blob: 119dff76d77f9424477ca66869db7e02b6d90967 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
#!/usr/bin/env bash
set -e
# @describe Get webpage content from a given URL.
# @meta require-tools pandoc
# @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 "$0" "$@")"
|
