From da38ba3839b378ee2e386dafd3aa518a96ad3f04 Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Thu, 21 Feb 2019 17:43:05 +0530
Subject: [PATCH] imdb: parse tenical info

---
 ox/web/imdb.py | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index 8e011cc..e52cfc5 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -90,6 +90,20 @@ def parse_aspectratio(value):
         value = '.'.join(value.strip().split('.')[:2])
     return value
 
+
+def technical(label):
+    return {
+        'page': 'technical',
+        're': [
+            '<td class="label">\s*?%s\s*?</td>.*?<td>\s*?(.*?)\s*?</td>' % label,
+            lambda data: [
+                re.sub('\s+', ' ', d.strip()) for d in data.strip().split('<br>')
+            ] if data else []
+        ],
+        'type': 'list'
+    }
+
+
 '''
 'posterIds': {
     'page': 'posters',
@@ -300,6 +314,11 @@ class Imdb(SiteParser):
             ],
             'type': 'list'
         },
+        'laboratory': technical('Laboratory'),
+        'camera': technical('Camera'),
+        'negative format': technical('Negative Format'),
+        'cinematographic process': technical('Cinematographic Process'),
+        'printed film format': technical('Printed Film Format'),
     }
 
     def read_url(self, url, timeout):