X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/ecaee9d66905db1d5836d396c705d18d6e5f1f72..0626de37fa3331c654d4affae363132a0d766ffb:/youtube_dl/extractor/ndr.py?ds=sidebyside diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index aec2ea1..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): @@ -220,11 +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,