# -*- coding: utf-8 -*-
import urllib2
import re
import os
BOR_amount=0.0
url='http://58921.com/'
req = urllib2.Request(url, headers={'User-Agent' : "Magic Browser"})
webpage= urllib2.urlopen(req)
strw=webpage.read()
s=strw.find("电影名称</th><th>总场次/占比")
e=strw[s:].find("各平台场次存在重叠，实时与预计票房为程序自行计算，仅供参考")
strw_tab=strw[s:s+e] # 14.
#print strw_tab
m=[]
m=re.
findall(
r'<tr class="[a-z]{3,4}"><td><a href="/film/[0-9]+/boxoffice" title=.+</tr>',strw_tab) # 15.
print '----------------------'
print m
if not m:
os.exit()
for t in m:
ss=[]
ss=re.findall(r'(\d+[\.|/]?\d*[\.]?\d*[%]*[^\x00-\xff]*)',t) # 16.
# print ss
if ss:
BOR_amount+= float(ss[-3]) #对 实时的票房 进行迭代累加 #如果 票房数据有缺失值 就会报错，需要注意
# print BOR_amount
else:
print "error"
print "票房总额是: "+str(BOR_amount)+"万元"
