aboutsummaryrefslogtreecommitdiffstats
path: root/python
diff options
context:
space:
mode:
Diffstat (limited to 'python')
-rw-r--r--python/sandcrawler/html.py2
1 files changed, 1 insertions, 1 deletions
diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py
index 6e346e7..3eadc7b 100644
--- a/python/sandcrawler/html.py
+++ b/python/sandcrawler/html.py
@@ -55,7 +55,7 @@ def extract_fulltext_url(html_url, html_body):
# researchgate does this; maybe others also?
meta = soup.find('meta', attrs={"property":"citation_pdf_url"})
# if tag is only partially populated
- if not meta.get('content'):
+ if meta and not meta.get('content'):
meta = None
# wiley has a weird almost-blank page we don't want to loop on
if meta and not "://onlinelibrary.wiley.com/doi/pdf/" in html_url: