python爬取酒店信息_python 爬虫 booking爬取酒店信息

import requests

from bs4 import BeautifulSoup as bs

import re

import time

import pandas as pd

headers ={"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36",

"Cookie":"设置好地区 货币等信息后的cookie"}

url_list=["用列表 好让爬虫自动遍历列表翻页。这里输入的url是在页面上选好地区 货币等信息后的url 这点一定注意！"]

info =[]

for ii in url_list:

time.sleep(2)

response = requests.get(ii,headers=headers)

#print(response.text)

#提取单个酒店信息代码块

soup = bs(response.text,"lxml")

hotle_info = soup.select("#hotellist_inner div.sr_item_content.sr_item_content_slider_wrapper")

#print(len(hotle_info))

#print(hotle_info)

#提取下一页链接

try:

next_page = soup.select("#search_results_table di