From 33cc50939619d1c30bdfa800aba2137397a7ee0d Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Tue, 11 Aug 2020 00:28:06 -0700
Subject: html: extract eprints PDF url (eg, ub.uni-heidelberg.de)

---
 python/sandcrawler/html.py | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'python')

diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py
index 1d24ca1..6236a3b 100644
--- a/python/sandcrawler/html.py
+++ b/python/sandcrawler/html.py
@@ -59,6 +59,8 @@ def extract_fulltext_url(html_url, html_body):
     if not meta:
         # researchgate does this; maybe others also?
         meta = soup.find('meta', attrs={"property":"citation_pdf_url"})
+    if not meta:
+        meta = soup.find('meta', attrs={"name":"eprints.document_url"})
     # if tag is only partially populated
     if meta and not meta.get('content'):
         meta = None
-- 
cgit v1.2.3