From 9fa75b797b72172676d2ede68ed68490e9058588 Mon Sep 17 00:00:00 2001
From: Robert Alimov <bobert129@gmail.com>
Date: Mon, 29 Oct 2018 15:28:40 -0700
Subject: [PATCH] Updated publish date parser to include NBC and Fox.

---
 newspaper/extractors.py | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/newspaper/extractors.py b/newspaper/extractors.py
index 120a5ff3..1420cf44 100644
--- a/newspaper/extractors.py
+++ b/newspaper/extractors.py
@@ -216,6 +216,8 @@ def parse_date_str(date_str):
              'content': 'content'},
             {'attribute': 'pubdate', 'value': 'pubdate',
              'content': 'datetime'},
+            {'attribute': 'name', 'value': 'dcterms.created',
+             'content': 'content'}, # Fox News
         ]
         for known_meta_tag in PUBLISH_DATE_TAGS:
             meta_tags = self.parser.getElementsByTag(
@@ -230,6 +232,24 @@ def parse_date_str(date_str):
                 if datetime_obj:
                     return datetime_obj
 
+        # NBC News
+        NBC_TAG = {
+            'tag': 'time',
+            'attribute': 'datetime'
+        }
+        date_tags = self.parser.getElementsByTag(
+            doc,
+            tag=NBC_TAG['tag']
+        )
+        if (date_tags):
+            date_str = self.parser.getAttribute(
+                date_tags[0],
+                NBC_TAG['attribute']
+            )
+            datetime_obj = parse_date_str(date_str)
+            if datetime_obj:
+                return datetime_obj
+
         return None
 
     def get_title(self, doc):