使用python爬虫实现网络股票信息爬取的demo

Python  /  管理员 发布于 7年前   440

实例如下所示：

import requestsfrom bs4 import BeautifulSoupimport tracebackimport 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 requestsfrom bs4 import BeautifulSoupimport tracebackimport redef 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:   continuedef 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="")   continuedef 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。