太不容易了，第一次爬（不知道算不算）

最新推荐文章于 2024-10-03 16:52:07 发布

给我砸

最新推荐文章于 2024-10-03 16:52:07 发布

阅读量71

点赞数

文章标签：爬虫 python

本文链接：https://blog.csdn.net/LV_AA/article/details/120026148

版权

from lxml import etree
import requests
from fake_useragent import UserAgent

url = "https://zuowen.jupeixun.cn/mingyan/c853/?p=2"

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3875.400 QQBrowser/10.8.4492.400"}
response = requests.get(url,headers = headers)
print(response.status_code)
#转码
html_str = response.text
#print(html_str)                     输出源码
# html_str = str(html_str.encode("iso-8859-1"),encoding="utf-8")
#etree = html.etree                  #创建解析树对象
html_obj = etree.HTML(html_str)     #调用HTML方法解析html文本，返回html对象
print(html_obj)
ul_li_p = html_obj.xpath("/html/body/div[1]/ul/li/p")           # Xpath                                 /html/body/div[1]/ul/li[1]/p[1]
for p in ul_li_p:
    print(p.text)