rijksmuseum URL can point to English catalog page
This commit is contained in:
		
							parent
							
								
									efa06c9e33
								
							
						
					
					
						commit
						52db7ac00f
					
				| 
						 | 
				
			
			@ -3,7 +3,7 @@ import lxml.html
 | 
			
		|||
import os
 | 
			
		||||
import re
 | 
			
		||||
 | 
			
		||||
re_url = re.compile(r'^https://www.rijksmuseum.nl/nl/collectie/([^/]+)$')
 | 
			
		||||
re_url = re.compile(r'^https://www.rijksmuseum.nl/(?:nl/collectie|en/collection)/([^/]+)$')
 | 
			
		||||
 | 
			
		||||
def get_html(catalog_id):
 | 
			
		||||
    filename = f'cache/rijksmuseum_{catalog_id}.html'
 | 
			
		||||
| 
						 | 
				
			
			
 | 
			
		|||
		Loading…
	
		Reference in a new issue