diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-02-24 13:21:57 -0800 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-02-24 13:21:57 -0800 |
| commit | 266b0a2d5928921d3b3f992fa249b22f7a5edb16 (patch) | |
| tree | dc59f501b8e4eb26ac00c05635046ec86ab83fdd | |
| parent | 1a42a73e8c494d13e671d0fc6729665d85010669 (diff) | |
| download | sandcrawler-266b0a2d5928921d3b3f992fa249b22f7a5edb16.tar.gz sandcrawler-266b0a2d5928921d3b3f992fa249b22f7a5edb16.zip | |
ingest: more direct americanarchivist PDF url guess
| -rw-r--r-- | python/sandcrawler/html.py | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py index 7189055..e993e74 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -224,6 +224,10 @@ def extract_fulltext_url(html_url, html_body): # american archivist (OA) # https://americanarchivist.org/doi/abs/10.17723/aarc.62.2.j475270470145630 if "://americanarchivist.org/doi/" in html_url and not "/doi/pdf" in html_url: + # use a more aggressive direct guess to avoid rate-limiting... + if "/doi/10." in html_url: + url = html_url.replace("/doi/10.", "/doi/pdf/10.") + return dict(pdf_url=url, technique='archivist-url') # <a href="/doi/pdf/10.17723/aarc.62.2.j475270470145630" target="_blank"> hrefs = soup.find_all('a', attrs={"target":"_blank"}) for href in hrefs: |