diff options
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). |