中国大学mooc网络爬虫嵩天老师——股票信息爬取

import requests
from bs4 import BeautifulSoup
import re
import traceback

def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print('Error!')

def getStockList(lst, stockURL):
    html = getHTMLText(stockURL)
    soup = BeautifulSoup(html, 'html.parser')
    a = soup.find_all('a')
    for i in a:
        try:
            href = i.attrs['href']  # 通过<tag>.attr[]找到a标签下的href属性的值；html中有2个href都含有链接，即查找出两个股票代码，所以用[0]
            string = re.findall(r'[s][h]\d{6}', href)[