一个python爬虫的实例-优快云博客

本文链接：https://blog.youkuaiyun.com/Alasding/article/details/117266989

该博客展示了如何使用Python的urllib、BeautifulSoup和xlwt库从和讯网站抓取2011年12月31日的股票数据，并将数据存储到Excel文件中。爬虫通过遍历页面并解析JSON响应来获取行业排名、价格限制等信息。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import urllib
import re,xlwt
from bs4 import BeautifulSoup
import demjson
 
#爬虫函数
def gydzf():
    workbook=xlwt.Workbook()
    num=0
    worksheet=workbook.add_sheet("爬虫数据")
    for k in range(1,135):
        url="http://stockdata.stock.hexun.com/zrbg/data/zrbList.aspx?date=2011-12-31&count=20&pname=20&titType=null&page="+str(k)+"&callback=hxbase_json11621778963605"
        user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36"
        headers={"User-Agent":user_agent}
        request=urllib.request.Request(url,headers=headers)
        response=urllib.request.urlopen(request)
        contents = response.read()
        soup = BeautifulSoup(contents, "html.parser")
        t = str(soup)[13:-1] 
        data = demjson.decode(t)
        ll=[]
        ll=data["list"]
        for i in ll:
            xuhao=int(i["Number"])
            gupiao=i["industry"]
            defen=float(i['industryrate'])
            dengji=i['Pricelimit']
            gudong=float(i['stockNumber'])
            yuangong=float(i['lootingchips'])
            gongying=float(i['Scramble'])
            huanjing=float(i['rscramble'])
            shehui=float(i['Strongstock'])
            valuelist=[]
            valuelist=[xuhao,gupiao,defen,dengji,gudong,yuangong,gongying,huanjing,shehui]
            for j in range(len(valuelist)):
                worksheet.write(num,j,valuelist[j])
            num+=1
            print(num)
    workbook.save("getValue.xls")

 
#主函数
if __name__ == '__main__':
    gydzf()