python pandas 用法大全之爬虫

1. import urllib.request

2. import urllib.parse

3.  

4. url='http://www.baidu.com'

5. hearder={

6. 'User-Agent':'Mozilla/5.0 (X11; Fedora; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'

7. }

8.  

9. request=urllib.request.Request(url,headers=header)

10. reponse=urllib.request.urlopen(request).read()

11.  

12. fhandle=open("./1.html","wb")

13. fhandle.write(reponse)

 

 

 

1. # -*- coding: utf-8 -*-

2.  

3. import urllib.request

4. import urllib.parse

5.  

6. url='http://www.baidu.com/s?wd='

7. key='fengxin的博客'

8. key_code=urllib.request.quote(key) #因为URL里含中文，需要进行编码

9. url_all=url+key_code

10. header={

11. 'User-Agent':'Mozilla/5.0 (X11; Fedora; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'

12. } #头部信息

13. request=urllib.request.Request(url_all,headers=header)

14. reponse=urllib.request.urlopen(request).read()

15.  

16. fh=open("./baidu.html","wb") #写入文件中

17. fh.write(reponse)

18. fh.close()

 

 

1. #!/usr/bin/env python3

2. # -*- coding: utf-8 -*-

3.  

4. import urllib.request

5. import urllib.parse

6.  

7. url='http://www.iqianyue.com/mypost'

8. header={

9. 'User-Agent':'Mozilla/5.0 (X11; Fedora; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'

10. }

11.  

12. data={'name':'fengxin','pass':'123'}

13. postdata=urllib.parse.urlencode(data).encode('utf8') #进行编码

14. request=urllib.request.Request(url,postdata)

15. reponse=urllib.request.urlopen(request).read()

16.  

17. fhandle=open("./1.html","wb")

18. fhandle.write(reponse)

19.