定向爬取新浪股票和百度股票数据

代码:

import re

import requests
from bs4 import BeautifulSoup


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_all('div',attrs={"class":"stock-bets"})[0]
            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 = 'http://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'https://gupiao.baidu.com/stock/'
    output_file = 'F:\\stockInfo.txt'
    slist = []
    getStockList(slist,stock_list_url)
    getStockInfo(slist,stock_info_url,output_file)

main()


你可能感兴趣的:(网络爬虫)