From 03c119155081f7b9f65e1f55d3a58708c9dc6704 Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Fri, 15 Nov 2019 14:51:32 +0100
Subject: [PATCH] fall back to storyline for summary

---
 ox/web/imdb.py | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index 7d91dc7..2f14e33 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -199,6 +199,11 @@ class Imdb(SiteParser):
         'summary': zebra_table('Plot Summary', more=[
             '<p>(.*?)<em'
         ]),
+        'storyline': {
+            'page': '',
+            're': '<h2>Storyline</h2>.*?<p>(.*?)</p>',
+            'type': 'string'
+        },
         'posterId': {
             'page': 'reference',
             're': '<img.*?class="titlereference-primary-image".*?src="(.*?)".*?>',
@@ -517,10 +522,13 @@ class Imdb(SiteParser):
             ])
             if self['releasedate'] == 'x':
                 del self['releasedate']
+
+        if 'summary' not in self and 'storyline' in self:
+            self['summary'] = self.pop('storyline')
         if 'summary' in self:
             if isinstance(self['summary'], list):
                 self['summary'] = self['summary'][0]
-            self['summary'] = self['summary'].split('</p')[0].strip()
+            self['summary'] = strip_tags(self['summary'].split('</p')[0]).split('  Written by\n')[0].strip()
 
         if 'credits' in self:
             credits = [