python用css方法爬取伯乐在线

1.css的用法

2.css的用法

 #通过css选择器提取字段
        # front_image_url = response.meta.get("front_image_url", "")  #文章封面图
        # title = response.css(".entry-header h1::text").extract()[0]
        # create_date = response.css("p.entry-meta-hide-on-mobile::text").extract()[0].strip().replace("·","").strip()
        # praise_nums = response.css(".vote-post-up h10::text").extract()[0]
        # fav_nums = response.css(".bookmark-btn::text").extract()[0]
        # match_re = re.match(".*?(\d+).*", fav_nums)
        # if match_re:
        #     fav_nums = int(match_re.group(1))
        # else:
        #     fav_nums = 0
        #
        # comment_nums = response.css("a[href='#article-comment'] span::text").extract()[0]
        # match_re = re.match(".*?(\d+).*", comment_nums)
        # if match_re:
        #     comment_nums = int(match_re.group(1))
        # else:
        #     comment_nums = 0
        #
        # content = response.css("div.entry").extract()[0]
        #
        # tag_list = response.css("p.entry-meta-hide-on-mobile a::text").extract()
        # tag_list = [element for element in tag_list if not element.strip().endswith("评论")]
        # tags = ",".join(tag_list)