爬虫练习（四）

利用requests + bs4 + re库进行股票数据定向爬虫

import requests
from bs4 import BeautifulSoup
import traceback
import re

#得到东方财富网的页面源代码
def getHTMLText(url, code = 'utf-8'):
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        r.encoding = code
        return r.text
    except:
        return ""


#从东方财富网的源代码中提取出每支股票信息列表
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']
            lst.append(re.findall(r"[s][hz]\d{6}", href)[0])
        except:
            continue
        
    
#利用提取的每支股票信息去百度股票网中找到其对应的位置下载并保存其信息
#此处增加了进度条显示爬取进度
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当前速度: {:/2f}%'.format(count*100/len(lst)), end='')
        except:
            traceback.print_exc()
            continue         

def main():
    stock_list_url = 'http://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'http://gupiao.baidu.com/stock/'
    output_file = 'D://BaiduStockInfo.txt'
    slist = []
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)



if __name__ == "__main__":
    main()

经验总结：

1.学会了爬虫爬取过程中动态不换行进度条的显示效果

2.多层网页嵌套爬虫