diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-05-03 19:38:19 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-05-03 19:38:22 -0700 |
| commit | 748678bc88ea31a362ec5e896fd991b3c8dcbe58 (patch) | |
| tree | e444a2f57564697c95bc2628a44bbd4068854139 /python | |
| parent | a61dd0c429b9e6d24987e14cd5d66057adb498da (diff) | |
| download | sandcrawler-748678bc88ea31a362ec5e896fd991b3c8dcbe58.tar.gz sandcrawler-748678bc88ea31a362ec5e896fd991b3c8dcbe58.zip | |
hotfix for html meta extract codepath
Didn't test last commit before pushing; bad Bryan!
Diffstat (limited to 'python')
| -rw-r--r-- | python/sandcrawler/html.py | 2 |
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: |