From 8a1b2c503efaf1d2cf410771d1f0966f90f2984e Mon Sep 17 00:00:00 2001 From: Bryan Bishop Date: Wed, 6 Feb 2013 20:00:50 -0600 Subject: [PATCH] ignore citation_pdf_url on aip.org --- modules/papers.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/modules/papers.py b/modules/papers.py index 2a11146..1014bca 100644 --- a/modules/papers.py +++ b/modules/papers.py @@ -164,6 +164,10 @@ def download_url(url): citation_pdf_url = find_citation_pdf_url(tree, url) citation_title = find_citation_title(tree) + # aip.org sucks, citation_pdf_url is wrong + if "link.aip.org/" in citation_pdf_url: + citation_pdf_url = None + # wow, this seriously needs to be cleaned up if citation_pdf_url and citation_title: citation_title = citation_title.encode("ascii", "ignore")