爬取并展示股票信息

最新推荐文章于 2024-08-02 09:56:06 发布

火柴林

最新推荐文章于 2024-08-02 09:56:06 发布

阅读量186

点赞数

分类专栏：爬虫

本文链接：https://blog.csdn.net/lin252931/article/details/105524313

版权

爬虫专栏收录该内容

3 篇文章 0 订阅

订阅专栏

要点： 1 写入headers
2 展示进展

 count = count + 1
 print("\r当前进度: {:.2f}%".format(count*100/len(gupiaoList)),end="")

全部程序如下

import re
from bs4 import BeautifulSoup
import requests

def getHTMLText(url):
    try:
        headers={
            "user-agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36",
            }
        r=requests.get(url, headers=headers)
        r.raise_for_status
        r.encoding=r.apparent_encoding
        #print(r.text)
        return r.text
                
    except:
        print('')
    

def getStockList(gupiaoList,html):    
    soup=BeautifulSoup(html,"html.parser")
    #print(soup)
    lis=soup.find("div",class_='quotebody')
    namelis=lis.find_all("a")
    for li in namelis:
        if li.has_attr("target") and li["target"]=="_blank":
            #li["href"]
            #print(li)
            #print(li["href"])
            stock_name=re.search(r'(sz|sh)\d{6}',str(li))
            gupiaoList.append(stock_name.group(0))
    #(gupiaoList)
    
    
def getStockPrick(gupiaoList,name_priceList):
    count=1
    for url_last in gupiaoList:        
            url="https://xueqiu.com/S/"+url_last
            html=getHTMLText(url)
            try:
                soup=BeautifulSoup(html,"html.parser")
                divli=soup.find("div",class_="stock-current")
                nameli=soup.find('div',class_='stock-name')                
                price=divli.string
                name=nameli.string
                name_priceList.append([name,price])
                
                if count>=10:
                    break
                
                with open('D:/BaiduStockInfo.txt', 'a', encoding='utf-8') as f:
                    f.write( str([name,price]) + '\n' )
                    count = count + 1
                    print("\r当前进度: {:.2f}%".format(count*100/len(gupiaoList)),end="")
                
            except:
                count = count + 1
                print("\r当前进度: {:.2f}%".format(count*100/len(gupiaoList)),end="")
                continue
    print(name_priceList)
                
list_url="http://quote.eastmoney.com/stock_list.html"
list_html=getHTMLText(list_url)
gupiaoList=[]
name_priceList=[]
getStockList(gupiaoList,list_html)
getStockPrick(gupiaoList,name_priceList)