python爬取股票信息

 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 = 'http://gupiao.baidu.com/stock/'
     output_file = 'D:/BaiduStockInfo.txt'
     slist = []
     getStockList(slist, stock_list_url)
     getStockInfo(slist, stock_info_url, output_file)

 main()

这是慕课上的源代码，直接粘贴的，不知道为什么运行一直报错。以下是错误。如果有人解决了，麻烦说一声，谢谢啦。

下面是慕课中修改的代码，也是源代码，直接粘贴的，但是是可以运行出来的。

 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 = 'http://gupiao.baidu.com/stock/'
     output_file = 'D:/BaiduStockInfo.txt'
     slist=[]
     getStockList(slist, stock_list_url)
     getStockInfo(slist, stock_info_url, output_file)

 main()

至于为什么，本人也不是特别清楚，代码主题部分是一样的，具体原因不清楚。我把编码方式删去了，和原先一样。但是程序依然可以运行。我不知道为什么，加了进度条，程序就可以运行了。

这是别人的代码分析 ，个人觉得还是很好的，很仔细：https://segmentfault.com/a/1190000010520835