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(amgId):
    html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=%s~T0" % amgId)
    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">(.*?)</')
    html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=%s~T1" % amgId)
    data['review'] = stripTags(findRe(html, 'Review</td>.*?<td colspan="2"><p>(.*?)</td>'))
    return data

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