[已解决]POST表单好像没有正确提交（python)

孙屹飞

1. import urllib.request
   
2. import urllib.parse
   
3. from bs4 import BeautifulSoup
   
4. import time
   
5.   
   
6. fs = ''
   
7. url = "http://app2.bjepb.gov.cn/cpout/showout/ListAccept.aspx"  
   
8. postdata = urllib.parse.urlencode({'_EVENTTARGET':"",
   
9. '_EVENTARGUMENT':"",
   
10. '_VIEWSTATE':"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",
    
11. 'ddlcounty':"市级",
    
12. 'txtAppName': "",'AspNetPager_input': '5', 'AspNetPager': '跳转'})  
    
13. postdata = postdata.encode('utf-8')
    
14. req = urllib.request.Request(url, postdata)
    
15. req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64; rv:48.0) Gecko/20100101 Firefox/48.0')
    
16. time.sleep(1.5)
    
17. res = urllib.request.urlopen(req)
    
18. html=res.read().decode('utf-8')
    
19. print(res.status, res.reason)  
    
20.   
    
21. if( res.status != 200 ):  
    
22.     exit()  
    
23.   
    
24. print('ok')
    
25. 
    
26. soup=BeautifulSoup(html,'html.parser')
    
27. trs=str(soup) #根据表格的style来定位表格，也可以通过id和第几个来定位，请参考函数重载
    
28. fs=fs+trs
    
29. res.close()
    
30. 
    
31. 
    
32. 
    
33. f=open(r'C:/temp/group1.txt','w',encoding='utf-8') #这个例子没有写新建文件的语句，需要自己提前在相应目录建好空文件，才能通过
    
34. f.write(fs)
    
35. f.close
    
36.   
    

复制代码

总是显示第一页，无法跳转到第五页，好像POST表单没有提交，请各位大神帮帮小弟！！！谢谢，谢谢

最佳答案

月排行榜 / 总排行榜

SixPy

2016-9-16 23:20:08

一个简单例子，自己完善吧~
这个页面的 字符集 设置得有些蛋疼~

• import re
• import requests as req
• url = r'http://app2.bjepb.gov.cn/cpout/showout/ListAccept.aspx'
• UA = {'User-Agent':'Mozilla/5.0'}
• formdata = {
•     '__EVENTTARGET':"",
•     '__EVENTARGUMENT':"",
•     '__VIEWSTATE':'',
•     'ddlcounty':"市级",
•     'txtAppName': "",
•     'AspNetPager_input': '5',
•     'AspNetPager': '跳转'
• }
• ssn = req.Session()
• ssn.headers = UA
• rsp = ssn.get(url)
• html = rsp.text
• vs = re.findall(r'<input[^>]+?name="__VIEWSTATE"[^>]+?value="([^"]+)',html)[0]
• formdata['__VIEWSTATE'] = vs
• rsp = ssn.post(url, data=formdata)
• html = rsp.text
• pg = ''.join(re.findall(r'(当前页：).+?(\d+)',html, re.S)[0])
• print(pg)
  

跳转到最佳答案楼层

SixPy

一个简单例子，自己完善吧~
这个页面的 字符集 设置得有些蛋疼~

• import re
• import requests as req
• url = r'http://app2.bjepb.gov.cn/cpout/showout/ListAccept.aspx'
• UA = {'User-Agent':'Mozilla/5.0'}
• formdata = {
•     '__EVENTTARGET':"",
•     '__EVENTARGUMENT':"",
•     '__VIEWSTATE':'',
•     'ddlcounty':"市级",
•     'txtAppName': "",
•     'AspNetPager_input': '5',
•     'AspNetPager': '跳转'
• }
• ssn = req.Session()
• ssn.headers = UA
• rsp = ssn.get(url)
• html = rsp.text
• vs = re.findall(r'<input[^>]+?name="__VIEWSTATE"[^>]+?value="([^"]+)',html)[0]
• formdata['__VIEWSTATE'] = vs
• rsp = ssn.post(url, data=formdata)
• html = rsp.text
• pg = ''.join(re.findall(r'(当前页：).+?(\d+)',html, re.S)[0])
• print(pg)
  

孙屹飞

多谢大神！