通过python爬取美团上沈阳酒店相关信息(含经纬度)

# -*- coding: utf-8 -*
import requests
import pymysql
from bs4 import BeautifulSoup
import json
import  psycopg2

def img_cover(url):
    req_header = {
        'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
    }
    response = requests.get(url,headers=req_header)
    res_dict = response.json()
    print(res_dict['data']['searchresult'])
    for  i in res_dict['data']['searchresult']:
        name=i['name']
        addr=i['addr']
        hotelstar=i['hotelStar']
        poiattrtaglist= ",".join(i['poiAttrTagList'])
        areaname=i['areaName']
        poiextendsinfosdesc=",".join(i['forward']['poiExtendsInfosDesc'])
        scoreinfo=i['forward']['scoreInfo']
        lat=i['lat']
        lng=i['lng']
        poirecommendtag = i['poiRecommendTag']
        originaltrice = i['originalPrice']
        db = psycopg2.connect(database="postgis", user="postgres", password="postgres", host="127.0.0.1", port="5432")
        print("已连接")
        # 使用 cursor() 方法创建一个游标对象 cursor
        cursor = db.cursor()
        sql = "insert into meituan_hotel (name,addr,hotelstar,poiattrtaglist,areaname,poiextendsinfosdesc,scoreinfo,lat,lng,poirecommendtag,originaltrice) values (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)"
        params = (name,addr,hotelstar,poiattrtaglist,areaname,poiextendsinfosdesc,scoreinfo,lat,lng,poirecommendtag,originaltrice)
        # 使用 execute()  方法执行 SQL 查询
        cursor.execute(sql,params)
        db.commit()
    print("已完成采集")
    db.close()

for i in range(1,52):
    j=20*i
    print(j)
    url = "https://ihotel.meituan.com/hbsearch/HotelSearch?utm_medium=pc&version_name=999.9&cateId=20&attr_28=129&uuid=6381C18DBC0D4CC4CCB68B5D3C1F5E7F28CCFDD30CD821AF556901879383F06E%401546569217582&cityId=66&offset={}&limit=20&startDay=20190104&endDay=20190104&q=&sort=defaults&X-FOR-WITH=XTq9L1SuHO3vg%2FQXCDEN92pN9bY0CnssexIACcrq%2FDsu%2BFC%2Bu73P0lwmv%2FnxR9qqJf5e7wxNQEQI9GfrtqbjytccvP7nZYyHB1lcd4xzLVVoqTU%2B%2Fw%2FwdNC6JdpKbivTHY6nJJaz38i1AA8NZ63rJg%3D%3D".format(j)
    img_cover(url)

最终结果:

发布了48 篇原创文章 · 获赞 24 · 访问量 4万+

猜你喜欢

转载自blog.csdn.net/xlp789/article/details/85782645