From c5b39c4323387e59fb53184711dd113f0483b42a Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Mon, 24 Feb 2020 11:50:49 -0800 Subject: small tweak to americanarchivist.org URL extraction --- python/sandcrawler/html.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py index 091162d..34da876 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -223,7 +223,7 @@ def extract_fulltext_url(html_url, html_body): # american archivist (OA) # https://americanarchivist.org/doi/abs/10.17723/aarc.62.2.j475270470145630 - if "://americanarchivist.org/doi/abs/" in html_url: + if "://americanarchivist.org/doi/" in html_url and not "/doi/pdf" in html_url: # hrefs = soup.find_all('a', attrs={"target":"_blank"}) for href in hrefs: -- cgit v1.2.3