4-14 截取文章 关键词 思路

 1     def parse(self, response):
 2         aa = response.css('#archive.floated-thumb.post-thumb a::attr(href)').extract()
 3         for i in aa:
 4             print(i)
 5         #res_select = response.xpath('//*[@id="post-94286"]/div[1]/h1/text()')
 6         #res_select2 = response.xpath('//div[@class="entry-header"]/h1/text()').extract_first()
 7         #res_select3 = response.xpath('//p[@class="entry-meta-hide-on-mobile"]')
 8         #cre_date = response.xpath('//p[@class="entry-meta-hide-on-mobile"]/text()') ##提取时间思路
 9         ##>>>  cre_date.extract()[0].strip().replace('.',"")
10         #>>> response.xpath('//span[contains(@class,"vote-post-up")]/h10/text()').extract()[0] ##点赞书
11         pass
原文地址:https://www.cnblogs.com/th-lyc/p/8845731.html