aboutsummaryrefslogtreecommitdiffstats
path: root/tools/sh/get_web_page.sh
diff options
context:
space:
mode:
authorsigoden <sigoden@gmail.com>2024-06-06 08:29:00 +0800
committerGitHub <noreply@github.com>2024-06-06 08:29:00 +0800
commitbfb7d75fe47ea588495c5be8157a67b1fec67a13 (patch)
treeb1996472711a1ccae391f1bded61adf3475b89ed /tools/sh/get_web_page.sh
parent005d23030dab2b7708996e779dc78dd5f8ebdb8d (diff)
downloadllm-functions-docker-bfb7d75fe47ea588495c5be8157a67b1fec67a13.tar.gz
refactor: move tools/$lang/** to tools/** (#17)
Diffstat (limited to 'tools/sh/get_web_page.sh')
-rwxr-xr-xtools/sh/get_web_page.sh14
1 files changed, 0 insertions, 14 deletions
diff --git a/tools/sh/get_web_page.sh b/tools/sh/get_web_page.sh
deleted file mode 100755
index 65e6d2a..0000000
--- a/tools/sh/get_web_page.sh
+++ /dev/null
@@ -1,14 +0,0 @@
-#!/usr/bin/env bash
-set -e
-
-# @describe Fetches the HTML content from a specified webpage URL and converts it to Markdown format.
-# Use it to answer user questions that require up-to-date content from web pages.
-# @meta require-tools curl,pandoc,sed
-# @option --url! The URL to scrape.
-
-main() {
- # span and div tags are dropped from the HTML https://pandoc.org/MANUAL.html#raw-htmltex and sed removes any inline SVG images in image tags from the Markdown content.
- curl -fsSL "$argc_url" | pandoc -f html-native_divs-native_spans -t gfm-raw_html | sed -E 's/!\[.*?\]\((data:image\/svg\+xml[^)]+)\)//g'
-}
-
-eval "$(argc --argc-eval "$0" "$@")"