diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2021-11-24 16:05:11 -0800 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2021-11-24 16:05:24 -0800 |
| commit | dfd13be5a7ac87b8b6c186986624f97da02b8923 (patch) | |
| tree | c1242cf5ae9d0b9f48967008e8906c5fffc0bbc1 /python/sandcrawler/html_metadata.py | |
| parent | a6cfb01063da8a5172d38d2da190a25e7d070993 (diff) | |
| download | sandcrawler-dfd13be5a7ac87b8b6c186986624f97da02b8923.tar.gz sandcrawler-dfd13be5a7ac87b8b6c186986624f97da02b8923.zip | |
codespell typos in python (comments)
Diffstat (limited to 'python/sandcrawler/html_metadata.py')
| -rw-r--r-- | python/sandcrawler/html_metadata.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/python/sandcrawler/html_metadata.py b/python/sandcrawler/html_metadata.py index 0d1a4a7..c46788e 100644 --- a/python/sandcrawler/html_metadata.py +++ b/python/sandcrawler/html_metadata.py @@ -843,7 +843,7 @@ def html_extract_resources( """ This function tries to find all the important resources in a page. The presumption is that the HTML document is article fulltext, and we want the - list of all resoures (by URL) necessary to replay the page. + list of all resources (by URL) necessary to replay the page. The returned resource URLs each have a type (script, img, css, etc), and should be fully-qualified URLs (not relative). |