diff options
| -rwxr-xr-x | tools/get_web_page.sh | 9 | ||||
| -rwxr-xr-x | tools/search_wikipedia.sh | 2 |
2 files changed, 6 insertions, 5 deletions
diff --git a/tools/get_web_page.sh b/tools/get_web_page.sh index 65e6d2a..4e1e16a 100755 --- a/tools/get_web_page.sh +++ b/tools/get_web_page.sh @@ -1,14 +1,15 @@ #!/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 +# @describe Get the contents from a 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' + 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 "$0" "$@")" diff --git a/tools/search_wikipedia.sh b/tools/search_wikipedia.sh index b352e40..8f055a4 100755 --- a/tools/search_wikipedia.sh +++ b/tools/search_wikipedia.sh @@ -1,7 +1,7 @@ #!/usr/bin/env bash set -e -# @describe Searche Wikipedia for a query. +# @describe Search Wikipedia for a query. # Uses it to get detailed information about a public figure, interpretation of a complex scientific concept or in-depth connectivity of a significant historical event,. # @option --query! The query to search for. |