Python爬虫 12306抢票开源代码过程详解
今天就和大家一起来讨论一下python实现12306余票查询(pycharm+python3.7),一起来感受一下python爬虫的简单实践
我们说先在浏览器中打开开发者工具(F12),尝试一次余票的查询,通过开发者工具查看发出请求的包
可以看到红框框中的URL就是我们向12306服务器发出的请求,那么具体是什么呢?我们来看看
https://kyfw.12306.cn/otn/leftTicket/queryZ?leftTicketDTO.train_date=2019-01-21&leftTicketDTO.from_station=CDW&leftTicketDTO.to_station=SZQ&purpose_codes=ADULT
可以看到发出请求的几个字段:
- leftTicketDTO.train_date:查询的日期
- leftTicketDTO.from_station:查询的出发地
- leftTicketDTO.to_station:查询的目的地
- purpose_codes:不太清楚这个字段是用来做什么的,就默认吧
可以从我们递交的URL请求看出,我们输入的成都,深圳都变成了对应的编号,比如,成都(CDW)、深圳(SZQ),所以当我们程序进行输入的时候要进行一下处理,12306的一个地方存储着这些城市名与编码对应的文档:
https://kyfw.12306.cn/otn/resources/js/framework/station_name.js?station_version=1.8971
下面我们就编写一个小程序,将这些城市名与编号提取出来:
import re,requests
url = "https://kyfw.12306.cn/otn/resources/js/framework/station_name.js?station_version=1.8971"
response = requests.get(url,verify=False)
#将车站的名字和编码进行提取
chezhan = re.findall(r'([\u4e00-\u9fa5]+)\|([A-Z]+)', response.text)
chezhan_code = dict(chezhan)
#进行交换
chezhan_names = dict(zip(chezhan_code.values(),chezhan_code.keys()))
#打印出得到的车站字典
print(chezhan_names)
得到的打印结果如下(只截取部分显示):
{'VAP': '北京北', 'BOP': '北京东', 'BJP': '北京', 'VNP': '北京南', 'BXP': '北京西', 'IZQ': '广州南', 'CUW': '重庆北', 'CQW': '重庆', 'CRW': '重庆南', 'CXW': '重庆西', 'GGQ': '广州东', 'SHH': '上海', 'SNH': '上海南', 'AOH': '上海虹桥', 'SXH': '上海西', 'TBP': '天津北', 'TJP': '天津', 'TIP': '天津南', 'TXP': '天津西', 'XJA': '香港西九龙', 'CCT': '长春', 'CET': '长春南', 'CRT': '长春西', 'ICW': '成都东', 'CNW': '成都南', 'CDW': '成都', 'CSQ': '长沙', 'CWQ': '长沙南',}
接下来我们就动手开始程序的主要代码编写:
def main():
date = input("请输入时间(如2019-01-22):\n")
from_station = chezhan_code[input("请输入起始站点:\n")]
to_station = chezhan_code[input("请输入目的站点:\n")]
url = "https://kyfw.12306.cn/otn/leftTicket/queryZ?"
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.5702.400 QQBrowser/10.2.1893.400"
}
url=url+"leftTicketDTO.train_date="+date+"&leftTicketDTO.from_station="+from_station+"&leftTicketDTO.to_station="+to_station+"&purpose_codes=ADULT"
#print(url) 已经检查过生成的URL是正确的
#request请求获取主页
r = requests.get(url,headers=headers)
r.raise_for_status() #如果发送了一个错误的请求,会抛出异常
r.encoding = r.apparent_encoding
showTicket(r.text)
用户输入时间、起始站点、目的站点,然后通过get来请求,然后我们对返回的网页信息进行解析。我们现将上面代码的r.text进行打印,看看我们请求之后,返回了什么样的信息,然后决定我们应该如何解析
这样看着不方便,我们粘贴到记事本中,进行详细的分析:
可以与12306显示的信息进行对比,K829是车次,CDW与BJQ是出发地和目的地,10:10是出发时间,06:13是到达时间,44:21是历时时间,20190123为查询的日期,剩下的就是一系列票的各种信息。
下面就是对这些返回的信息进行解析,其实这也是python爬虫的关键,就是解析!!!
我们先把信息转化为json格式,可以看到都是用“|”隔开的,那么我们就用split函数分割出来,下面是主要功能代码:
def showTicket(html):
html = json.loads(html)
table = PrettyTable([" 车次 ","出发车站","到达车站","出发时间","到达时间"," 历时 ","商务座"," 一等座","二等座","高级软卧","软卧","动卧","硬卧","软座","硬座","无座","其他","备注"])
for i in html['data']['result']:
name = [
"station_train_code",
"from_station_name",
"to_station_name",
"start_time",
"arrive_time",
"lishi",
"swz_num",
"zy_num",
"ze_num",
"dw_num",
"gr_num",
"rw_num",
"yw_num",
"rz_num",
"yz_num",
"wz_num",
"qt_num",
"note_num"
]
data = {
"station_train_code": '',
"from_station_name": '',
"to_station_name": '',
"start_time": '',
"arrive_time": '',
"lishi": '',
"swz_num": '',
"zy_num": '',
"ze_num": '',
"dw_num": '',
"gr_num": '',
"rw_num": '',
"yw_num": '',
"rz_num": '',
"yz_num": '',
"wz_num": '',
"qt_num": '',
"note_num": ''
}
#将各项信息提取并赋值
item = i.split('|') #使用“|”进行分割
data["station_train_code"] = item[3] #获取车次信息,在3号位置
data["from_station_name"] = item[6] #始发站信息在6号位置
data["to_station_name"] = item[7] #终点站信息在7号位置
data["start_time"] = item[8] #出发时间在8号位置
data["arrive_time"] = item[9] #抵达时间在9号位置
data["lishi"] = item[10] #经历时间在10号位置
data["swz_num"] = item[32] or item[25] #特别注意,商务座在32或25位置
data["zy_num"] = item[31] #一等座信息在31号位置
data["ze_num"] = item[30] #二等座信息在30号位置
data["gr_num"] = item[21] #高级软卧信息在21号位置
data["rw_num"] = item[23] #软卧信息在23号位置
data["dw_num"] = item[27] #动卧信息在27号位置
data["yw_num"] = item[28] #硬卧信息在28号位置
data["rz_num"] = item[24] #软座信息在24号位置
data["yz_num"] = item[29] #硬座信息在29号位置
data["wz_num"] = item[26] #无座信息在26号位置
data["qt_num"] = item[22] #其他信息在22号位置
data["note_num"] = item[1] #备注信息在1号位置
color = Colored()
data["note_num"] = color.white(item[1])
#如果没有信息,那么就用“-”代替
for pos in name:
if data[pos] == "":
data[pos] = "-"
tickets = []
cont = []
cont.append(data)
for x in cont:
tmp = []
for y in name:
if y == "from_station_name":
s = color.green(chezhan_names[data["from_station_name"]])
tmp.append(s)
elif y == "to_station_name":
s = color.red(chezhan_names[data["to_station_name"]])
tmp.append(s)
elif y == "start_time":
s = color.green(data["start_time"])
tmp.append(s)
elif y == "arrive_time":
s = color.red(data["arrive_time"])
tmp.append(s)
elif y == "station_train_code":
s = color.yellow(data["station_train_code"])
tmp.append(s)
else:
tmp.append(data[y])
tickets.append(tmp)
for ticket in tickets:
table.add_row(ticket)
print(table)
那么我们程序就成功啦!!!
但是在编译器里面Prettytable的格子没有对齐,不要担心,我们到终端运行一下脚本,就可以看到很好看的输出啦:
完成!!!下面是完整代码
main.py
# -*- coding: utf-8 -*-
import re,requests,datetime,time,json
from prettytable import PrettyTable
from colorama import init,Fore
from stationinfo import chezhan_code,chezhan_names
init(autoreset=False)
class Colored(object):
def yeah(self,s):
return Fore.LIGHTCYAN_EX + s + Fore.RESET
def green(self,s):
return Fore.LIGHTGREEN_EX + s + Fore.RESET
def yellow(self,s):
return Fore.LIGHTYELLOW_EX + s + Fore.RESET
def white(self,s):
return Fore.LIGHTWHITE_EX + s + Fore.RESET
def blue(self,s):
return Fore.LIGHTBLUE_EX + s + Fore.RESET
def showTicket(html):
html = json.loads(html)
table = PrettyTable([" 车次 ","出发车站","到达车站","出发时间","到达时间"," 历时 ","商务座"," 一等座","二等座","高级软卧","软卧","动卧","硬卧","软座","硬座","无座","其他","备注"])
for i in html['data']['result']:
name = [
"station_train_code",
"from_station_name",
"to_station_name",
"start_time",
"arrive_time",
"lishi",
"swz_num",
"zy_num",
"ze_num",
"dw_num",
"gr_num",
"rw_num",
"yw_num",
"rz_num",
"yz_num",
"wz_num",
"qt_num",
"note_num"
]
data = {
"station_train_code": '',
"from_station_name": '',
"to_station_name": '',
"start_time": '',
"arrive_time": '',
"lishi": '',
"swz_num": '',
"zy_num": '',
"ze_num": '',
"dw_num": '',
"gr_num": '',
"rw_num": '',
"yw_num": '',
"rz_num": '',
"yz_num": '',
"wz_num": '',
"qt_num": '',
"note_num": ''
}
#将各项信息提取并赋值
item = i.split('|') #使用“|”进行分割
data["station_train_code"] = item[3] #获取车次信息,在3号位置
data["from_station_name"] = item[6] #始发站信息在6号位置
data["to_station_name"] = item[7] #终点站信息在7号位置
data["start_time"] = item[8] #出发时间在8号位置
data["arrive_time"] = item[9] #抵达时间在9号位置
data["lishi"] = item[10] #经历时间在10号位置
data["swz_num"] = item[32] or item[25] #特别注意,商务座在32或25位置
data["zy_num"] = item[31] #一等座信息在31号位置
data["ze_num"] = item[30] #二等座信息在30号位置
data["gr_num"] = item[21] #高级软卧信息在21号位置
data["rw_num"] = item[23] #软卧信息在23号位置
data["dw_num"] = item[27] #动卧信息在27号位置
data["yw_num"] = item[28] #硬卧信息在28号位置
data["rz_num"] = item[24] #软座信息在24号位置
data["yz_num"] = item[29] #硬座信息在29号位置
data["wz_num"] = item[26] #无座信息在26号位置
data["qt_num"] = item[22] #其他信息在22号位置
data["note_num"] = item[1] #备注信息在1号位置
color = Colored()
data["note_num"] = color.white(item[1])
#如果没有信息,那么就用“-”代替
for pos in name:
if data[pos] == "":
data[pos] = "-"
tickets = []
cont = []
cont.append(data)
for x in cont:
tmp = []
for y in name:
if y == "from_station_name":
s = color.green(chezhan_names[data["from_station_name"]])
tmp.append(s)
elif y == "to_station_name":
s = color.yeah(chezhan_names[data["to_station_name"]])
tmp.append(s)
elif y == "start_time":
s = color.green(data["start_time"])
tmp.append(s)
elif y == "arrive_time":
s = color.yeah(data["arrive_time"])
tmp.append(s)
elif y == "station_train_code":
s = color.yellow(data["station_train_code"])
tmp.append(s)
else:
tmp.append(data[y])
tickets.append(tmp)
for ticket in tickets:
table.add_row(ticket)
print(table)
def main():
date = input("请输入时间:\n")
from_station = chezhan_code[input("请输入起始站点:\n")]
to_station = chezhan_code[input("请输入目的站点:\n")]
url = "https://kyfw.12306.cn/otn/leftTicket/queryZ?"
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.5702.400 QQBrowser/10.2.1893.400"
}
url=url+"leftTicketDTO.train_date="+date+"&leftTicketDTO.from_station="+from_station+"&leftTicketDTO.to_station="+to_station+"&purpose_codes=ADULT"
#print(url) 已经检查过生成的URL是正确的
#request请求获取主页
r = requests.get(url,headers=headers)
r.raise_for_status() #如果发送了一个错误的请求,会抛出异常
r.encoding = r.apparent_encoding
showTicket(r.text)
#print(r.text)
main()
stationinfo.py
import re,requests
url = "https://kyfw.12306.cn/otn/resources/js/framework/station_name.js?station_version=1.8971"
response = requests.get(url,verify=False)
#将车站的名字和编码进行提取
chezhan = re.findall(r'([\u4e00-\u9fa5]+)\|([A-Z]+)', response.text)
chezhan_code = dict(chezhan)
chezhan_names = dict(zip(chezhan_code.values(),chezhan_code.keys()))
#print(chezhan_names)
以上是 Python爬虫 12306抢票开源代码过程详解 的全部内容, 来源链接: utcz.com/z/312406.html