项目练习 —— 贴吧爬虫

Posted 2021-01-22 sure-feng

 1 # -*- coding:utf-8 -*-
 2 # Author:Sure Feng
 3 
 4 import requests
 5 
 6 class TiebaSpider(object):
 7     def __init__(self, tieba_name):
 8         self.tieba_name = tieba_name
 9         self.url_temp = "https://tieba.baidu.com/f?kw=" + tieba_name + "&ie=utf-8&pn={}"
10         self.headers = {
11             "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/67.0.3396.99 Safari/537.36"}
12 
13 
14     def get_url_list(self):
15         """构造URL列表"""
16         # url_list = []
17         # for i in range(10):
18         #     url_list.append(self.url_temp.format(i * 50))
19         # return url_list
20         return [self.url_temp.format(i * 50) for i in range(10)]
21 
22     def parse_url(self, url):
23         """遍历列表，发送请求，获取响应内容"""
24         # print(url)
25         respond = requests.get(url, headers = self.headers)
26         return respond.content.decode()
27 
28 
29     def save_html(self, html_str, page_number):
30         """保存数据"""
31         file_name = "{} 第{}页" .format(self.tieba_name, page_number)
32         with open(file_name, "w", encoding="utf-8") as f:
33             f.write(html_str)
34 
35     def run(self):
36 
37         # 构造URL列表
38         url_list = self.get_url_list()
39         print(url_list)
40         # 遍历列表，发送请求，获取响应内容
41         for url in url_list:
42             html_str = self.parse_url(url)
43             # 保存数据
44             page_number = url_list.index(url) + 1
45             self.save_html(html_str, page_number)
46 
47 
48 if __name__ == "__main__":
49     tieba_sipder = TiebaSpider("棋魂")
50     tieba_sipder.run()