diff options
| author | sigoden <sigoden@gmail.com> | 2024-06-05 18:37:52 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-06-05 18:37:52 +0800 |
| commit | 005d23030dab2b7708996e779dc78dd5f8ebdb8d (patch) | |
| tree | 0d05583d462a4795a4236a5006befc096047e969 /sh/get_web_page.sh | |
| parent | 7e3f47093f2dcb36cf94a35403027ec72bf7b084 (diff) | |
| download | llm-functions-docker-005d23030dab2b7708996e779dc78dd5f8ebdb8d.tar.gz | |
feat: adjust project structure (#16)
Diffstat (limited to 'sh/get_web_page.sh')
| -rwxr-xr-x | sh/get_web_page.sh | 14 |
1 files changed, 0 insertions, 14 deletions
diff --git a/sh/get_web_page.sh b/sh/get_web_page.sh deleted file mode 100755 index 65e6d2a..0000000 --- a/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 "$0" "$@")" |
