美团app人气榜套餐排名数据 1.0版本上线

最新推荐文章于 2022-11-03 19:58:48 发布

原创最新推荐文章于 2022-11-03 19:58:48 发布 · 987 阅读

CC 4.0 BY-SA版权

本文介绍了一款用于抓取美团网站上美食销售排行榜详细数据的Python爬虫程序。该程序能够获取包括店铺ID、名称、周销量等在内的多项关键信息，并将其保存为CSV文件。


# -*- coding:utf-8 -*-
# 仅需修改这个地方https://jn.lianjia.com/ershoufang/pg{}rs/   将jn换成你所在城市的拼写首字母小写
import requests
from lxml import etree
import time
import random
import csv
import requests
import json



class LianjiaSpider(object):
    def __init__(self):
        self.url = "https://mobilenext-web.meituan.com/api/newSalesBoard/getSaleBoardDetail?cityId=96&boardType=9&districtId=0&cateId={}&offset=0&limit=15&lat=36.526046191159445&lng=122.062217811"

        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1"}

    def get_page(self, url):
        res = requests.get(url=url, headers=self.headers)
        res.encoding = "utf-8"
        html = res.text
        print(html)



      #  results_temp = html.replace('{"totalSize":50,"saleBoardDealList":', "").replace("}}]}", "")
        #results = results_temp + "}}]"
      #  print(results)




        self.parse_page(html)
       #print(html)
       # print(i)
    def parse_page(self,html):
      #  results_temp = html.replace('{"totalSize":50,"saleBoardDealList":', "").replace("}}]}", "")
        #results = results_temp + "}}]"
        results = html[36:-1]

        print(results)
        for list in json.loads(results):

            print(list)
            id = list["id"]
            name = list["name"]
            weekSaleCount = list["weekSaleCount"]
            frontImg = list["frontImg"]
            dishes = list["dishes"]
            price = list["price"]
            value = list["value"]
            discount = list["discount"]
            recommendDish = list["recommendDish"]
            rank = list["rank"]
            saleBoardDealPoi = list["saleBoardDealPoi"]
            saleBoardDealPoi_name = list["saleBoardDealPoi"]["name"]
            with open('meituan.csv', 'a', newline='', encoding='utf-8')as f:
                write = csv.writer(f)
                write.writerow([id,name,weekSaleCount,frontImg,dishes,price,value,discount,recommendDish,rank,saleBoardDealPoi,saleBoardDealPoi_name])
                f.close()





    def main(self):
        for i in range(1, 14):
            time.sleep(random.randint(3, 5))
            url = self.url.format(i)
            print(url)
            self.get_page(url)
           # print(j)



if __name__ == '__main__':
    start = time.time()
    spider = LianjiaSpider()
    spider.main()
    end = time.time()
    print("执行时间：%.2f" % (end - start))