diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-02-18 23:08:06 -0800 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-02-18 23:08:09 -0800 |
| commit | e6f2a585868b0277145659b9d653a0288f76f5b6 (patch) | |
| tree | 418a3ce46fa0398a0776eca23c550cbf745edb4a | |
| parent | 3d663242e2dc4128bd4613657870e8dd42cac570 (diff) | |
| download | sandcrawler-e6f2a585868b0277145659b9d653a0288f76f5b6.tar.gz sandcrawler-e6f2a585868b0277145659b9d653a0288f76f5b6.zip | |
allow <meta property=citation_pdf_url>
at least researchgate does this (!)
| -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 e6f0f69..8e9eb1f 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -44,6 +44,9 @@ def extract_fulltext_url(html_url, html_body): meta = soup.find('meta', attrs={"name":"citation_pdf_url"}) if not meta: meta = soup.find('meta', attrs={"name":"bepress_citation_pdf_url"}) + if not meta: + # researchgate does this; maybe others also? + meta = soup.find('meta', attrs={"property":"citation_pdf_url"}) # 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() |