本文主要是介绍python爬取机票信息_python Ajax异步爬取机票航班信息，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
目标:
爬取未来40天多个航线的机票价格和航班信息python Ajax异步爬取机票航班信息www.wangwanghub.com
Ajax介绍:
AJAX = Asynchronous JavaScript and XML(异步的 JavaScript 和 XML)。 AJAX 是一种在无需重新加载整个网页的情况下，能够更新部分网页的技术。
起始URL:
明确爬取数据信息:
这个api网址是无法访问的,不过依旧有数据传送,我们只能通过模拟头部请求获取(payload是一种以JSON格式进行数据传输的一种方式)
发现有一个products 的文件 (如果没有 请尝试 F5 刷新页面)
我们可以看到Json数据都在response当中,也就是我们想要的航班信息,机票价格都是通过这个文件传送的. 我们复制这行Json数据在其他软件展开便于观察内容,(或者网页搜索:Json在线解析)
首先是航班信息:
往下有机票价格:
我们看到机票价格分了很多种类,有售价,打折的价格,我们就爬取第一个price就好了,经过观察大部分价格都是一样的
我们已经明确的要爬取的信息了, 接下来就开始抓取数据吧
先获取一天一个城市的航班信息
获取Json 信息:
import requests
import json
from fake_useragent import UserAgent
if __name__ == "__main__":
url = url = "https://flights.ctrip.com/itinerary/api/12808/products/oneway/sjw,sjw-xmn?date=2020-03-25"
# 这里的url 必须写全！！！
headers = {
"User-Agent": '{}'.format(UserAgent().random), # 构造随机请求头
"Referer": "https://flights.ctrip.com/itinerary/oneway/sjw-xmn?date=2020-03-25",
"Content-Type": "application/json"
}
request_payload = {
"flightWay": "Oneway",
"classType": "ALL",
"hasChild": False,
"hasBaby": False,
"searchIndex": 1,
"airportParams": [
{"dcity": "SJW", "acity": "XMN", "dcityname": "石家庄", "acityname": "厦门", "date": "2020-03-25", "dcityid": 428}
]
"token": 从头部获取的token,写在这里
}
# post请求
response = requests.post(url, data=json.dumps(request_payload), headers=headers).text
print(response)
Json 提取信息
# post请求
response = requests.post(url, data=json.dumps(request_payload), headers=headers, timeout=30).text
# 避免爬取过快 设置延迟
# json.dumps 将 Python 对象编码成 JSON 字符串
routeList = json.loads(response).get('data').get('routeList')
# json.loads 将已编码的 JSON 字符串解码为 Python 对象
# 依次读取每条信息
for route in routeList:
# 判断是否有信息，有时候没有会报错
if len(route.get('legs')) == 1:
legs = route.get('legs')
flight = legs[0].get('flight')
# 提取想要的信息
airlineName = flight.get('airlineName')
flightNumber = flight.get('flightNumber')
departureDate = flight.get('departureDate')
arrivalDate = flight.get('arrivalDate')
departureCityName = flight.get('departureAirportInfo').get('cityName')
departureAirportName = flight.get('departureAirportInfo').get('airportName')
arrivalCityName = flight.get('arrivalAirportInfo').get('cityName')
arrivalAirportName = flight.get('arrivalAirportInfo').get('airportName')
print(airlineName, "\t",
flightNumber, "\t",
price, "\t",
departureDate, "\t",
arrivalDate, "\t",
craftTypeName, "\t",
departureCityName, "\t",
departureAirportName, "\t",
departureterminal, "\t",
arrivalCityName, "\t",
arrivalAirportName, "\t",
arrivalterminal, )
else:
pass
然而我们只获取了一天的数据是并没有什么参考价值的,接下来我们获取未来40天的航班信息
未来40天爬取
首先我们先构造一个日期遍历的方法
def gen_dates(start_date, day_counts):
next_day = timedelta(days=1) # timedalte 是datetime中的一个对象，该对象表示两个时间的差值,day=1表示相差一天
for i in range(day_counts): # 从起始时间的现在
yield start_date + next_day * i
def get_date_list(start_date):
""":param start_date: 开始时间:return: 开始时间未来40天后的日期列表"""
if start_date < datetime.datetime.now():
start = datetime.datetime.now()
else:
start = start_date
end = start + datetime.timedelta(days=40) # 爬取未来一个月的机票
data = []
for d in gen_dates(start, ((end - start).days)):
data.append(d.strftime("%Y-%m-%d"))
return date
if __name__ == "__main__":
start_date = datetime.datetime.strptime("2020-03-25", "%Y-%m-%d") # 类型为
返回的data是一个日期列表,这样我们就能自定义起始日期,获取未来40天的航班信息!
当然,一个城市怎么够呢, 我们可以根据不同出发城市的头部获取更多的航班信息
多个城市航班信息
我们只需要把信息放在一个盒子里后面通过 format自动添加就可
cities_data = [
{"dcity": "SJW", "acity": "XMN", "dcityname": "石家庄", "acityname": "厦门", "date": "{}", "dcityid": 428, "token": "*********************"},
{"dcity": "BJS", "acity": "XMN", "dcityname": "北京", "acityname": "厦门", "date": "{}", "dcityid": 1, "token": "**********************"},
]
写入 CSV
path = "/home/liuyang/Spider/Scrapy_Project/ScrapyS/Airtickets/TO_XMN{}.csv".format(start_date)
# 创建csv文件对象
with open(path, "a+") as f:
writer = csv.writer(f, dialect="excel")
# 基于文件对象构建 csv写入对象
csv_write = csv.writer(f)
csv_data = [airlineName, flightNumber,
departureCityName, departureAirportName, departureterminal, departureDate,
arrivalDate, arrivalCityName, arrivalAirportName, arrivalterminal,
price, craftTypeName]
csv_write.writerow(csv_data)
f.close()
完整代码
import csv
import requests
import json
import datetime
from datetime import timedelta
from fake_useragent import UserAgent
def gen_dates(start_date, day_counts):
next_day = timedelta(days=1) # timedalte 是datetime中的一个对象，该对象表示两个时间的差值,day=1表示相差一天
for i in range(day_counts): # 从起始时间的现在
yield start_date + next_day * i
def get_date_list(start_date):
""":param start_date: 开始时间:return: 开始时间未来40天后的日期列表"""
if start_date < datetime.datetime.now():
start = datetime.datetime.now()
else:
start = start_date
end = start + datetime.timedelta(days=40) # 爬取未来一个月的机票
data = []
for d in gen_dates(start, ((end - start).days)):
data.append(d.strftime("%Y-%m-%d"))
return data
cities_data = [
{"dcity": "SJW", "acity": "XMN", "dcityname": "石家庄", "acityname": "厦门", "date": "{}", "dcityid": 428, "token": "********你的token令牌************"},
{"dcity": "BJS", "acity": "XMN", "dcityname": "北京", "acityname": "厦门", "date": "{}", "dcityid": 1, "token": "***********************"},
]
if __name__ == "__main__":
start_date = datetime.datetime.strptime("2020-03-25", "%Y-%m-%d") #
date_data = get_date_list(start_date)
for city_data in cities_data:
for day in date_data:
# url = "https://flights.ctrip.com/itinerary/api/12808/products/oneway/sjw,sjw-xmn?date={}".format(day)
url = "https://flights.ctrip.com/itinerary/api/12808/products/oneway/{},{}-xmn?date={}".format(city_data.get('dcity'),
city_data.get('dcity'),
day)
# 这里的url 必须写全！！！不能只写个path
headers = {
'User-Agent': '{}'.format(UserAgent().random),
'Referer': 'https://flights.ctrip.com/itinerary/oneway/{},{}-xmn?date={}'.format(city_data.get('dcity'),
city_data.get('dcity'),
day),
"Content-Type": "application/json"
}
request_payload = {
"flightWay": "Oneway",
"classType": "ALL",
"hasChild": False,
"hasBaby": False,
"searchIndex": 1,
"airportParams": [
{"dcity": "{}".format(city_data.get('dcity')),
"acity": "XMN",
"dcityname": "{}".format(city_data.get('dcityname')),
"acityname": "厦门",
"date": "{}".format(day),
"dcityid": "{}".format(city_data.get('dcityid'))}
],
"token": "{}".format(city_data.get('token'))
}
# post请求
response = requests.post(url, data=json.dumps(request_payload), headers=headers, timeout=30).text
# json.dumps 将 Python 对象编码成 JSON 字符串
routeList = json.loads(response).get('data').get('routeList') # 字典 get('key') 返回 value
# json.loads 将已编码的 JSON 字符串解码为 Python 对象
# 依次读取每条信息
for route in routeList:
# 判断是否有信息，有时候没有会报错
if len(route.get('legs')) == 1:
legs = route.get('legs')
flight = legs[0].get('flight')
# 提取想要的信息
airlineName = flight.get('airlineName')
flightNumber = flight.get('flightNumber')
craftTypeName = flight.get('craftTypeName')
departureCityName = flight.get('departureAirportInfo').get('cityName')
departureAirportName = flight.get('departureAirportInfo').get('airportName')
departureterminal = flight.get('departureAirportInfo').get('terminal').get('name')
departureDate = flight.get('departureDate')
arrivalCityName = flight.get('arrivalAirportInfo').get('cityName')
arrivalAirportName = flight.get('arrivalAirportInfo').get('airportName')
arrivalterminal = flight.get('arrivalAirportInfo').get('terminal').get('name')
arrivalDate = flight.get('arrivalDate')
cabins = legs[0].get('cabins')[0]
price = cabins.get('price').get('price')
path = "/home/liuyang/Spider/Scrapy_Project/ScrapyS/Airtickets/TO_XMN{}.csv".format(start_date)
# 创建csv文件对象
with open(path, "a+", encoding='utf-8-sig') as f:
writer = csv.writer(f, dialect="excel")
# 基于文件对象构建 csv写入对象
csv_write = csv.writer(f)
csv_data = [airlineName, flightNumber,
departureCityName, departureAirportName, departureterminal, departureDate,
arrivalDate, arrivalCityName, arrivalAirportName, arrivalterminal,
price, craftTypeName]
csv_write.writerow(csv_data)
f.close()
print(airlineName, "\t",
flightNumber, "\t",
price, "\t",
departureDate, "\t",
arrivalDate, "\t",
craftTypeName, "\t",
departureCityName, "\t",
departureAirportName, "\t",
departureterminal, "\t",
arrivalCityName, "\t",
arrivalAirportName, "\t",
arrivalterminal, )
else:
pass
结果展示
这篇关于python爬取机票信息_python Ajax异步爬取机票航班信息的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
