X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/87a0165ca7e39af4dacb7ec637063b2cd35ae40b..39393b81acfaf4045fb7f20454a0226f0dc9142e:/youtube_dl/extractor/ndr.py diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index e3b0da2..2447c81 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -7,8 +7,11 @@ from .common import InfoExtractor from ..utils import ( determine_ext, int_or_none, + merge_dicts, parse_iso8601, qualities, + try_get, + urljoin, ) @@ -85,21 +88,25 @@ class NDRIE(NDRBaseIE): def _extract_embed(self, webpage, display_id): embed_url = self._html_search_meta( - 'embedURL', webpage, 'embed URL', fatal=True) + 'embedURL', webpage, 'embed URL', + default=None) or self._search_regex( + r'\bembedUrl["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'embed URL', group='url') description = self._search_regex( r']+itemprop="description">([^<]+)

', webpage, 'description', default=None) or self._og_search_description(webpage) timestamp = parse_iso8601( self._search_regex( r']+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"', - webpage, 'upload date', fatal=False)) - return { + webpage, 'upload date', 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): @@ -190,10 +197,12 @@ class NDREmbedBaseIE(InfoExtractor): ext = determine_ext(src, None) if ext == 'f4m': formats.extend(self._extract_f4m_formats( - src + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, f4m_id='hds')) + src + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, + f4m_id='hds', fatal=False)) elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - src, video_id, 'mp4', m3u8_id='hls', entry_protocol='m3u8_native')) + src, video_id, 'mp4', m3u8_id='hls', + entry_protocol='m3u8_native', fatal=False)) else: quality = f.get('quality') ff = { @@ -218,11 +227,17 @@ class NDREmbedBaseIE(InfoExtractor): upload_date = ppjson.get('config', {}).get('publicationDate') duration = int_or_none(config.get('duration')) - thumbnails = [{ - 'id': thumbnail.get('quality') or thumbnail_id, - 'url': thumbnail['src'], - 'preference': quality_key(thumbnail.get('quality')), - } for thumbnail_id, thumbnail in config.get('poster', {}).items() if thumbnail.get('src')] + thumbnails = [] + poster = try_get(config, lambda x: x['poster'], dict) or {} + for thumbnail_id, thumbnail in poster.items(): + thumbnail_url = urljoin(url, thumbnail.get('src')) + if not thumbnail_url: + continue + thumbnails.append({ + 'id': thumbnail.get('quality') or thumbnail_id, + 'url': thumbnail_url, + 'preference': quality_key(thumbnail.get('quality')), + }) return { 'id': video_id, @@ -302,7 +317,7 @@ class NDREmbedIE(NDREmbedBaseIE): 'info_dict': { 'id': 'livestream217', 'ext': 'flv', - 'title': 're:^NDR Fernsehen Niedersachsen \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', + 'title': r're:^NDR Fernsehen Niedersachsen \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', 'is_live': True, 'upload_date': '20150910', }, @@ -367,7 +382,7 @@ class NJoyEmbedIE(NDREmbedBaseIE): 'info_dict': { 'id': 'webradioweltweit100', 'ext': 'mp3', - 'title': 're:^N-JOY Weltweit \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', + 'title': r're:^N-JOY Weltweit \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', 'is_live': True, 'uploader': 'njoy', 'upload_date': '20150810',