python-oxweb/oxweb/allmovie.py

# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
import re
import time

from oxlib import stripTags, findRe
from oxlib.cache import getUrlUnicode

def getMovieData(allmovieId):
    html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=1:%s~T0" % allmovieId)
    data = {}
    data['poster'] = findRe(html, '<img src="(http://image.*?)"')
    data['synopsis'] = stripTags(findRe(html, 'Plot Synopsis</td>.*?<td colspan="2"><p>(.*?)</td>'))
    data['year'] = findRe(html, '<a href="/cg/avg.dll\?p=avg&amp;sql=24:\d{4}">(\d{4})</a>')
    data['rating'] = findRe(html, '" alt="(\d+?) Stars"')
    data['country'] = findRe(html, '<a href="/cg/avg.dll\?p=avg&sql=24:D\|\|\|206">(.*?)</')
    data['director'] = stripTags(findRe(html, '<td class="formed-sub"><a href="/cg/avg.dll\?p=avg&sql=2:\d+">(.*?)</td>')).split(', ')
    data['genre'] = map(lambda x: stripTags(x), findRe(html, '<span>Genre / Type</span>(.*?)</table>').split('</li><li>'))
    data['keywords'] = map(lambda x: stripTags(x), findRe(html, '<span>Keywords</span>(.*?)</table>').split('</li><li>'))
    data['themes'] = map(lambda x: stripTags(x), findRe(html, '<span>Themes</span>(.*?)</table>').split('</li><li>'))
    html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=1:%s~T1" % allmovieId)
    data['review'] = stripTags(findRe(html, 'Review</td>.*?<td colspan="2"><p>(.*?)</td>'))
    return data

def getMoviePoster(allmovieId):
    data = getMovieData(allmovieId)
    if data:
        return data['poster']
    return ''

if __name__ == '__main__':
    print getMovieData('177524')