爬取股票信息，分别在两个网站上爬取股票名称和股票数据。并组合在一起。制表打印

import requests
import re
from bs4 import BeautifulSoup as bs
import traceback

def getHTMLtext(url,code = "utf-8 "):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = "utf-8"
        return r.text
    except:
        return ""

def getstocklist(lst,stockURL): #获取上市股票的数字号码
    html = getHTMLtext(stockURL,"GB2312") 
    soup = bs(html,"lxml")
    a = soup.find_all("a") #找到a 标签
    for i in a :
        try:
            href = i.attrs["href"]
            lst.append(re.findall(r"[s][hz]\d{6}",href)[0])  #找到s开头第二个字为h或z并且带有6位数字的内容，在href属性内
            #print(lst)  
        except:
            continue



def getstockinfo(lst,stockURL,fpath):  
    count = 0
    for stock in lst:
        url = stockURL + stock + ".html" #从股票号码列表中提取出号码，拼接成每只股票信息的完整链接
        html = getHTMLtext(url) #访问每一支股票
        try:
            if html == "":    #处理异常  判断是否为空页面 
                continue
            infoDict = {}
            soup = bs(html,"lxml") #解析每一个股票的网页
            stockinfo = soup.find("div",attrs={"class":"stock-bets"}) #提取相关信息的代码块

            name = stockinfo.find_all(attrs={"class":"bets-name"})[0] #提取出股票名字
            infoDict.update({"股票名称":name.text.split()[0]}) #.update 更新字典 把新的内容加入字典 

            keylist = stockinfo.find_all("dt") #提取所有股票信息的属性
            valuelist = stockinfo.find_all("dd") # 提取出属性相对的数值
            for i in range(len(keylist)):
                key = keylist[i].text
                val = valuelist[i].text
                infoDict[key] = val   # 将信息和数值kv对，放入字典中
                                      # dict[key]=value 为字典添加新的kv对

            with open(fpath,"a",encoding="utf-8") as f:   #a是只写模式 
                f.write(str(infoDict)+ "\n")
                count = count + 1
                print("\r当前进度:{:.2f}%".format(count*100/len(lst)),end="") #跟着教程学习的，制作一个进度条
                #\r  {:.2f}%.format end="" 3个位置需要了解
        except:
            count = count + 1 #不换行滚动条　需要记住　以后使用
            print("\r当前进度:{:.2f}%".format(count * 100 / len(lst)), end="")
            pass

def main():
    stock_list_url = "http://quote.eastmoney.com/stocklist.html"
    stock_info_url = "https://gupiao.baidu.com/stock/"
    output_file = "F:\\stockinfo.txt"
    slist = []  #股票信息列表
    getstocklist(slist,stock_list_url) #获得股票列表
    getstockinfo(slist,stock_info_url,output_file) #根据股票列表 获得相关信息并且保存

main()