From 2fe6a9e98906d6fd9ecb4e6a13ff908826b6842c Mon Sep 17 00:00:00 2001
From: Rolux <rolux@Rolux.local>
Date: Fri, 9 May 2008 13:54:41 +0200
Subject: [PATCH] better impawards module

---
 ox/impawards.py | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/ox/impawards.py b/ox/impawards.py
index 71881d5..2f0d79e 100644
--- a/ox/impawards.py
+++ b/ox/impawards.py
@@ -38,7 +38,21 @@ def parseArchivePage(html):
 def parseMoviePage(html):
     data = {}
     data['imdbId'] = findRe(html, 'imdb.com/title/tt(.*?) ')
-    data['posterUrl'] = 'http://impawards.com/%s' % findRe(html, '<td align=center><br><img SRC="(.*?)"')
+    data['title'] = findRe(html, '<font size=\+3>(.*?) \(')
+    data['year'] = findRe(html, '\(<a href="eligible.html">(.*?)</a>\)')
+    result = findRe(html, '<a href = (\w*?_xlg.html) target= _blank>')
+    if result:
+        url = 'http://impawards.com/%s/%s' % (data['year'], result)
+        html = getUrlUnicode(url, timeout = -1)
+        d = parsePosterPage(html, data['year'])
+        data['posterUrl'] = d['posterUrl']
+    else:
+        data['posterUrl'] = 'http://impawards.com/%s/%s' % (data['year'], findRe(html, '<td align=center><br><img SRC="(.*?)"'))
+    return data
+
+def parsePosterPage(html, year):
+    data = {}
+    data['posterUrl'] = 'http://impawards.com/%s/%s' % (year, findRe(html, '<img SRC="(.*?)"'))
     return data
 
 if __name__ == '__main__':