正则爬取某段子网站前20页段子(request库)

content_list = re.findall(r‘<a href="/detail-.*">(.+?)</a>‘, html_str) 

content_list = re.findall(r‘<div class="j-r-list-c-desc">\s*<a href="/detail-.*">(.+?)</a>‘, html_str) 

 1 import requests
 2 import re
 3 import json
 4 
 5 class NeihanSpider(object):
 6     """内涵段子，百思不得其姐，正则爬取一页的数据"""
 7     def __init__(self):
 8         self.temp_url = ‘http://www.budejie.com/text/{}‘  # 网站地址，给页码留个可替换的{}
 9         self.headers = {
10             ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36‘,
11         }
12 
13     def pass_url(self, url):  # 发送请求，获取响应
14         print(url)
15         response = requests.get(url, headers=self.headers)
16         return response.content.decode()
17 
18     def get_first_page_content_list(self, html_str):  # 提取第一页的数据
19         content_list = re.findall(r‘<div class="j-r-list-c-desc">\s*<a href="/detail-.*">(.+?)</a>‘, html_str)  # 非贪婪匹配
20         return content_list
21 
22     def save_content_list(self, content_list):
23         with open(‘neihan.txt‘, ‘a‘, encoding=‘utf-8‘) as f:
24             for content in content_list:
25                 f.write(json.dumps(content, ensure_ascii=False))
26                 f.write(‘\n‘)  # 换行
27             print(‘成功保存一页！‘)
28 
29     def run(self):  # 实现主要逻辑
30         for i in range(20):  # 只爬取前20页数据
31             # 1. 构造url
32             # 2. 发送请求，获取响应
33             html_str = self.pass_url(self.temp_url.format(i+1))
34             # 3. 提取数据
35             content_list = self.get_first_page_content_list(html_str)
36             # 4. 保存
37             self.save_content_list(content_list)
38 
39 if __name__ == ‘__main__‘:
40     neihan = NeihanSpider()
41     neihan.run()