From bd64a2dba3f96b56bd8581257aa802100c4184be Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Wed, 9 May 2018 12:09:13 +0100
Subject: [PATCH] more criterion fixes

---
 ox/web/criterion.py | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/ox/web/criterion.py b/ox/web/criterion.py
index 67187fd..09cf212 100644
--- a/ox/web/criterion.py
+++ b/ox/web/criterion.py
@@ -33,7 +33,8 @@ def get_data(id, timeout=ox.cache.cache_timeout, get_imdb=False):
     try:
         html = read_url(data["url"], timeout=timeout, unicode=True)
     except:
-        html = ox.cache.read_url(data["url"], timeout=timeout)
+        html = read_url(data["url"], timeout=timeout).decode('utf-8', 'ignore')
+
     data["number"] = find_re(html, "<b>Spine #(\d+)")
 
     data["title"] = decode_html(find_re(html, "<h1 class=\"header__primarytitle\".*?>(.*?)</h1>"))
@@ -42,11 +43,11 @@ def get_data(id, timeout=ox.cache.cache_timeout, get_imdb=False):
     info = re.compile('<li itemprop="(.*?)".*?>(.*?)</li>', re.DOTALL).findall(results)
     info = {k: strip_tags(v).strip() for k, v in info}
     if 'director' in info:
-        data['director'] =info['director']
+        data['director'] = info['director']
     if 'countryOfOrigin' in info:
-        data['country'] =info['countryOfOrigin']
+        data['country'] = [c.strip() for c in decode_html(info['countryOfOrigin']).split(', ')]
     if 'inLanguage' in info:
-        data['language'] =info['inLanguage']
+        data['language'] = [l.strip() for l in decode_html(info['inLanguage']).split(', ')]
     for v in re.compile('<li>(.*?)</li>', re.DOTALL).findall(results):
         if 'datePublished' in v:
             data['year'] = strip_tags(v).strip()