python采集搜索引擎关键字

ivor

python做爬虫的人真多，我就练练手

1. # Python 3.5.1
   
2. # coding:utf-8
   
3. # 采集搜索引擎关键字
   
4. import urllib.request, re
   
5. 
   
6. text = ["北京", "上海", "青岛"]
   
7. for choice in text:
   
8.         keywards = urllib.request.quote(choice)
   
9.         url = "http://sug.so.360.cn/suggest?callback=suggest_so&encodein=utf-8&encodeout=utf-8&format=json&fields=word,obdata&word=" + keywards
   
10.         headers = {
    
11.                 "GET":url,
    
12.                 "Host":"sug.so.360.cn",
    
13.                 "Referer":"http://www.so.com/",
    
14.                 "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 Safari/537.36"
    
15. }
    
16.         req = urllib.request.Request(url)
    
17.         for header in headers:
    
18.                 req.add_header(header,headers[header])
    
19.         html = urllib.request.urlopen(req).read()
    
20.         html_decode=html.decode("utf-8")
    
21.         result = re.findall(""([\u4e00-\u9fa5].*?)"",html_decode)
    
22.         for item in result:
    
23.                 print(item)
    
24. 
    
25. input("Press Enter key to continue……")

复制代码