python爬虫由浅入深9---定向爬取股票数据信息并保存至本地文件

技术路线：requests库+bs4库+re库的整合使用

目标：获得上交所和深交所所有股票的名称和交易信息

输出：保存至本地文件

可选数据网络有：新浪股票和百度股票，，通过查看网页源代码可知，新浪股票的数据是通过javascript脚本获取的，故通过以上方式无法解析

呃呃呃，可以说requests库+bs4库+re库可以爬的网站应该是---信息静态存在于HTML页面中，非js代码生成，没有Robots协议限制

所以最终确定了数据源为：东方财富网+百度股票

东方财富网：


百度股票：



程序结构设计：

1.从东方财富网中获取股票列表

2.根据股票列表逐个到百度股票获取个股信息

3.将结果存至文件

封装函数，编写代码

import requests
from bs4 import BeautifulSoup
import traceback
import re

def getHTMLText(url,code='utf-8'):
try:
r = requests.get(url,timeout = 30)
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('div',attrs={'class':'stock-bets'})

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')

except:
traceback.print_exc()
continue

return ""

def main():
stock_list_url = 'http://quote.eastmoney.com/stocklist.html'
stock_info_url = 'https://gupiao.baidu.com/stock/'
output_file = 'C://Users//kfc//Desktop//BaiduStockInfo.txt'
slist = []
getStockList(slist,stock_list_url)
getStockInfo(slist,stock_info_url,output_file)

main()