【Python爬虫】股票数据定向爬虫

逃离我推掉我的手 2023-02-25 12:27 10阅读 0赞

![format_png][]

爬取网站：

[http://quote.eastmoney.com/center/gridlist.html][http_quote.eastmoney.com_center_gridlist.html]

[https://stockapp.finance.qq.com/mstats/][https_stockapp.finance.qq.com_mstats]

![format_png 1][]

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
                infoDict = {}
                soup = BeautifulSoup(html, 'html.parser')
                stockInfo = soup.find('div',attrs={
        'class':'stock-bets'})
     
                name = stockInfo.find_all(attrs={
        'class':'bets-name'})[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
                    val = valueList[i].text
                    infoDict[key] = val
                 
                with open(fpath, 'a', encoding='utf-8') as f:
                    f.write( str(infoDict) + '\n' )
                    count = count + 1
                    print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
            except:
                count = count + 1
                print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
                continue
     
    def main():
        stock_list_url = 'https://quote.eastmoney.com/stocklist.html'
        stock_info_url = 'https://gupiao.baidu.com/stock/'
        output_file = 'D:/BaiduStockInfo.txt'
        slist=[]
        getStockList(slist, stock_list_url)
        getStockInfo(slist, stock_info_url, output_file)
     
    main()

[format_png]: /images/20230209/b10641e3c8244e5bbf496945bbb5b30e.png
[http_quote.eastmoney.com_center_gridlist.html]: http://quote.eastmoney.com/center/gridlist.html#hs_a_board
[https_stockapp.finance.qq.com_mstats]: https://stockapp.finance.qq.com/mstats/
[format_png 1]: /images/20230209/038112acf6ca4a5b95698ae45f450947.png