CSS选择器的使用

获取标题

>>> response.css(".entry-header h1").extract()
['<h1>写代码容易，编程并不容易</h1>']

>>> response.css(".entry-header h1::text").extract()
['写代码容易，编程并不容易']

获取时间

create_time = response.css("p.entry-meta-hide-on-mobile ::text").extract()[0].strip().replace("·", "")

获取点赞人数

praise_num = int(response.css(".vote-post-up h10 ::text").extract()[0])

获取收藏人数

fav_num = response.css(".bookmark-btn ::text").extract()[0]
match_re = re.match(r'.*?(\d+).*', fav_num)
if match_re:
    fav_num = match_re.group(1)

获取评论数

comments_num = response.css("a[href='#article-comment'] span::text").extract()[0]
match_re = re.match(r'.*?(\d+).*', comments_num)
if match_re:
    comments_num = match_re.group(1)
else:
    comments_num = 0

获取内容

content = response.css("div.entry").extract()[0]

获取标签

tag_list = response.css('p.entry-meta-hide-on-mobile a ::text').extract()
# 对标签进行过滤
tag_list = [element for element in tag_list if not element.strip().endswith("评论")]
tags = ",".join(tag_list)