美团人气榜

# -*- 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/rankingList/getSaleBoardList?cityId={}&boardType={}&cateId=10000&limit=10"
        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
        self.parse_page(html, i, j)

    def parse_page(self, html, i, j):
        results = html[71:-43]
        print(results)
        #  print(results.find("["))
        if (results.find("[") != 0):
            prefix = "["
            results = prefix + results


        for list in json.loads(results):
            id = list["id"]

            if (i == 20):  cityId = "广州"
            if (i == 57):  cityId = "武汉"


            if (j == 1):
                catId = "火锅"
            elif (j == 2):
                catId = "自助餐"

            with open('meituan.csv', 'a', newline='', encoding='utf-8') as f:
                write = csv.writer(f)
                write.writerow(
                    [cityId, catId, id])


    def main(self):
        cityId_lists = [20, 50]
        for i in cityId_lists:  # 第二个实例
            for j in range(1, 9):
                time.sleep(random.randint(3, 5))
                url = self.url.format(i, j)
                self.get_page(url, i, j)


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