爬虫入门01：爬取知乎热榜

最新推荐文章于 2025-06-11 19:50:48 发布

原创最新推荐文章于 2025-06-11 19:50:48 发布 · 3.3k 阅读

6 ·

CC 4.0 BY-SA版权

爬虫入门专栏收录该内容

1 篇文章

订阅专栏

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# author:qdf time:2019/1/21

from lxml import etree
import requests

url = "https://www.zhihu.com/hot"
headers = {"User-Agent":"",
           "Cookie":""}

response = requests.get(url, headers=headers)
html_str = response.content.decode()
html = etree.HTML(html_str)
# print(html)

#获取知乎热榜排名标题热度
ret = html.xpath("//section[@class='HotItem']")
# print(ret)

for table in ret:
    item = {}
    item['排名'] = table.xpath(".//div[@class='HotItem-index']/div/text()")
    item['标题'] = table.xpath(".//div[@class='HotItem-content']/a/@title")
    item['热度'] = table.xpath(".//div[@class='HotItem-metrics HotItem-metrics--bottom']/text()")
    print(item)