|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
- # -*- coding: utf-8 -*-
- import requests
- from bs4 import BeautifulSoup
- import traceback
- import re
- def getHTMLText(url, code= 'utf-8'):
- try:
- r = requests.get(url, timeout = 30)
- 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')#解析页面
- a = soup.find_all('a')#找到<a>标签里面的信息
- for i in a :
- try:
- href = i.attrs['href']
- lst.append(re.findall(r"[s][hz]\d{6}", href)[0]) # 找到股票代码
- except:
- continue
- def getStockInfo(lst, stockURL, fpath):
- count = 0
- for stock in lst:
- url = stockURL + stock + ".html"#得到每个股票的链接
- html = getHTMLText(url)
- try:
- if html == "":
- continue
- infoDict = {}
- soup = BeautifulSoup(html, 'html.parser')#对相应的股票页面解析
- stockInfo = soup.find('div', attrs = {'class':'stock-bets'})
-
- name = stockInfo.find_all(attrs = {'class':'bets-name'})[0]#获得股票代码的名称
- infoDict.update({'股票名称':name.text.split()[0]})#加入字典中
-
- 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当前速度:{:.2f}%".format(count*100/len(lst)), end ="")
- except:
- count = count + 1
- print("\r当前速度:{:.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 = 'G://anaconda_project/爬虫/baiduStockInfo.txt'
- sList = []
- getStockList(sList, stock_list_url)
- getStockInfo(sList, stock_info_url, output_file)
-
- main()
复制代码 |
-
|