hubo

class MySpider(CrawlSpider): start_urls = [ "http://www.example.com", ] rules = ( Rule( LxmlLinkExtractor( allow=[r'\w+\/\d+$', r'\w+\/\d+-p\d+$'], ), follow=True ), Rule( LxmlLinkExtractor( allow=(r'\d+.html$'), ), 'parse_action', ), ) def parse_action(self, response): yield WebdriverRequest(response.url, callback=self.parse_item)...