diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-09-14 14:14:22 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-09-14 14:15:59 -0700 |
| commit | 4bd6d443457bed67039c8d8a56a184c1f70247b6 (patch) | |
| tree | 90958ee00beb856ac7aa59b5ba4d855cf281a6f5 | |
| parent | ee6129ea884036b666de7cff4ad7891675a52b3c (diff) | |
| download | sandcrawler-4bd6d443457bed67039c8d8a56a184c1f70247b6.tar.gz sandcrawler-4bd6d443457bed67039c8d8a56a184c1f70247b6.zip | |
html parse: add another generic fulltext pattern
| -rw-r--r-- | python/sandcrawler/html.py | 11 |
1 files changed, 10 insertions, 1 deletions
diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py index acf1522..75e111e 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -95,13 +95,22 @@ def extract_fulltext_url(html_url, html_body): # https://pubs.acs.org/doi/10.1021/acs.estlett.9b00379 # <a href="/doi/pdf/10.1021/acs.estlett.9b00379" title="PDF" target="_blank" class="button_primary"><i class="icon-file-pdf-o"></i><span>PDF (1 MB)</span></a> href = soup.find('a', attrs={"title":"PDF"}) - if href and 'href' in href: + if href and href.get('href'): url = href['href'].strip() if url.startswith('http'): return dict(pdf_url=url, technique='href_title') elif url.startswith('/'): return dict(pdf_url=host_prefix+url, technique='href_title') + # http://www.revistas.unam.mx/index.php/rep/article/view/35503/32336 + href = soup.find('a', attrs={"id":"pdfDownloadLink"}) + if href and href.get('href'): + url = href['href'].strip() + if url.startswith('http'): + return dict(pdf_url=url, technique='href_pdfDownloadLink') + elif url.startswith('/'): + return dict(pdf_url=host_prefix+url, technique='href_pdfDownloadLink') + # http://www.jasstudies.com/DergiTamDetay.aspx?ID=3401 # <embed src="/files/jass_makaleler/1359848334_33-Okt.%20Yasemin%20KARADEM%C4%B0R.pdf" type="application/pdf" /> embed = soup.find('embed', attrs={"type": "application/pdf"}) |