Python数据抓取双色球开奖

抓取双色球开奖数据，源码如下： import urllib.request import urllib.parse import re import urllib.request,urllib.parse,http.cookiejar def getHtml(url): cj=http.cookiejar.CookieJar() opener=urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj)) opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.101 Safari/537.36'),('Cookie','4564564564564564565646540')] urllib.request.install_opener(opener) html_bytes = urllib.request.urlopen( url ).read() html_string = html_bytes.decode( 'utf-8' ) return html_string html = getHtml("http://zst.aicai.com/ssq/openInfo/") table = html[html.find('<table class="fzTab nbt">') : html.find('</table>')] tmp = table.split('<tr \r\n\t\t onmouseout=',1) trs = tmp[1] tr = trs[: trs.find('</tr>')] number = tr.split('<td >')[1].split('</td>')[0] print(number + '期开奖号码：',end='') redtmp = tr.split('<td class="redColor sz12">') reds = redtmp[1:len(redtmp)-1] for redstr in reds: print(redstr.split('</td>')[0] + ",",end='') print('蓝球：',end='') blue = tr.split('<td class="blueColor sz12">')[1].split('</td>')[0] print(blue)