Use python crawler to simulate 12306 login method-Python Tutorial-php.cn

Use python crawler to simulate 12306 login method
高洛峰
Release： 2017-03-22 13:08:35
Original
3175 people have browsed it
试了好久登录的时候总是显示:系统忙,请刷新,,,太折磨人了,搞了半天才想到是请求头部的问题.....
验证码还是要人工识图..
#!/bin/env python
# -*- coding=utf-8 -*-
import ssl
import sys
import urllib2
import random
import httplib
import json
from cookielib import LWPCookieJar
import urllib
import re
import getpass
 
reload(sys)
sys.setdefaultencoding(&#39;UTF8&#39;)
cookiejar = LWPCookieJar()
cookiesuppor = urllib2.HTTPCookieProcessor(cookiejar)
opener = urllib2.build_opener(cookiesuppor, urllib2.HTTPHandler)
urllib2.install_opener(opener)
ssl._create_default_https_context = ssl._create_unverified_context
codeimg = &#39;https://kyfw.12306.cn/otn/passcodeNew/getPassCodeNew?module=login&rand=sjrand&%s&#39; % random.random()
 
baner = """
##################################
    12306登录脚本,作者Mr RJL
    python版本:2.7,适用于linux
    验证码输入方式:
    输入问题对应的图片序号,1-8;
    多个以&#39;,&#39;分隔.如:1,2,3
##################################
"""
def get(url):
    try:
        request = urllib2.Request(url=url)
        # req.add_header(&#39;User-Agent&#39;, &#39;Mozilla/5.0 (X11; Fedora; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0&#39;)
        request.add_header("Content-Type", "application/x-www-form-urlencoded; charset=utf-8")
        request.add_header(&#39;X-Requested-With&#39;, &#39;xmlHttpRequest&#39;)
        request.add_header(&#39;User-Agent&#39;,
                           &#39;Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.154 Safari/537.36&#39;)
        request.add_header(&#39;Referer&#39;, &#39;https://kyfw.12306.cn/otn/login/init&#39;)
        request.add_header(&#39;Accept&#39;, &#39;*/*&#39;)
        result = urllib2.urlopen(request).read()
        assert isinstance(result, object)
        return result
    except httplib.error as e:
        print e
        pass
    except urllib2.URLError as e:
        print e
        pass
    except urllib2.HTTPBasicAuthHandler, urllib2.HTTPError:
        print &#39;error&#39;
        pass
 
 
def Post(url, data):
    try:
        request = urllib2.Request(url=url, data=urllib.urlencode(data))
        # req.add_header(&#39;User-Agent&#39;, &#39;Mozilla/5.0 (X11; Fedora; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0&#39;)
        # request = urllib2.Request(ajax_url, urllib.urlencode(dc))
        request.add_header("Content-Type", "application/x-www-form-urlencoded; charset=utf-8")
        request.add_header(&#39;X-Requested-With&#39;, &#39;xmlHttpRequest&#39;)
        request.add_header(&#39;User-Agent&#39;,
                           &#39;Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.154 Safari/537.36&#39;)
        request.add_header(&#39;Referer&#39;, &#39;https://kyfw.12306.cn/otn/login/init&#39;)
        request.add_header(&#39;Accept&#39;, &#39;*/*&#39;)
        # request.add_header(&#39;Accept-Encoding&#39;, &#39;gzip, deflate&#39;)
        result = urllib2.urlopen(request).read()
        return result
    except httplib.error as e:
        return e
    except urllib2.URLError as e:
        return e
    except urllib2.HTTPBasicAuthHandler, urllib2.HTTPError:
        return &#39;error&#39;
 
 
def cookietp():
    stoidinput("获取Cookie")
    Url = "https://kyfw.12306.cn/otn/login/init"
    get(Url)
    for index, c in enumerate(cookiejar):
        stoidinput(c)
 
 
def getImg():
    stoidinput("下载验证码...")
    result = get(codeimg)
    try:
        if open(&#39;/tmp/tkcode&#39;, &#39;wb&#39;).write(result) :
            import os
            os.system("oeg /tmp/tkcode &")
        else:
            return False
    except OSError as e:
        print e
        pass
 
 
def stoidinput(text):
    """
    正常信息输出
    :param text: 
    :return: 
    """
    print "\033[34m[*]\033[0m %s " % text
 
 
def errorinput(text):
    """
    错误信息输出
    :param text: 
    :return: 
    """
    print "\033[32m[!]\033[0m %s " % text
    return False
 
 
def codexy():
    """
    获取验证码
    :return: str
    """
     
    Ofset = raw_input("[*] 请输入验证码: ")
    select = Ofset.split(&#39;,&#39;)
    global randCode
    post = []
    offsetsX = 0  # 选择的答案的left值,通过浏览器点击8个小图的中点得到的,这样基本没问题
    offsetsY = 0  # 选择的答案的top值
    for ofset in select:
        if ofset == &#39;1&#39;:
            offsetsY = 46
            offsetsX = 42
        elif ofset == &#39;2&#39;:
            offsetsY = 46
            offsetsX = 105
        elif ofset == &#39;3&#39;:
            offsetsY = 45
            offsetsX = 184
        elif ofset == &#39;4&#39;:
            offsetsY = 48
            offsetsX = 256
        elif ofset == &#39;5&#39;:
            offsetsY = 36
            offsetsX = 117
        elif ofset == &#39;6&#39;:
            offsetsY = 112
            offsetsX = 115
        elif ofset == &#39;7&#39;:
            offsetsY = 114
            offsetsX = 181
        elif ofset == &#39;8&#39;:
            offsetsY = 111
            offsetsX = 252
        else:
            pass
        post.append(offsetsX)
        post.append(offsetsY)
    randCode = str(post).replace(&#39;]&#39;, &#39;&#39;).replace(&#39;[&#39;, &#39;&#39;).replace("&#39;", &#39;&#39;).replace(&#39; &#39;, &#39;&#39;)
 
 
def login(user, passwd):
    randurl = &#39;https://kyfw.12306.cn/otn/passcodeNew/checkRandCodeAnsyn&#39;
    logurl = &#39;https://kyfw.12306.cn/otn/login/loginAysnSuggest&#39;
    surl = &#39;https://kyfw.12306.cn/otn/login/userLogin&#39;
    geturl = &#39;https://kyfw.12306.cn/otn/index/initMy12306&#39;
    randdata = {
        "randCode": randCode,
        "rand": "sjrand"
    }
    logdata = {
        "loginUserDTO.user_name": user,
        "userDTO.password": passwd,
        "randCode": randCode
    }
    ldata = {
        "_json_att": None
    }
    fresult = json.loads(Post(randurl, randdata), encoding=&#39;utf8&#39;)
    checkcode = fresult[&#39;data&#39;][&#39;msg&#39;]
    if checkcode == &#39;FALSE&#39;:
        errorinput("验证码有误,请重试")
    else:
        stoidinput("验证码通过,开始登录..")
        try:
            tresult = json.loads(Post(logurl, logdata), encoding=&#39;utf8&#39;)
            if tresult[&#39;data&#39;].__len__() == 0:
                errorinput("登录失败: %s" % tresult[&#39;messages&#39;][0])
            else:
 
                stoidinput("登录成功")
                sult = Post(surl, ldata)
                getUserinfo()
        except ValueError as e:
            errorinput(e)
 
 
def getUserinfo():
    """
    登录成功后,显示用户名
    :return:
    """
    url = &#39;https://kyfw.12306.cn/otn/modifyUser/initQueryUserInfo&#39;
    data = dict(_json_att=None)
    result = Post(url, data)
    userinfo = result
    name = r&#39;<input name="userDTO.loginUserDTO.user_name" style="display:none;" type="text" value="(\S+)" />&#39;
    try:
        stoidinput("欢迎 %s 登录" % re.search(name, result).group(1))
    except AttributeError:
        pass
 
 
def main():
    user = raw_input("[+] 用户名(用户名/邮箱/手机): ")
    passwd = getpass.getpass("[+] 密码: ")
    if user == &#39;&#39; or passwd == &#39;&#39;:
        errorinput("用户名或密码不能为空!")
    else:
        cookietp()
        getImg()
        codexy()
        login(user, passwd)
def logout():
    url = &#39;https://kyfw.12306.cn/otn/login/loginOut&#39;
    result = get(url)
    if result:
        stoidinput("已退出")
    else:
        errorinput("退出失败")
 
if __name__ == "__main__":
    print baner
    main()
    logout()
Copy after login
The above is the detailed content of Use python crawler to simulate 12306 login method. For more information, please follow other related articles on the PHP Chinese website!