爬虫爬取股票数据

 1 import requests
 2 from bs4 import BeautifulSoup
 3 import traceback
 4 import re
 5 import bs4
 6 
 7 def getHTMLText(url,code=‘utf-8‘): #使用code提高解析效率
 8     try:
 9         r = requests.get(url)
10         r.raise_for_status()
11         r.encoding = code
12         return r.text
13     except:
14         return ‘爬取失败‘
15      
16 def getStockList(lst,stockURL):
17     html = getHTMLText(stockURL,‘GB2312‘)
18     soup = BeautifulSoup(html,‘html.parser‘)
19     a = soup.find_all(‘a‘)
20     for i in a :
21         try:
22             href = i.attrs[‘href‘]
23             #以s开头，中间是h或z，后面再接六位数字
24             lst.append(re.findall(r‘[s][hz]\d{6}‘,href)[0])
25         except:
26             continue
27     
28 def getStockInfo(lst,stockURL,fpath):
29     count = 0
30     for stock in lst:
31         url = stockURL + stock +‘.html‘
32         html = getHTMLText(url)
33         try:
34             if html == "":
35                 continue
36             infoDict = {}
37             soup = BeautifulSoup(html,‘html.parser‘)
38             stockInfo = soup.find(‘div‘,attrs={‘class‘:‘stock-bets‘}            
39             if isinstance(stockInfo,bs4.element.Tag)：
40                 name = stockInfo.find_all(attrs={‘class‘:‘bets-name‘})[0]
41                 infoDict.update({‘股票名称‘:name.text.split()[0]})
42                 keyList = stockInfo.find_all(‘dt‘)
43                 valueList = stockInfo.find_all(‘dd‘)
44                 for i in range(len(keyList)):
45                     key = keyList[i].text
46                     val = valueList[i].text
47                     infoDict[key] = val
48                 with open(fpath,‘a‘,encoding=‘utf-8‘) as f:
49                     f.write(str(infoDict) + ‘\n‘)
50                     count += 1
51                     print(‘\r当前速度:{:.2f}%‘.format(count*100/len(lst)),end=‘‘)
52                     #打印爬取进度
53         except:
54             print(‘\r当前速度:{:.2f}%‘.format(count*100/len(lst)),end=‘‘)
55             traceback.print_exc()
56             continue
57         
58 def main():
59     stock_list_url = ‘http://quote.eastmoney.com/stocklist.html‘
60     stock_info_url = ‘http://gupiao.baidu.com/stock/‘ 
61     output_file = ‘C:/Users/Administrator/Desktop/Python网络爬虫与信息提取/BaiduStockInfo.txt‘
62     slist = []
63     getStockList(slist,stock_list_url)
64     getStockInfo(slist,stock_info_url,output_file)
65 
66 main()