python利用re,bs4,requests模块获取股票数据

今天闲来无聊无意间看到了百度股票，就想着用python爬一下数据，于是就找到了东方财经网，结合这两个网站，写了一个小爬虫，数据保存在文件中，比较简单的示例，就当做用来练习正则表达式和BeautifulSoupl了。

首先页面分析，打开东方财经网股票列表页，

和百度股票详情页 ，右键查看网页源代码，

网址后面的代码就是股票代码，所以打算先获取股票代码，然后获取详情，废话少说，直接上代码吧：

import re
import requests
from bs4 import BeautifulSoup

#获取html
def getHtml(url):
try:
req=requests.get(url)
req.raise_for_status()
req.encoding=req.apparent_encoding
return req.text
except :
print('getHtml失败')

#获取股票代码
def getStockList(lst,stockUrl):
html=getHtml(stockUrl)
soup=BeautifulSoup(html,'html.parser')
a=soup.find_all('a')
for i in a:
try:
href=i.attrs['href']
lst.append(re.findall(r'[s][hz]\d{6}',href)[0])
except:
continue

#获取股票详情
def getStockInfo(lst,stockUrl,fpath):
count=0
for stock in lst:
url=stockUrl+stock+'.html'
html=getHtml(url)
try:
if html=='':
continue
infoDict={}
soup=BeautifulSoup(html,'html.parser')
stockInfo=soup.find('div',attrs={'class':'stock-bets'})
name=stockInfo.find_all(attrs={'class':'bets-name'})[0]
infoDict.update({'股票名称':name.text.split()[0]})
keyList=stockInfo.find_all('dt')
valueList=stockInfo.find_all('dd')
for i in range(len(keyList)):
key=keyList[i].text
val=valueList[i].text
infoDict[key]=val
with open(fpath,'a',encoding='utf-8') as f:
f.write(str(infoDict)+'\n')
count+=1
print('\r当前速度：{:.2f}％'.format(count*100/len(lst)),end='')
except:
count+=1
print('\r当前速度e：{:.2f}％'.format(count*100/len(lst)),end='')
continue

def main():
stockListUrl='http://quote.eastmoney.com/stocklist.html'
stockInfotUrl='https://gupiao.baidu.com/stock/'
outPutFile='D:\python\shuju\stockInfo.txt'
slist=[]
getStockList(slist,stockListUrl)
getStockInfo(slist,stockInfotUrl,outPutFile)

main()

来源：https://baagee.vip/index/article/id/85.html