marky

commit f4131c992e7e60795191bae870b3a3f5788942b3
parent 5f603fb84991b52ad00e9f75ecded99d83ed037a
Author: David Eisinger <[email protected]>
Date:   Tue,  7 Oct 2025 00:15:01 -0400

Prefer w3m if present

Diffstat:
M
README.md
 | 
2
+-
M
internal/archiver.go
 | 
24
+++++++++++++++++++++++-

2 files changed, 24 insertions(+), 2 deletions(-)
diff --git a/README.md b/README.md
@@ -11,7 +11,7 @@ A simple web API for bookmarking websites, written in Go. It stores bookmarks in
 
 - Go 1.24+ (tested with 1.24.5)
 - Make (optional, for the provided Makefile)
-  (No external tools required for archiving.)
+  (Optional) For archiving, if a `w3m` binary is available in `PATH`, marky uses it to render pages to plaintext; otherwise it falls back to the built‑in Go HTML‑to‑text renderer.
 
 ## Build
 
diff --git a/internal/archiver.go b/internal/archiver.go
@@ -7,6 +7,7 @@ import (
 	"io"
 	"net/http"
 	neturl "net/url"
+	"os/exec"
 	"strings"
 	"time"
 
@@ -33,10 +34,31 @@ func TitleAndText(ctx context.Context, rawURL string) (string, string, error) {
 	}
 	htmlStr := string(body)
 	title := extractTitle(htmlStr)
-	txt := strings.TrimSpace(htmlToText(htmlStr))
+	// Prefer external w3m if available for robust text rendering; fall back to built-in.
+	var txt string
+	if path, err := exec.LookPath("w3m"); err == nil && path != "" {
+		if out, err := w3mDump(ctx, rawURL); err == nil && strings.TrimSpace(out) != "" {
+			txt = strings.TrimSpace(out)
+		} else {
+			txt = strings.TrimSpace(htmlToText(htmlStr))
+		}
+	} else {
+		txt = strings.TrimSpace(htmlToText(htmlStr))
+	}
 	return title, txt, nil
 }
 
+// w3mDump runs `w3m -dump` to render the given URL to plaintext.
+func w3mDump(ctx context.Context, url string) (string, error) {
+	cmd := exec.CommandContext(ctx, "w3m", "-dump", "-T", "text/html", "-o", "display_link_number=1", url)
+	// Keep environment as-is; rely on user PATH. Capture stdout only.
+	b, err := cmd.Output()
+	if err != nil {
+		return "", fmt.Errorf("w3m dump: %w", err)
+	}
+	return string(b), nil
+}
+
 func fetchHTML(ctx context.Context, rawURL string) ([]byte, error) {
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, rawURL, nil)
 	if err != nil {