爬取12306车次信息

Posted 2020-10-14 青山应回首

#!/usr/bin/python2.7
# -*- coding:utf-8 -*-
# 2017-10-19

"""
12306 抢票

网页分析
    - 查看网页源码
    - 判断是否通过异步加载或者框架的形式接收并展示数据
    - 数据加密过，然后前端再通过js解密并展示（即js混淆）


urllib2.URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:590)>
证书作用：保证数据在传输的过程中不会被篡改或截取
"""

import sys
reload(sys)
sys.setdefaultencoding(‘utf8‘)

import ssl
import json
import urllib2

# 跳过证书验证
ssl._create_default_https_context = ssl._create_unverified_context

headers = {
    ‘Referer‘:‘https://kyfw.12306.cn/otn/leftTicket/init‘,
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/61.0.3163.100 Safari/537.36‘
}

def getTrainList():
    url = "https://kyfw.12306.cn/otn/leftTicket/query?leftTicketDTO.train_date=2017-10-20&leftTicketDTO.from_station=BJP&leftTicketDTO.to_station=CDW&purpose_codes=ADULT"
    req = urllib2.Request(url)
    req.headers = headers
    html = urllib2.urlopen(req).read()
    res = json.loads(html)
    return res[‘data‘][‘result‘]

if __name__ == ‘__main__‘:
    c = 0
    for i in getTrainList():
        tmp_list = i.split(‘|‘)
        # print "%s\t%s\t%s" % (tmp_list[13],tmp_list[23],tmp_list[3])
        if tmp_list[23] == u‘有‘:
            print "时间：%s 车次：%s 软卧有很多票..." % (tmp_list[13],tmp_list[3])
        elif tmp_list[23] == u‘无‘ or not tmp_list[23]:
            print "时间：%s 车次：%s 软卧无票..." % (tmp_list[13],tmp_list[3])
        elif int(tmp_list[23]) > 0:
            print "时间：%s 车次：%s 软卧有 %s 张票" % (tmp_list[13],tmp_list[3],tmp_list[23])
        else:
            print "时间：%s 车次：%s 软卧无票..." % (tmp_list[13], tmp_list[3])