利用xpath爬丁香园论坛帖子的所有回复内容

最新推荐文章于 2023-12-29 12:13:25 发布

原创最新推荐文章于 2023-12-29 12:13:25 发布 · 353 阅读

0 ·

CC 4.0 BY-SA版权

部署运行你感兴趣的模型镜像

from lxml import etree
import requests

def get_html(url, headers):
    response = requests.get(url, headers = headers)
    try:
        if response.status_code == 200:
            return response.text
    except:
        pass

def  get_parse(html):
    tree = etree.HTML(html)
    user = tree.xpath('//*/table/tbody/tr/td/div/a/text()')
    reply = tree.xpath('//*/table/tbody/tr/td/div/div/table/tbody/tr/td/text()')

    for users, replys in zip(user, reply):
        print('用户名:'+users, '回复内容：'+ replys.strip())


def main():
    url = 'http://www.dxy.cn/bbs/thread/626626'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
               }
    html = get_html(url, headers)
    get_parse(html)

if __name__ == '__main__':
    main()
    ```
    爬取结果：![在这里插入图片描述](https://img-blog.csdnimg.cn/20190304160450654.png)