时光网内地影视票房Top100爬取

# -*- coding:utf-8 -*-
from __future__ import print_function
import urllib2
import re

print(u"电影;首日票房;首周票房;时光评分;评分人数;总票房")
pre_url="http://movie.mtime.com/boxoffice/?area=china&type=MovieRankingHistory&category=all&page="
‘‘‘3&display=list&timestamp=1496903738364&version=07bb781100018dd58eafc3b35d42686804c6df8d&dataType=json‘‘‘
for index in range(10):
    aft_url=str(index)+"&display=list&timestamp=1496903738364&version=07bb781100018dd58eafc3b35d42686804c6df8d&dataType=json"
    url=pre_url+aft_url
    response = urllib2.urlopen(url)
    pageCode=response.read().decode(‘utf-8‘)
    pattern = re.compile(u"h3><a[^>]*>([^<]+)(?:.+?首日<strong>([^<]+)(?:.+?首周<strong>([^<]+))?)?.*?point[^>]*>(\d)<em>.(\d).*?<p>(.*?)人.*?totalnum[^>]*><strong>([^<]+).*?",re.S)
    divide = re.compile("(<\/div><\/div>.*?none\S\S>[^p]*p>)",re.S)
    items=re.findall(divide, pageCode)
    #print(pageCode)
    for item in items:
        #print(item)
        iitems=re.findall(pattern,item)
        for iitem in iitems:
            print(iitem[0], end=‘;‘)
            print(iitem[1], end=‘;‘)
            print(iitem[2], end=‘;‘)
            print(iitem[3], end=‘.‘)
            print(iitem[4], end=‘;‘)
            print(iitem[5], end=‘;‘)
            print(iitem[6]+u‘亿‘, end=‘;‘)
        print(‘‘)