cleanup: go module changes

README.md

@@ -4,18 +4,16 @@ Rollup aggregates the contents of text-based files and webpages into a markdown
 
 ## Features
 
-- File type filtering for targeted content aggregation
+- File type filtering
-- Ignore patterns for excluding specific files or directories
+- Ignore patterns for excluding files
-- Support for code-generated file detection and exclusion
+- Support for code-generated file detection
-- Advanced web scraping functionality with depth control
+- Advanced web scraping functionality
-- Verbose logging option for detailed operation insights
+- Verbose logging option for detailed output
-- Exclusionary CSS selectors for precise web content extraction
+- Exclusionary CSS selectors for web scraping
-- Support for multiple URLs in web scraping operations
+- Support for multiple URLs in web scraping
 - Configurable output format for web scraping (single file or separate files)
-- Flexible configuration file support (YAML)
+- Configuration file support (YAML)
-- Automatic generation of default configuration file
+- Generation of default configuration file
-- Custom output file naming
-- Rate limiting for web scraping to respect server resources
 
 ## Installation
 
@@ -66,36 +64,24 @@ Rollup can be configured using a YAML file. By default, it looks for `rollup.yml
 Example `rollup.yml`:
 
 ```yaml
-file_extensions:
+file_types:
   - go
   - md
-ignore_paths:
+ignore:
   - node_modules/**
   - vendor/**
   - .git/**
-code_generated_paths:
+code_generated:
   - **/generated/**
-sites:
+scrape:
-  - base_url: https://example.com
+  urls:
+    - url: https://example.com
       css_locator: .content
       exclude_selectors:
         - .ads
         - .navigation
-    max_depth: 2
-    allowed_paths:
-      - /blog
-      - /docs
-    exclude_paths:
-      - /admin
       output_alias: example
-    path_overrides:
+  output_type: single
-      - path: /special-page
-        css_locator: .special-content
-        exclude_selectors:
-          - .special-ads
-output_type: single
-requests_per_second: 1.0
-burst_limit: 3
 ```
 
 ## Examples
@@ -125,22 +111,10 @@ burst_limit: 3
    ```
 
 5. Web scraping with separate output files:
-
    ```bash
    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
-   ```
-
-7. Web scraping with depth and CSS selector:
-   ```bash
-   rollup web --urls=https://example.com --depth=2 --css=.main-content
-   ```
-
 ## Contributing
 
 Contributions are welcome! Please feel free to submit a Pull Request.

cmd/files.go

@@ -8,11 +8,8 @@ import (
 	"time"
 
 	"github.com/spf13/cobra"
-	"github.com/tnypxl/rollup/internal/config"
 )
 
-var cfg *config.Config
-
 var (
 	path            string
 	fileTypes       string
@@ -26,16 +23,8 @@ var filesCmd = &cobra.Command{
 	Long: `The files subcommand writes the contents of all files (with target custom file types provided)
 in a given project, current path or a custom path, to a single timestamped markdown file
 whose name is <project-directory-name>-rollup-<timestamp>.md.`,
-	PreRunE: func(cmd *cobra.Command, args []string) error {
-		var err error
-		cfg, err = config.Load("rollup.yml") // Assuming the config file is named rollup.yml
-		if err != nil {
-			return fmt.Errorf("failed to load configuration: %v", err)
-		}
-		return nil
-	},
 	RunE: func(cmd *cobra.Command, args []string) error {
-		return runRollup(cfg)
+		return runRollup()
 	},
 }
 
@@ -98,38 +87,30 @@ func isIgnored(filePath string, patterns []string) bool {
 				return true
 			}
 		} else {
-			// Check if the pattern matches the full path or any part of it
+			matched, err := filepath.Match(pattern, filepath.Base(filePath))
-			if matched, _ := filepath.Match(pattern, filePath); matched {
+			if err == nil && matched {
 				return true
 			}
-			pathParts := strings.Split(filePath, string(os.PathSeparator))
-			for i := range pathParts {
-				partialPath := filepath.Join(pathParts[:i+1]...)
-				if matched, _ := filepath.Match(pattern, partialPath); matched {
-					return true
-				}
-			}
 		}
 	}
 	return false
 }
 
-func runRollup(cfg *config.Config) error {
+func runRollup() error {
 	// Use config if available, otherwise use command-line flags
-	var types []string
+	var types, codeGenList, ignoreList []string
-	var codeGenList, ignoreList []string
+	if cfg != nil && len(cfg.FileTypes) > 0 {
-	if cfg != nil && len(cfg.FileExtensions) > 0 {
+		types = cfg.FileTypes
-		types = cfg.FileExtensions
 	} else {
 		types = strings.Split(fileTypes, ",")
 	}
-	if cfg != nil && len(cfg.CodeGeneratedPaths) > 0 {
+	if cfg != nil && len(cfg.CodeGenerated) > 0 {
-		codeGenList = cfg.CodeGeneratedPaths
+		codeGenList = cfg.CodeGenerated
 	} else {
 		codeGenList = strings.Split(codeGenPatterns, ",")
 	}
-	if cfg != nil && len(cfg.IgnorePaths) > 0 {
+	if cfg != nil && cfg.Ignore != nil && len(cfg.Ignore) > 0 {
-		ignoreList = cfg.IgnorePaths
+		ignoreList = cfg.Ignore
 	} else {
 		ignoreList = strings.Split(ignorePatterns, ",")
 	}
@@ -154,11 +135,6 @@ 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 {
@@ -174,25 +150,16 @@ 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\n", path, err)
+					fmt.Printf("Error reading file %s: %v", path, err)
 					return nil
 				}
 
@@ -208,43 +175,12 @@ 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)
 	}
 
-	if showProgress {
+	fmt.Printf("Rollup complete. Output file: %s", outputFileName)
-		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

@@ -21,9 +21,6 @@ func TestMatchGlob(t *testing.T) {
 		{"**/*.go", "dir/subdir/file.go", true},
 		{"dir/*.go", "dir/file.go", true},
 		{"dir/*.go", "otherdir/file.go", false},
-		{"**/test_*.go", "internal/test_helper.go", true},
-		{"docs/**/*.md", "docs/api/endpoints.md", true},
-		{"docs/**/*.md", "src/docs/readme.md", false},
 	}
 
 	for _, test := range tests {
@@ -35,7 +32,7 @@ func TestMatchGlob(t *testing.T) {
 }
 
 func TestIsCodeGenerated(t *testing.T) {
-	patterns := []string{"generated_*.go", "**/auto_*.go", "**/*_gen.go"}
+	patterns := []string{"generated_*.go", "**/auto_*.go"}
 	tests := []struct {
 		path     string
 		expected bool
@@ -44,8 +41,6 @@ func TestIsCodeGenerated(t *testing.T) {
 		{"normal_file.go", false},
 		{"subdir/auto_file.go", true},
 		{"subdir/normal_file.go", false},
-		{"pkg/models_gen.go", true},
-		{"pkg/handler.go", false},
 	}
 
 	for _, test := range tests {
@@ -57,7 +52,7 @@ func TestIsCodeGenerated(t *testing.T) {
 }
 
 func TestIsIgnored(t *testing.T) {
-	patterns := []string{"*.tmp", "**/*.log", ".git/**", "vendor/**"}
+	patterns := []string{"*.tmp", "**/*.log"}
 	tests := []struct {
 		path     string
 		expected bool
@@ -66,10 +61,6 @@ func TestIsIgnored(t *testing.T) {
 		{"file.go", false},
 		{"subdir/file.log", true},
 		{"subdir/file.txt", false},
-		{".git/config", true},
-		{"src/.git/config", false},
-		{"vendor/package/file.go", true},
-		{"internal/vendor/file.go", false},
 	}
 
 	for _, test := range tests {
@@ -94,52 +85,45 @@ func TestRunRollup(t *testing.T) {
 		"file2.txt":         "This is a text file.\n",
 		"subdir/file3.go":   "package subdir\n\nfunc Func() {}\n",
 		"subdir/file4.json": "{\"key\": \"value\"}\n",
-		"generated_model.go":   "// Code generated DO NOT EDIT.\n\npackage model\n",
-		"docs/api/readme.md":   "# API Documentation\n",
-		".git/config":          "[core]\n\trepositoryformatversion = 0\n",
-		"vendor/lib/helper.go": "package lib\n\nfunc Helper() {}\n",
 	}
 
 	for name, content := range files {
 		path := filepath.Join(tempDir, name)
-		if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
+		err := os.MkdirAll(filepath.Dir(path), 0755)
+		if err != nil {
 			t.Fatalf("Failed to create directory: %v", err)
 		}
-		if err := os.WriteFile(path, []byte(content), 0o644); err != nil {
+		err = os.WriteFile(path, []byte(content), 0644)
+		if err != nil {
 			t.Fatalf("Failed to write file: %v", err)
 		}
 	}
 
 	// Set up test configuration
 	cfg = &config.Config{
-		FileExtensions:     []string{"go", "txt", "md"},
+		FileTypes:     []string{"go", "txt"},
-		IgnorePaths:        []string{"*.json", ".git/**", "vendor/**"},
+		Ignore:        []string{"*.json"},
-		CodeGeneratedPaths: []string{"generated_*.go"},
+		CodeGenerated: []string{},
 	}
-
+	path = tempDir
-	// Change working directory to the temp directory
-	originalWd, _ := os.Getwd()
-	os.Chdir(tempDir)
-	defer os.Chdir(originalWd)
 
 	// Run the rollup
-	if err := runRollup(cfg); err != nil {
+	err = runRollup()
+	if err != nil {
 		t.Fatalf("runRollup() failed: %v", err)
 	}
 
 	// Check if the output file was created
-	outputFiles, err := filepath.Glob("*.rollup.md")
+	outputFiles, err := filepath.Glob(filepath.Join(tempDir, "*.rollup.md"))
 	if err != nil {
-		t.Fatalf("Error globbing for output file: %v", err)
+		t.Fatalf("Failed to glob output files: %v", err)
 	}
-	if len(outputFiles) == 0 {
+	if len(outputFiles) != 1 {
-		allFiles, _ := filepath.Glob("*")
+		t.Fatalf("Expected 1 output file, got %d", len(outputFiles))
-		t.Fatalf("No rollup.md file found. Files in directory: %v", allFiles)
 	}
-	outputFile := outputFiles[0]
 
 	// Read the content of the output file
-	content, err := os.ReadFile(outputFile)
+	content, err := os.ReadFile(outputFiles[0])
 	if err != nil {
 		t.Fatalf("Failed to read output file: %v", err)
 	}
@@ -149,8 +133,6 @@ func TestRunRollup(t *testing.T) {
 		"# File: file1.go",
 		"# File: file2.txt",
 		"# File: subdir/file3.go",
-		"# File: docs/api/readme.md",
-		"# File: generated_model.go (Code-generated, Read-only)",
 	}
 	for _, expected := range expectedContent {
 		if !strings.Contains(string(content), expected) {
@@ -158,15 +140,8 @@ func TestRunRollup(t *testing.T) {
 		}
 	}
 
-	// Check if the ignored files are not included
+	// Check if the ignored file is not included
-	ignoredContent := []string{
+	if strings.Contains(string(content), "file4.json") {
-		"file4.json",
+		t.Errorf("Output file contains ignored file: file4.json")
-		".git/config",
-		"vendor/lib/helper.go",
-	}
-	for _, ignored := range ignoredContent {
-		if strings.Contains(string(content), ignored) {
-			t.Errorf("Output file contains ignored file: %s", ignored)
-		}
 	}
 }

cmd/generate.go

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

cmd/root.go

@@ -7,6 +7,7 @@ import (
 
 var (
 	configFile string
+	cfg        *config.Config
 	verbose    bool
 )
 
@@ -18,10 +19,10 @@ Use subcommands to perform specific operations.`,
 }
 
 func Execute(conf *config.Config) error {
-	if conf == nil {
+	cfg = conf
-		conf = &config.Config{} // Use an empty config if none is provided
+	if cfg == nil {
+		cfg = &config.Config{} // Use an empty config if none is provided
 	}
-	cfg = conf // Set the cfg variable in cmd/files.go
 	return rootCmd.Execute()
 }
 

cmd/web.go

@@ -2,7 +2,7 @@ package cmd
 
 import (
 	"fmt"
-	"io"
+	"io/ioutil"
 	"log"
 	"net/url"
 	"os"
@@ -18,6 +18,7 @@ import (
 var (
 	urls             []string
 	outputType       string
+	depth            int
 	includeSelector  string
 	excludeSelectors []string
 )
@@ -34,6 +35,7 @@ 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().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)")
 }
@@ -42,27 +44,28 @@ func runWeb(cmd *cobra.Command, args []string) error {
     scraper.SetupLogger(verbose)
     logger := log.New(os.Stdout, "WEB: ", log.LstdFlags)
     if !verbose {
-		logger.SetOutput(io.Discard)
+        logger.SetOutput(ioutil.Discard)
     }
     logger.Printf("Starting web scraping process with verbose mode: %v", verbose)
     scraperConfig.Verbose = verbose
 
     var siteConfigs []scraper.SiteConfig
-	if len(cfg.Sites) > 0 {
+    if len(cfg.Scrape.Sites) > 0 {
-		logger.Printf("Using configuration from rollup.yml for %d sites", len(cfg.Sites))
+        logger.Printf("Using configuration from rollup.yml for %d sites", len(cfg.Scrape.Sites))
-		siteConfigs = make([]scraper.SiteConfig, len(cfg.Sites))
+        siteConfigs = make([]scraper.SiteConfig, len(cfg.Scrape.Sites))
-		for i, site := range cfg.Sites {
+        for i, site := range cfg.Scrape.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, 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 {
         logger.Printf("No sites defined in rollup.yml, falling back to URL-based configuration")
@@ -72,9 +75,10 @@ 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",
+            logger.Printf("URL %d configuration: BaseURL=%s, CSSLocator=%s, MaxDepth=%d", 
-				i+1, u, includeSelector)
+                       i+1, u, includeSelector, depth)
         }
     }
 
@@ -88,13 +92,13 @@ func runWeb(cmd *cobra.Command, args []string) error {
     defaultBurstLimit := 3
 
     // Use default values if not set in the configuration
-	requestsPerSecond := defaultRequestsPerSecond
+    requestsPerSecond := cfg.Scrape.RequestsPerSecond
-	if cfg.RequestsPerSecond != nil {
+    if requestsPerSecond == 0 {
-		requestsPerSecond = *cfg.RequestsPerSecond
+        requestsPerSecond = defaultRequestsPerSecond
     }
-	burstLimit := defaultBurstLimit
+    burstLimit := cfg.Scrape.BurstLimit
-	if cfg.BurstLimit != nil {
+    if burstLimit == 0 {
-		burstLimit = *cfg.BurstLimit
+        burstLimit = defaultBurstLimit
     }
 
     scraperConfig := scraper.Config{
@@ -110,32 +114,7 @@ func runWeb(cmd *cobra.Command, args []string) error {
                outputType, requestsPerSecond, burstLimit)
 
     logger.Println("Starting scraping process")
-	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
-			}
-		}
-	}()
-
     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)
@@ -152,7 +131,7 @@ func runWeb(cmd *cobra.Command, args []string) error {
 }
 
 func writeSingleFile(content map[string]string) error {
-	outputFile := generateDefaultFilename()
+	outputFile := generateDefaultFilename(urls)
 	file, err := os.Create(outputFile)
 	if err != nil {
 		return fmt.Errorf("error creating output file: %v", err)
@@ -160,7 +139,7 @@ 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 = file.WriteString(fmt.Sprintf("# 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)
 		}
@@ -182,7 +161,7 @@ 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)
@@ -195,23 +174,49 @@ func writeMultipleFiles(content map[string]string) error {
 	return nil
 }
 
-func generateDefaultFilename() string {
+func generateDefaultFilename(urls []string) string {
 	timestamp := time.Now().Format("20060102-150405")
 	return fmt.Sprintf("web-%s.rollup.md", timestamp)
 }
 
-func scrapeURL(urlStr string) (string, error) {
+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
+
 	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 (
+var testExtractAndConvertContent = extractAndConvertContent
-	testExtractAndConvertContent = extractAndConvertContent
+var testExtractLinks = scraper.ExtractLinks
-)
 
 func extractAndConvertContent(urlStr string) (string, error) {
 	content, err := scraper.FetchWebpageContent(urlStr)
@@ -235,7 +240,7 @@ 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() ([]string, error) {
+func mockExtractLinks(urlStr string) ([]string, error) {
 	return []string{"http://example.com/link1", "http://example.com/link2"}, nil
 }
 

docs/CHANGELOG.md

@@ -1,21 +0,0 @@
-# Changelog
-
-All notable changes to this project will be documented in this file.
-
-The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
-and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
-
-## [0.0.3] - 2024-09-22
-
-### Added
-- Implemented web scraping functionality using Playwright
-- Added support for CSS selectors to extract specific content
-- Introduced rate limiting for web requests
-- Created configuration options for scraping settings
-
-### Changed
-- Improved error handling and logging throughout the application
-- Enhanced URL parsing and validation
-
-### Fixed
-- Resolved issues with concurrent scraping operations

internal/config/config.go

@@ -7,63 +7,34 @@ import (
 	"gopkg.in/yaml.v2"
 )
 
-// Config represents the configuration for the rollup tool
 type Config struct {
-	// FileExtensions is a list of file extensions to include in the rollup
+	FileTypes     []string     `yaml:"file_types"`
-	FileExtensions []string `yaml:"file_extensions"`
+	Ignore        []string     `yaml:"ignore"`
-
+	CodeGenerated []string     `yaml:"code_generated"`
-	// IgnorePaths is a list of glob patterns for paths to ignore
+	Scrape        ScrapeConfig `yaml:"scrape"`
-	IgnorePaths []string `yaml:"ignore_paths"`
+}
-
+
-	// CodeGeneratedPaths is a list of glob patterns for code-generated files
+type ScrapeConfig struct {
-	CodeGeneratedPaths []string `yaml:"code_generated_paths"`
+    Sites             []SiteConfig `yaml:"sites"`
-
+    OutputType        string       `yaml:"output_type"`
-	// Sites is a list of site configurations for web scraping
+    RequestsPerSecond float64      `yaml:"requests_per_second"`
-	Sites []SiteConfig `yaml:"sites"`
+    BurstLimit        int          `yaml:"burst_limit"`
-
-	// 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 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 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 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"`
 }
 
@@ -79,28 +50,15 @@ 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
 }
 
-// Validate checks the configuration for any invalid values
+func DefaultConfigPath() string {
-func (c *Config) Validate() error {
+	return "rollup.yml"
-	if c.RequestsPerSecond != nil && *c.RequestsPerSecond <= 0 {
-		return fmt.Errorf("requests_per_second must be positive")
-	}
-
-	if c.BurstLimit != nil && *c.BurstLimit <= 0 {
-		return fmt.Errorf("burst_limit must be positive")
-	}
-
-	for _, site := range c.Sites {
-		if site.BaseURL == "" {
-			return fmt.Errorf("base_url must be specified for each site")
-		}
-	}
-
-	return nil
 }
+
+func FileExists(filename string) bool {
+	_, err := os.Stat(filename)
+	return err == nil
+}
+

internal/config/config_test.go

@@ -9,15 +9,16 @@ import (
 func TestLoad(t *testing.T) {
 	// Create a temporary config file
 	content := []byte(`
-file_extensions:
+file_types:
-  - .go
+  - go
-  - .md
+  - md
-ignore_paths:
+ignore:
   - "*.tmp"
   - "**/*.log"
-code_generated_paths:
+code_generated:
   - "generated_*.go"
-sites:
+scrape:
+  sites:
     - base_url: "https://example.com"
       css_locator: "main"
       exclude_selectors:
@@ -33,9 +34,9 @@ sites:
           css_locator: ".special-content"
           exclude_selectors:
             - ".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")
@@ -44,10 +45,10 @@ burst_limit: 5
 	}
 	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)
 	}
 
@@ -58,12 +59,11 @@ burst_limit: 5
 	}
 
 	// Check if the loaded config matches the expected values
-	rps := 1.0
-	bl := 5
 	expectedConfig := &Config{
-		FileExtensions:     []string{".go", ".md"},
+		FileTypes:     []string{"go", "md"},
-		IgnorePaths:        []string{"*.tmp", "**/*.log"},
+		Ignore:        []string{"*.tmp", "**/*.log"},
-		CodeGeneratedPaths: []string{"generated_*.go"},
+		CodeGenerated: []string{"generated_*.go"},
+		Scrape: ScrapeConfig{
 			Sites: []SiteConfig{
 				{
 					BaseURL:          "https://example.com",
@@ -83,8 +83,9 @@ burst_limit: 5
 				},
 			},
 			OutputType:        "single",
-		RequestsPerSecond: &rps,
+			RequestsPerSecond: 1.0,
-		BurstLimit:        &bl,
+			BurstLimit:        5,
+		},
 	}
 
 	if !reflect.DeepEqual(config, expectedConfig) {
@@ -92,67 +93,28 @@ burst_limit: 5
 	}
 }
 
-func TestValidate(t *testing.T) {
+func TestDefaultConfigPath(t *testing.T) {
-	tests := []struct {
+	expected := "rollup.yml"
-		name    string
+	result := DefaultConfigPath()
-		config  Config
+	if result != expected {
-		wantErr bool
+		t.Errorf("DefaultConfigPath() = %q, want %q", result, expected)
-	}{
+	}
-		{
+}
-			name: "Valid config",
+
-			config: Config{
+func TestFileExists(t *testing.T) {
-				FileExtensions: []string{".go"},
+	// Test with an existing file
-				Sites: []SiteConfig{
+	tmpfile, err := os.CreateTemp("", "testfile")
-					{BaseURL: "https://example.com", MaxDepth: 2},
+	if err != nil {
-				},
+		t.Fatalf("Failed to create temp file: %v", err)
-			},
+	}
-			wantErr: false,
+	defer os.Remove(tmpfile.Name())
-		},
+
-		{
+	if !FileExists(tmpfile.Name()) {
-			name:    "No file extensions",
+		t.Errorf("FileExists(%q) = false, want true", tmpfile.Name())
-			config:  Config{},
+	}
-			wantErr: true,
+
-		},
+	// Test with a non-existing file
-		{
+	if FileExists("non_existing_file.txt") {
-			name: "Invalid requests per second",
+		t.Errorf("FileExists(\"non_existing_file.txt\") = true, want false")
-			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"
+	"io/ioutil"
 	"log"
 	"math/rand"
 	"net/url"
 	"os"
 	"regexp"
 	"strings"
-	"sync"
 	"time"
+	"sync"
+	"context"
 
-	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"
 )
 
@@ -45,6 +45,7 @@ type SiteConfig struct {
 	BaseURL          string
 	CSSLocator       string
 	ExcludeSelectors []string
+	MaxDepth         int
 	AllowedPaths     []string
 	ExcludePaths     []string
 	OutputAlias      string
@@ -80,7 +81,7 @@ func ScrapeSites(config Config) (map[string]string, error) {
                 fullURL := site.BaseURL + path
                 totalURLs++
                 logger.Printf("Queueing URL for scraping: %s\n", fullURL)
-				scrapeSingleURL(fullURL, site, results, limiter)
+                scrapeSingleURL(fullURL, site, config, results, limiter)
             }
         }(site)
     }
@@ -107,12 +108,11 @@ func ScrapeSites(config Config) (map[string]string, error) {
     return scrapedContent, nil
 }
 
-func scrapeSingleURL(url string, site SiteConfig, results chan<- struct {
+func scrapeSingleURL(url string, site SiteConfig, config Config, results chan<- struct {
     url     string
     content string
     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
@@ -155,6 +155,56 @@ func scrapeSingleURL(url string, site SiteConfig, results chan<- struct {
     }{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)
@@ -246,7 +296,7 @@ func SetupLogger(verbose bool) {
 	if verbose {
 		logger = log.New(os.Stdout, "SCRAPER: ", log.LstdFlags)
 	} else {
-		logger = log.New(io.Discard, "", 0)
+		logger = log.New(ioutil.Discard, "", 0)
 	}
 }
 
@@ -289,16 +339,6 @@ func ClosePlaywright() {
 	}
 }
 
-// InitBrowser initializes the browser
-func InitBrowser() error {
-	return InitPlaywright()
-}
-
-// CloseBrowser closes the browser
-func CloseBrowser() {
-	ClosePlaywright()
-}
-
 // 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)
@@ -337,9 +377,7 @@ 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 {
@@ -356,7 +394,7 @@ func FetchWebpageContent(urlStr string) (string, error) {
 
 	if content == "" {
 		logger.Println(" content is empty, falling back to body content")
-		content, err = bodyElement.InnerHTML()
+		content, err = page.InnerHTML("body")
 		if err != nil {
 			logger.Printf("Error getting body content: %v\n", err)
 			return "", fmt.Errorf("could not get body content: %v", err)
@@ -409,8 +447,6 @@ 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));
 		}
 	`
 
@@ -442,9 +478,7 @@ func scrollPage(page playwright.Page) error {
 
 		previousHeight = currentHeight
 
-		// Wait for a while before scrolling again
+		page.WaitForTimeout(500)
-		
-		
 	}
 
 	logger.Println("Scrolling back to top")
@@ -458,6 +492,38 @@ 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{}) {
+		result = append(result, link.(string))
+	}
+
+	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) {
@@ -486,23 +552,6 @@ func ExtractContentWithCSS(content, includeSelector string, excludeSelectors []s
 		return "", fmt.Errorf("error extracting content with CSS selector: %v", err)
 	}
 
-	// Trim leading and trailing whitespace
-	selectedContent = strings.TrimSpace(selectedContent)
-
-	// Normalize newlines
-	selectedContent = strings.ReplaceAll(selectedContent, "\r\n", "\n")
-	selectedContent = strings.ReplaceAll(selectedContent, "\r", "\n")
-
-	// Remove indentation while preserving structure
-	lines := strings.Split(selectedContent, "\n")
-	for i, line := range lines {
-		lines[i] = strings.TrimSpace(line)
-	}
-	selectedContent = strings.Join(lines, "\n")
-
-	// Remove any leading or trailing newlines
-	selectedContent = strings.Trim(selectedContent, "\n")
-
 	logger.Printf("Extracted content length: %d\n", len(selectedContent))
 	return selectedContent, nil
 }

internal/scraper/scraper_test.go

@@ -1,13 +1,10 @@
 package scraper
 
 import (
-	"io"
+	"testing"
-	"log"
 	"net/http"
 	"net/http/httptest"
-	"reflect"
 	"strings"
-	"testing"
 )
 
 func TestIsAllowedURL(t *testing.T) {
@@ -72,9 +69,6 @@ func TestGetOverrides(t *testing.T) {
 }
 
 func TestExtractContentWithCSS(t *testing.T) {
-	// Initialize logger for testing
-	logger = log.New(io.Discard, "", 0)
-
 	html := `
 		<html>
 			<body>
@@ -144,12 +138,6 @@ This is a **test** paragraph.
 }
 
 func TestExtractLinks(t *testing.T) {
-	// Initialize Playwright before running the test
-	if err := InitPlaywright(); err != nil {
-		t.Fatalf("Failed to initialize Playwright: %v", err)
-	}
-	defer ClosePlaywright()
-
 	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		w.Header().Set("Content-Type", "text/html")
 		w.Write([]byte(`

main.go

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