discordo-plus/internal/ui/chat/url_extractor.go

package chat

import (
	"strings"

	"github.com/diamondburned/arikawa/v3/discord"
	"github.com/diamondburned/ningen/v3/discordmd"
	"github.com/yuin/goldmark/ast"
	"github.com/yuin/goldmark/parser"
	"github.com/yuin/goldmark/text"
)

func extractURLs(content string) []string {
	src := []byte(content)
	node := parser.NewParser(
		parser.WithBlockParsers(discordmd.BlockParsers()...),
		parser.WithInlineParsers(discordmd.InlineParserWithLink()...),
	).Parse(text.NewReader(src))

	var urls []string
	ast.Walk(node, func(n ast.Node, entering bool) (ast.WalkStatus, error) {
		if entering {
			switch n := n.(type) {
			case *ast.AutoLink:
				urls = append(urls, string(n.URL(src)))
			case *ast.Link:
				urls = append(urls, string(n.Destination))
			}
		}

		return ast.WalkContinue, nil
	})
	return urls
}

func extractEmbedURLs(embeds []discord.Embed) []string {
	urls := make([]string, 0, len(embeds)*3)
	for _, embed := range embeds {
		if embed.URL != "" {
			urls = append(urls, string(embed.URL))
		}
		if embed.Image != nil && embed.Image.URL != "" {
			urls = append(urls, string(embed.Image.URL))
		}
		if embed.Video != nil && embed.Video.URL != "" {
			urls = append(urls, string(embed.Video.URL))
		}
	}
	return urls
}

func messageURLs(msg discord.Message) []string {
	combined := extractURLs(msg.Content)
	combined = append(combined, extractEmbedURLs(msg.Embeds)...)

	urls := make([]string, 0, len(combined))
	seen := make(map[string]struct{}, len(combined))
	for _, u := range combined {
		u = strings.TrimSpace(u)
		if u == "" {
			continue
		}
		if _, ok := seen[u]; ok {
			continue
		}
		seen[u] = struct{}{}
		urls = append(urls, u)
	}
	return urls
}