requests+BeautifulSoup爬取双色球历史数据

#练习02：2014-11-01
#http://baidu.lecai.com/lottery/draw/list/50
#需求是获取http://baidu.lecai.com/lottery/draw/list/50 彩票网站上面开设双色球以来每一期的开奖日期，开奖期号，开奖号码，当期销量
#通过观察，发现该彩票网站上面包含2003～2014的数据，其url规律是：http://baidu.lecai.com/lottery/draw/list/50?d=2003-01-01
if __name__ == '__main__':
    output = file('双色球2003-2014历史数据.txt', 'w+')
    for i in range(2003, 2015):
        req_html_doc = requests.get("http://baidu.lecai.com/lottery/draw/list/50?d=" + str(i) + "-01-01").text
        my_soup = BeautifulSoup(req_html_doc)
        result = my_soup.findAll('tr')
        for each in result:
            reg_lottery_date = re.compile(r'<td class="td1">(.*)</td>')  # <td class="td1">2013-12-31</td>
            lottery_date = reg_lottery_date.findall(str(each))
            reg_lottery_qihao = re.compile(r'<a href="(.*)">(.*)</a>')   #<a href="/lottery/draw/view/50?phase=2013154">2013154</a>
            lottery_qihao = reg_lottery_qihao.findall(str(each))
            reg_lottery_haoma = re.compile(r'<span class="ball_[12]">(.*)</span>') # <span class="ball_1">07</span> 6个ball_1红球，1个ball_2篮球
            lottery_haoma = reg_lottery_haoma.findall(str(each))
            reg_lottery_amount = re.compile(r'<td class="td4">(.*)</td>') #<td class="td4">67,728,980</td>
            lottery_amount = reg_lottery_amount.findall(str(each))
            if len(lottery_qihao) != 0:
                out_line = str(lottery_date) + lottery_qihao[0][1] + str(lottery_haoma) + str(lottery_amount)+'\n'
                output.write(out_line)