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
 
@@ -66,37 +66,36 @@ 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:
-  sites:
+  - base_url: https://example.com
-    - base_url: https://example.com
+    css_locator: .content
-      css_locator: .content
+    exclude_selectors:
-      exclude_selectors:
+      - .ads
-        - .ads
+      - .navigation
-        - .navigation
+    max_depth: 2
-      max_depth: 2
+    allowed_paths:
-      allowed_paths:
+      - /blog
-        - /blog
+      - /docs
-        - /docs
+    exclude_paths:
-      exclude_paths:
+      - /admin
-        - /admin
+    output_alias: example
-      output_alias: example
+    path_overrides:
-      path_overrides:
+      - path: /special-page
-        - path: /special-page
+        css_locator: .special-content
-          css_locator: .special-content
+        exclude_selectors:
-          exclude_selectors:
+          - .special-ads
-            - .special-ads
+output_type: single
-  output_type: single
+requests_per_second: 1.0
-  requests_per_second: 1.0
+burst_limit: 3
-  burst_limit: 3
 ```
 
 ## Examples
@@ -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

@@ -2,7 +2,7 @@ package cmd
 
 import (
 	"fmt"
-	"io/ioutil"
+	"io"
 	"log"
 	"net/url"
 	"os"
@@ -18,7 +18,6 @@ import (
 var (
 	urls             []string
 	outputType       string
-	depth            int
 	includeSelector  string
 	excludeSelectors []string
 )
@@ -35,99 +34,121 @@ 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().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)")
 }
 
 func runWeb(cmd *cobra.Command, args []string) error {
-    scraper.SetupLogger(verbose)
+	scraper.SetupLogger(verbose)
-    logger := log.New(os.Stdout, "WEB: ", log.LstdFlags)
+	logger := log.New(os.Stdout, "WEB: ", log.LstdFlags)
-    if !verbose {
+	if !verbose {
-        logger.SetOutput(ioutil.Discard)
+		logger.SetOutput(io.Discard)
-    }
+	}
-    logger.Printf("Starting web scraping process with verbose mode: %v", verbose)
+	logger.Printf("Starting web scraping process with verbose mode: %v", verbose)
-    scraperConfig.Verbose = verbose
+	scraperConfig.Verbose = verbose
 
-    var siteConfigs []scraper.SiteConfig
+	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{
+			siteConfigs[i] = scraper.SiteConfig{
-                BaseURL:          site.BaseURL,
+				BaseURL:          site.BaseURL,
-                CSSLocator:       site.CSSLocator,
+				CSSLocator:       site.CSSLocator,
-                ExcludeSelectors: site.ExcludeSelectors,
+				ExcludeSelectors: site.ExcludeSelectors,
-                MaxDepth:         site.MaxDepth,
+				AllowedPaths:     site.AllowedPaths,
-                AllowedPaths:     site.AllowedPaths,
+				ExcludePaths:     site.ExcludePaths,
-                ExcludePaths:     site.ExcludePaths,
+				OutputAlias:      site.OutputAlias,
-                OutputAlias:      site.OutputAlias,
+				PathOverrides:    convertPathOverrides(site.PathOverrides),
-                PathOverrides:    convertPathOverrides(site.PathOverrides),
+			}
-            }
+			logger.Printf("Site %d configuration: BaseURL=%s, CSSLocator=%s, AllowedPaths=%v",
-            logger.Printf("Site %d configuration: BaseURL=%s, CSSLocator=%s, MaxDepth=%d, AllowedPaths=%v",
+				i+1, site.BaseURL, site.CSSLocator, site.AllowedPaths)
-                       i+1, site.BaseURL, site.CSSLocator, site.MaxDepth, site.AllowedPaths)
+		}
-        }
+	} else {
-    } else {
+		logger.Printf("No sites defined in rollup.yml, falling back to URL-based configuration")
-        logger.Printf("No sites defined in rollup.yml, falling back to URL-based configuration")
+		siteConfigs = make([]scraper.SiteConfig, len(urls))
-        siteConfigs = make([]scraper.SiteConfig, len(urls))
+		for i, u := range urls {
-        for i, u := range urls {
+			siteConfigs[i] = scraper.SiteConfig{
-            siteConfigs[i] = scraper.SiteConfig{
+				BaseURL:          u,
-                BaseURL:          u,
+				CSSLocator:       includeSelector,
-                CSSLocator:       includeSelector,
+				ExcludeSelectors: excludeSelectors,
-                ExcludeSelectors: excludeSelectors,
+			}
-                MaxDepth:         depth,
+			logger.Printf("URL %d configuration: BaseURL=%s, CSSLocator=%s",
-            }
+				i+1, u, includeSelector)
-            logger.Printf("URL %d configuration: BaseURL=%s, CSSLocator=%s, MaxDepth=%d",
+		}
-                       i+1, u, includeSelector, depth)
+	}
-        }
-    }
 
-    if len(siteConfigs) == 0 {
+	if len(siteConfigs) == 0 {
-        logger.Println("Error: No sites or URLs provided")
+		logger.Println("Error: No sites or URLs provided")
-        return fmt.Errorf("no sites or URLs provided. Use --urls flag with comma-separated URLs or set 'scrape.sites' in the rollup.yml file")
+		return fmt.Errorf("no sites or URLs provided. Use --urls flag with comma-separated URLs or set 'scrape.sites' in the rollup.yml file")
-    }
+	}
 
-    // Set default values for rate limiting
+	// Set default values for rate limiting
-    defaultRequestsPerSecond := 1.0
+	defaultRequestsPerSecond := 1.0
-    defaultBurstLimit := 3
+	defaultBurstLimit := 3
 
-    // Use default values if not set in the configuration
+	// 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{
+	scraperConfig := scraper.Config{
-        Sites:      siteConfigs,
+		Sites:      siteConfigs,
-        OutputType: outputType,
+		OutputType: outputType,
-        Verbose:    verbose,
+		Verbose:    verbose,
-        Scrape: scraper.ScrapeConfig{
+		Scrape: scraper.ScrapeConfig{
-            RequestsPerSecond: requestsPerSecond,
+			RequestsPerSecond: requestsPerSecond,
-            BurstLimit:        burstLimit,
+			BurstLimit:        burstLimit,
-        },
+		},
-    }
+	}
-    logger.Printf("Scraper configuration: OutputType=%s, RequestsPerSecond=%f, BurstLimit=%d",
+	logger.Printf("Scraper configuration: OutputType=%s, RequestsPerSecond=%f, BurstLimit=%d",
-               outputType, requestsPerSecond, burstLimit)
+		outputType, requestsPerSecond, burstLimit)
 
-    logger.Println("Starting scraping process")
+	logger.Println("Starting scraping process")
-    scrapedContent, err := scraper.ScrapeSites(scraperConfig)
+	startTime := time.Now()
-    if err != nil {
+	progressTicker := time.NewTicker(time.Second)
-        logger.Printf("Error occurred during scraping: %v", err)
+	defer progressTicker.Stop()
-        return fmt.Errorf("error scraping content: %v", err)
-    }
-    logger.Printf("Scraping completed. Total content scraped: %d", len(scrapedContent))
 
-    if outputType == "single" {
+	done := make(chan bool)
-        logger.Println("Writing content to a single file")
+	messagePrinted := false
-        return writeSingleFile(scrapedContent)
+	go func() {
-    } else {
+		for {
-        logger.Println("Writing content to multiple files")
+			select {
-        return writeMultipleFiles(scrapedContent)
+			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
+			}
+		}
+	}()
+
+	scrapedContent, 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))
+
+	if outputType == "single" {
+		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 {
@@ -139,7 +160,7 @@ func writeSingleFile(content map[string]string) error {
 	defer file.Close()
 
 	for url, c := range content {
-		_, err = fmt.Fprintf(file, "# Content from %s\n\n%s\n\n---\n\n", url, c)
+		_, err = fmt.Fprintf(file, "# ::: Content from %s\n\n%s\n\n---\n\n", url, c)
 		if err != nil {
 			return fmt.Errorf("error writing content to file: %v", err)
 		}
@@ -161,7 +182,7 @@ func writeMultipleFiles(content map[string]string) error {
 			return fmt.Errorf("error creating output file %s: %v", filename, err)
 		}
 
-		_, err = file.WriteString(fmt.Sprintf("# Content from %s\n\n%s\n", url, c))
+		_, err = file.WriteString(fmt.Sprintf("# ::: Content from %s\n\n%s\n", url, c))
 		if err != nil {
 			file.Close()
 			return fmt.Errorf("error writing content to file %s: %v", filename, err)
@@ -179,44 +200,18 @@ 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
+var (
-var testExtractLinks = scraper.ExtractLinks
+	testExtractAndConvertContent = extractAndConvertContent
+)
 
 func extractAndConvertContent(urlStr string) (string, error) {
 	content, err := scraper.FetchWebpageContent(urlStr)
@@ -240,7 +235,7 @@ func extractAndConvertContent(urlStr string) (string, error) {
 	if err != nil {
 		return "", fmt.Errorf("error parsing URL: %v", err)
 	}
-	header := fmt.Sprintf("# Content from %s\n\n", parsedURL.String())
+	header := fmt.Sprintf("# ::: Content from %s\n\n", parsedURL.String())
 
 	return header + markdown + "\n\n", nil
 }

cmd/web_test.go

@@ -103,7 +103,7 @@ func mockExtractAndConvertContent(urlStr string) (string, error) {
 	return "Mocked content for " + urlStr, nil
 }
 
-func mockExtractLinks(urlStr string) ([]string, error) {
+func mockExtractLinks() ([]string, error) {
 	return []string{"http://example.com/link1", "http://example.com/link2"}, nil
 }
 

internal/config/config.go

@@ -7,35 +7,64 @@ 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"`
+	// IgnorePaths is a list of glob patterns for paths to ignore
-}
+	IgnorePaths []string `yaml:"ignore_paths"`
-
+
-type ScrapeConfig struct {
+	// CodeGeneratedPaths is a list of glob patterns for code-generated files
-    Sites             []SiteConfig `yaml:"sites"`
+	CodeGeneratedPaths []string `yaml:"code_generated_paths"`
-    OutputType        string       `yaml:"output_type"`
+
-    RequestsPerSecond float64      `yaml:"requests_per_second"`
+	// Sites is a list of site configurations for web scraping
-    BurstLimit        int          `yaml:"burst_limit"`
+	Sites []SiteConfig `yaml:"sites"`
+
+	// OutputType specifies how the output should be generated
+	OutputType string `yaml:"output_type"`
+
+	// 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          string            `yaml:"base_url"`
+	// BaseURL is the starting point for scraping this site
-    CSSLocator       string            `yaml:"css_locator"`
+	BaseURL string `yaml:"base_url"`
-    ExcludeSelectors []string          `yaml:"exclude_selectors"`
+
-    MaxDepth         int               `yaml:"max_depth"`
+	// CSSLocator is used to extract specific content
-    AllowedPaths     []string          `yaml:"allowed_paths"`
+	CSSLocator string `yaml:"css_locator"`
-    ExcludePaths     []string          `yaml:"exclude_paths"`
+
-    OutputAlias      string            `yaml:"output_alias"`
+	// ExcludeSelectors lists CSS selectors for content to exclude
-    PathOverrides    []PathOverride    `yaml:"path_overrides"`
+	ExcludeSelectors []string `yaml:"exclude_selectors"`
+
+	// 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 provides an alternative name for output files
+	OutputAlias string `yaml:"output_alias"`
+
+	// PathOverrides allows for path-specific configurations
+	PathOverrides []PathOverride `yaml:"path_overrides"`
 }
 
+// PathOverride allows for path-specific configurations
 type PathOverride struct {
-    Path             string   `yaml:"path"`
+	// Path is the URL path this override applies to
-    CSSLocator       string   `yaml:"css_locator"`
+	Path string `yaml:"path"`
-    ExcludeSelectors []string `yaml:"exclude_selectors"`
+
+	// 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"`
 }
 
 func Load(configPath string) (*Config, error) {
@@ -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

@@ -9,34 +9,33 @@ 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:
-  sites:
+  - base_url: "https://example.com"
-    - base_url: "https://example.com"
+    css_locator: "main"
-      css_locator: "main"
+    exclude_selectors:
-      exclude_selectors:
+      - ".ads"
-        - ".ads"
+    max_depth: 2
-      max_depth: 2
+    allowed_paths:
-      allowed_paths:
+      - "/blog"
-        - "/blog"
+    exclude_paths:
-      exclude_paths:
+      - "/admin"
-        - "/admin"
+    output_alias: "example"
-      output_alias: "example"
+    path_overrides:
-      path_overrides:
+      - path: "/special"
-        - path: "/special"
+        css_locator: ".special-content"
-          css_locator: ".special-content"
+        exclude_selectors:
-          exclude_selectors:
+          - ".sidebar"
-            - ".sidebar"
+output_type: "single"
-  output_type: "single"
+requests_per_second: 1.0
-  requests_per_second: 1.0
+burst_limit: 5
-  burst_limit: 5
 `)
 
 	tmpfile, err := os.CreateTemp("", "config*.yml")
@@ -45,10 +44,10 @@ scrape:
 	}
 	defer os.Remove(tmpfile.Name())
 
-	if _, err := tmpfile.Write(content); err != nil {
+	if _, err = tmpfile.Write(content); err != nil {
 		t.Fatalf("Failed to write to temp file: %v", err)
 	}
-	if err := tmpfile.Close(); err != nil {
+	if err = tmpfile.Close(); err != nil {
 		t.Fatalf("Failed to close temp file: %v", err)
 	}
 
@@ -59,33 +58,33 @@ 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{
-			Sites: []SiteConfig{
+			{
-				{
+				BaseURL:          "https://example.com",
-					BaseURL:          "https://example.com",
+				CSSLocator:       "main",
-					CSSLocator:       "main",
+				ExcludeSelectors: []string{".ads"},
-					ExcludeSelectors: []string{".ads"},
+				MaxDepth:         2,
-					MaxDepth:         2,
+				AllowedPaths:     []string{"/blog"},
-					AllowedPaths:     []string{"/blog"},
+				ExcludePaths:     []string{"/admin"},
-					ExcludePaths:     []string{"/admin"},
+				OutputAlias:      "example",
-					OutputAlias:      "example",
+				PathOverrides: []PathOverride{
-					PathOverrides: []PathOverride{
+					{
-						{
+						Path:             "/special",
-							Path:             "/special",
+						CSSLocator:       ".special-content",
-							CSSLocator:       ".special-content",
+						ExcludeSelectors: []string{".sidebar"},
-							ExcludeSelectors: []string{".sidebar"},
-						},
 					},
 				},
 			},
-			OutputType:        "single",
-			RequestsPerSecond: 1.0,
-			BurstLimit:        5,
 		},
+		OutputType:        "single",
+		RequestsPerSecond: &rps,
+		BurstLimit:        &bl,
 	}
 
 	if !reflect.DeepEqual(config, expectedConfig) {
@@ -93,28 +92,67 @@ 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",
-func TestFileExists(t *testing.T) {
+			config: Config{
-	// Test with an existing file
+				FileExtensions: []string{".go"},
-	tmpfile, err := os.CreateTemp("", "testfile")
+				Sites: []SiteConfig{
-	if err != nil {
+					{BaseURL: "https://example.com", MaxDepth: 2},
-		t.Fatalf("Failed to create temp file: %v", err)
+				},
-	}
+			},
-	defer os.Remove(tmpfile.Name())
+			wantErr: false,
-
+		},
-	if !FileExists(tmpfile.Name()) {
+		{
-		t.Errorf("FileExists(%q) = false, want true", tmpfile.Name())
+			name:    "No file extensions",
-	}
+			config:  Config{},
-
+			wantErr: true,
-	// Test with a non-existing file
+		},
-	if FileExists("non_existing_file.txt") {
+		{
-		t.Errorf("FileExists(\"non_existing_file.txt\") = true, want false")
+			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", MaxDepth: -1}},
+			},
+			wantErr: true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			err := tt.config.Validate()
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Validate() error = %v, wantErr %v", err, tt.wantErr)
+			}
+		})
 	}
 }

internal/scraper/scraper.go

@@ -1,21 +1,21 @@
 package scraper
 
 import (
+	"context"
 	"fmt"
-	"io/ioutil"
+	"io"
 	"log"
 	"math/rand"
 	"net/url"
 	"os"
 	"regexp"
 	"strings"
-	"time"
 	"sync"
-	"context"
+	"time"
 
+	md "github.com/JohannesKaufmann/html-to-markdown"
 	"github.com/PuerkitoBio/goquery"
 	"github.com/playwright-community/playwright-go"
-	md "github.com/JohannesKaufmann/html-to-markdown"
 	"golang.org/x/time/rate"
 )
 
@@ -45,7 +45,6 @@ type SiteConfig struct {
 	BaseURL          string
 	CSSLocator       string
 	ExcludeSelectors []string
-	MaxDepth         int
 	AllowedPaths     []string
 	ExcludePaths     []string
 	OutputAlias      string
@@ -60,208 +59,159 @@ type PathOverride struct {
 }
 
 func ScrapeSites(config Config) (map[string]string, error) {
-    logger.Println("Starting ScrapeSites function - Verbose mode is active")
+	logger.Println("Starting ScrapeSites function - Verbose mode is active")
-    results := make(chan struct {
+	results := make(chan struct {
-        url     string
+		url     string
-        content string
+		content string
-        err     error
+		err     error
-    })
+	})
 
-    limiter := rate.NewLimiter(rate.Limit(config.Scrape.RequestsPerSecond), config.Scrape.BurstLimit)
+	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
+	var wg sync.WaitGroup
-    totalURLs := 0
+	totalURLs := 0
-    for _, site := range config.Sites {
+	for _, site := range config.Sites {
-        logger.Printf("Processing site: %s\n", site.BaseURL)
+		logger.Printf("Processing site: %s\n", site.BaseURL)
-        wg.Add(1)
+		wg.Add(1)
-        go func(site SiteConfig) {
+		go func(site SiteConfig) {
-            defer wg.Done()
+			defer wg.Done()
-            for _, path := range site.AllowedPaths {
+			for _, path := range site.AllowedPaths {
-                fullURL := site.BaseURL + path
+				fullURL := site.BaseURL + path
-                totalURLs++
+				totalURLs++
-                logger.Printf("Queueing URL for scraping: %s\n", fullURL)
+				logger.Printf("Queueing URL for scraping: %s\n", fullURL)
-                scrapeSingleURL(fullURL, site, config, results, limiter)
+				scrapeSingleURL(fullURL, site, results, limiter)
-            }
+			}
-        }(site)
+		}(site)
-    }
+	}
 
-    go func() {
+	go func() {
-        wg.Wait()
+		wg.Wait()
-        close(results)
+		close(results)
-        logger.Println("All goroutines completed, results channel closed")
+		logger.Println("All goroutines completed, results channel closed")
-    }()
+	}()
 
-    scrapedContent := make(map[string]string)
+	scrapedContent := make(map[string]string)
-    for result := range results {
+	for result := range results {
-        if result.err != nil {
+		if result.err != nil {
-            logger.Printf("Error scraping %s: %v\n", result.url, result.err)
+			logger.Printf("Error scraping %s: %v\n", result.url, result.err)
-            continue
+			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", result.url, len(result.content))
-        scrapedContent[result.url] = result.content
+		scrapedContent[result.url] = result.content
-    }
+	}
 
-    logger.Printf("Total URLs processed: %d\n", totalURLs)
+	logger.Printf("Total URLs processed: %d\n", totalURLs)
-    logger.Printf("Successfully scraped content from %d URLs\n", len(scrapedContent))
+	logger.Printf("Successfully scraped content from %d URLs\n", len(scrapedContent))
 
-    return scrapedContent, nil
+	return scrapedContent, nil
 }
 
-func scrapeSingleURL(url string, site SiteConfig, config Config, results chan<- struct {
+func scrapeSingleURL(url string, site SiteConfig, results chan<- struct {
-    url     string
+	url     string
-    content string
+	content string
-    err     error
+	err     error
-}, limiter *rate.Limiter) {
+}, limiter *rate.Limiter,
-    logger.Printf("Starting to scrape URL: %s\n", url)
+) {
+	logger.Printf("Starting to scrape URL: %s\n", url)
 
-    // Wait for rate limiter before making the request
+	// Wait for rate limiter before making the request
-    err := limiter.Wait(context.Background())
+	err := limiter.Wait(context.Background())
-    if err != nil {
+	if err != nil {
-        logger.Printf("Rate limiter error for %s: %v\n", url, err)
+		logger.Printf("Rate limiter error for %s: %v\n", url, err)
-        results <- struct {
+		results <- struct {
-            url     string
+			url     string
-            content string
+			content string
-            err     error
+			err     error
-        }{url, "", fmt.Errorf("rate limiter error: %v", err)}
+		}{url, "", fmt.Errorf("rate limiter error: %v", err)}
-        return
+		return
-    }
+	}
 
-    cssLocator, excludeSelectors := getOverrides(url, site)
+	cssLocator, excludeSelectors := getOverrides(url, site)
-    logger.Printf("Using CSS locator for %s: %s\n", url, cssLocator)
+	logger.Printf("Using CSS locator for %s: %s\n", url, cssLocator)
-    logger.Printf("Exclude selectors for %s: %v\n", url, excludeSelectors)
+	logger.Printf("Exclude selectors for %s: %v\n", url, excludeSelectors)
 
-    content, err := scrapeURL(url, cssLocator, excludeSelectors)
+	content, err := scrapeURL(url, cssLocator, excludeSelectors)
-    if err != nil {
+	if err != nil {
-        logger.Printf("Error scraping %s: %v\n", url, err)
+		logger.Printf("Error scraping %s: %v\n", url, err)
-        results <- struct {
+		results <- struct {
-            url     string
+			url     string
-            content string
+			content string
-            err     error
+			err     error
-        }{url, "", err}
+		}{url, "", err}
-        return
+		return
-    }
+	}
 
-    if content == "" {
+	if content == "" {
-        logger.Printf("Warning: Empty content scraped from %s\n", url)
+		logger.Printf("Warning: Empty content scraped from %s\n", url)
-    } else {
+	} else {
-        logger.Printf("Successfully scraped content from %s (length: %d)\n", url, len(content))
+		logger.Printf("Successfully scraped content from %s (length: %d)\n", url, len(content))
-    }
+	}
 
-    results <- struct {
+	results <- struct {
-        url     string
+		url     string
-        content string
+		content string
-        err     error
+		err     error
-    }{url, content, nil}
+	}{url, content, nil}
 }
 
-func scrapeSite(site SiteConfig, config Config, 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
-                err     error
-            }{url, "", fmt.Errorf("rate limiter error: %v", err)}
-            continue
-        }
-
-        cssLocator, excludeSelectors := getOverrides(url, site)
-        content, err := scrapeURL(url, cssLocator, excludeSelectors)
-        results <- struct {
-            url     string
-            content string
-            err     error
-        }{url, content, err}
-
-        if len(visited) < site.MaxDepth {
-            links, _ := ExtractLinks(url)
-            for _, link := range links {
-                if !visited[link] && isAllowedURL(link, site) {
-                    queue = append(queue, link)
-                }
-            }
-        }
-    }
-}
 
 func isAllowedURL(urlStr string, site SiteConfig) bool {
-    parsedURL, err := url.Parse(urlStr)
+	parsedURL, err := url.Parse(urlStr)
-    if err != nil {
+	if err != nil {
-        return false
+		return false
-    }
+	}
 
-    baseURL, _ := url.Parse(site.BaseURL)
+	baseURL, _ := url.Parse(site.BaseURL)
-    if parsedURL.Host != baseURL.Host {
+	if parsedURL.Host != baseURL.Host {
-        return false
+		return false
-    }
+	}
 
-    path := parsedURL.Path
+	path := parsedURL.Path
-    for _, allowedPath := range site.AllowedPaths {
+	for _, allowedPath := range site.AllowedPaths {
-        if strings.HasPrefix(path, allowedPath) {
+		if strings.HasPrefix(path, allowedPath) {
-            for _, excludePath := range site.ExcludePaths {
+			for _, excludePath := range site.ExcludePaths {
-                if strings.HasPrefix(path, excludePath) {
+				if strings.HasPrefix(path, excludePath) {
-                    return false
+					return false
-                }
+				}
-            }
+			}
-            return true
+			return true
-        }
+		}
-    }
+	}
 
-    return false
+	return false
 }
 
 func getOverrides(urlStr string, site SiteConfig) (string, []string) {
-    parsedURL, _ := url.Parse(urlStr)
+	parsedURL, _ := url.Parse(urlStr)
-    path := parsedURL.Path
+	path := parsedURL.Path
 
-    for _, override := range site.PathOverrides {
+	for _, override := range site.PathOverrides {
-        if strings.HasPrefix(path, override.Path) {
+		if strings.HasPrefix(path, override.Path) {
-            if override.CSSLocator != "" {
+			if override.CSSLocator != "" {
-                return override.CSSLocator, override.ExcludeSelectors
+				return override.CSSLocator, override.ExcludeSelectors
-            }
+			}
-            return site.CSSLocator, override.ExcludeSelectors
+			return site.CSSLocator, override.ExcludeSelectors
-        }
+		}
-    }
+	}
 
-    return site.CSSLocator, site.ExcludeSelectors
+	return site.CSSLocator, site.ExcludeSelectors
 }
 
 func scrapeURL(url, cssLocator string, excludeSelectors []string) (string, error) {
-    content, err := FetchWebpageContent(url)
+	content, err := FetchWebpageContent(url)
-    if err != nil {
+	if err != nil {
-        return "", err
+		return "", err
-    }
+	}
 
-    if cssLocator != "" {
+	if cssLocator != "" {
-        content, err = ExtractContentWithCSS(content, cssLocator, excludeSelectors)
+		content, err = ExtractContentWithCSS(content, cssLocator, excludeSelectors)
-        if err != nil {
+		if err != nil {
-            return "", err
+			return "", err
-        }
+		}
-    }
+	}
 
-    return ProcessHTMLContent(content, Config{})
+	return ProcessHTMLContent(content, Config{})
 }
 
 func getFilenameFromContent(content, url string) string {
@@ -296,7 +246,7 @@ func SetupLogger(verbose bool) {
 	if verbose {
 		logger = log.New(os.Stdout, "SCRAPER: ", log.LstdFlags)
 	} else {
-		logger = log.New(ioutil.Discard, "", 0)
+		logger = log.New(io.Discard, "", 0)
 	}
 }
 
@@ -387,7 +337,9 @@ func FetchWebpageContent(urlStr string) (string, error) {
 	}
 
 	logger.Println("Waiting for body element")
-	_, err = page.WaitForSelector("body", playwright.PageWaitForSelectorOptions{
+	
+	bodyElement := page.Locator("body")
+	err = bodyElement.WaitFor(playwright.LocatorWaitForOptions{
 		State: playwright.WaitForSelectorStateVisible,
 	})
 	if err != nil {
@@ -404,7 +356,7 @@ func FetchWebpageContent(urlStr string) (string, error) {
 
 	if content == "" {
 		logger.Println(" content is empty, falling back to body content")
-		content, err = page.InnerHTML("body")
+		content, err = bodyElement.InnerHTML()
 		if err != nil {
 			logger.Printf("Error getting body content: %v\n", err)
 			return "", fmt.Errorf("could not get body content: %v", err)
@@ -457,6 +409,8 @@ func scrollPage(page playwright.Page) error {
 		() => {
 			window.scrollTo(0, document.body.scrollHeight);
 			return document.body.scrollHeight;
+			// wait for 500 ms
+			new Promise(resolve => setTimeout(resolve, 500));
 		}
 	`
 
@@ -488,7 +442,9 @@ func scrollPage(page playwright.Page) error {
 
 		previousHeight = currentHeight
 
-		page.WaitForTimeout(500)
+		// Wait for a while before scrolling again
+		
+		
 	}
 
 	logger.Println("Scrolling back to top")
@@ -502,40 +458,6 @@ 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) {

internal/scraper/scraper_test.go

@@ -1,13 +1,13 @@
 package scraper
 
 import (
-	"testing"
+	"io"
+	"log"
 	"net/http"
 	"net/http/httptest"
-	"strings"
 	"reflect"
-	"log"
+	"strings"
-	"io/ioutil"
+	"testing"
 )
 
 func TestIsAllowedURL(t *testing.T) {
@@ -51,9 +51,9 @@ func TestGetOverrides(t *testing.T) {
 	}
 
 	tests := []struct {
-		url               string
+		url              string
-		expectedLocator   string
+		expectedLocator  string
-		expectedExcludes  []string
+		expectedExcludes []string
 	}{
 		{"https://example.com/normal", "main", []string{".ads"}},
 		{"https://example.com/special", ".special-content", []string{".sidebar"}},
@@ -73,7 +73,7 @@ func TestGetOverrides(t *testing.T) {
 
 func TestExtractContentWithCSS(t *testing.T) {
 	// Initialize logger for testing
-	logger = log.New(ioutil.Discard, "", 0)
+	logger = log.New(io.Discard, "", 0)
 
 	html := `
 		<html>

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)