import requests
from bs4 import BeautifulSoup
import re
## 获取也页面r.text
def getHTMLText(url, code="utf-8"):
try:
r = requests.get(url)
r.raise_for_status( )
r.encoding = code
return r.text
except:
return ""
## 获取所有股票编号
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
## 根据股票编号获取股票信息并存储
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'}) ## 列表
name = stockInfo.find_all(attrs={'class': 'bets-name'})[0] ## 转换为字符串
infoDict.update({'股票名称': name.text.split( )[0]}) ## 字典更新,标签文本拆分,取序号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:/BaiduStockInfo.txt'
slist = []
getStockList(slist, stock_list_url)
getStockInfo(slist, stock_info_url, output_file)
main()
python爬虫--12 股票爬虫
最新推荐文章于 2024-03-18 15:58:34 发布