better criterion.py

ox/criterion.py

@@ -6,6 +6,10 @@ from oxutils.html import stripTags
 from oxutils.text import findRe
 
 def getPosterUrl(title, director):
+    # imdb module is currently broken
+    '''
+    imdbId = imdb.getMovieId(title, director)
+    '''
     html = getUrl('http://criterion.com/asp/list.asp?sort=spine')
     strings = findRe(html, '<table cellspacing="0" id="browse-all-table">(.*?)</table>').split('<tr>')
     strings.pop(0)
@@ -14,13 +18,10 @@ def getPosterUrl(title, director):
         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)
-        # imdb module is currently broken
+        criterionDirector = stripTags(findRe(string, '</a>.*?</td>(.*?)</td>')).strip()
+        print '%s: %s (%s)' % (criterionId, criterionTitle, criterionDirector)
         '''
-        imdbId = imdb.getMovieId(title, director)
-        imdbData = imdb.getMovieData(imdbId)
-        if imdbData['title'] == title and imdbData['director'] == director:
+        if imdb.getMovieId(criterionTitle, criterionDirector) == imdbId:
             return 'http://criterion.com/content/images/full_boxshot/%s_box_348x490.jpg' % criterionId
         '''
     return ''
@@ -29,4 +30,4 @@ def test():
     return
 
 if __name__ == '__main__':
-    getPosterUrl('Le Mepris', 'Jean-Luc Godard')
+    getPosterUrl('Le mepris', 'Jean-Luc Godard')

ox/imdb.py

@@ -25,7 +25,6 @@ def getMovieId(title, director='', year=''):
     query = 'site:imdb.com %s "%s"' % (director, title)
   else:
     query = 'site:imdb.com "%s"' % title
-  print google.find(query, 3)
   for (name, url, desc) in google.find(query, 3):
     if url.startswith('http://www.imdb.com/title/tt'):
       return url[28:35]