fix: remove MaxDepth and link extraction functionality

cmd/web.go

@@ -204,45 +204,17 @@ func generateDefaultFilename() string {
 	return fmt.Sprintf("web-%s.rollup.md", timestamp)
 }
 
-func scrapeRecursively(urlStr string, depth int) (string, error) {
-	visited := make(map[string]bool)
-	return scrapeURL(urlStr, depth, visited)
-}
-
-func scrapeURL(urlStr string, depth int, visited map[string]bool) (string, error) {
-	if depth < 0 || visited[urlStr] {
-		return "", nil
-	}
-
-	visited[urlStr] = true
-
+func scrapeURL(urlStr string) (string, error) {
 	content, err := testExtractAndConvertContent(urlStr)
 	if err != nil {
 		return "", err
 	}
 
-	if depth > 0 {
-		links, err := testExtractLinks(urlStr)
-		if err != nil {
-			return content, fmt.Errorf("error extracting links: %v", err)
-		}
-
-		for _, link := range links {
-			subContent, err := scrapeURL(link, depth-1, visited)
-			if err != nil {
-				fmt.Printf("Warning: Error scraping %s: %v\n", link, err)
-				continue
-			}
-			content += "\n\n---\n\n" + subContent
-		}
-	}
-
 	return content, nil
 }
 
 var (
 	testExtractAndConvertContent = extractAndConvertContent
-	testExtractLinks             = scraper.ExtractLinks
 )
 
 func extractAndConvertContent(urlStr string) (string, error) {

internal/config/config.go

@@ -42,9 +42,6 @@ type SiteConfig struct {
 	// ExcludeSelectors lists CSS selectors for content to exclude
 	ExcludeSelectors []string `yaml:"exclude_selectors"`
 
-	// MaxDepth sets the maximum depth for link traversal
-	MaxDepth int `yaml:"max_depth"`
-
 	// AllowedPaths lists paths that are allowed to be scraped
 	AllowedPaths []string `yaml:"allowed_paths"`
 
@@ -103,9 +100,6 @@ func (c *Config) Validate() error {
 		if site.BaseURL == "" {
 			return fmt.Errorf("base_url must be specified for each site")
 		}
-		if site.MaxDepth < 0 {
-			return fmt.Errorf("max_depth must be non-negative")
-		}
 	}
 
 	return nil

internal/scraper/scraper.go

@@ -45,7 +45,6 @@ type SiteConfig struct {
 	BaseURL          string
 	CSSLocator       string
 	ExcludeSelectors []string
-	MaxDepth         int
 	AllowedPaths     []string
 	ExcludePaths     []string
 	OutputAlias      string
@@ -510,40 +509,6 @@ func scrollPage(page playwright.Page) error {
 	return nil
 }
 
-// ExtractLinks extracts all links from the given URL
-func ExtractLinks(urlStr string) ([]string, error) {
-	logger.Printf("Extracting links from URL: %s\n", urlStr)
-
-	page, err := browser.NewPage()
-	if err != nil {
-		return nil, fmt.Errorf("could not create page: %v", err)
-	}
-	defer page.Close()
-
-	if _, err = page.Goto(urlStr, playwright.PageGotoOptions{
-		WaitUntil: playwright.WaitUntilStateNetworkidle,
-	}); err != nil {
-		return nil, fmt.Errorf("could not go to page: %v", err)
-	}
-
-	links, err := page.Evaluate(`() => {
-		const anchors = document.querySelectorAll('a');
-		return Array.from(anchors).map(a => a.href);
-	}`)
-	if err != nil {
-		return nil, fmt.Errorf("could not extract links: %v", err)
-	}
-
-	var result []string
-	for _, link := range links.([]interface{}) {
-		// Normalize URL by removing trailing slash
-		normalizedLink := strings.TrimRight(link.(string), "/")
-		result = append(result, normalizedLink)
-	}
-
-	logger.Printf("Extracted %d links\n", len(result))
-	return result, nil
-}
 
 // ExtractContentWithCSS extracts content from HTML using a CSS selector
 func ExtractContentWithCSS(content, includeSelector string, excludeSelectors []string) (string, error) {