Last active
June 15, 2016 07:41
-
-
Save no13bus/ce19d3a08aeae2096d32 to your computer and use it in GitHub Desktop.
模拟登录带有验证码的登录页面
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from bs4 import BeautifulSoup | |
| import requests | |
| from PIL import image | |
| import pytesseract | |
| mysession = requests.Session() | |
| url = 'http://110.249.223.91/hbhb/Default.aspx' | |
| r = mysession.get(url,timeout=60*4) | |
| c = r.content | |
| mysoup = BeautifulSoup(c) | |
| inputstring = mysoup.find_all('input', attrs={"name":"__VIEWSTATE"}) | |
| inputstring = inputstring[0] | |
| ##获取post需要的请求参数__VIEWSTATE的值 赋值为变量viewstate | |
| viewstate = inputstring['value'] | |
| captcha_url = 'http://110.249.223.91/hbhb/CheckCode.aspx' | |
| capr = mysession.get(captcha_url,timeout=60*4) | |
| with open('/home/captcha.jpg', 'wb') as f: | |
| f.write(capr.content) | |
| ###获取验证码字串 赋值cap_str | |
| cap_str = pytesseract.image_to_string(Image.open('/home/captcha.jpg')) | |
| payload = {'__EVENTTARGET':'','__EVENTARGUMENT':'','__VIEWSTATE':viewstate,'txtUserName':'guest','txtPWD':'123','txtCheckCode':cap_str,'ibtnLogin.x':'25','ibtnLogin.y':'8'} | |
| headers = { | |
| 'Content-Type':'application/x-www-form-urlencoded', | |
| 'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', | |
| 'Accept-Encoding':'gzip,deflate,sdch', | |
| 'Accept-Language':'zh-CN,zh;q=0.8,en;q=0.6,zh-TW;q=0.4', | |
| 'Cache-Control':'max-age=0', | |
| 'Connection':'keep-alive', | |
| 'Content-Type':'application/x-www-form-urlencoded', | |
| 'Host':'110.249.223.91', | |
| 'Origin':'http://110.249.223.91', | |
| 'Referer':'http://110.249.223.91/hbhb/Default.aspx', | |
| 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.125 Safari/537.3' | |
| } | |
| result = mysession.post(url, data=payload, headers=headers,timeout=60*4) | |
| print result.content |
from PIL import image中image首字母是不是应该大写，我小写运行不通过，请指教
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
我的怎么识别不出来 。。。求帮助