想要爬取股票信息,新手不熟悉,希望能有大神给出解决方法!!急
# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
import re
import traceback
import bs4
import sys
import time
reload(sys)
sys.setdefaultencoding('utf-8')
def getHTMLText(url,code='utf-8'):
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = code
return r.text
except:
return ""
def SetFileName():
dirname = time.strftime ( '%Y%m%d' , time.localtime ( time.time () ) ) #获取当前日期
dirname += 'sh'
return dirname
def getStockList(lst,stockURL):
# html = getHTMLText(stockURL,'GB2312')
html = getHTMLText(stockURL, 'utf-8')
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'})
if isinstance(stockInfo,bs4.element.Tag):
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(r'D:lps.txt', 'w') as f:
# f.write(str(infoDict) + '\n')
# print(str(infoDict) + '\n')
f.write(key + str(val))
print(key +str(val))
f.close()
except:
count = count + 1
traceback.print_exc()
continue
def main():
stock_list_url = 'http://quote.eastmoney.com/stocklist.html'
stock_info_url = 'https://gupiao.baidu.com/stock/'
output_file = 'D://lps.txt'
slist = []
getStockList(slist,stock_list_url)
getStockInfo(slist,stock_info_url,output_file)
main()
结果如图