 'upload_date': '20091129', - 'is_live': False + 'id': 'mdb-103364', + '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}$', + 'alt_title': 'WDR Fernsehen Live', + 'upload_date': None, + 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9', + 'is_live': True, + 'subtitles': {} + }, + 'params': { + 'skip_download': True, # m3u8 download }, }, { - 'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html', - 'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa', + 'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html', + 'playlist_mincount': 8, 'info_dict': { - 'id': 'mdb-478135', - 'ext': 'mp3', - 'title': 'Flavia Coelho: Amar é Amar', - 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a', - 'upload_date': '20140717', - 'is_live': False + 'id': 'aktuelle-stunde/aktuelle-stunde-120', }, - 'skip': 'Page Not Found', }, { - 'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html', - 'playlist_mincount': 146, + 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5', 'info_dict': { - 'id': 'mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100', - } + 'id': 'mdb-1096487', + 'ext': 'flv', + 'upload_date': 're:^[0-9]{8}$', + 'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$', + 'description': '- Die Sendung mit der Maus -', + }, + 'skip': 'The id changes from week to week because of the new episode' }, { - 'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html', + 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5', + 'md5': 'ca365705551e4bd5217490f3b0591290', 'info_dict': { - 'id': 'mdb-103364', - 'title': 're:^WDR Fernsehen Live [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9', + 'id': 'mdb-186083', 'ext': 'flv', - 'upload_date': '20150101', - 'is_live': True + 'upload_date': '20130919', + 'title': 'Sachgeschichte - Achterbahn ', + 'description': '- Die Sendung mit der Maus -', }, 'params': { - 'skip_download': True, + 'skip_download': True, # the file has different versions :( }, - } + }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - page_url = mobj.group('url') - page_id = mobj.group('id') - - webpage = self._download_webpage(url, page_id) - - if mobj.group('player') is None: + url_type = mobj.group('type') + page_url = mobj.group('page_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) + + if not json_metadata: entries = [ - self.url_result(page_url + href, 'WDR') + self.url_result(page_url + href[0], 'WDR') for href in re.findall( - r']+data-extension=' % self._PAGE_REGEX, webpage) ] if entries: # Playlist page - return self.playlist_result(entries, page_id) + return self.playlist_result(entries, playlist_id=display_id) - # Overview page - entries = [] - for page_num in itertools.count(2): - hrefs = re.findall( - r'
  • \s*]*>\s*\s*]+href="([^"]+)"', - webpage, 'm3u8 url', default=None) - if m3u8_url: - formats.extend(self._extract_m3u8_formats( - m3u8_url, page_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - - direct_urls = re.findall( - r'rel="web(S|M|L|XL)"[^>]+href="([^"]+)"', webpage) - if direct_urls: - for quality, video_url in direct_urls: - formats.append({ - 'url': video_url, - 'preference': preference(quality), - 'http_headers': { - 'User-Agent': 'mobile', - }, - }) - self._sort_formats(formats) - description = self._html_search_meta('Description', webpage, 'description') - return { - 'id': page_id, - 'formats': formats, + 'id': metadata_tracker_data.get('trackerClipId', display_id), + 'display_id': display_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, + 'alt_title': metadata_tracker_data.get('trackerClipSubcategory'), + 'formats': formats, 'upload_date': upload_date, - 'is_live': is_live + 'description': self._html_search_meta('Description', webpage), + 'is_live': is_live, + 'subtitles': subtitles, } @@ -241,81 +232,3 @@ class WDRMobileIE(InfoExtractor): 'User-Agent': 'mobile', }, } - - -class WDRMausIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P[^/?#]+)(?:/index\.php5|(?

    Sendedatum:\s*([0-9\.]+)

    ', - webpage, 'air date') - title_str = self._html_search_regex( - r'

    (.*?)

    ', 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[^']+)',\s*download:\s*'(?P
    [^']+)'\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, - }