python-oxweb/oxweb/movieposterdb.py

# -*- coding: UTF-8 -*-
# vi:si:et:sw=4:sts=4:ts=4

import re

from oxlib.cache import getUrlUnicode
from oxlib import findRe

def getData(id):
    data = {
        "url": getUrl(id)
    }
    data["posters"] = getPostersByUrl(data["url"])
    return data

def getId(url):
    return url.split("/")[-2]

def getPostersByUrl(url):
    posters = []
    html = getUrlUnicode(url)
    results = re.compile('<a href="(http://www.movieposterdb.com/group/.*?)">', re.DOTALL).findall(html)
    for result in results:
        posters += getPostersByUrl(result)
    results = re.compile('<a href="(http://www.movieposterdb.com/poster/.*?)">', re.DOTALL).findall(html)
    for result in results:
        html = getUrlUnicode(result)
        posters.append(findRe(html, '"(http://www.movieposterdb.com/posters/.*?\.jpg)"'))
    return posters

def getUrl(id):
    return "http://www.movieposterdb.com/movie/%s/" % id

if __name__ == '__main__':
    print getData('0060304')
    print getData('0133093')