python爬取酒店列表_python爬去酒店信息

一、代码是跟着网上一个视频教学敲的，还有一部分待优化

二、全部源码

import requests#网络请求

import re#正则

import time

import random

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

#网页真实网址

url='http://hotel.elong.com/ajax/list/asyncsearch'

header={

'Accept': 'application/json, text/javascript, */*; q=0.01',

'Accept-Encoding': 'gzip, deflate',

'Accept-Language': 'zh-CN,zh;q=0.9',

'Cache-Control': 'no-cache',

'Connection': 'keep-alive',

'Content-Length': '1599',

'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',

'Host': 'hotel.elong.com',

'Origin': 'http://hotel.elong.com',

'Pragma': 'no-cache',

'Referer': 'http://hotel.elong.com/beijing/',

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36',

'X-Requested-With': 'XMLHttpRequest'}

#提交数据

for n in range(20):

dat={

'code': '9254658',

'listRequest.areaID': '',

'listRequest.bookingChannel': '1',

'listRequest.cardNo': '192928',

'listRequest.checkInDate': '2018-06-19 00:00:00',

'listRequest.checkOutDate': '2018-06-20 00:00:00',

'listRequest.cityID': '0101',

'listRequest.cityName': '北京市',

'listRequest.customLevel': '11',

'listRequest.distance': '20',

'listRequest.endLat': '0',

'listRequest.endLng': '0',

'listRequest.facilityIds': '',

'listRequest.highPrice': '0',

'listRequest.hotelBrandIDs': '',

'listRequest.isAdvanceSave': 'false',

'listRequest.isAfterCouponPrice': 'true',

'listRequest.isCoupon': 'false',

'listRequest.isDebug': 'false',

'listRequest.isLimitTime': 'false',

'listRequest.isLogin': 'false',

'listRequest.isMobileOnly': 'true',

'listRequest.isNeed5Discount': 'true',

'listRequest.isNeedNotContractedHotel': 'false',

'listRequest.isNeedSimilarPrice': 'false',

'listRequest.isReturnNoRoomHotel': 'true',

'listRequest.isStaySave': 'false',

'listRequest.isTrace': 'false',

'listRequest.isUnionSite': 'false',

'listRequest.keywords':'',

'listRequest.keywordsType': '0',

'listRequest.language': 'cn',

'listRequest.listType': '0',

'listRequest.lowPrice': '0',

'listRequest.orderFromID': '50',#

'listRequest.pageIndex': n,

'listRequest.pageSize': '20',

'listRequest.payMethod': '0',

'listRequest.personOfRoom': '0',

'listRequest.poiId': '0',

'listRequest.promotionChannelCode': '0000',

'listRequest.proxyID': 'ZD',

'listRequest.rankType': '0',

'listRequest.returnFilterItem': 'true',

'listRequest.sellChannel': '1',

'listRequest.seoHotelStar': '0',

'listRequest.sortDirection': '1',

'listRequest.sortMethod': '1',

'listRequest.starLevels':'',

'listRequest.startLat': '0',

'listRequest.startLng': '0',

'listRequest.taRecommend': 'false',

'listRequest.themeIds':'',

'listRequest.ctripToken': 'c3502aec-c095-4f09-b122-5d5d6dfb6a8f',

'listRequest.elongToken': 'a7af9982-c0fb-4bcf-ba63-b9f70e801680'}

html=requests.post(url,data=dat,headers=header)

content=html.json()['value']['hotelListHtml']

#print(content)

hotel_pri=re.findall('n class="h_pri_num ">(.*?)

hotol_name=re.findall(' target="_blank" title="(.*?)">

data=list(map(lambda x:(hotol_name[x],hotel_pri[x]),range(20)))

data2=pd.DataFrame(data)

data2.to_csv('C:\\Users\\你若成风618\\Desktop\\aa\\1.csv',header=False,index=False,mode='a+')