fix: Remove MaxDepth references from cmd/web.go

cmd/web.go

@@ -33,7 +33,7 @@ var webCmd = &cobra.Command{
 
 func init() {
 	webCmd.Flags().StringSliceVarP(&urls, "urls", "u", []string{}, "URLs of the webpages to scrape (comma-separated)")
-	webCmd.Flags().StringVarP(&outputType, "output", "o", "", "Output type: 'single' for one file, 'separate' for multiple files")
+	webCmd.Flags().StringVarP(&outputType, "output", "o", "single", "Output type: 'single' for one file, 'separate' for multiple files")
 	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)")
 }
@@ -58,6 +58,7 @@ func runWeb(cmd *cobra.Command, args []string) error {
 				ExcludeSelectors: site.ExcludeSelectors,
 				AllowedPaths:     site.AllowedPaths,
 				ExcludePaths:     site.ExcludePaths,
+				OutputAlias:      site.OutputAlias,
 				PathOverrides:    convertPathOverrides(site.PathOverrides),
 			}
 			logger.Printf("Site %d configuration: BaseURL=%s, CSSLocator=%s, AllowedPaths=%v",
@@ -131,7 +132,7 @@ func runWeb(cmd *cobra.Command, args []string) error {
 		}
 	}()
 
-	err := scraper.ScrapeSites(scraperConfig)
+	scrapedContent, err := scraper.ScrapeSites(scraperConfig)
 	done <- true
 	fmt.Println() // New line after progress indicator
 
@@ -139,9 +140,15 @@ func runWeb(cmd *cobra.Command, args []string) error {
 		logger.Printf("Error occurred during scraping: %v", err)
 		return fmt.Errorf("error scraping content: %v", err)
 	}
-	logger.Println("Scraping completed")
+	logger.Printf("Scraping completed. Total content scraped: %d", len(scrapedContent))
 
-	return nil
+	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 {

cmd/web_test.go

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

internal/config/config.go

@@ -48,8 +48,8 @@ type SiteConfig struct {
 	// ExcludePaths lists paths that should not be scraped
 	ExcludePaths []string `yaml:"exclude_paths"`
 
-	// FileNamePrefix provides the base name for output files
-	FileNamePrefix string `yaml:"file_name_prefix"`
+	// OutputAlias provides an alternative name for output files
+	OutputAlias string `yaml:"output_alias"`
 
 	// PathOverrides allows for path-specific configurations
 	PathOverrides []PathOverride `yaml:"path_overrides"`

internal/config/config_test.go

@@ -27,7 +27,7 @@ sites:
       - "/blog"
     exclude_paths:
       - "/admin"
-      file_name_prefix: "example"
+    output_alias: "example"
     path_overrides:
       - path: "/special"
         css_locator: ".special-content"
@@ -69,9 +69,10 @@ burst_limit: 5
 				BaseURL:          "https://example.com",
 				CSSLocator:       "main",
 				ExcludeSelectors: []string{".ads"},
+				MaxDepth:         2,
 				AllowedPaths:     []string{"/blog"},
 				ExcludePaths:     []string{"/admin"},
-				FileNamePrefix:   "example",
+				OutputAlias:      "example",
 				PathOverrides: []PathOverride{
 					{
 						Path:             "/special",
@@ -102,7 +103,7 @@ func TestValidate(t *testing.T) {
 			config: Config{
 				FileExtensions: []string{".go"},
 				Sites: []SiteConfig{
-					{BaseURL: "https://example.com"},
+					{BaseURL: "https://example.com", MaxDepth: 2},
 				},
 			},
 			wantErr: false,
@@ -140,7 +141,7 @@ func TestValidate(t *testing.T) {
 			name: "Negative max depth",
 			config: Config{
 				FileExtensions: []string{".go"},
-				Sites:          []SiteConfig{{BaseURL: "https://example.com"}},
+				Sites:          []SiteConfig{{BaseURL: "https://example.com", MaxDepth: -1}},
 			},
 			wantErr: true,
 		},

internal/scraper/scraper.go

@@ -8,7 +8,6 @@ import (
 	"math/rand"
 	"net/url"
 	"os"
-	"path/filepath"
 	"regexp"
 	"strings"
 	"sync"
@@ -48,7 +47,7 @@ type SiteConfig struct {
 	ExcludeSelectors []string
 	AllowedPaths     []string
 	ExcludePaths     []string
-	FileNamePrefix   string
+	OutputAlias      string
 	PathOverrides    []PathOverride
 }
 
@@ -59,18 +58,16 @@ type PathOverride struct {
 	ExcludeSelectors []string
 }
 
-func ScrapeSites(config Config) error {
+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
-		site    SiteConfig // Add site config to track which site the content came from
 		err     error
 	})
 
 	limiter := rate.NewLimiter(rate.Limit(config.Scrape.RequestsPerSecond), config.Scrape.BurstLimit)
-	logger.Printf("Rate limiter configured with %f requests per second and burst limit of %d\n",
-		config.Scrape.RequestsPerSecond, config.Scrape.BurstLimit)
+	logger.Printf("Rate limiter configured with %f requests per second and burst limit of %d\n", config.Scrape.RequestsPerSecond, config.Scrape.BurstLimit)
 
 	var wg sync.WaitGroup
 	totalURLs := 0
@@ -94,73 +91,71 @@ func ScrapeSites(config Config) error {
 		logger.Println("All goroutines completed, results channel closed")
 	}()
 
-	// Use a map that includes site configuration
-	scrapedContent := make(map[string]struct {
-		content string
-		site    SiteConfig
-	})
-
+	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] = struct {
-			content string
-			site    SiteConfig
-		}{
-			content: result.content,
-			site:    result.site,
-		}
+		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 SaveToFiles(scrapedContent, config)
+	return scrapedContent, nil
 }
 
 func scrapeSingleURL(url string, site SiteConfig, results chan<- struct {
 	url     string
 	content string
-	site    SiteConfig
 	err     error
-}, limiter *rate.Limiter) {
+}, limiter *rate.Limiter,
+) {
 	logger.Printf("Starting to scrape URL: %s\n", url)
 
+	// Wait for rate limiter before making the request
 	err := limiter.Wait(context.Background())
 	if err != nil {
+		logger.Printf("Rate limiter error for %s: %v\n", url, err)
 		results <- struct {
 			url     string
 			content string
-			site    SiteConfig
 			err     error
-		}{url, "", site, fmt.Errorf("rate limiter error: %v", err)}
+		}{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
-			site    SiteConfig
 			err     error
-		}{url, "", site, err}
+		}{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
-		site    SiteConfig
 		err     error
-	}{url, content, site, nil}
+	}{url, content, nil}
 }
 
+
 func isAllowedURL(urlStr string, site SiteConfig) bool {
 	parsedURL, err := url.Parse(urlStr)
 	if err != nil {
@@ -233,14 +228,9 @@ func getFilenameFromContent(content, url string) string {
 }
 
 func sanitizeFilename(name string) string {
-	// Replace all non-alphanumeric characters with dashes
-	reg := regexp.MustCompile("[^a-zA-Z0-9]+")
-	name = reg.ReplaceAllString(name, "-")
-	// Remove any leading or trailing dashes
-	name = strings.Trim(name, "-")
-	// Collapse multiple consecutive dashes into one
-	reg = regexp.MustCompile("-+")
-	return reg.ReplaceAllString(name, "-")
+	// Remove any character that isn't alphanumeric, dash, or underscore
+	reg, _ := regexp.Compile("[^a-zA-Z0-9-_]+")
+	return reg.ReplaceAllString(name, "_")
 }
 
 // URLConfig holds configuration for a single URL
@@ -248,7 +238,7 @@ type URLConfig struct {
 	URL              string
 	CSSLocator       string
 	ExcludeSelectors []string
-	FileNamePrefix   string
+	OutputAlias      string
 }
 
 // SetupLogger initializes the logger based on the verbose flag
@@ -276,7 +266,7 @@ func InitPlaywright() error {
 		return fmt.Errorf("could not start Playwright: %v", err)
 	}
 
-	userAgent := "Mozilla/5.0 (Linux; Android 15; Pixel 9 Build/AP3A.241105.008) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.6723.106 Mobile Safari/537.36 OPX/2.5"
+	userAgent := "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
 
 	browser, err = pw.Chromium.Launch(playwright.BrowserTypeLaunchOptions{
 		Args: []string{fmt.Sprintf("--user-agent=%s", userAgent)},
@@ -309,119 +299,6 @@ func CloseBrowser() {
 	ClosePlaywright()
 }
 
-// SaveToFiles writes the scraped content to files based on output type
-func SaveToFiles(content map[string]struct {
-	content string
-	site    SiteConfig
-}, config Config) error {
-	if config.OutputType == "" {
-		config.OutputType = "separate" // default to separate files if not specified
-	}
-
-	switch config.OutputType {
-	case "single":
-		if err := os.MkdirAll("output", 0755); err != nil {
-			return fmt.Errorf("failed to create output directory: %v", err)
-		}
-		var combined strings.Builder
-		for url, data := range content {
-			combined.WriteString(fmt.Sprintf("## %s\n\n", url))
-			combined.WriteString(data.content)
-			combined.WriteString("\n\n")
-		}
-		return os.WriteFile(filepath.Join("output", "combined.md"), []byte(combined.String()), 0644)
-
-	case "separate":
-		if err := os.MkdirAll("output", 0755); err != nil {
-			return fmt.Errorf("failed to create output directory: %v", err)
-		}
-
-		// Group content by site and path
-		contentBySitePath := make(map[string]map[string]string)
-		for urlStr, data := range content {
-			parsedURL, err := url.Parse(urlStr)
-			if err != nil {
-				logger.Printf("Warning: Could not parse URL %s: %v", urlStr, err)
-				continue
-			}
-
-			// Find matching allowed path for this URL
-			var matchingPath string
-			for _, path := range data.site.AllowedPaths {
-				if strings.HasPrefix(parsedURL.Path, path) {
-					matchingPath = path
-					break
-				}
-			}
-			if matchingPath == "" {
-				logger.Printf("Warning: No matching allowed path for URL %s", urlStr)
-				continue
-			}
-
-			siteKey := fmt.Sprintf("%s-%s", data.site.BaseURL, data.site.FileNamePrefix)
-			if contentBySitePath[siteKey] == nil {
-				contentBySitePath[siteKey] = make(map[string]string)
-			}
-
-			// Combine all content for the same path
-			if existing, exists := contentBySitePath[siteKey][matchingPath]; exists {
-				contentBySitePath[siteKey][matchingPath] = existing + "\n\n" + data.content
-			} else {
-				contentBySitePath[siteKey][matchingPath] = data.content
-			}
-		}
-
-		// Write files for each site and path
-		for siteKey, pathContent := range contentBySitePath {
-			for path, content := range pathContent {
-				parts := strings.SplitN(siteKey, "-", 2) // Split only on first hyphen
-				prefix := parts[1]                       // Get the FileNamePrefix part
-				if prefix == "" {
-					prefix = "doc" // default prefix if none specified
-				}
-
-				normalizedPath := NormalizePathForFilename(path)
-				if normalizedPath == "" {
-					normalizedPath = "index"
-				}
-
-				filename := filepath.Join("output", fmt.Sprintf("%s-%s.md",
-					prefix, normalizedPath))
-
-				// Ensure we don't have empty files
-				if strings.TrimSpace(content) == "" {
-					logger.Printf("Skipping empty content for path %s", path)
-					continue
-				}
-
-				if err := os.WriteFile(filename, []byte(content), 0644); err != nil {
-					return fmt.Errorf("failed to write file %s: %v", filename, err)
-				}
-				logger.Printf("Wrote content to %s", filename)
-			}
-		}
-		return nil
-
-	default:
-		return fmt.Errorf("unsupported output type: %s", config.OutputType)
-	}
-}
-
-// NormalizePathForFilename converts a URL path into a valid filename component
-func NormalizePathForFilename(urlPath string) string {
-	// Remove leading/trailing slashes
-	path := strings.Trim(urlPath, "/")
-	// Replace all non-alphanumeric characters with dashes
-	reg := regexp.MustCompile("[^a-zA-Z0-9]+")
-	path = reg.ReplaceAllString(path, "-")
-	// Remove any leading or trailing dashes
-	path = strings.Trim(path, "-")
-	// Collapse multiple consecutive dashes into one
-	reg = regexp.MustCompile("-+")
-	path = reg.ReplaceAllString(path, "-")
-	return path
-}
-
 // FetchWebpageContent retrieves the content of a webpage using Playwright
 func FetchWebpageContent(urlStr string) (string, error) {
 	logger.Printf("Fetching webpage content for URL: %s\n", urlStr)
@@ -567,6 +444,7 @@ func scrollPage(page playwright.Page) error {
 
 		// Wait for a while before scrolling again
 		
+		
 	}
 
 	logger.Println("Scrolling back to top")
@@ -580,6 +458,7 @@ func scrollPage(page playwright.Page) error {
 	return nil
 }
 
+
 // ExtractContentWithCSS extracts content from HTML using a CSS selector
 func ExtractContentWithCSS(content, includeSelector string, excludeSelectors []string) (string, error) {
 	logger.Printf("Extracting content with CSS selector: %s\n", includeSelector)

internal/scraper/scraper_test.go

@@ -3,8 +3,8 @@ package scraper
 import (
 	"io"
 	"log"
-	// "net/http"
-	// "net/http/httptest"
+	"net/http"
+	"net/http/httptest"
 	"reflect"
 	"strings"
 	"testing"
@@ -143,39 +143,39 @@ 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()
+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()
+	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)
-// 	}
+	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",
-// 	}
+	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)
-// 	}
-// }
+	if !reflect.DeepEqual(links, expectedLinks) {
+		t.Errorf("ExtractLinks() = %v, want %v", links, expectedLinks)
+	}
+}