[ndr] Fix extraction (closes #24326)
This commit is contained in:
		
							parent
							
								
									541fe3eaff
								
							
						
					
					
						commit
						4cbce88f8b
					
				
					 1 changed files with 9 additions and 4 deletions
				
			
		| 
						 | 
					@ -7,6 +7,7 @@ from .common import InfoExtractor
 | 
				
			||||||
from ..utils import (
 | 
					from ..utils import (
 | 
				
			||||||
    determine_ext,
 | 
					    determine_ext,
 | 
				
			||||||
    int_or_none,
 | 
					    int_or_none,
 | 
				
			||||||
 | 
					    merge_dicts,
 | 
				
			||||||
    parse_iso8601,
 | 
					    parse_iso8601,
 | 
				
			||||||
    qualities,
 | 
					    qualities,
 | 
				
			||||||
    try_get,
 | 
					    try_get,
 | 
				
			||||||
| 
						 | 
					@ -87,21 +88,25 @@ class NDRIE(NDRBaseIE):
 | 
				
			||||||
 | 
					
 | 
				
			||||||
    def _extract_embed(self, webpage, display_id):
 | 
					    def _extract_embed(self, webpage, display_id):
 | 
				
			||||||
        embed_url = self._html_search_meta(
 | 
					        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<url>(?:(?!\1).)+)\1', webpage,
 | 
				
			||||||
 | 
					            'embed URL', group='url')
 | 
				
			||||||
        description = self._search_regex(
 | 
					        description = self._search_regex(
 | 
				
			||||||
            r'<p[^>]+itemprop="description">([^<]+)</p>',
 | 
					            r'<p[^>]+itemprop="description">([^<]+)</p>',
 | 
				
			||||||
            webpage, 'description', default=None) or self._og_search_description(webpage)
 | 
					            webpage, 'description', default=None) or self._og_search_description(webpage)
 | 
				
			||||||
        timestamp = parse_iso8601(
 | 
					        timestamp = parse_iso8601(
 | 
				
			||||||
            self._search_regex(
 | 
					            self._search_regex(
 | 
				
			||||||
                r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"',
 | 
					                r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"',
 | 
				
			||||||
                webpage, 'upload date', fatal=False))
 | 
					                webpage, 'upload date', default=None))
 | 
				
			||||||
        return {
 | 
					        info = self._search_json_ld(webpage, display_id, default={})
 | 
				
			||||||
 | 
					        return merge_dicts({
 | 
				
			||||||
            '_type': 'url_transparent',
 | 
					            '_type': 'url_transparent',
 | 
				
			||||||
            'url': embed_url,
 | 
					            'url': embed_url,
 | 
				
			||||||
            'display_id': display_id,
 | 
					            'display_id': display_id,
 | 
				
			||||||
            'description': description,
 | 
					            'description': description,
 | 
				
			||||||
            'timestamp': timestamp,
 | 
					            'timestamp': timestamp,
 | 
				
			||||||
        }
 | 
					        }, info)
 | 
				
			||||||
 | 
					
 | 
				
			||||||
 | 
					
 | 
				
			||||||
class NJoyIE(NDRBaseIE):
 | 
					class NJoyIE(NDRBaseIE):
 | 
				
			||||||
| 
						 | 
					
 | 
				
			||||||
		Loading…
	
	Add table
		Add a link
		
	
		Reference in a new issue