docs: update configuration section in README.md

README.md

@@ -4,16 +4,18 @@ Rollup aggregates the contents of text-based files and webpages into a markdown
 
 ## Features
 
-- File type filtering
-- Ignore patterns for excluding files
-- Support for code-generated file detection
-- Advanced web scraping functionality
-- Verbose logging option for detailed output
-- Exclusionary CSS selectors for web scraping
-- Support for multiple URLs in web scraping
+- File type filtering for targeted content aggregation
+- Ignore patterns for excluding specific files or directories
+- Support for code-generated file detection and exclusion
+- Advanced web scraping functionality with depth control
+- Verbose logging option for detailed operation insights
+- Exclusionary CSS selectors for precise web content extraction
+- Support for multiple URLs in web scraping operations
 - Configurable output format for web scraping (single file or separate files)
-- Configuration file support (YAML)
-- Generation of default configuration file
+- Flexible configuration file support (YAML)
+- Automatic generation of default configuration file
+- Custom output file naming
+- Concurrent processing for improved performance
 
 ## Installation
 
@@ -74,14 +76,27 @@ ignore:
 code_generated:
   - **/generated/**
 scrape:
-  urls:
-    - url: https://example.com
+  sites:
+    - base_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:
+        - path: /special-page
+          css_locator: .special-content
+          exclude_selectors:
+            - .special-ads
   output_type: single
+  requests_per_second: 1.0
+  burst_limit: 3
 ```
 
 ## Examples
@@ -92,10 +107,10 @@ scrape:
    rollup files
    ```
 
-2. Web scraping with multiple URLs:
+2. Web scraping with multiple URLs and increased concurrency:
 
    ```bash
-   rollup web --urls=https://example.com,https://another-example.com
+   rollup web --urls=https://example.com,https://another-example.com --concurrent=8
    ```
 
 3. Generate a default configuration file:
@@ -104,15 +119,25 @@ scrape:
    rollup generate
    ```
 
-4. Use a custom configuration file:
+4. Use a custom configuration file and specify output:
 
    ```bash
-   rollup files --config=my-config.yml
+   rollup files --config=my-config.yml --output=project_summary.md
    ```
 
-5. Web scraping with separate output files:
+5. Web scraping with separate output files and custom timeout:
    ```bash
-   rollup web --urls=https://example.com,https://another-example.com --output=separate
+   rollup web --urls=https://example.com,https://another-example.com --output=separate --timeout=60
+   ```
+
+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

cmd/files.go

@@ -8,8 +8,11 @@ import (
 	"time"
 
 	"github.com/spf13/cobra"
+	"github.com/tnypxl/rollup/internal/config"
 )
 
+var cfg *config.Config
+
 var (
 	path            string
 	fileTypes       string
@@ -24,7 +27,7 @@ var filesCmd = &cobra.Command{
 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.`,
 	RunE: func(cmd *cobra.Command, args []string) error {
-		return runRollup()
+		return runRollup(cfg)
 	},
 }
 
@@ -87,16 +90,23 @@ func isIgnored(filePath string, patterns []string) bool {
 				return true
 			}
 		} else {
-			matched, err := filepath.Match(pattern, filepath.Base(filePath))
-			if err == nil && matched {
+			// Check if the pattern matches the full path or any part of it
+			if matched, _ := filepath.Match(pattern, filePath); 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() error {
+func runRollup(cfg *config.Config) error {
 	// Use config if available, otherwise use command-line flags
 	var types, codeGenList, ignoreList []string
 	if cfg != nil && len(cfg.FileTypes) > 0 {

cmd/files_test.go

@@ -0,0 +1,172 @@
+package cmd
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/tnypxl/rollup/internal/config"
+)
+
+func TestMatchGlob(t *testing.T) {
+	tests := []struct {
+		pattern  string
+		path     string
+		expected bool
+	}{
+		{"*.go", "file.go", true},
+		{"*.go", "file.txt", false},
+		{"**/*.go", "dir/file.go", true},
+		{"**/*.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 {
+		result := matchGlob(test.pattern, test.path)
+		if result != test.expected {
+			t.Errorf("matchGlob(%q, %q) = %v; want %v", test.pattern, test.path, result, test.expected)
+		}
+	}
+}
+
+func TestIsCodeGenerated(t *testing.T) {
+	patterns := []string{"generated_*.go", "**/auto_*.go", "**/*_gen.go"}
+	tests := []struct {
+		path     string
+		expected bool
+	}{
+		{"generated_file.go", true},
+		{"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 {
+		result := isCodeGenerated(test.path, patterns)
+		if result != test.expected {
+			t.Errorf("isCodeGenerated(%q, %v) = %v; want %v", test.path, patterns, result, test.expected)
+		}
+	}
+}
+
+func TestIsIgnored(t *testing.T) {
+	patterns := []string{"*.tmp", "**/*.log", ".git/**", "vendor/**"}
+	tests := []struct {
+		path     string
+		expected bool
+	}{
+		{"file.tmp", true},
+		{"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 {
+		result := isIgnored(test.path, patterns)
+		if result != test.expected {
+			t.Errorf("isIgnored(%q, %v) = %v; want %v", test.path, patterns, result, test.expected)
+		}
+	}
+}
+
+func TestRunRollup(t *testing.T) {
+	// Create a temporary directory for testing
+	tempDir, err := os.MkdirTemp("", "rollup_test")
+	if err != nil {
+		t.Fatalf("Failed to create temp dir: %v", err)
+	}
+	defer os.RemoveAll(tempDir)
+
+	// Create some test files
+	files := map[string]string{
+		"file1.go":             "package main\n\nfunc main() {}\n",
+		"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 {
+			t.Fatalf("Failed to create directory: %v", err)
+		}
+		if err := os.WriteFile(path, []byte(content), 0o644); err != nil {
+			t.Fatalf("Failed to write file: %v", err)
+		}
+	}
+
+	// Set up test configuration
+	cfg = &config.Config{
+		FileTypes:     []string{"go", "txt", "md"},
+		Ignore:        []string{"*.json", ".git/**", "vendor/**"},
+		CodeGenerated: []string{"generated_*.go"},
+	}
+
+	// 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 {
+		t.Fatalf("runRollup() failed: %v", err)
+	}
+
+	// Check if the output file was created
+	outputFiles, err := filepath.Glob("*.rollup.md")
+	if err != nil {
+		t.Fatalf("Error globbing for output file: %v", err)
+	}
+	if len(outputFiles) == 0 {
+		allFiles, _ := filepath.Glob("*")
+		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)
+	if err != nil {
+		t.Fatalf("Failed to read output file: %v", err)
+	}
+
+	// Check if the content includes the expected files
+	expectedContent := []string{
+		"# 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) {
+			t.Errorf("Output file does not contain expected content: %s", expected)
+		}
+	}
+
+	// Check if the ignored files are not included
+	ignoredContent := []string{
+		"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/root.go

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

@@ -2,6 +2,8 @@ package cmd
 
 import (
 	"fmt"
+	"io/ioutil"
+	"log"
 	"net/url"
 	"os"
 	"regexp"
@@ -9,6 +11,7 @@ import (
 	"time"
 
 	"github.com/spf13/cobra"
+	"github.com/tnypxl/rollup/internal/config"
 	"github.com/tnypxl/rollup/internal/scraper"
 )
 
@@ -38,51 +41,97 @@ func init() {
 }
 
 func runWeb(cmd *cobra.Command, args []string) error {
-	scraperConfig.Verbose = verbose
+    scraper.SetupLogger(verbose)
+    logger := log.New(os.Stdout, "WEB: ", log.LstdFlags)
+    if !verbose {
+        logger.SetOutput(ioutil.Discard)
+    }
+    logger.Printf("Starting web scraping process with verbose mode: %v", verbose)
+    scraperConfig.Verbose = verbose
 
-	// Use config if available, otherwise use command-line flags
-	var urlConfigs []scraper.URLConfig
-	if len(urls) == 0 && len(cfg.Scrape.URLs) > 0 {
-		urlConfigs = make([]scraper.URLConfig, len(cfg.Scrape.URLs))
-		for i, u := range cfg.Scrape.URLs {
-			urlConfigs[i] = scraper.URLConfig{
-				URL:              u.URL,
-				CSSLocator:       u.CSSLocator,
-				ExcludeSelectors: u.ExcludeSelectors,
-				OutputAlias:      u.OutputAlias,
-			}
-		}
-	} else {
-		urlConfigs = make([]scraper.URLConfig, len(urls))
-		for i, u := range urls {
-			urlConfigs[i] = scraper.URLConfig{URL: u, CSSLocator: includeSelector}
-		}
-	}
+    var siteConfigs []scraper.SiteConfig
+    if len(cfg.Scrape.Sites) > 0 {
+        logger.Printf("Using configuration from rollup.yml for %d sites", len(cfg.Scrape.Sites))
+        siteConfigs = make([]scraper.SiteConfig, len(cfg.Scrape.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, MaxDepth=%d, AllowedPaths=%v",
+                       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")
+        siteConfigs = make([]scraper.SiteConfig, len(urls))
+        for i, u := range urls {
+            siteConfigs[i] = scraper.SiteConfig{
+                BaseURL:          u,
+                CSSLocator:       includeSelector,
+                ExcludeSelectors: excludeSelectors,
+                MaxDepth:         depth,
+            }
+            logger.Printf("URL %d configuration: BaseURL=%s, CSSLocator=%s, MaxDepth=%d",
+                       i+1, u, includeSelector, depth)
+        }
+    }
 
-	if len(urlConfigs) == 0 {
-		return fmt.Errorf("no URLs provided. Use --urls flag with comma-separated URLs or set 'scrape.urls' in the rollup.yml file")
-	}
+    if len(siteConfigs) == 0 {
+        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")
+    }
 
-	scraperConfig := scraper.Config{
-		URLs:       urlConfigs,
-		OutputType: outputType,
-		Verbose:    verbose,
-	}
+    // Set default values for rate limiting
+    defaultRequestsPerSecond := 1.0
+    defaultBurstLimit := 3
 
-	scrapedContent, err := scraper.ScrapeMultipleURLs(scraperConfig)
-	if err != nil {
-		return fmt.Errorf("error scraping content: %v", err)
-	}
+    // Use default values if not set in the configuration
+    requestsPerSecond := cfg.Scrape.RequestsPerSecond
+    if requestsPerSecond == 0 {
+        requestsPerSecond = defaultRequestsPerSecond
+    }
+    burstLimit := cfg.Scrape.BurstLimit
+    if burstLimit == 0 {
+        burstLimit = defaultBurstLimit
+    }
 
-	if outputType == "single" {
-		return writeSingleFile(scrapedContent)
-	} else {
-		return writeMultipleFiles(scrapedContent)
-	}
+    scraperConfig := scraper.Config{
+        Sites:      siteConfigs,
+        OutputType: outputType,
+        Verbose:    verbose,
+        Scrape: scraper.ScrapeConfig{
+            RequestsPerSecond: requestsPerSecond,
+            BurstLimit:        burstLimit,
+        },
+    }
+    logger.Printf("Scraper configuration: OutputType=%s, RequestsPerSecond=%f, BurstLimit=%d",
+               outputType, requestsPerSecond, burstLimit)
+
+    logger.Println("Starting scraping process")
+    scrapedContent, err := scraper.ScrapeSites(scraperConfig)
+    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 {
-	outputFile := generateDefaultFilename(urls)
+	outputFile := generateDefaultFilename()
 	file, err := os.Create(outputFile)
 	if err != nil {
 		return fmt.Errorf("error creating output file: %v", err)
@@ -90,7 +139,7 @@ func writeSingleFile(content map[string]string) error {
 	defer file.Close()
 
 	for url, c := range content {
-		_, err = file.WriteString(fmt.Sprintf("# 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)
 		}
@@ -102,24 +151,30 @@ func writeSingleFile(content map[string]string) error {
 
 func writeMultipleFiles(content map[string]string) error {
 	for url, c := range content {
-		filename := getFilenameFromContent(c, url)
+		filename, err := getFilenameFromContent(c, url)
+		if err != nil {
+			return fmt.Errorf("error generating filename for %s: %v", url, err)
+		}
+
 		file, err := os.Create(filename)
 		if err != nil {
 			return fmt.Errorf("error creating output file %s: %v", filename, err)
 		}
 
-		_, err = file.WriteString(fmt.Sprintf("# Content from %s\n\n%s", url, c))
-		file.Close()
+		_, 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)
 		}
 
+		file.Close()
 		fmt.Printf("Content from %s has been saved to %s\n", url, filename)
 	}
+
 	return nil
 }
 
-func generateDefaultFilename(urls []string) string {
+func generateDefaultFilename() string {
 	timestamp := time.Now().Format("20060102-150405")
 	return fmt.Sprintf("web-%s.rollup.md", timestamp)
 }
@@ -136,13 +191,13 @@ func scrapeURL(urlStr string, depth int, visited map[string]bool) (string, error
 
 	visited[urlStr] = true
 
-	content, err := extractAndConvertContent(urlStr)
+	content, err := testExtractAndConvertContent(urlStr)
 	if err != nil {
 		return "", err
 	}
 
 	if depth > 0 {
-		links, err := scraper.ExtractLinks(urlStr)
+		links, err := testExtractLinks(urlStr)
 		if err != nil {
 			return content, fmt.Errorf("error extracting links: %v", err)
 		}
@@ -160,6 +215,9 @@ func scrapeURL(urlStr string, depth int, visited map[string]bool) (string, error
 	return content, nil
 }
 
+var testExtractAndConvertContent = extractAndConvertContent
+var testExtractLinks = scraper.ExtractLinks
+
 func extractAndConvertContent(urlStr string) (string, error) {
 	content, err := scraper.FetchWebpageContent(urlStr)
 	if err != nil {
@@ -187,17 +245,32 @@ func extractAndConvertContent(urlStr string) (string, error) {
 	return header + markdown + "\n\n", nil
 }
 
-func getFilenameFromContent(content, url string) string {
+func getFilenameFromContent(content, urlStr string) (string, error) {
 	// Try to extract title from content
 	titleStart := strings.Index(content, "<title>")
 	titleEnd := strings.Index(content, "</title>")
 	if titleStart != -1 && titleEnd != -1 && titleEnd > titleStart {
-		title := content[titleStart+7 : titleEnd]
-		return sanitizeFilename(title) + ".md"
+		title := strings.TrimSpace(content[titleStart+7 : titleEnd])
+		if title != "" {
+			return sanitizeFilename(title) + ".rollup.md", nil
+		}
 	}
 
-	// If no title found, use the URL
-	return sanitizeFilename(url) + ".md"
+	// If no title found or title is empty, use the URL
+	parsedURL, err := url.Parse(urlStr)
+	if err != nil {
+		return "", fmt.Errorf("invalid URL: %v", err)
+	}
+
+	if parsedURL.Host == "" {
+		return "", fmt.Errorf("invalid URL: missing host")
+	}
+
+	filename := parsedURL.Host
+	if parsedURL.Path != "" && parsedURL.Path != "/" {
+		filename += strings.TrimSuffix(parsedURL.Path, "/")
+	}
+	return sanitizeFilename(filename) + ".rollup.md", nil
 }
 
 func sanitizeFilename(name string) string {
@@ -215,3 +288,15 @@ func sanitizeFilename(name string) string {
 
 	return name
 }
+
+func convertPathOverrides(configOverrides []config.PathOverride) []scraper.PathOverride {
+	scraperOverrides := make([]scraper.PathOverride, len(configOverrides))
+	for i, override := range configOverrides {
+		scraperOverrides[i] = scraper.PathOverride{
+			Path:             override.Path,
+			CSSLocator:       override.CSSLocator,
+			ExcludeSelectors: override.ExcludeSelectors,
+		}
+	}
+	return scraperOverrides
+}

cmd/web_test.go

@@ -0,0 +1,154 @@
+package cmd
+
+import (
+	"testing"
+	"strings"
+	"github.com/tnypxl/rollup/internal/config"
+)
+
+func TestConvertPathOverrides(t *testing.T) {
+	configOverrides := []config.PathOverride{
+		{
+			Path:             "/blog",
+			CSSLocator:       "article",
+			ExcludeSelectors: []string{".ads", ".comments"},
+		},
+		{
+			Path:             "/products",
+			CSSLocator:       ".product-description",
+			ExcludeSelectors: []string{".related-items"},
+		},
+	}
+
+	scraperOverrides := convertPathOverrides(configOverrides)
+
+	if len(scraperOverrides) != len(configOverrides) {
+		t.Errorf("Expected %d overrides, got %d", len(configOverrides), len(scraperOverrides))
+	}
+
+	for i, override := range scraperOverrides {
+		if override.Path != configOverrides[i].Path {
+			t.Errorf("Expected Path %s, got %s", configOverrides[i].Path, override.Path)
+		}
+		if override.CSSLocator != configOverrides[i].CSSLocator {
+			t.Errorf("Expected CSSLocator %s, got %s", configOverrides[i].CSSLocator, override.CSSLocator)
+		}
+		if len(override.ExcludeSelectors) != len(configOverrides[i].ExcludeSelectors) {
+			t.Errorf("Expected %d ExcludeSelectors, got %d", len(configOverrides[i].ExcludeSelectors), len(override.ExcludeSelectors))
+		}
+		for j, selector := range override.ExcludeSelectors {
+			if selector != configOverrides[i].ExcludeSelectors[j] {
+				t.Errorf("Expected ExcludeSelector %s, got %s", configOverrides[i].ExcludeSelectors[j], selector)
+			}
+		}
+	}
+}
+
+func TestSanitizeFilename(t *testing.T) {
+	tests := []struct {
+		input    string
+		expected string
+	}{
+		{"Hello, World!", "Hello_World"},
+		{"file/with/path", "file_with_path"},
+		{"file.with.dots", "file_with_dots"},
+		{"___leading_underscores___", "leading_underscores"},
+		{"", "untitled"},
+		{"!@#$%^&*()", "untitled"},
+	}
+
+	for _, test := range tests {
+		result := sanitizeFilename(test.input)
+		if result != test.expected {
+			t.Errorf("sanitizeFilename(%q) = %q; want %q", test.input, result, test.expected)
+		}
+	}
+}
+
+func TestGetFilenameFromContent(t *testing.T) {
+	tests := []struct {
+		content  string
+		url      string
+		expected string
+		expectErr bool
+	}{
+		{"<title>Test Page</title>", "http://example.com", "Test_Page.rollup.md", false},
+		{"No title here", "http://example.com/page", "example_com_page.rollup.md", false},
+		{"<title>  Trim  Me  </title>", "http://example.com", "Trim_Me.rollup.md", false},
+		{"<title></title>", "http://example.com", "example_com.rollup.md", false},
+		{"<title>   </title>", "http://example.com", "example_com.rollup.md", false},
+		{"Invalid URL", "not a valid url", "", true},
+		{"No host", "http://", "", true},
+	}
+
+	for _, test := range tests {
+		result, err := getFilenameFromContent(test.content, test.url)
+		if test.expectErr {
+			if err == nil {
+				t.Errorf("getFilenameFromContent(%q, %q) expected an error, but got none", test.content, test.url)
+			}
+		} else {
+			if err != nil {
+				t.Errorf("getFilenameFromContent(%q, %q) unexpected error: %v", test.content, test.url, err)
+			}
+			if result != test.expected {
+				t.Errorf("getFilenameFromContent(%q, %q) = %q; want %q", test.content, test.url, result, test.expected)
+			}
+		}
+	}
+}
+
+// Mock functions for testing
+func mockExtractAndConvertContent(urlStr string) (string, error) {
+	return "Mocked content for " + urlStr, nil
+}
+
+func mockExtractLinks(urlStr string) ([]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)
+		}
+	}
+}

docs/CHANGELOG.md

@@ -0,0 +1,21 @@
+# 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

go.mod

@@ -5,6 +5,7 @@ go 1.23
 require (
 	github.com/JohannesKaufmann/html-to-markdown v1.6.0
 	github.com/spf13/cobra v1.8.1
+	golang.org/x/time v0.6.0
 )
 
 require (
@@ -21,7 +22,6 @@ require (
 	github.com/PuerkitoBio/goquery v1.9.2
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
 	github.com/playwright-community/playwright-go v0.4501.1
-	github.com/russross/blackfriday/v2 v2.1.0
 	github.com/spf13/pflag v1.0.5 // indirect
 	gopkg.in/yaml.v2 v2.4.0
 )

go.sum

@@ -32,7 +32,6 @@ github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZb
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/rogpeppe/go-internal v1.11.0 h1:cWPaGQEPrBb5/AsnsZesgZZ9yb1OQ+GOISoDNXVBh4M=
 github.com/rogpeppe/go-internal v1.11.0/go.mod h1:ddIwULY96R17DhadqLgMfk9H9tvdUzkipdSkR5nkCZA=
-github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/sebdah/goldie/v2 v2.5.3 h1:9ES/mNN+HNUbNWpVAlrzuZ7jE+Nrczbj8uFRjM7624Y=
 github.com/sebdah/goldie/v2 v2.5.3/go.mod h1:oZ9fp0+se1eapSRjfYbsV/0Hqhbuu3bJVvKI/NNtssI=
@@ -103,6 +102,8 @@ golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/time v0.6.0 h1:eTDhh4ZXt5Qf0augr54TN6suAUudPcawVZeIAPU7D4U=
+golang.org/x/time v0.6.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=

internal/config/config.go

@@ -15,15 +15,27 @@ type Config struct {
 }
 
 type ScrapeConfig struct {
-	URLs       []URLConfig `yaml:"urls"`
-	OutputType string      `yaml:"output_type"`
+    Sites             []SiteConfig `yaml:"sites"`
+    OutputType        string       `yaml:"output_type"`
+    RequestsPerSecond float64      `yaml:"requests_per_second"`
+    BurstLimit        int          `yaml:"burst_limit"`
 }
 
-type URLConfig struct {
-	URL              string   `yaml:"url"`
-	CSSLocator       string   `yaml:"css_locator"`
-	ExcludeSelectors []string `yaml:"exclude_selectors"`
-	OutputAlias      string   `yaml:"output_alias"`
+type SiteConfig struct {
+    BaseURL          string            `yaml:"base_url"`
+    CSSLocator       string            `yaml:"css_locator"`
+    ExcludeSelectors []string          `yaml:"exclude_selectors"`
+    MaxDepth         int               `yaml:"max_depth"`
+    AllowedPaths     []string          `yaml:"allowed_paths"`
+    ExcludePaths     []string          `yaml:"exclude_paths"`
+    OutputAlias      string            `yaml:"output_alias"`
+    PathOverrides    []PathOverride    `yaml:"path_overrides"`
+}
+
+type PathOverride struct {
+    Path             string   `yaml:"path"`
+    CSSLocator       string   `yaml:"css_locator"`
+    ExcludeSelectors []string `yaml:"exclude_selectors"`
 }
 
 func Load(configPath string) (*Config, error) {

internal/config/config_test.go

@@ -0,0 +1,120 @@
+package config
+
+import (
+	"os"
+	"reflect"
+	"testing"
+)
+
+func TestLoad(t *testing.T) {
+	// Create a temporary config file
+	content := []byte(`
+file_types:
+  - go
+  - md
+ignore:
+  - "*.tmp"
+  - "**/*.log"
+code_generated:
+  - "generated_*.go"
+scrape:
+  sites:
+    - base_url: "https://example.com"
+      css_locator: "main"
+      exclude_selectors:
+        - ".ads"
+      max_depth: 2
+      allowed_paths:
+        - "/blog"
+      exclude_paths:
+        - "/admin"
+      output_alias: "example"
+      path_overrides:
+        - path: "/special"
+          css_locator: ".special-content"
+          exclude_selectors:
+            - ".sidebar"
+  output_type: "single"
+  requests_per_second: 1.0
+  burst_limit: 5
+`)
+
+	tmpfile, err := os.CreateTemp("", "config*.yml")
+	if err != nil {
+		t.Fatalf("Failed to create temp file: %v", err)
+	}
+	defer os.Remove(tmpfile.Name())
+
+	if _, err := tmpfile.Write(content); err != nil {
+		t.Fatalf("Failed to write to temp file: %v", err)
+	}
+	if err := tmpfile.Close(); err != nil {
+		t.Fatalf("Failed to close temp file: %v", err)
+	}
+
+	// Test loading the config
+	config, err := Load(tmpfile.Name())
+	if err != nil {
+		t.Fatalf("Load() failed: %v", err)
+	}
+
+	// Check if the loaded config matches the expected values
+	expectedConfig := &Config{
+		FileTypes:     []string{"go", "md"},
+		Ignore:        []string{"*.tmp", "**/*.log"},
+		CodeGenerated: []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",
+					PathOverrides: []PathOverride{
+						{
+							Path:             "/special",
+							CSSLocator:       ".special-content",
+							ExcludeSelectors: []string{".sidebar"},
+						},
+					},
+				},
+			},
+			OutputType:        "single",
+			RequestsPerSecond: 1.0,
+			BurstLimit:        5,
+		},
+	}
+
+	if !reflect.DeepEqual(config, expectedConfig) {
+		t.Errorf("Loaded config does not match expected config.\nGot: %+v\nWant: %+v", config, expectedConfig)
+	}
+}
+
+func TestDefaultConfigPath(t *testing.T) {
+	expected := "rollup.yml"
+	result := DefaultConfigPath()
+	if result != expected {
+		t.Errorf("DefaultConfigPath() = %q, want %q", result, expected)
+	}
+}
+
+func TestFileExists(t *testing.T) {
+	// Test with an existing file
+	tmpfile, err := os.CreateTemp("", "testfile")
+	if err != nil {
+		t.Fatalf("Failed to create temp file: %v", err)
+	}
+	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

@@ -5,13 +5,18 @@ import (
 	"io/ioutil"
 	"log"
 	"math/rand"
+	"net/url"
+	"os"
 	"regexp"
 	"strings"
 	"time"
+	"sync"
+	"context"
 
 	"github.com/PuerkitoBio/goquery"
 	"github.com/playwright-community/playwright-go"
 	md "github.com/JohannesKaufmann/html-to-markdown"
+	"golang.org/x/time/rate"
 )
 
 var logger *log.Logger
@@ -23,57 +28,240 @@ var (
 
 // Config holds the scraper configuration
 type Config struct {
-	URLs       []URLConfig
+	Sites      []SiteConfig
 	OutputType string
 	Verbose    bool
+	Scrape     ScrapeConfig
 }
 
-// ScrapeMultipleURLs scrapes multiple URLs concurrently
-func ScrapeMultipleURLs(config Config) (map[string]string, error) {
-	results := make(chan struct {
-		url     string
-		content string
-		err     error
-	}, len(config.URLs))
-
-	for _, urlConfig := range config.URLs {
-		go func(cfg URLConfig) {
-			content, err := scrapeURL(cfg)
-			results <- struct {
-				url     string
-				content string
-				err     error
-			}{cfg.URL, content, err}
-		}(urlConfig)
-	}
-
-	scrapedContent := make(map[string]string)
-	for i := 0; i < len(config.URLs); i++ {
-		result := <-results
-		if result.err != nil {
-			logger.Printf("Error scraping %s: %v\n", result.url, result.err)
-			continue
-		}
-		scrapedContent[result.url] = result.content
-	}
-
-	return scrapedContent, nil
+// ScrapeConfig holds the scraping-specific configuration
+type ScrapeConfig struct {
+	RequestsPerSecond float64
+	BurstLimit        int
 }
 
-func scrapeURL(config URLConfig) (string, error) {
-	content, err := FetchWebpageContent(config.URL)
-	if err != nil {
-		return "", err
-	}
+// SiteConfig holds configuration for a single site
+type SiteConfig struct {
+	BaseURL          string
+	CSSLocator       string
+	ExcludeSelectors []string
+	MaxDepth         int
+	AllowedPaths     []string
+	ExcludePaths     []string
+	OutputAlias      string
+	PathOverrides    []PathOverride
+}
 
-	if config.CSSLocator != "" {
-		content, err = ExtractContentWithCSS(content, config.CSSLocator, config.ExcludeSelectors)
-		if err != nil {
-			return "", err
-		}
-	}
+// PathOverride holds path-specific overrides
+type PathOverride struct {
+	Path             string
+	CSSLocator       string
+	ExcludeSelectors []string
+}
 
-	return ProcessHTMLContent(content, Config{})
+func ScrapeSites(config Config) (map[string]string, error) {
+    logger.Println("Starting ScrapeSites function - Verbose mode is active")
+    results := make(chan struct {
+        url     string
+        content string
+        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)
+
+    var wg sync.WaitGroup
+    totalURLs := 0
+    for _, site := range config.Sites {
+        logger.Printf("Processing site: %s\n", site.BaseURL)
+        wg.Add(1)
+        go func(site SiteConfig) {
+            defer wg.Done()
+            for _, path := range site.AllowedPaths {
+                fullURL := site.BaseURL + path
+                totalURLs++
+                logger.Printf("Queueing URL for scraping: %s\n", fullURL)
+                scrapeSingleURL(fullURL, site, config, results, limiter)
+            }
+        }(site)
+    }
+
+    go func() {
+        wg.Wait()
+        close(results)
+        logger.Println("All goroutines completed, results channel closed")
+    }()
+
+    scrapedContent := make(map[string]string)
+    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))
+        scrapedContent[result.url] = result.content
+    }
+
+    logger.Printf("Total URLs processed: %d\n", totalURLs)
+    logger.Printf("Successfully scraped content from %d URLs\n", len(scrapedContent))
+
+    return scrapedContent, nil
+}
+
+func scrapeSingleURL(url string, site SiteConfig, config Config, results chan<- struct {
+    url     string
+    content string
+    err     error
+}, 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, 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)
+    if err != nil {
+        return false
+    }
+
+    baseURL, _ := url.Parse(site.BaseURL)
+    if parsedURL.Host != baseURL.Host {
+        return false
+    }
+
+    path := parsedURL.Path
+    for _, allowedPath := range site.AllowedPaths {
+        if strings.HasPrefix(path, allowedPath) {
+            for _, excludePath := range site.ExcludePaths {
+                if strings.HasPrefix(path, excludePath) {
+                    return false
+                }
+            }
+            return true
+        }
+    }
+
+    return false
+}
+
+func getOverrides(urlStr string, site SiteConfig) (string, []string) {
+    parsedURL, _ := url.Parse(urlStr)
+    path := parsedURL.Path
+
+    for _, override := range site.PathOverrides {
+        if strings.HasPrefix(path, override.Path) {
+            if override.CSSLocator != "" {
+                return override.CSSLocator, override.ExcludeSelectors
+            }
+            return site.CSSLocator, override.ExcludeSelectors
+        }
+    }
+
+    return site.CSSLocator, site.ExcludeSelectors
+}
+
+func scrapeURL(url, cssLocator string, excludeSelectors []string) (string, error) {
+    content, err := FetchWebpageContent(url)
+    if err != nil {
+        return "", err
+    }
+
+    if cssLocator != "" {
+        content, err = ExtractContentWithCSS(content, cssLocator, excludeSelectors)
+        if err != nil {
+            return "", err
+        }
+    }
+
+    return ProcessHTMLContent(content, Config{})
 }
 
 func getFilenameFromContent(content, url string) string {
@@ -106,7 +294,7 @@ type URLConfig struct {
 // SetupLogger initializes the logger based on the verbose flag
 func SetupLogger(verbose bool) {
 	if verbose {
-		logger = log.New(log.Writer(), "SCRAPER: ", log.LstdFlags)
+		logger = log.New(os.Stdout, "SCRAPER: ", log.LstdFlags)
 	} else {
 		logger = log.New(ioutil.Discard, "", 0)
 	}
@@ -151,6 +339,16 @@ 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)
@@ -330,7 +528,9 @@ func ExtractLinks(urlStr string) ([]string, error) {
 
 	var result []string
 	for _, link := range links.([]interface{}) {
-		result = append(result, link.(string))
+		// Normalize URL by removing trailing slash
+		normalizedLink := strings.TrimRight(link.(string), "/")
+		result = append(result, normalizedLink)
 	}
 
 	logger.Printf("Extracted %d links\n", len(result))
@@ -364,6 +564,23 @@ 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

@@ -0,0 +1,181 @@
+package scraper
+
+import (
+	"testing"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"reflect"
+	"log"
+	"io/ioutil"
+)
+
+func TestIsAllowedURL(t *testing.T) {
+	site := SiteConfig{
+		BaseURL:      "https://example.com",
+		AllowedPaths: []string{"/blog", "/products"},
+		ExcludePaths: []string{"/admin", "/private"},
+	}
+
+	tests := []struct {
+		url      string
+		expected bool
+	}{
+		{"https://example.com/blog/post1", true},
+		{"https://example.com/products/item1", true},
+		{"https://example.com/admin/dashboard", false},
+		{"https://example.com/private/data", false},
+		{"https://example.com/other/page", false},
+		{"https://othersite.com/blog/post1", false},
+	}
+
+	for _, test := range tests {
+		result := isAllowedURL(test.url, site)
+		if result != test.expected {
+			t.Errorf("isAllowedURL(%q) = %v, want %v", test.url, result, test.expected)
+		}
+	}
+}
+
+func TestGetOverrides(t *testing.T) {
+	site := SiteConfig{
+		CSSLocator:       "main",
+		ExcludeSelectors: []string{".ads"},
+		PathOverrides: []PathOverride{
+			{
+				Path:             "/special",
+				CSSLocator:       ".special-content",
+				ExcludeSelectors: []string{".sidebar"},
+			},
+		},
+	}
+
+	tests := []struct {
+		url               string
+		expectedLocator   string
+		expectedExcludes  []string
+	}{
+		{"https://example.com/normal", "main", []string{".ads"}},
+		{"https://example.com/special", ".special-content", []string{".sidebar"}},
+		{"https://example.com/special/page", ".special-content", []string{".sidebar"}},
+	}
+
+	for _, test := range tests {
+		locator, excludes := getOverrides(test.url, site)
+		if locator != test.expectedLocator {
+			t.Errorf("getOverrides(%q) locator = %q, want %q", test.url, locator, test.expectedLocator)
+		}
+		if !reflect.DeepEqual(excludes, test.expectedExcludes) {
+			t.Errorf("getOverrides(%q) excludes = %v, want %v", test.url, excludes, test.expectedExcludes)
+		}
+	}
+}
+
+func TestExtractContentWithCSS(t *testing.T) {
+	// Initialize logger for testing
+	logger = log.New(ioutil.Discard, "", 0)
+
+	html := `
+		<html>
+			<body>
+				<main>
+					<h1>Main Content</h1>
+					<p>This is the main content.</p>
+					<div class="ads">Advertisement</div>
+				</main>
+				<aside>Sidebar content</aside>
+			</body>
+		</html>
+	`
+
+	tests := []struct {
+		includeSelector  string
+		excludeSelectors []string
+		expected         string
+	}{
+		{"main", nil, "<h1>Main Content</h1>\n<p>This is the main content.</p>\n<div class=\"ads\">Advertisement</div>"},
+		{"main", []string{".ads"}, "<h1>Main Content</h1>\n<p>This is the main content.</p>"},
+		{"aside", nil, "Sidebar content"},
+	}
+
+	for _, test := range tests {
+		result, err := ExtractContentWithCSS(html, test.includeSelector, test.excludeSelectors)
+		if err != nil {
+			t.Errorf("ExtractContentWithCSS() returned error: %v", err)
+			continue
+		}
+		if strings.TrimSpace(result) != strings.TrimSpace(test.expected) {
+			t.Errorf("ExtractContentWithCSS() = %q, want %q", result, test.expected)
+		}
+	}
+}
+
+func TestProcessHTMLContent(t *testing.T) {
+	html := `
+		<html>
+			<body>
+				<h1>Test Heading</h1>
+				<p>This is a <strong>test</strong> paragraph.</p>
+				<ul>
+					<li>Item 1</li>
+					<li>Item 2</li>
+				</ul>
+			</body>
+		</html>
+	`
+
+	expected := strings.TrimSpace(`
+# Test Heading
+
+This is a **test** paragraph.
+
+- Item 1
+- Item 2
+	`)
+
+	result, err := ProcessHTMLContent(html, Config{})
+	if err != nil {
+		t.Fatalf("ProcessHTMLContent() returned error: %v", err)
+	}
+
+	if strings.TrimSpace(result) != expected {
+		t.Errorf("ProcessHTMLContent() = %q, want %q", result, expected)
+	}
+}
+
+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(`
+			<html>
+				<body>
+					<a href="https://example.com/page1">Page 1</a>
+					<a href="https://example.com/page2">Page 2</a>
+					<a href="https://othersite.com">Other Site</a>
+				</body>
+			</html>
+		`))
+	}))
+	defer server.Close()
+
+	links, err := ExtractLinks(server.URL)
+	if err != nil {
+		t.Fatalf("ExtractLinks() returned error: %v", err)
+	}
+
+	expectedLinks := []string{
+		"https://example.com/page1",
+		"https://example.com/page2",
+		"https://othersite.com",
+	}
+
+	if !reflect.DeepEqual(links, expectedLinks) {
+		t.Errorf("ExtractLinks() = %v, want %v", links, expectedLinks)
+	}
+}