股票数据定向爬虫.py（亲测有效）

import requests
from bs4 import BeautifulSoup
import traceback
import re

def getHTMLText(url,code='utf-8'):
    try:
        r = requests.get(url,timeout=30)
        r.encoding = code
        return r.text
    except:
        return ""

def getStockList(lst,stockURL):
    html = getHTMLText(stockURL)
    soup = BeautifulSoup(html,'html.parser')
    a = soup.find_all('tr')
    for i in a:
        try:
            href = i.attrs['id']
            lst.append(re.findall(r'[tr]d{6}',href)[0])
        except:
            continue

def getStockInfo(lst,stockURL,fpath):
    count = 0
    for stock in lst:
        url = stockURL + stock[1:] +".html"
        html = getHTMLText(url)
        try:
            if html == "":
                continue
            infoDict = {}
            soup = BeautifulSoup(html,'html.parser')
            stockInfo = soup.find('div',attrs={'class':'merchandiseDetail'})
            name = stockInfo.find_all(attrs={'class':'fundDetail-tit'})[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
                print(key)
                val = valuelist[i].text
                infoDict[key] = val
            with open(fpath,'a',encoding='utf-8')as f:
                f.write(str(infoDict)+'
')
                count = count+1
                print('
当前速度：{:.2f}%'.format(count*100/len(lst)),end='')

        except:
            count = count + 1
            print('
当前速度：{:.2f}%'.format(count * 100 / len(lst)), end='')
            traceback.print_exc()
            continue

def main():
    stock_list_url = 'https://fund.eastmoney.com/fund.html#os_0;isall_0;ft_;pt_1'
    stock_info_url = 'https://fund.eastmoney.com/'
    output_file = 'D://桌面//BaiduStockInfo.txt'
    slist = []
    getStockList(slist,stock_list_url)
    getStockInfo(slist,stock_info_url,output_file)

main()