diff options
| -rw-r--r-- | python/sandcrawler/html.py | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py index 8fbb0ba..6e346e7 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -54,6 +54,9 @@ 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 tag is only partially populated + if 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: url = meta['content'].strip() |