【python爬虫学习笔记】07 股票数据定向爬虫实例

功能描述

目标:获取上交所和深交所所有股票的名称和交易信息
输出:保存到文件中
技术路线：requests-bs4-re

候选数据网站的选择

新浪股票:http://finance.sina.com.cn/stock/
百度股票:http://gupiao.baidu.com/stock/
东方财富网:http://quote.eastmoney.com/stocklist.html

1. 选取原则:
   股票信息静态存在于HTML页面中，非js代码生成，没有Robots协议限制

2. 选取方法:
   浏览器F12，源代码查看等

程序的结构设计

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')
    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
            #字典形式
            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
            #以追加的方式打开文件
            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

if __name__ == '__main__':
    stock_list_url = 'http://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'http://gupiao.baidu.com/stock/'
    output_file = 'E://BaiduStockInfo.txt'
    slist = []
    getStockList(slist,stock_list_url)
    getStockInfo(slist,stock_info_url,output_file)