手动爬虫之报头及代理封装类（python3）

　　本人刚刚学习爬虫，见每次都需要添加报头比较繁琐，故将该过程封装为Url_ProxyHelper类，代码如下

 1 import urllib.request as ur
 2 
 3 class Url_ProxyHelper:
 4     def __init__(self, url, proxy_add, savepath=None):
 5         self.url = url
 6         self.proxy_add = proxy_add
 7         self.req = None
 8         self.proxy = None
 9         self.opener = None
10         self.info = None
11         self.save_path = savepath
12 
13     # 报头代理设置
14     def set_UrlAndProxy(self):
15         # 添加报头
16         self.req = ur.Request(self.url)
17         self.req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0')
18 
19         # 设置代理服务器
20         self.proxy = ur.ProxyHandler({'http': self.proxy_add})
21         self.opener = ur.build_opener(self.proxy, ur.HTTPHandler)
22         ur.install_opener(self.opener)
23         return self.req
24 
25     # 数据存档
26     def save_InFile(self):
27         self.req = self.set_UrlAndProxy()
28         self.info = ur.urlopen(self.req).read()
29         open(self.save_path, 'wb').write(self.info)
30 
31     # 数据返回
32     def feedbak_info(self):
33         self.req = self.set_UrlAndProxy()
34         self.info = ur.urlopen(self.req).read().decode('utf-8')  # decode()用来解码，特别是中文
35         return str(self.info)

 

测试：

 1 from Url_ProxyHelper import Url_ProxyHelper
 2 
 3 url = "https://www.baidu.com/"
 4 save_path = "E:/workspace/PyCharm/codeSpace/books/python_web_crawler_book/chapter6/demo4/test_url_proxy.html"
 5 proxy = "175.155.24.20:808"
 6 
 7 # 调用Url_ProxyHelper类
 8 #uph = Url_ProxyHelper(url, proxy, savepath=save_path)
 9 uph = Url_ProxyHelper(url, proxy)
10 
11 info = uph.feedbak_info()
12 
13 print(info)

 

posted on 2017-07-03 13:25  小明在线  阅读(528)  评论(0)    收藏  举报

导航