python-requests正则 

 1 以抓取豆瓣分页为例
 2 from re import S
 3 
 4 import requests
 5 from setuptools import findall  # S多行匹配 M单行匹配
 6 from urllib3 import response
 7 
 8 
 9 def get_all_movies():
10     page = 10
11     # 请求头
12     header = {
13         'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36'
14     }
15     for n in range(page):
16         url = f'https://movie.douban.com/top250?start={n * 25}&filter='
17         response = requests.get(url, headers=header)
18         print(response.text)
19         print(f'==============第{n + 1}页=============')
20         if response.status_code == 200:
21             analysis_data(response.text)
22         else:
23             print(f'爬取失败')

 

posted @ 2020-10-16 09:17  橙子皮！  阅读(446)  评论(0)    收藏  举报