爬取博客园有关爬虫的文章

 1 # coding: utf-8
 2 import requests
 3 from bs4 import BeautifulSoup
 4 # 定义变量，这里可以用一个
 5 d = 1
 6 p = 0
 7 k = 0
 8 Reptilian_url = []
 9 Reptilian_title = []
10 # 打开session
11 s = requests.session()
12 # 伪装头部
13 h = {
14     'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4094.1 Safari/537.36',
15     'accept-encoding':'gzip, deflate, br'
16 }
17 # 从第1页到最大页数的url，总共有200页，这个数值也可以从页面读取
18 while d in range(200):
19     url = 'https://www.cnblogs.com/cate/python/%d'% d
20     r = s.get(url, headers=h)
21     t = r.text
22     soup = BeautifulSoup(t, 'lxml')
23     list = soup.select('div.post_item_body h3')
24     list2 = soup.find_all(attrs={'class':"titlelnk"})
25     while p < d:
26         # 把标题写入空列表
27         for z1 in list:
28             Reptilian_title.append(z1.string)
29         # 把url写入空列表
30         for u1 in list2:
31             Reptilian_url.append(u1['href'])
32         p += 1
33     d += 1
34 # 打印爬取的总数据量
35 print(len(Reptilian_title))
36 # 加入筛选条件，包含爬虫字段的帖子
37 while k < len(Reptilian_title):
38     if '爬虫' in Reptilian_title[k]:
39         print(k+1,'%s'%Reptilian_title[k],'','%s'%Reptilian_url[k])
40         print('===============================')
41     k += 1

1 Reptilian = open('1.txt', 'a')
2 Reptilian.writelines(['标题：',Reptilian_title,' ','url：',Reptilian_url])
3 Reptilian.close()