python爬虫登录12306失败_使用python爬虫模拟12306登录方法
試了好久登錄的時候總是顯示:系統忙,請刷新,,,太折磨人了,搞了半天才想到是請求頭部的問題.....
驗證碼還是要人工識圖..#!/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登錄腳本,作者Mr RJL
python版本:2.7,適用于linux
驗證碼輸入方式:
輸入問題對應的圖片序號,1-8;
多個以','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("獲取Cookie")
Url = "https://kyfw.12306.cn/otn/login/init"
get(Url)
for index, c in enumerate(cookiejar):
stoidinput(c)
def getImg():
stoidinput("下載驗證碼...")
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):
"""
正常信息輸出
:param text:
:return:
"""
print "\033[34m[*]\033[0m %s " % text
def errorinput(text):
"""
錯誤信息輸出
:param text:
:return:
"""
print "\033[32m[!]\033[0m %s " % text
return False
def codexy():
"""
獲取驗證碼
:return: str
"""
Ofset = raw_input("[*] 請輸入驗證碼: ")
select = Ofset.split(',')
global randCode
post = []
offsetsX = 0 # 選擇的答案的left值,通過瀏覽器點擊8個小圖的中點得到的,這樣基本沒問題
offsetsY = 0 # 選擇的答案的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("驗證碼有誤,請重試")
else:
stoidinput("驗證碼通過,開始登錄..")
try:
tresult = json.loads(Post(logurl, logdata), encoding='utf8')
if tresult['data'].__len__() == 0:
errorinput("登錄失敗: %s" % tresult['messages'][0])
else:
stoidinput("登錄成功")
sult = Post(surl, ldata)
getUserinfo()
except ValueError as e:
errorinput(e)
def getUserinfo():
"""
登錄成功后,顯示用戶名
:return:
"""
url = 'https://kyfw.12306.cn/otn/modifyUser/initQueryUserInfo'
data = dict(_json_att=None)
result = Post(url, data)
userinfo = result
name = r''
try:
stoidinput("歡迎 %s 登錄" % re.search(name, result).group(1))
except AttributeError:
pass
def main():
user = raw_input("[+] 用戶名(用戶名/郵箱/手機): ")
passwd = getpass.getpass("[+] 密碼: ")
if user == '' or passwd == '':
errorinput("用戶名或密碼不能為空!")
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("退出失敗")
if __name__ == "__main__":
print baner
main()
logout()
總結
以上是生活随笔為你收集整理的python爬虫登录12306失败_使用python爬虫模拟12306登录方法的全部內容，希望文章能夠幫你解決所遇到的問題。
- 上一篇： window下jenkin安装，小白一看
- 下一篇： websocket python爬虫_p