爬取北京新发地蔬菜价格

最新推荐文章于 2024-08-30 00:58:42 发布

追随光、成为光

最新推荐文章于 2024-08-30 00:58:42 发布

阅读量1.1k

点赞数 2

分类专栏： Python爬虫从入门到入土文章标签： chrome safari python

本文链接：https://blog.csdn.net/Stillboring/article/details/122246817

版权

Python爬虫从入门到入土专栏收录该内容

6 篇文章

订阅专栏

北京新发地

# -*- coding:utf-8 -*-
#@Time : 2021/12/30 11:25
#@Author : dogge
#@File :test.py
#@software:PyCharm

import  requests
import  csv
class vegatable_data:

    def __init__(self):
        self.url = 'http://www.xinfadi.com.cn/getPriceData.html'
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
        }
        self.formdata = {
            'limit': '',
            'current': '',
            'pubDateStartTime': '',
            'pubDateEndTime': '',
            'prodPcatid': '',
            'prodCatid': '',
            'prodName': ''
        }
        # 使用office打开csv 需要使用utf-8-sig编码保存中文
        # 使用wps 则序使用utf-8
        file = open('蔬菜价格.csv','w',encoding='utf-8',newline='')
        self.csv_file = csv.writer(file)
        self.csv_file.writerow(['蔬菜名称','最低价格','最高价格','平均价格','产地','更新时间'])
    def parse(self,data):
        list = data['list']
        for cur in list:
            prodName = cur['prodName']
            lowPrice = cur['lowPrice']
            highPrice = cur['highPrice']
            avgPrice = cur['avgPrice']
            place = cur['place']
            pubDate = cur['pubDate']
            self.csv_file.writerow([prodName,lowPrice,highPrice,avgPrice,place,pubDate])

    def get_data(self):
        for i in range(1,11):
            print("第{}页".format(i))
            self.formdata['current']=i;
            resp = requests.post(url=self.url,data=self.formdata,headers=self.headers)
            data = resp.json()
            self.parse(data)
if __name__ == '__main__':
    v = vegatable_data()
    v.get_data()