#该程序先从东方财富网爬取股票列表 然后在从百度股票的找出对应股票的信息
import requests
from bs4 import BeautifulSoup
import traceback
import re
def getHTMLText(url, code="utf-8"):
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = code#直接告诉编码类型 加快程序速度
return r.text
except:
return ""
def getStockList(lst, stockURL):
html = getHTMLText(stockURL, "GB2312")#告诉编码类型 加快程序速度
soup = BeautifulSoup(html, 'html.parser')
a = soup.find_all('a')#找出所有a标签
for i in a:
try:
href = i.attrs['href']#把a标签中所有href 存到数组href中
lst.append(re.findall(r"[s][hz]\d{6}", href)[0])#用正则表达式提取href中股票编号 存到lst中
except:
continue
def getStockInfo(lst, stockURL, fpath):
count = 0#计数
for stock in lst:
url = stockURL + stock + ".html"#每一只股票的html页面
html = getHTMLText(url)
try:
if html=="":#页面为空 继续爬取其他
continue
infoDict = {}
soup = BeautifulSoup(html, 'html.parser')#解析html
stockInfo = soup.find('div',attrs={'class':'stock-bets'})#找出div 标签中属性为stock-bets的
name = stockInfo.find_all(attrs={'class':'bets-name'})[0]#找出所有属性为 bets-name 并存到name列表中
infoDict.update({'股票名称': name.text.split()[0]})#lst 填入 name中空格前的内容（真正的name）
keyList = stockInfo.find_all('dt')#找出与股票相关的键值对列表
valueList = stockInfo.find_all('dd')
for i in range(len(keyList)):
key = keyList[i].text#还原成键
val = valueList[i].text#还原值
infoDict[key] = val #向字典中新增内容
with open(fpath, 'a', encoding='utf-8') as f:#保存到文件中
f.write( str(infoDict) + '\n' )
count = count + 1
print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")#进度条
except:
count = count + 1
print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
traceback.print_exc()#获得错误信息
continue
def main():
stock_list_url = 'http://quote.eastmoney.com/stocklist.html'
stock_info_url = 'https://gupiao.baidu.com/stock/'
output_file = 'D:/BaiduStockInfo1.txt'
slist=[]
getStockList(slist, stock_list_url)
getStockInfo(slist, stock_info_url, output_file)
main()
