From e385c1d30285b3dd00e0492f63f6336b0c13000a Mon Sep 17 00:00:00 2001
From: JustAnotherArchivist <JustAnotherArchivist@users.noreply.github.com>
Date: Mon, 18 Nov 2019 01:40:42 +0000
Subject: [PATCH] Limit curl to 10 seconds

---
 social-media-extract-profile-link | 2 +-
 url-normalise                     | 6 +++---
 website-extract-social-media      | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/social-media-extract-profile-link b/social-media-extract-profile-link
index be29f80..0896f44 100755
--- a/social-media-extract-profile-link
+++ b/social-media-extract-profile-link
@@ -10,7 +10,7 @@ function verbose_echo {
 
 function fetch {
 	verbose_echo "Fetching $1" >&2
-	curl -sL -A 'Mozilla/5.0 (Windows NT 6.1; rv:60.0) Gecko/20100101 Firefox/60.0' "$1"
+	curl -sL --max-time 10 -A 'Mozilla/5.0 (Windows NT 6.1; rv:60.0) Gecko/20100101 Firefox/60.0' "$1"
 }
 
 function fetch_n_extract {
diff --git a/url-normalise b/url-normalise
index 982ae37..66ad505 100755
--- a/url-normalise
+++ b/url-normalise
@@ -63,7 +63,7 @@ do
 		else
 			url="${url%%\?*}"
 		fi
-		page="$(curl -sL -A "${userAgent}" -H 'Accept-Language: en-US,en;q=0.5' "https://www.facebook.com/${url#*facebook.com/}")"
+		page="$(curl -sL --max-time 10 -A "${userAgent}" -H 'Accept-Language: en-US,en;q=0.5' "https://www.facebook.com/${url#*facebook.com/}")"
 		user="$(grep -Po '<div\s[^>]*(?<=\s)data-key\s*=\s*"tab_home".*?</div>' <<< "${page}" | grep -Po '<a\s[^>]*(?<=\s)href="/\K[^/]+')"
 		if [[ "${user}" ]]
 		then
@@ -94,7 +94,7 @@ do
 		url="${url%%\?*}"
 		url="${url%/}"
 		unnormalisedUser="${url##*/}"
-		user="$(curl -sL -A "${userAgent}" "https://twitter.com/${unnormalisedUser}" | grep -Po '<a class="([^"]*\s)?ProfileHeaderCard-screennameLink(\s[^"]*)?" href="/\K[^/"]+(?=")')"
+		user="$(curl -sL --max-time 10 -A "${userAgent}" "https://twitter.com/${unnormalisedUser}" | grep -Po '<a class="([^"]*\s)?ProfileHeaderCard-screennameLink(\s[^"]*)?" href="/\K[^/"]+(?=")')"
 		if [[ "${user}" ]]
 		then
 			echo "${prefix}https://twitter.com/${user}"
@@ -123,7 +123,7 @@ do
 		else
 			rurl="${url}?disable_polymer=1"
 		fi
-		page="$(curl -4sL -A "${userAgent}" -H 'Accept-Language: en-US,en;q=0.5' "${rurl}")"
+		page="$(curl -4sL --max-time 10 -A "${userAgent}" -H 'Accept-Language: en-US,en;q=0.5' "${rurl}")"
 		canonical="$(grep -Po '<link itemprop="url" href="http://www\.youtube\.com/\Kuser/[^"]+' <<< "${page}")"
 		if [[ "${canonical}" ]]
 		then
diff --git a/website-extract-social-media b/website-extract-social-media
index 96afcff..6d1b877 100755
--- a/website-extract-social-media
+++ b/website-extract-social-media
@@ -5,7 +5,7 @@ function fetch_n_extract {
 	local url="$1"
 	verbose_echo "Fetching ${url}" >&2
 	{
-		curl -sSL -A 'Mozilla/5.0 (Windows NT 6.1; rv:60.0) Gecko/20100101 Firefox/60.0' "${url}" | \
+		curl -sSL --max-time 10 -A 'Mozilla/5.0 (Windows NT 6.1; rv:60.0) Gecko/20100101 Firefox/60.0' "${url}" | \
 		  grep -Fi -e 'facebook' -e 'flickr' -e 'instagram' -e 'twitter' -e 't.me' -e 'youtube' -e 'youtu.be' -e 'vk.com' | \
 		  tee \
 			>(