Python爬虫---爬取股票信息
程序员文章站
2022-05-14 21:22:25
...
最近开了个股票账户,爬取一下300和600开头的股票信息,来筛选股票
仅仅爬取信息,不做排序和分析
包含的库
import requests
from bs4 import BeautifulSoup
import traceback
import re
获取网页源码信息
def getHTMLText(url, code="utf-8"):
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = code
return r.text
except:
return ""
所有股票中选择300或者600开头的股票加入列表
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][36]\d{5}", href)[0])
except:
continue
获得股票的详细信息
这里选择了股票公司的总市值、净资产、净利润、市盈率、市净率、毛利率、净利率和ROE进行爬取,并保存到文件中
def getStockInfo(lst, stockURL, fpath):
Listtitle=['名称','总市值','净资产','净利润','市盈率','市净率','毛利率','净利率','ROE']
with open(fpath,'w',encoding='utf-8') as f:
for i in range(len(Listtitle)):
f.write("{0:<10}\t".format(Listtitle[i],chr(12288)))
count = 0
for stock in lst:
url = stockURL + stock + ".html"
html = getHTMLText(url,"GB2312")
try:
if html=="":
continue
List=[]
soup = BeautifulSoup(html, 'html.parser')
stock = soup.find('div',attrs={'class':'cwzb'}).find_all('tbody')[0]
name=stock.find_all('b')[0]
List.append(name.text)
keyList = stock.find_all('td')[1:9]
for i in range(len(keyList)):
List.append(keyList[i].text)
with open(fpath,'a',encoding='utf-8') as f:
f.write('\n')
for i in range(len(List)):
f.write('{0:<10}\t'.format(List[i],chr(12288)))
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
主函数调用
def main():
stock_list_url = 'http://quote.eastmoney.com/stocklist.html'
stock_info_url = 'http://quote.eastmoney.com/'
output_file = './Stock.txt'
slist=[]
getStockList(slist, stock_list_url)
getStockInfo(slist, stock_info_url, output_file)