fix multi-file output

* flatten scrape config to 'sites:'. Update unit tests and readme.
* remove check for file_extensions configuration. 
* show progress indication after 5 seconds.
* add documentation to functions
* fix: remove MaxDepth and link extraction functionality
* fix: Remove MaxDepth references from cmd/web.go

README.md

@@ -15,7 +15,7 @@ Rollup aggregates the contents of text-based files and webpages into a markdown
 - Flexible configuration file support (YAML)
 - Automatic generation of default configuration file
 - Custom output file naming
-- Concurrent processing for improved performance
+- Rate limiting for web scraping to respect server resources
 
 ## Installation
 
@@ -66,16 +66,15 @@ Rollup can be configured using a YAML file. By default, it looks for `rollup.yml
 Example `rollup.yml`:
 
 ```yaml
-file_types:
+file_extensions:
   - go
   - md
-ignore:
+ignore_paths:
   - node_modules/**
   - vendor/**
   - .git/**
-code_generated:
+code_generated_paths:
   - **/generated/**
-scrape:
 sites:
   - base_url: https://example.com
     css_locator: .content
@@ -107,10 +106,10 @@ scrape:
    rollup files
    ```
 
-2. Web scraping with multiple URLs and increased concurrency:
+2. Web scraping with multiple URLs:
 
    ```bash
-   rollup web --urls=https://example.com,https://another-example.com --concurrent=8
+   rollup web --urls=https://example.com,https://another-example.com
    ```
 
 3. Generate a default configuration file:
@@ -119,20 +118,22 @@ scrape:
    rollup generate
    ```
 
-4. Use a custom configuration file and specify output:
+4. Use a custom configuration file:
 
    ```bash
-   rollup files --config=my-config.yml --output=project_summary.md
+   rollup files --config=my-config.yml
    ```
 
-5. Web scraping with separate output files and custom timeout:
+5. Web scraping with separate output files:
+
    ```bash
-   rollup web --urls=https://example.com,https://another-example.com --output=separate --timeout=60
+   rollup web --urls=https://example.com,https://another-example.com --output=separate
    ```
 
 6. Rollup files with specific types and ignore patterns:
+
    ```bash
-   rollup files --types=.go,.md --ignore=vendor/**,*_test.go
+   rollup files --types=go,md --ignore=vendor/**,*_test.go
    ```
 
 7. Web scraping with depth and CSS selector:

cmd/files.go

@@ -108,19 +108,20 @@ func isIgnored(filePath string, patterns []string) bool {
 
 func runRollup(cfg *config.Config) error {
 	// Use config if available, otherwise use command-line flags
-	var types, codeGenList, ignoreList []string
+	var types []string
-	if cfg != nil && len(cfg.FileTypes) > 0 {
+	var codeGenList, ignoreList []string
-		types = cfg.FileTypes
+	if cfg != nil && len(cfg.FileExtensions) > 0 {
+		types = cfg.FileExtensions
 	} else {
 		types = strings.Split(fileTypes, ",")
 	}
-	if cfg != nil && len(cfg.CodeGenerated) > 0 {
+	if cfg != nil && len(cfg.CodeGeneratedPaths) > 0 {
-		codeGenList = cfg.CodeGenerated
+		codeGenList = cfg.CodeGeneratedPaths
 	} else {
 		codeGenList = strings.Split(codeGenPatterns, ",")
 	}
-	if cfg != nil && cfg.Ignore != nil && len(cfg.Ignore) > 0 {
+	if cfg != nil && len(cfg.IgnorePaths) > 0 {
-		ignoreList = cfg.Ignore
+		ignoreList = cfg.IgnorePaths
 	} else {
 		ignoreList = strings.Split(ignorePatterns, ",")
 	}
@@ -145,6 +146,11 @@ func runRollup(cfg *config.Config) error {
 	}
 	defer outputFile.Close()
 
+	startTime := time.Now()
+	showProgress := false
+	progressTicker := time.NewTicker(500 * time.Millisecond)
+	defer progressTicker.Stop()
+
 	// Walk through the directory
 	err = filepath.Walk(absPath, func(path string, info os.FileInfo, err error) error {
 		if err != nil {
@@ -160,16 +166,25 @@ func runRollup(cfg *config.Config) error {
 
 		// Check if the file should be ignored
 		if isIgnored(relPath, ignoreList) {
+			if verbose {
+				fmt.Printf("Ignoring file: %s\n", relPath)
+			}
 			return nil
 		}
 
 		ext := filepath.Ext(path)
 		for _, t := range types {
 			if ext == "."+t {
+				// Verbose logging for processed file
+				if verbose {
+					size := humanReadableSize(info.Size())
+					fmt.Printf("Processing file: %s (%s)\n", relPath, size)
+				}
+
 				// Read file contents
 				content, err := os.ReadFile(path)
 				if err != nil {
-					fmt.Printf("Error reading file %s: %v", path, err)
+					fmt.Printf("Error reading file %s: %v\n", path, err)
 					return nil
 				}
 
@@ -185,12 +200,43 @@ func runRollup(cfg *config.Config) error {
 				break
 			}
 		}
+
+		if !showProgress && time.Since(startTime) > 5*time.Second {
+			showProgress = true
+			fmt.Print("This is taking a while (hold tight) ")
+		}
+
+		select {
+		case <-progressTicker.C:
+			if showProgress {
+				fmt.Print(".")
+			}
+		default:
+		}
+
 		return nil
 	})
 	if err != nil {
 		return fmt.Errorf("error walking through directory: %v", err)
 	}
 
-	fmt.Printf("Rollup complete. Output file: %s", outputFileName)
+	if showProgress {
+		fmt.Println() // Print a newline after the progress dots
+	}
+
+	fmt.Printf("Rollup complete. Output file: %s\n", outputFileName)
 	return nil
 }
+
+func humanReadableSize(size int64) string {
+	const unit = 1024
+	if size < unit {
+		return fmt.Sprintf("%d B", size)
+	}
+	div, exp := int64(unit), 0
+	for n := size / unit; n >= unit; n /= unit {
+		div *= unit
+		exp++
+	}
+	return fmt.Sprintf("%.1f %cB", float64(size)/float64(div), "KMGTPE"[exp])
+}

cmd/files_test.go

@@ -112,9 +112,9 @@ func TestRunRollup(t *testing.T) {
 
 	// Set up test configuration
 	cfg = &config.Config{
-		FileTypes:     []string{"go", "txt", "md"},
+		FileExtensions:     []string{"go", "txt", "md"},
-		Ignore:        []string{"*.json", ".git/**", "vendor/**"},
+		IgnorePaths:        []string{"*.json", ".git/**", "vendor/**"},
-		CodeGenerated: []string{"generated_*.go"},
+		CodeGeneratedPaths: []string{"generated_*.go"},
 	}
 
 	// Change working directory to the temp directory

cmd/generate.go

@@ -38,23 +38,23 @@ func runGenerate(cmd *cobra.Command, args []string) error {
 	}
 
 	cfg := config.Config{
-		FileTypes: make([]string, 0, len(fileTypes)),
+		FileExtensions: make([]string, 0, len(fileTypes)),
-		Ignore:    []string{"node_modules/**", "vendor/**", ".git/**"},
+		IgnorePaths:    []string{"node_modules/**", "vendor/**", ".git/**"},
 	}
 
 	for ext := range fileTypes {
-		cfg.FileTypes = append(cfg.FileTypes, ext)
+		cfg.FileExtensions = append(cfg.FileExtensions, ext)
 	}
 
 	// Sort file types for consistency
-	sort.Strings(cfg.FileTypes)
+	sort.Strings(cfg.FileExtensions)
 
 	yamlData, err := yaml.Marshal(&cfg)
 	if err != nil {
 		return fmt.Errorf("error marshaling config: %v", err)
 	}
 
-	outputPath := config.DefaultConfigPath()
+	outputPath := "rollup.yml"
 	err = os.WriteFile(outputPath, yamlData, 0644)
 	if err != nil {
 		return fmt.Errorf("error writing config file: %v", err)

cmd/web.go

@@ -18,7 +18,6 @@ import (
 var (
 	urls             []string
 	outputType       string
-	depth            int
 	includeSelector  string
 	excludeSelectors []string
 )
@@ -34,8 +33,7 @@ var webCmd = &cobra.Command{
 
 func init() {
 	webCmd.Flags().StringSliceVarP(&urls, "urls", "u", []string{}, "URLs of the webpages to scrape (comma-separated)")
-	webCmd.Flags().StringVarP(&outputType, "output", "o", "single", "Output type: 'single' for one file, 'separate' for multiple files")
+	webCmd.Flags().StringVarP(&outputType, "output", "o", "", "Output type: 'single' for one file, 'separate' for multiple files")
-	webCmd.Flags().IntVarP(&depth, "depth", "d", 0, "Depth of link traversal (default: 0, only scrape the given URLs)")
 	webCmd.Flags().StringVar(&includeSelector, "css", "", "CSS selector to extract specific content")
 	webCmd.Flags().StringSliceVar(&excludeSelectors, "exclude", []string{}, "CSS selectors to exclude from the extracted content (comma-separated)")
 }
@@ -50,22 +48,20 @@ func runWeb(cmd *cobra.Command, args []string) error {
 	scraperConfig.Verbose = verbose
 
 	var siteConfigs []scraper.SiteConfig
-	if len(cfg.Scrape.Sites) > 0 {
+	if len(cfg.Sites) > 0 {
-		logger.Printf("Using configuration from rollup.yml for %d sites", len(cfg.Scrape.Sites))
+		logger.Printf("Using configuration from rollup.yml for %d sites", len(cfg.Sites))
-		siteConfigs = make([]scraper.SiteConfig, len(cfg.Scrape.Sites))
+		siteConfigs = make([]scraper.SiteConfig, len(cfg.Sites))
-		for i, site := range cfg.Scrape.Sites {
+		for i, site := range cfg.Sites {
 			siteConfigs[i] = scraper.SiteConfig{
 				BaseURL:          site.BaseURL,
 				CSSLocator:       site.CSSLocator,
 				ExcludeSelectors: site.ExcludeSelectors,
-				MaxDepth:         site.MaxDepth,
 				AllowedPaths:     site.AllowedPaths,
 				ExcludePaths:     site.ExcludePaths,
-				OutputAlias:      site.OutputAlias,
 				PathOverrides:    convertPathOverrides(site.PathOverrides),
 			}
-			logger.Printf("Site %d configuration: BaseURL=%s, CSSLocator=%s, MaxDepth=%d, AllowedPaths=%v",
+			logger.Printf("Site %d configuration: BaseURL=%s, CSSLocator=%s, AllowedPaths=%v",
-				i+1, site.BaseURL, site.CSSLocator, site.MaxDepth, site.AllowedPaths)
+				i+1, site.BaseURL, site.CSSLocator, site.AllowedPaths)
 		}
 	} else {
 		logger.Printf("No sites defined in rollup.yml, falling back to URL-based configuration")
@@ -75,10 +71,9 @@ func runWeb(cmd *cobra.Command, args []string) error {
 				BaseURL:          u,
 				CSSLocator:       includeSelector,
 				ExcludeSelectors: excludeSelectors,
-				MaxDepth:         depth,
 			}
-			logger.Printf("URL %d configuration: BaseURL=%s, CSSLocator=%s, MaxDepth=%d",
+			logger.Printf("URL %d configuration: BaseURL=%s, CSSLocator=%s",
-				i+1, u, includeSelector, depth)
+				i+1, u, includeSelector)
 		}
 	}
 
@@ -92,13 +87,13 @@ func runWeb(cmd *cobra.Command, args []string) error {
 	defaultBurstLimit := 3
 
 	// Use default values if not set in the configuration
-	requestsPerSecond := cfg.Scrape.RequestsPerSecond
+	requestsPerSecond := defaultRequestsPerSecond
-	if requestsPerSecond == 0 {
+	if cfg.RequestsPerSecond != nil {
-		requestsPerSecond = defaultRequestsPerSecond
+		requestsPerSecond = *cfg.RequestsPerSecond
 	}
-	burstLimit := cfg.Scrape.BurstLimit
+	burstLimit := defaultBurstLimit
-	if burstLimit == 0 {
+	if cfg.BurstLimit != nil {
-		burstLimit = defaultBurstLimit
+		burstLimit = *cfg.BurstLimit
 	}
 
 	scraperConfig := scraper.Config{
@@ -114,20 +109,39 @@ func runWeb(cmd *cobra.Command, args []string) error {
 		outputType, requestsPerSecond, burstLimit)
 
 	logger.Println("Starting scraping process")
-	scrapedContent, err := scraper.ScrapeSites(scraperConfig)
+	startTime := time.Now()
+	progressTicker := time.NewTicker(time.Second)
+	defer progressTicker.Stop()
+
+	done := make(chan bool)
+	messagePrinted := false
+	go func() {
+		for {
+			select {
+			case <-progressTicker.C:
+				if time.Since(startTime) > 5*time.Second && !messagePrinted {
+					fmt.Print("This is taking a while (hold tight) ")
+					messagePrinted = true
+				} else if messagePrinted {
+					fmt.Print(".")
+				}
+			case <-done:
+				return
+			}
+		}
+	}()
+
+	err := scraper.ScrapeSites(scraperConfig)
+	done <- true
+	fmt.Println() // New line after progress indicator
+
 	if err != nil {
 		logger.Printf("Error occurred during scraping: %v", err)
 		return fmt.Errorf("error scraping content: %v", err)
 	}
-	logger.Printf("Scraping completed. Total content scraped: %d", len(scrapedContent))
+	logger.Println("Scraping completed")
 
-	if outputType == "single" {
+	return nil
-		logger.Println("Writing content to a single file")
-		return writeSingleFile(scrapedContent)
-	} else {
-		logger.Println("Writing content to multiple files")
-		return writeMultipleFiles(scrapedContent)
-	}
 }
 
 func writeSingleFile(content map[string]string) error {
@@ -179,45 +193,17 @@ func generateDefaultFilename() string {
 	return fmt.Sprintf("web-%s.rollup.md", timestamp)
 }
 
-func scrapeRecursively(urlStr string, depth int) (string, error) {
+func scrapeURL(urlStr string) (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
-
 	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) {

cmd/web_test.go

@@ -2,7 +2,7 @@ package cmd
 
 import (
 	"testing"
-	"strings"
+
 	"github.com/tnypxl/rollup/internal/config"
 )
 
@@ -102,53 +102,3 @@ func TestGetFilenameFromContent(t *testing.T) {
 func mockExtractAndConvertContent(urlStr string) (string, error) {
 	return "Mocked content for " + urlStr, nil
 }
-
-func mockExtractLinks() ([]string, error) {
-	return []string{"http://example.com/link1", "http://example.com/link2"}, nil
-}
-
-func TestScrapeURL(t *testing.T) {
-	// Store the original functions
-	originalExtractAndConvertContent := testExtractAndConvertContent
-	originalExtractLinks := testExtractLinks
-
-	// Define mock functions
-	testExtractAndConvertContent = func(urlStr string) (string, error) {
-		return "Mocked content for " + urlStr, nil
-	}
-	testExtractLinks = func(urlStr string) ([]string, error) {
-		return []string{"http://example.com/link1", "http://example.com/link2"}, nil
-	}
-
-	// Defer the restoration of original functions
-	defer func() {
-		testExtractAndConvertContent = originalExtractAndConvertContent
-		testExtractLinks = originalExtractLinks
-	}()
-
-	tests := []struct {
-		url           string
-		depth         int
-		expectedCalls int
-	}{
-		{"http://example.com", 0, 1},
-		{"http://example.com", 1, 3},
-		{"http://example.com", 2, 3}, // Same as depth 1 because our mock only returns 2 links
-	}
-
-	for _, test := range tests {
-		visited := make(map[string]bool)
-		content, err := scrapeURL(test.url, test.depth, visited)
-		if err != nil {
-			t.Errorf("scrapeURL(%q, %d) returned error: %v", test.url, test.depth, err)
-			continue
-		}
-		if len(visited) != test.expectedCalls {
-			t.Errorf("scrapeURL(%q, %d) made %d calls, expected %d", test.url, test.depth, len(visited), test.expectedCalls)
-		}
-		expectedContent := "Mocked content for " + test.url
-		if !strings.Contains(content, expectedContent) {
-			t.Errorf("scrapeURL(%q, %d) content doesn't contain %q", test.url, test.depth, expectedContent)
-		}
-	}
-}

internal/config/config.go

@@ -7,34 +7,63 @@ import (
 	"gopkg.in/yaml.v2"
 )
 
+// Config represents the configuration for the rollup tool
 type Config struct {
-	FileTypes     []string     `yaml:"file_types"`
+	// FileExtensions is a list of file extensions to include in the rollup
-	Ignore        []string     `yaml:"ignore"`
+	FileExtensions []string `yaml:"file_extensions"`
-	CodeGenerated []string     `yaml:"code_generated"`
-	Scrape        ScrapeConfig `yaml:"scrape"`
-}
 
-type ScrapeConfig struct {
+	// IgnorePaths is a list of glob patterns for paths to ignore
+	IgnorePaths []string `yaml:"ignore_paths"`
+
+	// CodeGeneratedPaths is a list of glob patterns for code-generated files
+	CodeGeneratedPaths []string `yaml:"code_generated_paths"`
+
+	// Sites is a list of site configurations for web scraping
 	Sites []SiteConfig `yaml:"sites"`
+
+	// OutputType specifies how the output should be generated
 	OutputType string `yaml:"output_type"`
-    RequestsPerSecond float64      `yaml:"requests_per_second"`
+
-    BurstLimit        int          `yaml:"burst_limit"`
+	// RequestsPerSecond limits the rate of web requests
+	RequestsPerSecond *float64 `yaml:"requests_per_second,omitempty"`
+
+	// BurstLimit sets the maximum burst size for rate limiting
+	BurstLimit *int `yaml:"burst_limit,omitempty"`
 }
 
+// SiteConfig contains configuration for scraping a single site
 type SiteConfig struct {
+	// BaseURL is the starting point for scraping this site
 	BaseURL string `yaml:"base_url"`
+
+	// CSSLocator is used to extract specific content
 	CSSLocator string `yaml:"css_locator"`
+
+	// ExcludeSelectors lists CSS selectors for content to exclude
 	ExcludeSelectors []string `yaml:"exclude_selectors"`
-    MaxDepth         int               `yaml:"max_depth"`
+
+	// AllowedPaths lists paths that are allowed to be scraped
 	AllowedPaths []string `yaml:"allowed_paths"`
+
+	// ExcludePaths lists paths that should not be scraped
 	ExcludePaths []string `yaml:"exclude_paths"`
-    OutputAlias      string            `yaml:"output_alias"`
+
+	// FileNamePrefix provides the base name for output files
+	FileNamePrefix string `yaml:"file_name_prefix"`
+
+	// PathOverrides allows for path-specific configurations
 	PathOverrides []PathOverride `yaml:"path_overrides"`
 }
 
+// PathOverride allows for path-specific configurations
 type PathOverride struct {
+	// Path is the URL path this override applies to
 	Path string `yaml:"path"`
+
+	// CSSLocator overrides the site-wide CSS locator for this path
 	CSSLocator string `yaml:"css_locator"`
+
+	// ExcludeSelectors overrides the site-wide exclude selectors for this path
 	ExcludeSelectors []string `yaml:"exclude_selectors"`
 }
 
@@ -50,15 +79,28 @@ func Load(configPath string) (*Config, error) {
 		return nil, fmt.Errorf("error parsing config file: %v", err)
 	}
 
+	if err := config.Validate(); err != nil {
+		return nil, fmt.Errorf("invalid configuration: %v", err)
+	}
+
 	return &config, nil
 }
 
-func DefaultConfigPath() string {
+// Validate checks the configuration for any invalid values
-	return "rollup.yml"
+func (c *Config) Validate() error {
+	if c.RequestsPerSecond != nil && *c.RequestsPerSecond <= 0 {
+		return fmt.Errorf("requests_per_second must be positive")
 	}
 
-func FileExists(filename string) bool {
+	if c.BurstLimit != nil && *c.BurstLimit <= 0 {
-	_, err := os.Stat(filename)
+		return fmt.Errorf("burst_limit must be positive")
-	return err == nil
 	}
 
+	for _, site := range c.Sites {
+		if site.BaseURL == "" {
+			return fmt.Errorf("base_url must be specified for each site")
+		}
+	}
+
+	return nil
+}

internal/config/config_test.go

@@ -9,15 +9,14 @@ import (
 func TestLoad(t *testing.T) {
 	// Create a temporary config file
 	content := []byte(`
-file_types:
+file_extensions:
-  - go
+  - .go
-  - md
+  - .md
-ignore:
+ignore_paths:
   - "*.tmp"
   - "**/*.log"
-code_generated:
+code_generated_paths:
   - "generated_*.go"
-scrape:
 sites:
   - base_url: "https://example.com"
     css_locator: "main"
@@ -28,7 +27,7 @@ scrape:
       - "/blog"
     exclude_paths:
       - "/admin"
-      output_alias: "example"
+      file_name_prefix: "example"
     path_overrides:
       - path: "/special"
         css_locator: ".special-content"
@@ -59,20 +58,20 @@ scrape:
 	}
 
 	// Check if the loaded config matches the expected values
+	rps := 1.0
+	bl := 5
 	expectedConfig := &Config{
-		FileTypes:     []string{"go", "md"},
+		FileExtensions:     []string{".go", ".md"},
-		Ignore:        []string{"*.tmp", "**/*.log"},
+		IgnorePaths:        []string{"*.tmp", "**/*.log"},
-		CodeGenerated: []string{"generated_*.go"},
+		CodeGeneratedPaths: []string{"generated_*.go"},
-		Scrape: ScrapeConfig{
 		Sites: []SiteConfig{
 			{
 				BaseURL:          "https://example.com",
 				CSSLocator:       "main",
 				ExcludeSelectors: []string{".ads"},
-					MaxDepth:         2,
 				AllowedPaths:     []string{"/blog"},
 				ExcludePaths:     []string{"/admin"},
-					OutputAlias:      "example",
+				FileNamePrefix:   "example",
 				PathOverrides: []PathOverride{
 					{
 						Path:             "/special",
@@ -83,9 +82,8 @@ scrape:
 			},
 		},
 		OutputType:        "single",
-			RequestsPerSecond: 1.0,
+		RequestsPerSecond: &rps,
-			BurstLimit:        5,
+		BurstLimit:        &bl,
-		},
 	}
 
 	if !reflect.DeepEqual(config, expectedConfig) {
@@ -93,28 +91,67 @@ scrape:
 	}
 }
 
-func TestDefaultConfigPath(t *testing.T) {
+func TestValidate(t *testing.T) {
-	expected := "rollup.yml"
+	tests := []struct {
-	result := DefaultConfigPath()
+		name    string
-	if result != expected {
+		config  Config
-		t.Errorf("DefaultConfigPath() = %q, want %q", result, expected)
+		wantErr bool
-	}
+	}{
+		{
+			name: "Valid config",
+			config: Config{
+				FileExtensions: []string{".go"},
+				Sites: []SiteConfig{
+					{BaseURL: "https://example.com"},
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name:    "No file extensions",
+			config:  Config{},
+			wantErr: true,
+		},
+		{
+			name: "Invalid requests per second",
+			config: Config{
+				FileExtensions:    []string{".go"},
+				RequestsPerSecond: func() *float64 { f := -1.0; return &f }(),
+			},
+			wantErr: true,
+		},
+		{
+			name: "Invalid burst limit",
+			config: Config{
+				FileExtensions: []string{".go"},
+				BurstLimit:     func() *int { i := -1; return &i }(),
+			},
+			wantErr: true,
+		},
+		{
+			name: "Site without base URL",
+			config: Config{
+				FileExtensions: []string{".go"},
+				Sites:          []SiteConfig{{}},
+			},
+			wantErr: true,
+		},
+		{
+			name: "Negative max depth",
+			config: Config{
+				FileExtensions: []string{".go"},
+				Sites:          []SiteConfig{{BaseURL: "https://example.com"}},
+			},
+			wantErr: true,
+		},
 	}
 
-func TestFileExists(t *testing.T) {
+	for _, tt := range tests {
-	// Test with an existing file
+		t.Run(tt.name, func(t *testing.T) {
-	tmpfile, err := os.CreateTemp("", "testfile")
+			err := tt.config.Validate()
-	if err != nil {
+			if (err != nil) != tt.wantErr {
-		t.Fatalf("Failed to create temp file: %v", err)
+				t.Errorf("Validate() error = %v, wantErr %v", err, tt.wantErr)
 			}
-	defer os.Remove(tmpfile.Name())
+		})
-
-	if !FileExists(tmpfile.Name()) {
-		t.Errorf("FileExists(%q) = false, want true", tmpfile.Name())
-	}
-
-	// Test with a non-existing file
-	if FileExists("non_existing_file.txt") {
-		t.Errorf("FileExists(\"non_existing_file.txt\") = true, want false")
 	}
 }

internal/scraper/scraper.go

@@ -8,6 +8,7 @@ import (
 	"math/rand"
 	"net/url"
 	"os"
+	"path/filepath"
 	"regexp"
 	"strings"
 	"sync"
@@ -45,10 +46,9 @@ type SiteConfig struct {
 	BaseURL          string
 	CSSLocator       string
 	ExcludeSelectors []string
-	MaxDepth         int
 	AllowedPaths     []string
 	ExcludePaths     []string
-	OutputAlias      string
+	FileNamePrefix   string
 	PathOverrides    []PathOverride
 }
 
@@ -59,16 +59,18 @@ type PathOverride struct {
 	ExcludeSelectors []string
 }
 
-func ScrapeSites(config Config) (map[string]string, error) {
+func ScrapeSites(config Config) error {
 	logger.Println("Starting ScrapeSites function - Verbose mode is active")
 	results := make(chan struct {
 		url     string
 		content string
+		site    SiteConfig // Add site config to track which site the content came from
 		err     error
 	})
 
 	limiter := rate.NewLimiter(rate.Limit(config.Scrape.RequestsPerSecond), config.Scrape.BurstLimit)
-	logger.Printf("Rate limiter configured with %f requests per second and burst limit of %d\n", config.Scrape.RequestsPerSecond, config.Scrape.BurstLimit)
+	logger.Printf("Rate limiter configured with %f requests per second and burst limit of %d\n",
+		config.Scrape.RequestsPerSecond, config.Scrape.BurstLimit)
 
 	var wg sync.WaitGroup
 	totalURLs := 0
@@ -92,120 +94,71 @@ func ScrapeSites(config Config) (map[string]string, error) {
 		logger.Println("All goroutines completed, results channel closed")
 	}()
 
-	scrapedContent := make(map[string]string)
+	// Use a map that includes site configuration
+	scrapedContent := make(map[string]struct {
+		content string
+		site    SiteConfig
+	})
+
 	for result := range results {
 		if result.err != nil {
 			logger.Printf("Error scraping %s: %v\n", result.url, result.err)
 			continue
 		}
-		logger.Printf("Successfully scraped content from %s (length: %d)\n", result.url, len(result.content))
+		logger.Printf("Successfully scraped content from %s (length: %d)\n",
-		scrapedContent[result.url] = result.content
+			result.url, len(result.content))
+		scrapedContent[result.url] = struct {
+			content string
+			site    SiteConfig
+		}{
+			content: result.content,
+			site:    result.site,
+		}
 	}
 
 	logger.Printf("Total URLs processed: %d\n", totalURLs)
 	logger.Printf("Successfully scraped content from %d URLs\n", len(scrapedContent))
 
-	return scrapedContent, nil
+	return SaveToFiles(scrapedContent, config)
 }
 
 func scrapeSingleURL(url string, site SiteConfig, results chan<- struct {
 	url     string
 	content string
+	site    SiteConfig
 	err     error
-}, limiter *rate.Limiter,
+}, limiter *rate.Limiter) {
-) {
 	logger.Printf("Starting to scrape URL: %s\n", url)
 
-	// Wait for rate limiter before making the request
-	err := limiter.Wait(context.Background())
-	if err != nil {
-		logger.Printf("Rate limiter error for %s: %v\n", url, err)
-		results <- struct {
-			url     string
-			content string
-			err     error
-		}{url, "", fmt.Errorf("rate limiter error: %v", err)}
-		return
-	}
-
-	cssLocator, excludeSelectors := getOverrides(url, site)
-	logger.Printf("Using CSS locator for %s: %s\n", url, cssLocator)
-	logger.Printf("Exclude selectors for %s: %v\n", url, excludeSelectors)
-
-	content, err := scrapeURL(url, cssLocator, excludeSelectors)
-	if err != nil {
-		logger.Printf("Error scraping %s: %v\n", url, err)
-		results <- struct {
-			url     string
-			content string
-			err     error
-		}{url, "", err}
-		return
-	}
-
-	if content == "" {
-		logger.Printf("Warning: Empty content scraped from %s\n", url)
-	} else {
-		logger.Printf("Successfully scraped content from %s (length: %d)\n", url, len(content))
-	}
-
-	results <- struct {
-		url     string
-		content string
-		err     error
-	}{url, content, nil}
-}
-
-func scrapeSite(site SiteConfig, results chan<- struct {
-	url     string
-	content string
-	err     error
-}, limiter *rate.Limiter,
-) {
-	visited := make(map[string]bool)
-	queue := []string{site.BaseURL}
-
-	for len(queue) > 0 {
-		url := queue[0]
-		queue = queue[1:]
-
-		if visited[url] {
-			continue
-		}
-		visited[url] = true
-
-		if !isAllowedURL(url, site) {
-			continue
-		}
-
-		// Wait for rate limiter before making the request
 	err := limiter.Wait(context.Background())
 	if err != nil {
 		results <- struct {
 			url     string
 			content string
+			site    SiteConfig
 			err     error
-			}{url, "", fmt.Errorf("rate limiter error: %v", err)}
+		}{url, "", site, fmt.Errorf("rate limiter error: %v", err)}
-			continue
+		return
 	}
 
 	cssLocator, excludeSelectors := getOverrides(url, site)
 	content, err := scrapeURL(url, cssLocator, excludeSelectors)
+	if err != nil {
 		results <- struct {
 			url     string
 			content string
+			site    SiteConfig
 			err     error
-		}{url, content, err}
+		}{url, "", site, err}
+		return
+	}
 
-		if len(visited) < site.MaxDepth {
+	results <- struct {
-			links, _ := ExtractLinks(url)
+		url     string
-			for _, link := range links {
+		content string
-				if !visited[link] && isAllowedURL(link, site) {
+		site    SiteConfig
-					queue = append(queue, link)
+		err     error
-				}
+	}{url, content, site, nil}
-			}
-		}
-	}
 }
 
 func isAllowedURL(urlStr string, site SiteConfig) bool {
@@ -280,9 +233,14 @@ func getFilenameFromContent(content, url string) string {
 }
 
 func sanitizeFilename(name string) string {
-	// Remove any character that isn't alphanumeric, dash, or underscore
+	// Replace all non-alphanumeric characters with dashes
-	reg, _ := regexp.Compile("[^a-zA-Z0-9-_]+")
+	reg := regexp.MustCompile("[^a-zA-Z0-9]+")
-	return reg.ReplaceAllString(name, "_")
+	name = reg.ReplaceAllString(name, "-")
+	// Remove any leading or trailing dashes
+	name = strings.Trim(name, "-")
+	// Collapse multiple consecutive dashes into one
+	reg = regexp.MustCompile("-+")
+	return reg.ReplaceAllString(name, "-")
 }
 
 // URLConfig holds configuration for a single URL
@@ -290,7 +248,7 @@ type URLConfig struct {
 	URL              string
 	CSSLocator       string
 	ExcludeSelectors []string
-	OutputAlias      string
+	FileNamePrefix   string
 }
 
 // SetupLogger initializes the logger based on the verbose flag
@@ -318,7 +276,7 @@ func InitPlaywright() error {
 		return fmt.Errorf("could not start Playwright: %v", err)
 	}
 
-	userAgent := "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
+	userAgent := "Mozilla/5.0 (Linux; Android 15; Pixel 9 Build/AP3A.241105.008) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.6723.106 Mobile Safari/537.36 OPX/2.5"
 
 	browser, err = pw.Chromium.Launch(playwright.BrowserTypeLaunchOptions{
 		Args: []string{fmt.Sprintf("--user-agent=%s", userAgent)},
@@ -351,6 +309,119 @@ func CloseBrowser() {
 	ClosePlaywright()
 }
 
+// SaveToFiles writes the scraped content to files based on output type
+func SaveToFiles(content map[string]struct {
+	content string
+	site    SiteConfig
+}, config Config) error {
+	if config.OutputType == "" {
+		config.OutputType = "separate" // default to separate files if not specified
+	}
+
+	switch config.OutputType {
+	case "single":
+		if err := os.MkdirAll("output", 0755); err != nil {
+			return fmt.Errorf("failed to create output directory: %v", err)
+		}
+		var combined strings.Builder
+		for url, data := range content {
+			combined.WriteString(fmt.Sprintf("## %s\n\n", url))
+			combined.WriteString(data.content)
+			combined.WriteString("\n\n")
+		}
+		return os.WriteFile(filepath.Join("output", "combined.md"), []byte(combined.String()), 0644)
+
+	case "separate":
+		if err := os.MkdirAll("output", 0755); err != nil {
+			return fmt.Errorf("failed to create output directory: %v", err)
+		}
+
+		// Group content by site and path
+		contentBySitePath := make(map[string]map[string]string)
+		for urlStr, data := range content {
+			parsedURL, err := url.Parse(urlStr)
+			if err != nil {
+				logger.Printf("Warning: Could not parse URL %s: %v", urlStr, err)
+				continue
+			}
+
+			// Find matching allowed path for this URL
+			var matchingPath string
+			for _, path := range data.site.AllowedPaths {
+				if strings.HasPrefix(parsedURL.Path, path) {
+					matchingPath = path
+					break
+				}
+			}
+			if matchingPath == "" {
+				logger.Printf("Warning: No matching allowed path for URL %s", urlStr)
+				continue
+			}
+
+			siteKey := fmt.Sprintf("%s-%s", data.site.BaseURL, data.site.FileNamePrefix)
+			if contentBySitePath[siteKey] == nil {
+				contentBySitePath[siteKey] = make(map[string]string)
+			}
+
+			// Combine all content for the same path
+			if existing, exists := contentBySitePath[siteKey][matchingPath]; exists {
+				contentBySitePath[siteKey][matchingPath] = existing + "\n\n" + data.content
+			} else {
+				contentBySitePath[siteKey][matchingPath] = data.content
+			}
+		}
+
+		// Write files for each site and path
+		for siteKey, pathContent := range contentBySitePath {
+			for path, content := range pathContent {
+				parts := strings.SplitN(siteKey, "-", 2) // Split only on first hyphen
+				prefix := parts[1]                       // Get the FileNamePrefix part
+				if prefix == "" {
+					prefix = "doc" // default prefix if none specified
+				}
+
+				normalizedPath := NormalizePathForFilename(path)
+				if normalizedPath == "" {
+					normalizedPath = "index"
+				}
+
+				filename := filepath.Join("output", fmt.Sprintf("%s-%s.md",
+					prefix, normalizedPath))
+
+				// Ensure we don't have empty files
+				if strings.TrimSpace(content) == "" {
+					logger.Printf("Skipping empty content for path %s", path)
+					continue
+				}
+
+				if err := os.WriteFile(filename, []byte(content), 0644); err != nil {
+					return fmt.Errorf("failed to write file %s: %v", filename, err)
+				}
+				logger.Printf("Wrote content to %s", filename)
+			}
+		}
+		return nil
+
+	default:
+		return fmt.Errorf("unsupported output type: %s", config.OutputType)
+	}
+}
+
+// NormalizePathForFilename converts a URL path into a valid filename component
+func NormalizePathForFilename(urlPath string) string {
+	// Remove leading/trailing slashes
+	path := strings.Trim(urlPath, "/")
+	// Replace all non-alphanumeric characters with dashes
+	reg := regexp.MustCompile("[^a-zA-Z0-9]+")
+	path = reg.ReplaceAllString(path, "-")
+	// Remove any leading or trailing dashes
+	path = strings.Trim(path, "-")
+	// Collapse multiple consecutive dashes into one
+	reg = regexp.MustCompile("-+")
+	path = reg.ReplaceAllString(path, "-")
+	return path
+}
+
 // FetchWebpageContent retrieves the content of a webpage using Playwright
 func FetchWebpageContent(urlStr string) (string, error) {
 	logger.Printf("Fetching webpage content for URL: %s\n", urlStr)
@@ -496,7 +567,6 @@ func scrollPage(page playwright.Page) error {
 
 		// Wait for a while before scrolling again
 
-		
 	}
 
 	logger.Println("Scrolling back to top")
@@ -510,41 +580,6 @@ 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) {
 	logger.Printf("Extracting content with CSS selector: %s\n", includeSelector)

internal/scraper/scraper_test.go

@@ -3,8 +3,8 @@ package scraper
 import (
 	"io"
 	"log"
-	"net/http"
+	// "net/http"
-	"net/http/httptest"
+	// "net/http/httptest"
 	"reflect"
 	"strings"
 	"testing"
@@ -143,39 +143,39 @@ This is a **test** paragraph.
 	}
 }
 
-func TestExtractLinks(t *testing.T) {
+// func TestExtractLinks(t *testing.T) {
-	// Initialize Playwright before running the test
+// 	// Initialize Playwright before running the test
-	if err := InitPlaywright(); err != nil {
+// 	if err := InitPlaywright(); err != nil {
-		t.Fatalf("Failed to initialize Playwright: %v", err)
+// 		t.Fatalf("Failed to initialize Playwright: %v", err)
-	}
+// 	}
-	defer ClosePlaywright()
+// 	defer ClosePlaywright()
 
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+// 	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		w.Header().Set("Content-Type", "text/html")
+// 		w.Header().Set("Content-Type", "text/html")
-		w.Write([]byte(`
+// 		w.Write([]byte(`
-			<html>
+// 			<html>
-				<body>
+// 				<body>
-					<a href="https://example.com/page1">Page 1</a>
+// 					<a href="https://example.com/page1">Page 1</a>
-					<a href="https://example.com/page2">Page 2</a>
+// 					<a href="https://example.com/page2">Page 2</a>
-					<a href="https://othersite.com">Other Site</a>
+// 					<a href="https://othersite.com">Other Site</a>
-				</body>
+// 				</body>
-			</html>
+// 			</html>
-		`))
+// 		`))
-	}))
+// 	}))
-	defer server.Close()
+// 	defer server.Close()
 
-	links, err := ExtractLinks(server.URL)
+// 	links, err := ExtractLinks(server.URL)
-	if err != nil {
+// 	if err != nil {
-		t.Fatalf("ExtractLinks() returned error: %v", err)
+// 		t.Fatalf("ExtractLinks() returned error: %v", err)
-	}
+// 	}
 
-	expectedLinks := []string{
+// 	expectedLinks := []string{
-		"https://example.com/page1",
+// 		"https://example.com/page1",
-		"https://example.com/page2",
+// 		"https://example.com/page2",
-		"https://othersite.com",
+// 		"https://othersite.com",
-	}
+// 	}
 
-	if !reflect.DeepEqual(links, expectedLinks) {
+// 	if !reflect.DeepEqual(links, expectedLinks) {
-		t.Errorf("ExtractLinks() = %v, want %v", links, expectedLinks)
+// 		t.Errorf("ExtractLinks() = %v, want %v", links, expectedLinks)
-	}
+// 	}
-}
+// }

main.go

@@ -20,7 +20,7 @@ func main() {
 	var err error
 
 	if !isHelpCommand {
-		configPath := config.DefaultConfigPath()
+		configPath := "rollup.yml"
 		cfg, err = config.Load(configPath)
 		if err != nil {
 			log.Printf("Warning: Failed to load configuration: %v", err)