From 486a593f15f83b879b2404c5250daf89f9c15344 Mon Sep 17 00:00:00 2001 From: JustAnotherArchivist Date: Tue, 22 Oct 2019 16:24:54 +0000 Subject: [PATCH] Add support for more weird Facebook URLs --- url-normalise | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/url-normalise b/url-normalise index 294a2d8..a590ceb 100755 --- a/url-normalise +++ b/url-normalise @@ -47,7 +47,14 @@ do url="${line}" fi - if [[ "${url}" =~ ^https?://((www|m|[a-z][a-z]-[a-z][a-z]).)?facebook.com/([^/]+/?(\?|$)|pages/[^/]+/[0-9]+/?(\?|$)|pg/[^/]+([/?]|$)|profile\.php\?id=[0-9]+(&|$)) ]] + if [[ "${url}" =~ ^https?://((www|m|[a-z][a-z]-[a-z][a-z]).)?facebook.com/login/.*[?\&]next=https?%3A%2F%2F((www|m|[a-z][a-z]-[a-z][a-z]).)?facebook.com%2F && "${url}" != *'%0A'* && "${url}" != *'%00'* ]] + then + url="${url##*\?next=}" + url="${url##*&next=}" + url="${url%%&*}" + url="$(printf '%b' "${url//%/\\x}")" + fi + if [[ "${url}" =~ ^https?://((www|m|[a-z][a-z]-[a-z][a-z]).)?facebook.com/([^/]+/?(\?|$)|pages/[^/]+/[0-9]+/?(\?|$)|pages/category/[^/]+/[^/]+/?(\?|$)|pg/[^/]+([/?]|$)|profile\.php\?id=[0-9]+(&|$)) ]] then verbose_echo "Normalising Facebook URL: ${url}" >&2 if [[ "${url}" == *profile.php* ]]