金融界网站股票信息爬取，输入日期，对金融界页面股票股票进行爬取并存储进数据库

import requests from bs4 import BeautifulSoup import bs4 import re import urllib.request,urllib.error import requests import json import peewee from peewee import* import datetime def main(): a=input("请输入查询日期：") baseurl = "http://homeflashdata2.jrj.com.cn/limitStatistic/ztForce/"+a+".js" #1.爬取网页 datalist = getData(baseurl) savedata(datalist) def getData(baseurl): html = askURL(baseurl) html=re.sub('\s+','',html).strip() sear_html=re.search('.*?"Data":(.*?)};',html) data=json.loads(sear_html.group(1)) return data def askURL(url): head = { "User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36" } request = urllib.request.Request(url,headers=head) try: response = urllib.request.urlopen(request) html = response.read().decode("gbk") except Exception as e: print(e) return html def savedata(data): db = MySQLDatabase('stock', host='127.0.0.1', user='用户名', passwd='密码') db.connect() class BaseModel(Model): class Meta: database = db # 每一个继承BaseModel类的子类都是连接db表 class Stock(BaseModel): code = CharField() name = CharField() newprice = CharField() updown = CharField() price = CharField() time = CharField() Stock.create_table() i = 0 length = len(data) while i < length: Stock.create(code=data[i][0], name=data[i][1], newprice=data[i][2], updown=data[i][3], price=data[i][6],time=data[i][7],getTime=) i += 1 if __name__ == "__main__": # 当程序执行时 # 调用函数 main()