From 9fb29422a863bb06c115438e0afebb56fbe98663 Mon Sep 17 00:00:00 2001 From: Guy Rosin Date: Thu, 7 Mar 2019 21:23:29 +0200 Subject: [PATCH 1/2] Update extractors.py Added a date tag --- newspaper/extractors.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/newspaper/extractors.py b/newspaper/extractors.py index c097df2a..96255401 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': 'publish_date', + 'content': 'content'}, ] for known_meta_tag in PUBLISH_DATE_TAGS: meta_tags = self.parser.getElementsByTag( From e1945129d3d5571ea30039e314a8db2a9c1ca153 Mon Sep 17 00:00:00 2001 From: Guy Rosin Date: Wed, 20 Mar 2019 20:16:13 +0200 Subject: [PATCH 2/2] Update extractors.py Added a date tag --- newspaper/extractors.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/newspaper/extractors.py b/newspaper/extractors.py index 96255401..26ead02a 100644 --- a/newspaper/extractors.py +++ b/newspaper/extractors.py @@ -218,6 +218,8 @@ def parse_date_str(date_str): 'content': 'datetime'}, {'attribute': 'name', 'value': 'publish_date', 'content': 'content'}, + {'attribute': 'itemprop', 'value': 'dateCreated', + 'content': 'content'}, ] for known_meta_tag in PUBLISH_DATE_TAGS: meta_tags = self.parser.getElementsByTag(