diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2021-10-26 13:35:36 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2021-10-26 13:35:36 -0700 |
| commit | 600ad67925a748200ddf21d5aeabd157d2bb3664 (patch) | |
| tree | 89ae6bc24e6eb3821c03efd7d781430345c68aa0 /python/sandcrawler/html.py | |
| parent | 05bd7cbcc62588e431c5efd533189e246b2a997e (diff) | |
| download | sandcrawler-600ad67925a748200ddf21d5aeabd157d2bb3664.tar.gz sandcrawler-600ad67925a748200ddf21d5aeabd157d2bb3664.zip | |
start handling trivial lint cleanups: unused imports, 'is None', etc
Diffstat (limited to 'python/sandcrawler/html.py')
| -rw-r--r-- | python/sandcrawler/html.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py index a44fc67..5b9742a 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -53,12 +53,12 @@ def extract_fulltext_url(html_url, html_body): print(f"\tdoi.org in citation_pdf_url (loop?): {url}", file=sys.stderr) elif url.startswith('/'): if host_prefix + url == html_url: - print(f"\tavoiding citation_pdf_url link-loop", file=sys.stderr) + print("\tavoiding citation_pdf_url link-loop", file=sys.stderr) else: return dict(pdf_url=host_prefix + url, technique='citation_pdf_url') elif url.startswith('http'): if url == html_url: - print(f"\tavoiding citation_pdf_url link-loop", file=sys.stderr) + print("\tavoiding citation_pdf_url link-loop", file=sys.stderr) else: return dict(pdf_url=url, technique='citation_pdf_url') else: |