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
        return r.text
    except:
        return ""

def getStockList(lst, stockURL):
    html = getHTMLText(stockURL, "GB2312")
    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

def getStockInfo(lst,stockURL,fpath):
    count=0
    for stock in lst:
        url=stockURL+stock+'.html'
        html=getHTMLText(url)
        try:
            if html=='':
                continue
            soup=BeautifulSoup(html,'html.parser')
            stockInfo=soup.find('div',attrs={'class':'stock-info'})
            if stockInfo is None:
                continue
            name=stockInfo.find('a',attrs={'class':'bets-name'}).get_text().split()[0]
            stockDict={}
            stockDict.update({'名称':name})

            dt=stockInfo.find_all('dt')
            dd=stockInfo.find_all('dd')
            for i in range(len(dt)):
                stockDict[dt[i].text]=dd[i].text
            with open(fpath,'a',encoding='utf-8') as f:
                f.write(str(stockDict)+'\n')
                count=count+1
                print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
        except:
            traceback.print_exc()
            count=count+1
            print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
            continue
def main():
    stock_list_url = 'http://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'https://gupiao.baidu.com/stock/'
    output_file = 'try.txt'
    slist=[]
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)
 
main()