From 9578097c4556d72d790ac2ebf06e63beec573e75 Mon Sep 17 00:00:00 2001
From: Rolux <rolux@Rolux.local>
Date: Fri, 9 May 2008 12:39:20 +0200
Subject: [PATCH] even better criterion.py

---
 ox/criterion.py | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/ox/criterion.py b/ox/criterion.py
index 1d1927f..6daf4d7 100644
--- a/ox/criterion.py
+++ b/ox/criterion.py
@@ -5,22 +5,33 @@ from oxutils.cache import getUrlUnicode
 from oxutils.html import stripTags
 from oxutils.text import findRe
 
-def getPosterUrl(title, director):
-    # imdb module is currently broken
-    imdbId = imdb.getMovieId(title, director)
+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:
-        criterionId = findRe(string, '"release.asp\?id=(.*?)"')
+        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()
-        # print ('%s: %s (%s)' % (criterionId, criterionTitle, criterionDirector)).encode('utf-8')
         if imdb.getMovieId(criterionTitle, criterionDirector) == imdbId:
-            return 'http://criterion.com/content/images/full_boxshot/%s_box_348x490.jpg' % criterionId
+            return id
     return ''
 
+def getMovieData(title = '', director = '', imdbId = ''):
+    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 = {}
+        data['synopsis'] = stripTags(findRe(html, '<h3>Synopsis</h3>(.*?)</div>'))
+        data['posterUrl'] = 'http://criterion.com/content/images/full_boxshot/%s_box_348x490.jpg' % id
+        return data
+    return {}
+
 if __name__ == '__main__':
-    getPosterUrl('Le mepris', 'Jean-Luc Godard')
\ No newline at end of file
+    print getMovieData('Le mepris', 'Jean-Luc Godard')
\ No newline at end of file