From e655080e204e96aa5c0f357a4b3995b2abe5aa18 Mon Sep 17 00:00:00 2001 From: JustAnotherArchivist Date: Wed, 19 Feb 2020 17:53:45 +0000 Subject: [PATCH] Add support for Facebook /pages/category/Category/Name-ID URLs --- website-extract-social-media | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website-extract-social-media b/website-extract-social-media index fa422f4..b66f9ef 100755 --- a/website-extract-social-media +++ b/website-extract-social-media @@ -10,7 +10,7 @@ function fetch_n_extract { tee \ >( # Facebook - grep -Poi 'facebook\.com/((pages|people)/((?!")[^/ <"'"'"'])+/|groups/|pg/)?((?!")[^/ <"'"'"'])+' | \ + grep -Poi 'facebook\.com/((pages(/category)?|people)/((?!")[^/ <"'"'"'])+/|groups/|pg/)?((?!")[^/ <"'"'"'])+' | \ sed 's,^,https://www.,' | \ grep -vi -e '^https://www\.facebook\.com/2008$' -e '^https://www\.facebook\.com/tr\?' -e '^https://www\.facebook\.com/plugins$' -e '^https://www\.facebook\.com/l\.php\?' | \ grep -Pvi '^https://www\.facebook\.com/share(r(\.php)?)?(\?|$)'