diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-03-25 16:29:12 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-03-25 16:29:12 -0700 |
| commit | b91987978330b6da1c6bb5650418c2c6068340a1 (patch) | |
| tree | f95415a7355724988d9bfd37b0abe33c8636faa2 /python | |
| parent | 11f7c22e1de104918d32274feaea310c11476cc7 (diff) | |
| download | sandcrawler-b91987978330b6da1c6bb5650418c2c6068340a1.tar.gz sandcrawler-b91987978330b6da1c6bb5650418c2c6068340a1.zip | |
ingest: eurosurveillance PDF parser
Diffstat (limited to 'python')
| -rw-r--r-- | python/sandcrawler/html.py | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py index c76d7a2..04b3afe 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -310,4 +310,15 @@ def extract_fulltext_url(html_url, html_body): if url and url.startswith('http'): return dict(pdf_url=url, technique='figshare-json') + # eurosurveillance + # https://www.eurosurveillance.org/content/10.2807/1560-7917.ES.2020.25.11.2000230 + if "://www.eurosurveillance.org/content/" in html_url: + # <a href="/deliver/fulltext/eurosurveillance/25/11/eurosurv-25-11-3.pdf?itemId=/content/10.2807/1560-7917.ES.2020.25.11.2000230&mimeType=pdf&containerItemId=content/eurosurveillance" class="pdf " title="Download" rel="http://instance.metastore.ingenta.com/content/10.2807/1560-7917.ES.2020.25.11.2000230" target="/content/10.2807/1560-7917.ES.2020.25.11.2000230-pdf" > + href = soup.find('a', attrs={"class":"pdf", "title": "Download"}) + if href: + url = href['href'].strip() + if not url.startswith('http'): + url = host_prefix + url + return dict(pdf_url=url, technique='eurosurveillance-href') + return dict() |