使用python爬蟲實現(xiàn)網(wǎng)絡股票信息爬取的demo

更新時間：2018年01月05日 14:12:00 作者：OliverkingLi

下面小編就為大家分享一篇使用python爬蟲實現(xiàn)網(wǎng)絡股票信息爬取的demo，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧

實例如下所示：

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({'股票名稱': 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()

優(yōu)化并且加入進度條顯示

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({'股票名稱': 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當前進度: {:.2f}%".format(count * 100 / len(lst)), end="")
  except:
   count = count + 1
   print("\r當前進度: {:.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()