diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-09-15 20:26:24 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-09-15 20:26:24 -0700 |
| commit | d86a87f5000b97a2dc93c4a60ba4a18e834c9e0f (patch) | |
| tree | d78c9e11385c37424fdc7f4ee5f3c8077d004db5 /python | |
| parent | c1f60b1e31c8ff3b25c7cdcd442ccd91512d1db8 (diff) | |
| download | sandcrawler-d86a87f5000b97a2dc93c4a60ba4a18e834c9e0f.tar.gz sandcrawler-d86a87f5000b97a2dc93c4a60ba4a18e834c9e0f.zip | |
html: handle JMIR URL pattern
Diffstat (limited to 'python')
| -rw-r--r-- | python/sandcrawler/html.py | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py index a5cbaf5..70761a3 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -395,6 +395,12 @@ def extract_fulltext_url(html_url, html_body): if url.encode('utf-8') in html_body: return dict(pdf_url=url, technique='href-eperiodica') + # JMIR + # https://mhealth.jmir.org/2020/7/e17891/ + if '.jmir.org/' in html_url and not "/pdf" in html_url and html_url.endswith("/"): + url = html_url + "pdf" + return dict(pdf_url=url, technique='jmir-url') + ### below here we are doing guesses # generic guess: try current URL plus .pdf, if it exists in the HTML body |