首先感谢一下 飞友网提供的网站数据
大神们有其他获取航班的渠道可以告诉我。我想要本地数据库使用。
功能:
爬所有航班信息保存到本地文件。保存格式参考12306的
下面还需要做的。
解析 中途经停的航班。和班次起飞日期(根据星期1234567计算)。
#coding:utf-8
__author__ = 'watsy'
from sgmllib import SGMLParser
import urllib
import urllib2
import datetime
import json
import os
from time import sleep
import time
import sys
import urlparse
class flightCityObject(object):
def __init__(self, name="", url="", leaveurl = ""):
self.name = name
self.url = url
self.leaveurl = leaveurl
class flightAirObject(object):
def __init__(self, air_code = "", start_place = "", start_time = "", end_place = "", end_time = "", air_type = "",flightWeekend = "", hasCenterPlace = "" ,hasFood = "", zhundian = ""):
self.air_code = air_code
self.start_place = start_place
self.start_time = start_time
self.end_place = end_place
self.end_time = end_time
self.air_type = air_type
self.flightWeekend = flightWeekend
self.hasFood = hasFood
self.zhundianlv = zhundian
self.needQuery = False
#需要查询具体信息
if hasCenterPlace != '-':
self.needQuery = True
if flightWeekend.find('.') != -1:
self.needQuery &