From 282cecb8800be93d700302b48115326e47783991 Mon Sep 17 00:00:00 2001
From: P M D Scully <pmdscully@github.com>
Date: Thu, 27 Apr 2017 00:44:21 +0700
Subject: [PATCH] Added extraction of url_pdf from right hand side [PDF] link.

---
 scholar.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/scholar.py b/scholar.py
index 13ccd43..5499e94 100755
--- a/scholar.py
+++ b/scholar.py
@@ -621,6 +621,11 @@ def _parse_article(self, div):
                         raw_text = raw_text.replace('\n', '')
                         self.article['excerpt'] = raw_text
 
+            if self.article['url_pdf'] is None and tag.name == 'div' and self._tag_has_class(tag, 'gs_ggs') \
+                    and tag.div and tag.div.div and tag.div.div.a and tag.div.div.a.span \
+                    and tag.div.div.a.span.get_text() == "[PDF]":
+                self.article['url_pdf'] = self._path2url(tag.div.div.a['href'])
+
 
 class ScholarQuery(object):
     """