From 80641b54615695942ad3da4ba5b94962e62e17b5 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Mon, 30 Nov 2009 01:46:56 +0100
Subject: [PATCH] imdb cleanups

---
 oxweb/imdb.py | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/oxweb/imdb.py b/oxweb/imdb.py
index 2f7225a..3543714 100644
--- a/oxweb/imdb.py
+++ b/oxweb/imdb.py
@@ -75,8 +75,8 @@ def getRawMovieData(imdbId):
     data['release date'] = getMovieReleaseDate(imdbId)
     return data
 
-def getMovieInfo(imdbId):
-    data = readUrlUnicode(getUrlBase(imdbId))
+def getMovieInfo(imdbId, timeout=-1):
+    data = readUrlUnicode(getUrlBase(imdbId), timeout=timeout)
     info = dict()
     info['poster'] = findRe(data, 'name="poster".*?<img .*?src="(.*?)"')
     if info['poster'] and '_V' in info['poster']:
@@ -84,7 +84,12 @@ def getMovieInfo(imdbId):
 
     for i in re.compile('<h5>(.*?):</h5>(.*?)<div class="info"', re.DOTALL).findall(data):
         title = stripTags(i[0]).strip().lower()
-        txt= stripTags(i[1]).strip()
+        if title in ('genre', ):
+            txt = i[1].split('</div>')[0]
+        else:
+            txt= i[1]
+        txt = stripTags(txt).strip()
+
         def cleanUp(k):
             k = decodeHtml(k).replace(u'\xa0', ' ').strip()
             if k.endswith('more'): k=k[:-len('more')].strip()
@@ -258,7 +263,7 @@ def creditList(data, section=None):
         credits_ = re.compile('''<tr>.*?<td valign="top">(.*?)</td><td.*?</td><td valign="top">(.*?)</td></tr>''').findall(data)
     credits = []
     for c_ in credits_:
-        c = [decodeHtml(c_[0]).strip(), decodeHtml(c_[1]).strip()]
+        c = [stripTags(decodeHtml(c_[0]).strip()), stripTags(decodeHtml(c_[1]).strip())]
         if section=='writers':
             c[1] = c[1].replace('<br>', '').strip().replace(')', '').replace('(','')
             if c[1].endswith(' and'): c[1] = c[1][:-4]
@@ -328,6 +333,7 @@ def getMovieLocations(imdbId):
     url = "%slocations" % getUrlBase(imdbId)
     data = readUrlUnicode(url)
     locations = re.compile('<dt><a href="/List.*?>(.*?)</a></dt>').findall(data)
+    locations = [decodeHtml(l) for l in locations]
     return locations
 
 def getMovieImages(imdbId, keys=('still_frame', 'poster', 'product')):
@@ -366,6 +372,8 @@ def getMovieTrivia(imdbId):
         t = t.replace(u'”', '"')
         if t.endswith('<br><br>'):
             t = t[:-8]
+        if t.endswith('<br>\n<br>'):
+            t = t[:-len('<br>\n<br>')]
         return t.strip()
     trivia = [clean(t) for t in trivia]
     return trivia 
@@ -454,7 +462,9 @@ def getMovieBusinessSum(imdbId):
         b_['budget'] = int(intValue(budget[0].replace(',', '')))
         
     if 'gross' in business:
-        b_['gross'] = int(intValue(business['gross'][0].replace(',', '')))
+        gross = filter(lambda x: x.startswith('$'), business['gross'])
+        if gross:
+            b_['gross'] = int(intValue(gross[0].replace(',', '')))
         #b_['gross'] = sum([int(intValue(i.replace(',', ''))) for i in business['gross']])
         #if 'weekend gross' in business:
         #    b_['gross'] += sum([int(intValue(i.replace(',', ''))) for i in business['weekend gross']])