diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-08-10 21:50:50 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-08-10 21:50:50 -0700 |
| commit | 26d4766a2835aab00b0201198376d4ca42cc1d82 (patch) | |
| tree | 1909749bb0fe7e23fb19f2347011c1a003c220a2 | |
| parent | a551e4deb4d577a552938dda9dc504a29c033fdf (diff) | |
| download | sandcrawler-26d4766a2835aab00b0201198376d4ca42cc1d82.tar.gz sandcrawler-26d4766a2835aab00b0201198376d4ca42cc1d82.zip | |
extract PDF urls for e-periodica.ch
| -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 85d32c0..1d24ca1 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -372,6 +372,12 @@ def extract_fulltext_url(html_url, html_body): url = host_prefix + url return dict(pdf_url=url, technique='ojs-galley-href') + # ETH zurich e-periodica + if '://www.e-periodica.ch/digbib/view' in html_url: + url = html_url.replace('digbib/view', 'cntmng').split('#')[0] + if url.encode('utf-8') in html_body: + return dict(pdf_url=url, technique='href-eperiodica') + ### below here we are doing guesses # generic guess: try current URL plus .pdf, if it exists in the HTML body |