抓取博客园个人主页目录制作

 1 #-*- coding:utf-8 -*-
 2 
 3 import urllib2
 4 from lxml import etree
 5 
 6 class CrawlJs():
 7     #定义函数，爬取对应的数据
 8     def getArticle(self,url):
 9         print ‘█████████████◣开始爬取数据‘
10         my_headers = {
11             ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.104 Safari/537.36‘,
12         }
13         request = urllib2.Request(url,headers=my_headers)
14         content = urllib2.urlopen(request).read()
15         return content
16 
17     #定义函数，筛选和保存爬取到的数据
18     def save(self,content):
19         xml = etree.HTML(content)
20         title = xml.xpath(‘//*[@class="postTitle"]/a/text()‘)
21         link = xml.xpath(‘//*[@class="postTitle"]/a/@href‘)
22         print (title,link)
23         # print(zip(title,link))
24         # print(map(lambda x,y:[x,y], title,link))
25         for t,li in zip(title,link):
26             print(t+li)
27             with open(‘bokeyuan.txt‘,‘a+‘) as f:
28                 f.write(t.encode(‘utf-8‘)+li+ ‘\n‘)
29         print ‘█████████████◣爬取完成！‘
30 
31 #定义主程序接口
32 if __name__ == ‘__main__‘:
33     page = int(raw_input(‘请输入你要抓取的页码总数：‘))
34     for num in range(page):
35         #这里输入个人主页，
36         url = ‘http://www.cnblogs.com/zhouxinfei/default.html?page=%s‘%(num+1)
37         js = CrawlJs()
38         content = js.getArticle(url)
39         js.save(content)