爬取12306验证码图片

# -*- coding:utf-8 -*-
import time
import urllib2
import ssl
 
def get_code_picture(local_filename):
    #目的为了通过未认证的12306证书
    ssl._create_default_https_context = ssl._create_unverified_context

    req = urllib2.Request("https://kyfw.12306.cn/passport/captcha/captcha-image?login_site=E&module=login&rand=sjrand&0.6551712691897946")
    req.add_header("Referer","https://kyfw.12306.cn/otn/login/init")
    req.add_header("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36")
    codeimg = urllib2.urlopen(req).read()    
    
    with open(local_filename, 'wb') as f:
        f.write(codeimg)

if __name__ == "__main__":
    for i in xrange(0x7fffffff):
        path = './123062/' + str(i+1) +'.jpg'
        get_code_picture(path)
        print path
        
        #由于12306过快刷新会提示稍后再来，所以再此休眠一秒。
        time.sleep(1)