mt包括空值和totalsize为个位数的数值，缺少全部城市

最新推荐文章于 2023-11-23 08:57:34 发布

原创最新推荐文章于 2023-11-23 08:57:34 发布 · 185 阅读

CC 4.0 BY-SA版权

该博客内容展示了如何使用Python的requests和lxml库从美团网站抓取二手房产信息。程序通过修改URL获取不同城市和分类的数据，解析JSON响应并存储关键信息（如ID、名称、周销量等）到CSV文件中。



# -*- 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={}&boardType=8&districtId=0&cateId={}&offset=0&limit=50"

        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,i,j):
        print(url)
        res = requests.get(url=url, headers=self.headers)
        res.encoding = "utf-8"
        html = res.text
      #  if(html == '{"totalSize":0,"saleBoardPoiList":[],"boardDigest":null}'):
    #        html ={"totalSize":50,"saleBoardPoiList":[{"id":0,"name":"","weekSaleCount":"周销量 0","score":0,"avgPrice":0,"cateName":"","areaName":"","distance":"","rank":0,"frontImg":"https://img.meituan.net/msmerchant/","oneSentence":"","saleBoardPoiGroup":null,"saleBoardPoiCoupon":{"icon":"https://p0.meituan.net/travelcube/","content":""},"saleBoardPoiPay":null,"branchList":null}],"boardDigest":null}



       # print(i)
        # print(html)

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

        self.parse_page(html,i,j)

    # print(html)
    # print(i)
    def parse_page(self, html,i,j):

        results = html[35:-20]
       # print(len(results))
        print(results)
      #  print(results.find("["))
        if (results.find("[") == -1):
            prefix = "["
            results =  prefix + results
            print(results)
            print(len(results))


        for list in json.loads(results):
            print(list)
            id = list["id"]
            print(id)
            name = list["name"]
            print(name)
            weekSaleCount = list["weekSaleCount"]
            score = list["score"]
            avgPrice = list["avgPrice"]
            cateName = list["cateName"]
            areaName = list["areaName"]
            distance = list["distance"]
            rank = list["rank"]
            frontImg = list["frontImg"]
            oneSentence = list["oneSentence"]
            with open('meituan.csv', 'a', newline='', encoding='utf-8')as f:
                write = csv.writer(f)
                write.writerow(
                    [ name, weekSaleCount, score, avgPrice, cateName, areaName, distance, rank, frontImg,
                     oneSentence])



    def main(self):
        #20广州、香港118，165白山，170鹤岗
        cityId_lists = [1,10,20,118,165,178]
        for i in cityId_lists:  # 第二个实例

          #  print(i)
            for j in range(1, 2):
           #     print(j)
                time.sleep(random.randint(3, 5))
                url = self.url.format(i,j)
            #  print(url)
                self.get_page(url,i,j)
        # print(j)


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