#python爬虫#爬取搜狐股票

完整程序

利用搜狐新闻的股票列表，构造url爬取信息

import requests
from bs4 import BeautifulSoup
import json
import csv

def getnum():
    html = requests.get("https://q.stock.sohu.com/cn/bk_3137.shtml")#获取想要的股票号码
    html.raise_for_status
    text = html.text
    soup = BeautifulSoup(text,'html.parser')
    tdL1 = soup.find_all('td',attrs={"class": "e1"})
    tdL2 = soup.find_all('td',attrs={"class": "e2"})
    numL =[]
    for td1,td2 in zip(tdL1,tdL2):
        try:
            numL.append([td1.text,td2.text])
        except:
            continue
    return numL#返回所有股票号码

def getgupiao(numL):
    for num in numL:
        try:
            url = 'https://q.stock.sohu.com/hisHq?code=cn_'+num[0]+'&stat=1&order=D&period=d&callback=historySearchHandler&rt=jsonp&0.13888967033291877'
            r = requests.get(url)
            r.raise_for_status()
            r.encoding = "gbk"
            html = r.text[21:-2]#去BOM头
            data = json.loads(html)
            datalist = data[0]['hq']
            with open(num[1]+'.csv', "w",newline='') as csvFile:#写入股票信息
                    csvWriter = csv.writer(csvFile)
                    csvWriter.writerow(['日期','开盘','收盘','涨跌额','涨跌幅	','最低','最高','成交量(手)','成交金额(万)','换手率'])
                    for data in datalist:
                        csvWriter.writerow(data)
                    csvFile.close
            print(num[1],'爬取成功')
        except:
            continue
        
        
def main():
    numL = getnum()
    getgupiao(numL)
    print("爬取完成！")
    
    
main()