python-oxweb/ox/criterion.py

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

import ox.imdb as imdb
from oxutils.cache import getUrlUnicode
from oxutils.html import stripTags
from oxutils.text import findRe, removeSpecialCharacters


def getData(criterionId):
    '''
    >>> getData(348)['imdbId']
    '0068205'
    '''
    data = {}
    html = getUrlUnicode('http://criterion.com/asp/release.asp?id=%s' % criterionId)
    data['criterionId'] = criterionId
    data['posterUrl'] = getPosterUrl(criterionId)
    data['synopsis'] = stripTags(findRe(html, '<h3>Synopsis</h3>(.*?)</div>'))
    result = re.compile("<title>The Criterion Collection: (.*?) by (.*?)</title>").findall(html)
    data['title'] = stripTags(result[0][0])
    data['director'] = stripTags(result[0][1])
    data['imdbId'] = imdb.getMovieId(data['title'], data['director'])
    return data

def getCriterionIds():
    html = getUrlUnicode('http://criterion.com/asp/list.asp?sort=spine')
    return re.compile('release.asp\?id=(.*?)"').findall(html)

def getPosterUrl(criterionId):
    return 'http://criterion.com/content/images/full_boxshot/%s_box_348x490.jpg' % criterionId

def getMovieId(title = '', director = '', imdbId = ''):
    if not imdbId:
        imdbId = imdb.getMovieId(title, director)
    html = getUrlUnicode('http://criterion.com/asp/list.asp?sort=spine', timeout = -1)
    strings = findRe(html, '<table cellspacing="0" id="browse-all-table">(.*?)</table>').split('<tr>')
    strings.pop(0)
    for string in strings:
        id = findRe(string, '"release.asp\?id=(.*?)"')
        criterionTitle = findRe(string, 'class="title">(.*?)</a>')
        criterionTitle = re.sub('(?<=\\w)<br>(?=\\w)', ' / ', criterionTitle)
        criterionTitle = criterionTitle.replace('<br>', '')
        criterionDirector = stripTags(findRe(string, '</a>.*?</td>(.*?)</td>')).strip()
        if imdb.getMovieId(criterionTitle, criterionDirector) == imdbId:
            return id
    return ''

def getMovieData(title = '', director = '', imdbId = ''):
    data = {}
    if not imdbId:
        imdbId = imdb.getMovieId(title, director)
    id = getMovieId(imdbId = imdbId)
    if id:
        html = getUrlUnicode('http://criterion.com/asp/release.asp?id=%s' % id)
        data['id'] = id
        data['posterUrl'] = getPosterUrl(id)
        data['synopsis'] = stripTags(findRe(html, '<h3>Synopsis</h3>(.*?)</div>'))
    return data

if __name__ == '__main__':
    print getMovieData('Le mepris', 'Jean-Luc Godard')