1 #!/usr/bin/env python
2 # -*- coding:utf-8 -*-
3
4 import urllib
5 import urllib2
6
7 def loadPage(url, filename):
8 """
9 作用：根据url发送请求，获取服务器响应文件
10 url: 需要爬取的url地址
11 filename : 处理的文件名
12 """
13 print "正在下载 " + filename
14 headers = {"User-Agent" : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"}
15
16 request = urllib2.Request(url, headers = headers)
17 return urllib2.urlopen(request).read()
18
19 def writePage(html, filename):
20 """
21 作用：将html内容写入到本地
22 html：服务器相应文件内容
23 """
24 print "正在保存 " + filename
25 # 文件写入
26 with open(filename, "w") as f:
27 f.write(html)
28 print "-" * 30
29
30 def tiebaSpider(url, beginPage, endPage):
31 """
32 作用：贴吧爬虫调度器，负责组合处理每个页面的url
33 url : 贴吧url的前部分
34 beginPage : 起始页
35 endPage : 结束页
36 """
37 for page in range(beginPage, endPage + 1):
38 pn = (page - 1) * 50
39 filename = "第" + str(page) + "页.html"
40 fullurl = url + "&pn=" + str(pn)
41 #print fullurl
42 html = loadPage(fullurl, filename)
43 #print html
44 writePage(html, filename)
45 print "谢谢使用"
46
47 if __name__ == "__main__":
48 kw = raw_input("请输入需要爬取的贴吧名:")
49 beginPage = int(raw_input("请输入起始页："))
50 endPage = int(raw_input("请输入结束页："))
51
52 url = "http://tieba.baidu.com/f?"
53 key = urllib.urlencode({"kw": kw})
54 fullurl = url + key
55 tiebaSpider(fullurl, beginPage, endPage)
