使用python爬虫实现网络股票信息爬取的demo

yipeiwu_com5年前Python爬虫

实例如下所示:

import requests
from bs4 import BeautifulSoup
import traceback
import re
 
def getHTMLText(url):
 try:
  r = requests.get(url)
  r.raise_for_status()
  r.encoding = r.apparent_encoding
  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.findall(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 = 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
 
def main():
 stock_list_url = 'http://quote.eastmoney.com/stocklist.html'
 stock_info_url = 'https://gupiao.baidu.com/stock/'
 output_file = 'D:/BaiduStockInfo.txt'
 slist=[]
 getStockList(slist, stock_list_url)
 getStockInfo(slist, stock_info_url, output_file)
 
main()

优化并且加入进度条显示

import requests
from bs4 import BeautifulSoup
import traceback
import re
def getHTMLText(url, code="utf-8"):
 try:
  r = requests.get(url)
  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')
    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 = 'BaiduStockInfo.txt'
 slist = []
 getStockList(slist, stock_list_url)
 getStockInfo(slist, stock_info_url, output_file)
main()

以上这篇使用python爬虫实现网络股票信息爬取的demo就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持【听图阁-专注于Python设计】。

相关文章

Python使用Scrapy爬虫框架全站爬取图片并保存本地的实现代码

Python使用Scrapy爬虫框架全站爬取图片并保存本地的实现代码

大家可以在Github上clone全部源码。 Github:https://github.com/williamzxl/Scrapy_CrawlMeiziTu Scrapy官方文档:ht...

零基础写python爬虫之爬虫的定义及URL构成

一、网络爬虫的定义网络爬虫,即Web Spider,是一个很形象的名字。把互联网比喻成一个蜘蛛网,那么Spider就是在网上爬来爬去的蜘蛛。网络蜘蛛是通过网页的链接地址来寻找网页的。从网站...

用python爬取历史天气数据的方法示例

用python爬取历史天气数据的方法示例

某天气网站(www.数字.com)存有2011年至今的天气数据,有天看到一本爬虫教材提到了爬取这些数据的方法,学习之,并加以改进。 准备爬的历史天气 爬之前先分析url。左上有年份、...

Python实现爬虫抓取与读写、追加到excel文件操作示例

本文实例讲述了Python实现爬虫抓取与读写、追加到excel文件操作。分享给大家供大家参考,具体如下: 爬取糗事百科热门 安装 读写excel 依赖 pip install xlwt...

python爬取基于m3u8协议的ts文件并合并

前言 简单学习过网络爬虫,只是之前都是照着书上做并发,大概能理解,却还是无法自己用到自己项目中,这里自己研究实现一个网页嗅探HTML5播放控件中基于m3u8协议ts格式视频资源的项目,并...