From d17ae60f8ec369aa60930e63a5c207b92e770ea6 Mon Sep 17 00:00:00 2001
From: Rolux <rolux@Rolux.local>
Date: Sun, 6 Jul 2008 20:12:30 +0200
Subject: [PATCH] movieposterdb module

---
 oxweb/movieposterdb.py | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100644 oxweb/movieposterdb.py

diff --git a/oxweb/movieposterdb.py b/oxweb/movieposterdb.py
new file mode 100644
index 0000000..d77e7b3
--- /dev/null
+++ b/oxweb/movieposterdb.py
@@ -0,0 +1,32 @@
+# -*- coding: UTF-8 -*-
+# vi:si:et:sw=4:sts=4:ts=4
+
+import re
+
+from oxlib import cache
+from oxlib import findRe
+
+def getPosterUrls(imdbId):
+    url = 'http://www.movieposterdb.com/movie/%s' % imdbId
+    posterUrls = []
+    if cache.exists(url):
+        posterUrls = parsePage(url)
+    return posterUrls
+            
+def parsePage(url):
+    print url
+    posterUrls = []
+    html = cache.getUrlUnicode(url, timeout=86400)
+    groups = re.compile('<a href="(http://www.movieposterdb.com/group/.*?)">', re.DOTALL).findall(html)
+    print '%s Groups' % len(groups)
+    for group in groups:
+        posterUrls += parsePage(group)
+    posters = re.compile('<a href="(http://www.movieposterdb.com/poster/.*?)">', re.DOTALL).findall(html)
+    for poster in posters:
+        print 'Poster: ' + poster
+        html = cache.getUrlUnicode(poster)
+        posterUrls.append(findRe(html, '"(http://www.movieposterdb.com/posters/.*?\.jpg)"'))
+    return posterUrls
+
+if __name__ == '__main__':
+    print getPosterUrls('0133093')
\ No newline at end of file