curl-grabtitle: do not try to get title for non-HTML URLs - annna - Annna the nice friendly bot.
(HTM) git clone git://bitreich.org/annna/ git://enlrupgkhuxnvlhsf6lc3fziv5h2hhfrinws65d7roiv6bfj7d652fid.onion/annna/
(DIR) Log
(DIR) Files
(DIR) Refs
(DIR) Tags
(DIR) README
---
(DIR) commit 408ac5316fd5a2b720b21bc5ae11db810bf33a7b
(DIR) parent a3e40e235d62c466db9c6c9a50b4e80ecad24958
(HTM) Author: Quentin Rameau <quinq@fifth.space>
Date: Thu, 15 Jul 2021 00:24:15 +0200
curl-grabtitle: do not try to get title for non-HTML URLs
Signed-off-by: Annna Robert-Houdin <annna@bitreich.org>
Diffstat:
M curl-grabtitle | 7 ++++---
M fetch-uri | 20 +++++++++++++++++---
2 files changed, 21 insertions(+), 6 deletions(-)
---
(DIR) diff --git a/curl-grabtitle b/curl-grabtitle
@@ -1,11 +1,12 @@
#!/bin/sh
export PATH="$HOME/bin:$PATH"
-if [ $# -lt 1 ];
+if [ $# -lt 1 ]
then
- printf "usage: %s\n" "$(basename "$0")" >&2
+ printf "usage: %s URI\n" "$(basename "$0")" >&2
exit 1
fi
-fetch-uri "$1" | grabtitle
+fetch-uri -h "$1" | grep '^content-type:.* text/html' >/dev/null 2>&1 || exit
+fetch-uri "$1" | grabtitle
(DIR) diff --git a/fetch-uri b/fetch-uri
@@ -1,9 +1,22 @@
#!/bin/sh
-if [ $# -lt 1 ];
-then
- printf "usage: %s\n" "$(basename "$0")" >&2
+set -x
+
+usage() {
+ printf "usage: %s [-h] URI\n" "$(basename "$0")" >&2
exit 1
+}
+
+if [ $# -lt 1 ] || [ $# -gt 2 ]
+then
+ usage
+fi
+
+if [ $# -eq 2 ]
+then
+ [ $1 = -h ] || usage
+ opth=-I
+ shift
fi
curl \
@@ -12,4 +25,5 @@ curl \
-L --max-redirs 3 \
-m 5 \
-H 'User-Agent:' \
+ $opth \
"$1" 2>/dev/null