目标分析及描述

#CrawBaiduStocksA.py
import requests
from bs4 import BeautifulSoup
import traceback
import redef getHTMLText(url):try:r = requests.get(url)r.raise_for_status()r.encoding = r.apparent_encodingreturn r.textexcept: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:continuedef getStockInfo(lst, stockURL, fpath):for stock in lst:url = stockURL + stock + ".html"html = getHTMLText(url)try:if html=="":continueinfoDict = {}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].textval = valueList[i].textinfoDict[key] = valwith open(fpath, 'a', encoding='utf-8') as f:f.write( str(infoDict) + '\n' )except:traceback.print_exc()continuedef 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()
复制代码

优化一下：

import requests
from bs4 import BeautifulSoup
import traceback
import redef getHTMLText(url, code="utf-8"):try:r = requests.get(url)r.raise_for_status()r.encoding = codereturn r.textexcept: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 = 0for stock in lst:url = stockURL + stock + ".html"html = getHTMLText(url)try:if html=="":continueinfoDict = {}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].textval = valueList[i].textinfoDict[key] = valwith open(fpath, 'a', encoding='utf-8') as f:f.write( str(infoDict) + '\n' )count = count + 1print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")except:count = count + 1print("\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 = 'D:/BaiduStockInfo.txt'slist=[]getStockList(slist, stock_list_url)getStockInfo(slist, stock_info_url, output_file)main()复制代码