1 import requests
2 from lxml import etree
3
4 header = {
5 "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36"
6 }
7
8
9 def spider(page_num):
10 url = f"https://www.169tp.com/xingganmeinv/list_1_{page_num}.html"
11
12 # 获取到网页初始数据text
13 res = requests.get(url, headers=header)
14 res.encoding = 'gbk'
15 text = res.text
16 tree = etree.HTML(text)
17
18 lis = tree.xpath("/html/body/div[4]/ul/li")
19
20 for i in lis:
21 addr = i.xpath("./a/img/@src")[0]
22 title = i.xpath("./a/p/text()")
23
24 detail = requests.get(addr,headers=header).content
25
26 f = open(f"imgs/{title}.jpg", mode="wb")
27 f.write(detail)
28 f.close()
29 print(f"图片 --------- {title} ------------- 完成！！")
30
31
32 def start():
33 for i in range(1,101):
34 spider(i)
35
36
37 if __name__ == '__main__':
38 start()
标签：__,title,Python,text,header,res,requests,图片 From： https://www.cnblogs.com/zhangyh-blog/p/17308014.html