一、项目介绍
目标:获取上交所和深交所所有股票的名称和交易信息,保存到文件中
技术路线:使用requests-bs4-re
网站选择:没有robots协议限制;股票信息静态存在于HTML页面中,非JS代码生成
结构设计:
- 从东方财富网获取股票列表
- 根据股票列表逐个到百度股票获取个股信息
- 将结果存在文件中
二、获取解析
通过查看源码的方式定位到需要的字段
三、源码
#(未测试)
import requests
import re
from bs4 import BeautifulSoup
import traceback
def getHTMLText(url):
try:
r = requests.get(url, timeout = 30)
r.raise_for_status()
r.encoding = r.apparent_encoding #防止中文乱码
#print(r.text)
return r.text
except:
return ""
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.find_all(r"[s][hz]\d{6}", href)[0]))
except:
continue
def getStockInfo(lst, stockURL, fpath):
for stock in lst:
url = stockURL + stock + ".html"
html = getHTMLText(url)
try:
if html == "":
continue
infoDict = {}
soup = BeautifulSoup(html, 'html.parser')
stockInfo = sou.find('div', attra={'class':'stock-bets'})
name = stockInfo.find_all(attrs={'class':'bets-name'})[0]
infoDict.update({'股票名称': name.text.split()[0]})
keyList = stocInfo.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
def main():
stoc_list_url = 'http://quote.eastmoney.com/stocklist.html'
stoc_info_url = 'https://gupiao.baidu.com/stock/'
ouput_file = 'D://test.txt'
slist = []
getStockList(slist, stock_list_url)
getStockInfo(slist, stoc_info_url, ouput_file)
main()