使用python爬虫模拟12306登录方法
内容导读
互联网集市收集整理的这篇技术教程文章主要介绍了使用python爬虫模拟12306登录方法，小编现在分享给大家，供广大互联网技能从业者学习和参考。文章包含5524字，纯文字阅读大概需要8分钟。
内容图文
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('UTF8')
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 = 'https://kyfw.12306.cn/otn/passcodeNew/getPassCodeNew?module=login&rand=sjrand&%s' % 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','分隔.如:1,2,3
##################################
"""
def get(url):
try:
request = urllib2.Request(url=url)
# req.add_header('User-Agent', 'Mozilla/5.0 (X11; Fedora; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0')
request.add_header("Content-Type", "application/x-www-form-urlencoded; charset=utf-8")
request.add_header('X-Requested-With', 'xmlHttpRequest')
request.add_header('User-Agent',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.154 Safari/537.36')
request.add_header('Referer', 'https://kyfw.12306.cn/otn/login/init')
request.add_header('Accept', '*/*')
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 'error'
pass
def Post(url, data):
try:
request = urllib2.Request(url=url, data=urllib.urlencode(data))
# req.add_header('User-Agent', 'Mozilla/5.0 (X11; Fedora; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0')
# request = urllib2.Request(ajax_url, urllib.urlencode(dc))
request.add_header("Content-Type", "application/x-www-form-urlencoded; charset=utf-8")
request.add_header('X-Requested-With', 'xmlHttpRequest')
request.add_header('User-Agent',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.154 Safari/537.36')
request.add_header('Referer', 'https://kyfw.12306.cn/otn/login/init')
request.add_header('Accept', '*/*')
# request.add_header('Accept-Encoding', 'gzip, deflate')
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 'error'
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('/tmp/tkcode', 'wb').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(',')
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 == '1':
offsetsY = 46
offsetsX = 42
elif ofset == '2':
offsetsY = 46
offsetsX = 105
elif ofset == '3':
offsetsY = 45
offsetsX = 184
elif ofset == '4':
offsetsY = 48
offsetsX = 256
elif ofset == '5':
offsetsY = 36
offsetsX = 117
elif ofset == '6':
offsetsY = 112
offsetsX = 115
elif ofset == '7':
offsetsY = 114
offsetsX = 181
elif ofset == '8':
offsetsY = 111
offsetsX = 252
else:
pass
post.append(offsetsX)
post.append(offsetsY)
randCode = str(post).replace(']', '').replace('[', '').replace("'", '').replace(' ', '')
def login(user, passwd):
randurl = 'https://kyfw.12306.cn/otn/passcodeNew/checkRandCodeAnsyn'
logurl = 'https://kyfw.12306.cn/otn/login/loginAysnSuggest'
surl = 'https://kyfw.12306.cn/otn/login/userLogin'
geturl = 'https://kyfw.12306.cn/otn/index/initMy12306'
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='utf8')
checkcode = fresult['data']['msg']
if checkcode == 'FALSE':
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='utf8')
if tresult['data'].__len__() == 0:
errorinput("登录失败: %s" % tresult['messages'][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 = 'https://kyfw.12306.cn/otn/modifyUser/initQueryUserInfo'
data = dict(_json_att=None)
result = Post(url, data)
userinfo = result
name = r'<input name="userDTO.loginUserDTO.user_name" style="display:none;" type="text" value="(\S+)" />'
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 == '' or passwd == '':
errorinput("用户名或密码不能为空!")
else:
cookietp()
getImg()
codexy()
login(user, passwd)
def logout():
url = 'https://kyfw.12306.cn/otn/login/loginOut'
result = get(url)
if result:
stoidinput("已退出")
else:
errorinput("退出失败")
if __name__ == "__main__":
print baner
main()
logout()以上就是使用python爬虫模拟12306登录方法的详细内容，更多请关注Gxl网其它相关文章！
内容总结
以上是互联网集市为您收集整理的使用python爬虫模拟12306登录方法全部内容，希望文章能够帮你解决使用python爬虫模拟12306登录方法所遇到的程序开发问题。 如果觉得互联网集市技术教程内容还不错，欢迎将互联网集市网站推荐给程序员好友。
内容备注
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 gblab@vip.qq.com 举报，一经查实，本站将立刻删除。
内容手机端
扫描二维码推送至手机访问。
来源：【匿名】