diff options
Diffstat (limited to 'hypervideo_dl/extractor/ndr.py')
| -rw-r--r-- | hypervideo_dl/extractor/ndr.py | 252 |
1 files changed, 142 insertions, 110 deletions
diff --git a/hypervideo_dl/extractor/ndr.py b/hypervideo_dl/extractor/ndr.py index 1917254..41ea362 100644 --- a/hypervideo_dl/extractor/ndr.py +++ b/hypervideo_dl/extractor/ndr.py @@ -1,14 +1,15 @@ -# coding: utf-8 -from __future__ import unicode_literals +import re from .common import InfoExtractor +from ..compat import compat_urllib_parse_urlparse from ..utils import ( determine_ext, + ExtractorError, int_or_none, - parse_duration, + merge_dicts, + parse_iso8601, qualities, try_get, - unified_strdate, urljoin, ) @@ -17,120 +18,139 @@ class NDRBaseIE(InfoExtractor): def _real_extract(self, url): mobj = self._match_valid_url(url) display_id = next(group for group in mobj.groups() if group) - id = mobj.group('id') webpage = self._download_webpage(url, display_id) - return self._extract_embed(webpage, display_id, id) + return self._extract_embed(webpage, display_id, url) class NDRIE(NDRBaseIE): IE_NAME = 'ndr' IE_DESC = 'NDR.de - Norddeutscher Rundfunk' - _VALID_URL = r'https?://(?:www\.)?(?:daserste\.)?ndr\.de/(?:[^/]+/)*(?P<display_id>[^/?#]+),(?P<id>[\da-z]+)\.html' + _VALID_URL = r'https?://(?:\w+\.)*ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html' _TESTS = [{ + # httpVideo, same content id 'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html', + 'md5': '6515bc255dc5c5f8c85bbc38e035a659', 'info_dict': { 'id': 'hafengeburtstag988', + 'display_id': 'Party-Poette-und-Parade', 'ext': 'mp4', 'title': 'Party, Pötte und Parade', - 'thumbnail': 'https://www.ndr.de/fernsehen/hafengeburtstag990_v-contentxl.jpg', 'description': 'md5:ad14f9d2f91d3040b6930c697e5f6b4c', - 'series': None, - 'channel': 'NDR Fernsehen', - 'upload_date': '20150508', + 'uploader': 'ndrtv', + 'timestamp': 1431255671, + 'upload_date': '20150510', 'duration': 3498, }, - }, { - 'url': 'https://www.ndr.de/sport/fussball/Rostocks-Matchwinner-Froede-Ein-Hansa-Debuet-wie-im-Maerchen,hansa10312.html', - 'only_matching': True - }, { - 'url': 'https://www.ndr.de/nachrichten/niedersachsen/kommunalwahl_niedersachsen_2021/Grosse-Parteien-zufrieden-mit-Ergebnissen-der-Kommunalwahl,kommunalwahl1296.html', - 'info_dict': { - 'id': 'kommunalwahl1296', - 'ext': 'mp4', - 'title': 'Die Spitzenrunde: Die Wahl aus Sicht der Landespolitik', - 'thumbnail': 'https://www.ndr.de/fernsehen/screenshot1194912_v-contentxl.jpg', - 'description': 'md5:5c6e2ad744cef499135735a1036d7aa7', - 'series': 'Hallo Niedersachsen', - 'channel': 'NDR Fernsehen', - 'upload_date': '20210913', - 'duration': 438, + 'params': { + 'skip_download': True, }, + 'expected_warnings': ['Unable to download f4m manifest'], }, { - 'url': 'https://www.ndr.de/fernsehen/sendungen/extra_3/extra-3-Satiremagazin-mit-Christian-Ehring,sendung1091858.html', + # httpVideo, different content id + 'url': 'http://www.ndr.de/sport/fussball/40-Osnabrueck-spielt-sich-in-einen-Rausch,osna270.html', + 'md5': '1043ff203eab307f0c51702ec49e9a71', 'info_dict': { - 'id': 'sendung1091858', + 'id': 'osna272', + 'display_id': '40-Osnabrueck-spielt-sich-in-einen-Rausch', 'ext': 'mp4', - 'title': 'Extra 3 vom 11.11.2020 mit Christian Ehring', - 'thumbnail': 'https://www.ndr.de/fernsehen/screenshot983938_v-contentxl.jpg', - 'description': 'md5:700f6de264010585012a72f97b0ac0c9', - 'series': 'extra 3', - 'channel': 'NDR Fernsehen', - 'upload_date': '20201111', - 'duration': 1749, - } + 'title': 'Osnabrück - Wehen Wiesbaden: Die Highlights', + 'description': 'md5:32e9b800b3d2d4008103752682d5dc01', + 'uploader': 'ndrtv', + 'timestamp': 1442059200, + 'upload_date': '20150912', + 'duration': 510, + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'No longer available', }, { + # httpAudio, same content id 'url': 'http://www.ndr.de/info/La-Valette-entgeht-der-Hinrichtung,audio51535.html', + 'md5': 'bb3cd38e24fbcc866d13b50ca59307b8', 'info_dict': { 'id': 'audio51535', + 'display_id': 'La-Valette-entgeht-der-Hinrichtung', 'ext': 'mp3', 'title': 'La Valette entgeht der Hinrichtung', - 'thumbnail': 'https://www.ndr.de/mediathek/mediathekbild140_v-podcast.jpg', 'description': 'md5:22f9541913a40fe50091d5cdd7c9f536', - 'upload_date': '20140729', - 'duration': 884.0, + 'uploader': 'ndrinfo', + 'timestamp': 1631711863, + 'upload_date': '20210915', + 'duration': 884, + }, + 'params': { + 'skip_download': True, + }, + }, { + # with subtitles + 'url': 'https://www.ndr.de/fernsehen/sendungen/extra_3/extra-3-Satiremagazin-mit-Christian-Ehring,sendung1091858.html', + 'info_dict': { + 'id': 'extra18674', + 'display_id': 'extra-3-Satiremagazin-mit-Christian-Ehring', + 'ext': 'mp4', + 'title': 'Extra 3 vom 11.11.2020 mit Christian Ehring', + 'description': 'md5:700f6de264010585012a72f97b0ac0c9', + 'uploader': 'ndrtv', + 'upload_date': '20201207', + 'timestamp': 1614349457, + 'duration': 1749, + 'subtitles': { + 'de': [{ + 'ext': 'ttml', + 'url': r're:^https://www\.ndr\.de.+', + }], + }, }, - 'expected_warnings': ['unable to extract json url'], + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Unable to download f4m manifest'], + }, { + 'url': 'https://www.ndr.de/Fettes-Brot-Ferris-MC-und-Thees-Uhlmann-live-on-stage,festivalsommer116.html', + 'only_matching': True, }] - def _extract_embed(self, webpage, display_id, id): - formats = [] - base_url = 'https://www.ndr.de' - json_url = self._search_regex(r'<iframe[^>]+src=\"([^\"]+)_theme-ndrde[^\.]*\.html\"', webpage, - 'json url', fatal=False) - if json_url: - data_json = self._download_json(base_url + json_url.replace('ardplayer_image', 'ardjson_image') + '.json', - id, fatal=False) - info_json = data_json.get('_info', {}) - media_json = try_get(data_json, lambda x: x['_mediaArray'][0]['_mediaStreamArray']) - for media in media_json: - if media.get('_quality') == 'auto': - formats.extend(self._extract_m3u8_formats(media['_stream'], id)) - subtitles = {} - sub_url = data_json.get('_subtitleUrl') - if sub_url: - subtitles.setdefault('de', []).append({ - 'url': base_url + sub_url, - }) - self._sort_formats(formats) - return { - 'id': id, - 'title': info_json.get('clipTitle'), - 'thumbnail': base_url + data_json.get('_previewImage'), - 'description': info_json.get('clipDescription'), - 'series': info_json.get('seriesTitle') or None, - 'channel': info_json.get('channelTitle'), - 'upload_date': unified_strdate(info_json.get('clipDate')), - 'duration': data_json.get('_duration'), - 'formats': formats, - 'subtitles': subtitles, - } - else: - json_url = base_url + self._search_regex(r'apiUrl\s?=\s?\'([^\']+)\'', webpage, 'json url').replace( - '_belongsToPodcast-', '') - data_json = self._download_json(json_url, id, fatal=False) - return { - 'id': id, - 'title': data_json.get('title'), - 'thumbnail': base_url + data_json.get('poster'), - 'description': data_json.get('summary'), - 'upload_date': unified_strdate(data_json.get('publicationDate')), - 'duration': parse_duration(data_json.get('duration')), - 'formats': [{ - 'url': try_get(data_json, (lambda x: x['audio'][0]['url'], lambda x: x['files'][0]['url'])), - 'vcodec': 'none', - 'ext': 'mp3', - }], - } + def _extract_embed(self, webpage, display_id, url): + embed_url = ( + self._html_search_meta( + 'embedURL', webpage, 'embed URL', + default=None) + or self._search_regex( + r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'embed URL', group='url', default=None) + or self._search_regex( + r'\bvar\s*sophoraID\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'embed URL', group='url', default='')) + # some more work needed if we only found sophoraID + if re.match(r'^[a-z]+\d+$', embed_url): + # get the initial part of the url path,. eg /panorama/archiv/2022/ + parsed_url = compat_urllib_parse_urlparse(url) + path = self._search_regex(r'(.+/)%s' % display_id, parsed_url.path or '', 'embed URL', default='') + # find tell-tale image with the actual ID + ndr_id = self._search_regex(r'%s([a-z]+\d+)(?!\.)\b' % (path, ), webpage, 'embed URL', default=None) + # or try to use special knowledge! + NDR_INFO_URL_TPL = 'https://www.ndr.de/info/%s-player.html' + embed_url = 'ndr:%s' % (ndr_id, ) if ndr_id else NDR_INFO_URL_TPL % (embed_url, ) + if not embed_url: + raise ExtractorError('Unable to extract embedUrl') + + description = self._search_regex( + r'<p[^>]+itemprop="description">([^<]+)</p>', + webpage, 'description', default=None) or self._og_search_description(webpage) + timestamp = parse_iso8601( + self._search_regex( + (r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="(?P<cont>[^"]+)"', + r'\bvar\s*pdt\s*=\s*(?P<q>["\'])(?P<cont>(?:(?!(?P=q)).)+)(?P=q)', ), + webpage, 'upload date', group='cont', default=None)) + info = self._search_json_ld(webpage, display_id, default={}) + return merge_dicts({ + '_type': 'url_transparent', + 'url': embed_url, + 'display_id': display_id, + 'description': description, + 'timestamp': timestamp, + }, info) class NJoyIE(NDRBaseIE): @@ -154,19 +174,19 @@ class NJoyIE(NDRBaseIE): 'params': { 'skip_download': True, }, + 'skip': 'No longer available', }, { # httpVideo, different content id 'url': 'http://www.n-joy.de/musik/Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-,felixjaehn168.html', 'md5': '417660fffa90e6df2fda19f1b40a64d8', 'info_dict': { - 'id': 'dockville882', + 'id': 'livestream283', 'display_id': 'Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-', - 'ext': 'mp4', - 'title': '"Ich hab noch nie" mit Felix Jaehn', - 'description': 'md5:85dd312d53be1b99e1f998a16452a2f3', + 'ext': 'mp3', + 'title': 'Das frueheste DJ Set des Nordens live mit Felix Jaehn', + 'description': 'md5:681698f527b8601e511e7b79edde7d2c', 'uploader': 'njoy', - 'upload_date': '20150822', - 'duration': 211, + 'upload_date': '20210830', }, 'params': { 'skip_download': True, @@ -176,22 +196,29 @@ class NJoyIE(NDRBaseIE): 'only_matching': True, }] - def _extract_embed(self, webpage, display_id, id): + def _extract_embed(self, webpage, display_id, url=None): + # find tell-tale URL with the actual ID, or ... video_id = self._search_regex( - r'<iframe[^>]+id="pp_([\da-z]+)"', webpage, 'embed id') - description = self._search_regex( - r'<div[^>]+class="subline"[^>]*>[^<]+</div>\s*<p>([^<]+)</p>', - webpage, 'description', fatal=False) + (r'''\bsrc\s*=\s*["']?(?:/\w+)+/([a-z]+\d+)(?!\.)\b''', + r'<iframe[^>]+id="pp_([\da-z]+)"', ), + webpage, 'NDR id', default=None) + + description = ( + self._html_search_meta('description', webpage) + or self._search_regex( + r'<div[^>]+class="subline"[^>]*>[^<]+</div>\s*<p>([^<]+)</p>', + webpage, 'description', fatal=False)) return { '_type': 'url_transparent', 'ie_key': 'NDREmbedBase', 'url': 'ndr:%s' % video_id, 'display_id': display_id, 'description': description, + 'title': display_id.replace('-', ' ').strip(), } -class NDREmbedBaseIE(InfoExtractor): +class NDREmbedBaseIE(InfoExtractor): # XXX: Conventionally, Concrete class names do not end in BaseIE IE_NAME = 'ndr:embed:base' _VALID_URL = r'(?:ndr:(?P<id_s>[\da-z]+)|https?://www\.ndr\.de/(?P<id>[\da-z]+)-ppjson\.json)' _TESTS = [{ @@ -239,7 +266,6 @@ class NDREmbedBaseIE(InfoExtractor): ff['vcodec'] = 'none' ff['ext'] = ext or 'mp3' formats.append(ff) - self._sort_formats(formats) config = playlist['config'] @@ -288,9 +314,9 @@ class NDREmbedBaseIE(InfoExtractor): } -class NDREmbedIE(NDREmbedBaseIE): +class NDREmbedIE(NDREmbedBaseIE): # XXX: Do not subclass from concrete IE IE_NAME = 'ndr:embed' - _VALID_URL = r'https?://(?:www\.)?(?:daserste\.)?ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html' + _VALID_URL = r'https?://(?:\w+\.)*ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:(?:ard)?player|externalPlayer)\.html' _TESTS = [{ 'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html', 'md5': '8b9306142fe65bbdefb5ce24edb6b0a9', @@ -303,6 +329,7 @@ class NDREmbedIE(NDREmbedBaseIE): 'upload_date': '20150907', 'duration': 132, }, + 'skip': 'No longer available', }, { 'url': 'http://www.ndr.de/ndr2/events/soundcheck/soundcheck3366-player.html', 'md5': '002085c44bae38802d94ae5802a36e78', @@ -318,6 +345,7 @@ class NDREmbedIE(NDREmbedBaseIE): 'params': { 'skip_download': True, }, + 'skip': 'No longer available', }, { 'url': 'http://www.ndr.de/info/audio51535-player.html', 'md5': 'bb3cd38e24fbcc866d13b50ca59307b8', @@ -327,7 +355,7 @@ class NDREmbedIE(NDREmbedBaseIE): 'title': 'La Valette entgeht der Hinrichtung', 'is_live': False, 'uploader': 'ndrinfo', - 'upload_date': '20140729', + 'upload_date': '20210915', 'duration': 884, }, 'params': { @@ -348,15 +376,17 @@ class NDREmbedIE(NDREmbedBaseIE): 'params': { 'skip_download': True, }, + 'skip': 'No longer available', }, { # httpVideoLive 'url': 'http://www.ndr.de/fernsehen/livestream/livestream217-externalPlayer.html', 'info_dict': { 'id': 'livestream217', - 'ext': 'flv', + 'ext': 'mp4', 'title': r're:^NDR Fernsehen Niedersachsen \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', 'is_live': True, - 'upload_date': '20150910', + 'upload_date': '20210409', + 'uploader': 'ndrtv', }, 'params': { 'skip_download': True, @@ -382,7 +412,7 @@ class NDREmbedIE(NDREmbedBaseIE): }] -class NJoyEmbedIE(NDREmbedBaseIE): +class NJoyEmbedIE(NDREmbedBaseIE): # XXX: Do not subclass from concrete IE IE_NAME = 'njoy:embed' _VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html' _TESTS = [{ @@ -394,9 +424,10 @@ class NJoyEmbedIE(NDREmbedBaseIE): 'ext': 'mp4', 'title': 'Zehn Jahre Reeperbahn Festival - die Doku', 'is_live': False, - 'upload_date': '20150807', + 'upload_date': '20200826', 'duration': 1011, }, + 'expected_warnings': ['Unable to download f4m manifest'], }, { # httpAudio 'url': 'http://www.n-joy.de/news_wissen/stefanrichter100-player_image-d5e938b1-f21a-4b9a-86b8-aaba8bca3a13_theme-n-joy.html', @@ -413,6 +444,7 @@ class NJoyEmbedIE(NDREmbedBaseIE): 'params': { 'skip_download': True, }, + 'skip': 'No longer available', }, { # httpAudioLive, no explicit ext 'url': 'http://www.n-joy.de/news_wissen/webradioweltweit100-player_image-3fec0484-2244-4565-8fb8-ed25fd28b173_theme-n-joy.html', @@ -422,7 +454,7 @@ class NJoyEmbedIE(NDREmbedBaseIE): 'title': r're:^N-JOY Weltweit \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', 'is_live': True, 'uploader': 'njoy', - 'upload_date': '20150810', + 'upload_date': '20210830', }, 'params': { 'skip_download': True, |