remove old commands

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

README.md

@@ -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
+- Rate limiting for web scraping to respect server resources
 
 ## Installation
 
@@ -64,24 +66,36 @@ Rollup can be configured using a YAML file. By default, it looks for `rollup.yml
 Example `rollup.yml`:
 
 ```yaml
-file_types:
+file_extensions:
   - go
   - md
-ignore:
+ignore_paths:
   - node_modules/**
   - vendor/**
   - .git/**
-code_generated:
+code_generated_paths:
   - **/generated/**
-scrape:
-  urls:
-    - url: https://example.com
-      css_locator: .content
-      exclude_selectors:
-        - .ads
-        - .navigation
-      output_alias: example
-  output_type: single
+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
@@ -111,10 +125,22 @@ scrape:
    ```
 
 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

@@ -1,186 +0,0 @@
-package cmd
-
-import (
-	"fmt"
-	"os"
-	"path/filepath"
-	"strings"
-	"time"
-
-	"github.com/spf13/cobra"
-)
-
-var (
-	path            string
-	fileTypes       string
-	codeGenPatterns string
-	ignorePatterns  string
-)
-
-var filesCmd = &cobra.Command{
-	Use:   "files",
-	Short: "Rollup files into a single Markdown file",
-	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.`,
-	RunE: func(cmd *cobra.Command, args []string) error {
-		return runRollup()
-	},
-}
-
-func init() {
-	filesCmd.Flags().StringVarP(&path, "path", "p", ".", "Path to the project directory")
-	filesCmd.Flags().StringVarP(&fileTypes, "types", "t", ".go,.md,.txt", "Comma-separated list of file extensions to include")
-	filesCmd.Flags().StringVarP(&codeGenPatterns, "codegen", "g", "", "Comma-separated list of glob patterns for code-generated files")
-	filesCmd.Flags().StringVarP(&ignorePatterns, "ignore", "i", "", "Comma-separated list of glob patterns for files to ignore")
-}
-
-func matchGlob(pattern, path string) bool {
-	parts := strings.Split(pattern, "/")
-	return matchGlobRecursive(parts, path)
-}
-
-func matchGlobRecursive(patternParts []string, path string) bool {
-	if len(patternParts) == 0 {
-		return path == ""
-	}
-
-	if patternParts[0] == "**" {
-		for i := 0; i <= len(path); i++ {
-			if matchGlobRecursive(patternParts[1:], path[i:]) {
-				return true
-			}
-		}
-		return false
-	}
-
-	i := strings.IndexByte(path, '/')
-	if i < 0 {
-		matched, _ := filepath.Match(patternParts[0], path)
-		return matched && len(patternParts) == 1
-	}
-
-	matched, _ := filepath.Match(patternParts[0], path[:i])
-	return matched && matchGlobRecursive(patternParts[1:], path[i+1:])
-}
-
-func isCodeGenerated(filePath string, patterns []string) bool {
-	for _, pattern := range patterns {
-		if strings.Contains(pattern, "**") {
-			if matchGlob(pattern, filePath) {
-				return true
-			}
-		} else {
-			matched, err := filepath.Match(pattern, filepath.Base(filePath))
-			if err == nil && matched {
-				return true
-			}
-		}
-	}
-	return false
-}
-
-func isIgnored(filePath string, patterns []string) bool {
-	for _, pattern := range patterns {
-		if strings.Contains(pattern, "**") {
-			if matchGlob(pattern, filePath) {
-				return true
-			}
-		} else {
-			matched, err := filepath.Match(pattern, filepath.Base(filePath))
-			if err == nil && matched {
-				return true
-			}
-		}
-	}
-	return false
-}
-
-func runRollup() error {
-	// Use config if available, otherwise use command-line flags
-	var types, codeGenList, ignoreList []string
-	if cfg != nil && len(cfg.FileTypes) > 0 {
-		types = cfg.FileTypes
-	} else {
-		types = strings.Split(fileTypes, ",")
-	}
-	if cfg != nil && len(cfg.CodeGenerated) > 0 {
-		codeGenList = cfg.CodeGenerated
-	} else {
-		codeGenList = strings.Split(codeGenPatterns, ",")
-	}
-	if cfg != nil && cfg.Ignore != nil && len(cfg.Ignore) > 0 {
-		ignoreList = cfg.Ignore
-	} else {
-		ignoreList = strings.Split(ignorePatterns, ",")
-	}
-
-	// Get the absolute path
-	absPath, err := filepath.Abs(path)
-	if err != nil {
-		return fmt.Errorf("error getting absolute path: %v", err)
-	}
-
-	// Get the project directory name
-	projectName := filepath.Base(absPath)
-
-	// Generate the output file name
-	timestamp := time.Now().Format("20060102-150405")
-	outputFileName := fmt.Sprintf("%s-%s.rollup.md", projectName, timestamp)
-
-	// Open the output file
-	outputFile, err := os.Create(outputFileName)
-	if err != nil {
-		return fmt.Errorf("error creating output file: %v", err)
-	}
-	defer outputFile.Close()
-
-	// Walk through the directory
-	err = filepath.Walk(absPath, func(path string, info os.FileInfo, err error) error {
-		if err != nil {
-			return err
-		}
-		if info.IsDir() {
-			if strings.HasPrefix(info.Name(), ".") {
-				return filepath.SkipDir
-			}
-			return nil
-		}
-		relPath, _ := filepath.Rel(absPath, path)
-
-		// Check if the file should be ignored
-		if isIgnored(relPath, ignoreList) {
-			return nil
-		}
-
-		ext := filepath.Ext(path)
-		for _, t := range types {
-			if ext == "."+t {
-				// Read file contents
-				content, err := os.ReadFile(path)
-				if err != nil {
-					fmt.Printf("Error reading file %s: %v", path, err)
-					return nil
-				}
-
-				// Check if the file is code-generated
-				isCodeGen := isCodeGenerated(relPath, codeGenList)
-				codeGenNote := ""
-				if isCodeGen {
-					codeGenNote = " (Code-generated, Read-only)"
-				}
-
-				// Write file name and contents to the output file
-				fmt.Fprintf(outputFile, "# File: %s%s\n\n```%s\n%s```\n\n", relPath, codeGenNote, t, string(content))
-				break
-			}
-		}
-		return nil
-	})
-	if err != nil {
-		return fmt.Errorf("error walking through directory: %v", err)
-	}
-
-	fmt.Printf("Rollup complete. Output file: %s", outputFileName)
-	return nil
-}

cmd/generate.go

@@ -1,80 +0,0 @@
-package cmd
-
-import (
-	"fmt"
-	"os"
-	"path/filepath"
-	"sort"
-	"strings"
-
-	"github.com/spf13/cobra"
-	"github.com/tnypxl/rollup/internal/config"
-	"gopkg.in/yaml.v2"
-)
-
-var generateCmd = &cobra.Command{
-	Use:   "generate",
-	Short: "Generate a rollup.yml config file",
-	Long:  `Scan the current directory for text and code files and generate a rollup.yml config file based on the found file extensions.`,
-	RunE:  runGenerate,
-}
-
-func runGenerate(cmd *cobra.Command, args []string) error {
-	fileTypes := make(map[string]bool)
-	err := filepath.Walk(".", func(path string, info os.FileInfo, err error) error {
-		if err != nil {
-			return err
-		}
-		if !info.IsDir() {
-			ext := strings.TrimPrefix(filepath.Ext(path), ".")
-			if isTextFile(ext) {
-				fileTypes[ext] = true
-			}
-		}
-		return nil
-	})
-	if err != nil {
-		return fmt.Errorf("error walking the path: %v", err)
-	}
-
-	cfg := config.Config{
-		FileTypes: make([]string, 0, len(fileTypes)),
-		Ignore:    []string{"node_modules/**", "vendor/**", ".git/**"},
-	}
-
-	for ext := range fileTypes {
-		cfg.FileTypes = append(cfg.FileTypes, ext)
-	}
-
-	// Sort file types for consistency
-	sort.Strings(cfg.FileTypes)
-
-	yamlData, err := yaml.Marshal(&cfg)
-	if err != nil {
-		return fmt.Errorf("error marshaling config: %v", err)
-	}
-
-	outputPath := config.DefaultConfigPath()
-	err = os.WriteFile(outputPath, yamlData, 0644)
-	if err != nil {
-		return fmt.Errorf("error writing config file: %v", err)
-	}
-
-	fmt.Printf("Generated %s file successfully.\n", outputPath)
-	return nil
-}
-
-func isTextFile(ext string) bool {
-	textExtensions := map[string]bool{
-		"txt": true, "md": true, "go": true, "py": true, "js": true, "html": true, "css": true,
-		"json": true, "xml": true, "yaml": true, "yml": true, "toml": true, "ini": true,
-		"sh": true, "bash": true, "zsh": true, "fish": true,
-		"c": true, "cpp": true, "h": true, "hpp": true, "java": true, "kt": true, "scala": true,
-		"rs": true, "rb": true, "php": true, "ts": true, "swift": true,
-	}
-	return textExtensions[ext]
-}
-
-func init() {
-	// Add any flags for the generate command here if needed
-}

cmd/root.go

@@ -1,36 +0,0 @@
-package cmd
-
-import (
-	"github.com/spf13/cobra"
-	config "github.com/tnypxl/rollup/internal/config"
-)
-
-var (
-	configFile string
-	cfg        *config.Config
-	verbose    bool
-)
-
-var rootCmd = &cobra.Command{
-	Use:   "rollup",
-	Short: "Rollup is a tool for combining and processing files",
-	Long: `Rollup is a versatile tool that can combine and process files in various ways.
-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
-	}
-	return rootCmd.Execute()
-}
-
-func init() {
-	rootCmd.PersistentFlags().StringVarP(&configFile, "config", "f", "", "Path to the config file (default: rollup.yml in the current directory)")
-	rootCmd.PersistentFlags().BoolVarP(&verbose, "verbose", "v", false, "Enable verbose logging")
-
-	rootCmd.AddCommand(filesCmd)
-	rootCmd.AddCommand(webCmd)
-	rootCmd.AddCommand(generateCmd)
-}

cmd/web.go

@@ -1,217 +0,0 @@
-package cmd
-
-import (
-	"fmt"
-	"net/url"
-	"os"
-	"regexp"
-	"strings"
-	"time"
-
-	"github.com/spf13/cobra"
-	"github.com/tnypxl/rollup/internal/scraper"
-)
-
-var (
-	urls             []string
-	outputType       string
-	depth            int
-	includeSelector  string
-	excludeSelectors []string
-)
-
-var scraperConfig scraper.Config
-
-var webCmd = &cobra.Command{
-	Use:   "web",
-	Short: "Scrape main content from webpages and convert to Markdown",
-	Long:  `Scrape the main content from one or more webpages, ignoring navigational elements, ads, and other UI aspects. Convert the content to a well-structured Markdown file.`,
-	RunE:  runWeb,
-}
-
-func init() {
-	webCmd.Flags().StringSliceVarP(&urls, "urls", "u", []string{}, "URLs of the webpages to scrape (comma-separated)")
-	webCmd.Flags().StringVarP(&outputType, "output", "o", "single", "Output type: 'single' for one file, 'separate' for multiple files")
-	webCmd.Flags().IntVarP(&depth, "depth", "d", 0, "Depth of link traversal (default: 0, only scrape the given URLs)")
-	webCmd.Flags().StringVar(&includeSelector, "css", "", "CSS selector to extract specific content")
-	webCmd.Flags().StringSliceVar(&excludeSelectors, "exclude", []string{}, "CSS selectors to exclude from the extracted content (comma-separated)")
-}
-
-func runWeb(cmd *cobra.Command, args []string) error {
-	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}
-		}
-	}
-
-	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")
-	}
-
-	scraperConfig := scraper.Config{
-		URLs:       urlConfigs,
-		OutputType: outputType,
-		Verbose:    verbose,
-	}
-
-	scrapedContent, err := scraper.ScrapeMultipleURLs(scraperConfig)
-	if err != nil {
-		return fmt.Errorf("error scraping content: %v", err)
-	}
-
-	if outputType == "single" {
-		return writeSingleFile(scrapedContent)
-	} else {
-		return writeMultipleFiles(scrapedContent)
-	}
-}
-
-func writeSingleFile(content map[string]string) error {
-	outputFile := generateDefaultFilename(urls)
-	file, err := os.Create(outputFile)
-	if err != nil {
-		return fmt.Errorf("error creating output file: %v", err)
-	}
-	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))
-		if err != nil {
-			return fmt.Errorf("error writing content to file: %v", err)
-		}
-	}
-
-	fmt.Printf("Content has been extracted from %d URL(s) and saved to %s\n", len(content), outputFile)
-	return nil
-}
-
-func writeMultipleFiles(content map[string]string) error {
-	for url, c := range content {
-		filename := getFilenameFromContent(c, url)
-		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()
-		if err != nil {
-			return fmt.Errorf("error writing content to file %s: %v", filename, err)
-		}
-
-		fmt.Printf("Content from %s has been saved to %s\n", url, filename)
-	}
-	return nil
-}
-
-func generateDefaultFilename(urls []string) string {
-	timestamp := time.Now().Format("20060102-150405")
-	return fmt.Sprintf("web-%s.rollup.md", timestamp)
-}
-
-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 := extractAndConvertContent(urlStr)
-	if err != nil {
-		return "", err
-	}
-
-	if depth > 0 {
-		links, err := scraper.ExtractLinks(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
-}
-
-func extractAndConvertContent(urlStr string) (string, error) {
-	content, err := scraper.FetchWebpageContent(urlStr)
-	if err != nil {
-		return "", fmt.Errorf("error fetching webpage content: %v", err)
-	}
-
-	if includeSelector != "" {
-		content, err = scraper.ExtractContentWithCSS(content, includeSelector, excludeSelectors)
-		if err != nil {
-			return "", fmt.Errorf("error extracting content with CSS: %v", err)
-		}
-	}
-
-	markdown, err := scraper.ProcessHTMLContent(content, scraper.Config{})
-	if err != nil {
-		return "", fmt.Errorf("error processing HTML content: %v", err)
-	}
-
-	parsedURL, err := url.Parse(urlStr)
-	if err != nil {
-		return "", fmt.Errorf("error parsing URL: %v", err)
-	}
-	header := fmt.Sprintf("# Content from %s\n\n", parsedURL.String())
-
-	return header + markdown + "\n\n", nil
-}
-
-func getFilenameFromContent(content, url string) string {
-	// 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"
-	}
-
-	// If no title found, use the URL
-	return sanitizeFilename(url) + ".md"
-}
-
-func sanitizeFilename(name string) string {
-	// Remove any character that isn't alphanumeric, dash, or underscore
-	reg := regexp.MustCompile("[^a-zA-Z0-9-_]+")
-	name = reg.ReplaceAllString(name, "_")
-
-	// Trim any leading or trailing underscores
-	name = strings.Trim(name, "_")
-
-	// If the name is empty after sanitization, use a default name
-	if name == "" {
-		name = "untitled"
-	}
-
-	return name
-}

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

@@ -1,52 +0,0 @@
-package config
-
-import (
-	"fmt"
-	"os"
-
-	"gopkg.in/yaml.v2"
-)
-
-type Config struct {
-	FileTypes     []string     `yaml:"file_types"`
-	Ignore        []string     `yaml:"ignore"`
-	CodeGenerated []string     `yaml:"code_generated"`
-	Scrape        ScrapeConfig `yaml:"scrape"`
-}
-
-type ScrapeConfig struct {
-	URLs       []URLConfig `yaml:"urls"`
-	OutputType string      `yaml:"output_type"`
-}
-
-type URLConfig struct {
-	URL              string   `yaml:"url"`
-	CSSLocator       string   `yaml:"css_locator"`
-	ExcludeSelectors []string `yaml:"exclude_selectors"`
-	OutputAlias      string   `yaml:"output_alias"`
-}
-
-func Load(configPath string) (*Config, error) {
-	data, err := os.ReadFile(configPath)
-	if err != nil {
-		return nil, fmt.Errorf("error reading config file: %v", err)
-	}
-
-	var config Config
-	err = yaml.Unmarshal(data, &config)
-	if err != nil {
-		return nil, fmt.Errorf("error parsing config file: %v", err)
-	}
-
-	return &config, nil
-}
-
-func DefaultConfigPath() string {
-	return "rollup.yml"
-}
-
-func FileExists(filename string) bool {
-	_, err := os.Stat(filename)
-	return err == nil
-}
-

internal/scraper/scraper.go

@@ -1,369 +0,0 @@
-package scraper
-
-import (
-	"fmt"
-	"io/ioutil"
-	"log"
-	"math/rand"
-	"regexp"
-	"strings"
-	"time"
-
-	"github.com/PuerkitoBio/goquery"
-	"github.com/playwright-community/playwright-go"
-	md "github.com/JohannesKaufmann/html-to-markdown"
-)
-
-var logger *log.Logger
-
-var (
-	pw      *playwright.Playwright
-	browser playwright.Browser
-)
-
-// Config holds the scraper configuration
-type Config struct {
-	URLs       []URLConfig
-	OutputType string
-	Verbose    bool
-}
-
-// 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
-}
-
-func scrapeURL(config URLConfig) (string, error) {
-	content, err := FetchWebpageContent(config.URL)
-	if err != nil {
-		return "", err
-	}
-
-	if config.CSSLocator != "" {
-		content, err = ExtractContentWithCSS(content, config.CSSLocator, config.ExcludeSelectors)
-		if err != nil {
-			return "", err
-		}
-	}
-
-	return ProcessHTMLContent(content, Config{})
-}
-
-func getFilenameFromContent(content, url string) string {
-	// 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"
-	}
-
-	// If no title found, use the URL
-	return sanitizeFilename(url) + ".md"
-}
-
-func sanitizeFilename(name string) string {
-	// 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
-type URLConfig struct {
-	URL              string
-	CSSLocator       string
-	ExcludeSelectors []string
-	OutputAlias      string
-}
-
-// SetupLogger initializes the logger based on the verbose flag
-func SetupLogger(verbose bool) {
-	if verbose {
-		logger = log.New(log.Writer(), "SCRAPER: ", log.LstdFlags)
-	} else {
-		logger = log.New(ioutil.Discard, "", 0)
-	}
-}
-
-// InitPlaywright initializes Playwright and launches the browser
-func InitPlaywright() error {
-	logger.Println("Initializing Playwright")
-	var err error
-
-	// Install Playwright and Chromium browser
-	err = playwright.Install(&playwright.RunOptions{Browsers: []string{"chromium"}})
-	if err != nil {
-		return fmt.Errorf("could not install Playwright and Chromium: %v", err)
-	}
-
-	pw, err = playwright.Run()
-	if err != nil {
-		return fmt.Errorf("could not start Playwright: %v", err)
-	}
-
-	userAgent := "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
-
-	browser, err = pw.Chromium.Launch(playwright.BrowserTypeLaunchOptions{
-		Args: []string{fmt.Sprintf("--user-agent=%s", userAgent)},
-	})
-	if err != nil {
-		return fmt.Errorf("could not launch browser: %v", err)
-	}
-
-	logger.Println("Playwright initialized successfully")
-	return nil
-}
-
-// ClosePlaywright closes the browser and stops Playwright
-func ClosePlaywright() {
-	if browser != nil {
-		browser.Close()
-	}
-	if pw != nil {
-		pw.Stop()
-	}
-}
-
-// 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)
-
-	page, err := browser.NewPage()
-	if err != nil {
-		logger.Printf("Error creating new page: %v\n", err)
-		return "", fmt.Errorf("could not create page: %v", err)
-	}
-	defer page.Close()
-
-	time.Sleep(time.Duration(rand.Intn(2000)+1000) * time.Millisecond)
-
-	logger.Printf("Navigating to URL: %s\n", urlStr)
-	if _, err = page.Goto(urlStr, playwright.PageGotoOptions{
-		WaitUntil: playwright.WaitUntilStateNetworkidle,
-	}); err != nil {
-		logger.Printf("Error navigating to page: %v\n", err)
-		return "", fmt.Errorf("could not go to page: %v", err)
-	}
-
-	logger.Println("Waiting for page load state")
-	err = page.WaitForLoadState(playwright.PageWaitForLoadStateOptions{
-		State: playwright.LoadStateNetworkidle,
-	})
-	if err != nil {
-		logger.Printf("Error waiting for page load: %v\n", err)
-		return "", fmt.Errorf("error waiting for page load: %v", err)
-	}
-
-	logger.Println("Scrolling page")
-	err = scrollPage(page)
-	if err != nil {
-		logger.Printf("Error scrolling page: %v\n", err)
-		return "", fmt.Errorf("error scrolling page: %v", err)
-	}
-
-	logger.Println("Waiting for body element")
-	_, err = page.WaitForSelector("body", playwright.PageWaitForSelectorOptions{
-		State: playwright.WaitForSelectorStateVisible,
-	})
-	if err != nil {
-		logger.Printf("Error waiting for body: %v\n", err)
-		return "", fmt.Errorf("error waiting for body: %v", err)
-	}
-
-	logger.Println("Getting page content")
-	content, err := page.Content()
-	if err != nil {
-		logger.Printf("Error getting page content: %v\n", err)
-		return "", fmt.Errorf("could not get page content: %v", err)
-	}
-
-	if content == "" {
-		logger.Println(" content is empty, falling back to body content")
-		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)
-		}
-	}
-
-	logger.Printf("Successfully fetched webpage content (length: %d)\n", len(content))
-	return content, nil
-}
-
-// ProcessHTMLContent converts HTML content to Markdown
-func ProcessHTMLContent(htmlContent string, config Config) (string, error) {
-	logger.Printf("Processing HTML content (length: %d)\n", len(htmlContent))
-	doc, err := goquery.NewDocumentFromReader(strings.NewReader(htmlContent))
-	if err != nil {
-		logger.Printf("Error parsing HTML: %v\n", err)
-		return "", fmt.Errorf("error parsing HTML: %v", err)
-	}
-
-	selection := doc.Find("body")
-	logger.Println("Processing entire body")
-
-	if selection.Length() == 0 {
-		return "", fmt.Errorf("no content found in the document")
-	}
-
-	content, err := selection.Html()
-	if err != nil {
-		logger.Printf("Error extracting content: %v\n", err)
-		return "", fmt.Errorf("error extracting content: %v", err)
-	}
-
-	// Create a new converter
-	converter := md.NewConverter("", true, nil)
-
-	// Convert HTML to Markdown
-	markdown, err := converter.ConvertString(content)
-	if err != nil {
-		logger.Printf("Error converting HTML to Markdown: %v\n", err)
-		return "", fmt.Errorf("error converting HTML to Markdown: %v", err)
-	}
-
-	logger.Printf("Converted HTML to Markdown (length: %d)\n", len(markdown))
-	return markdown, nil
-}
-
-func scrollPage(page playwright.Page) error {
-	logger.Println("Starting page scroll")
-	script := `
-		() => {
-			window.scrollTo(0, document.body.scrollHeight);
-			return document.body.scrollHeight;
-		}
-	`
-
-	previousHeight := 0
-	for i := 0; i < 250; i++ {
-		height, err := page.Evaluate(script)
-		if err != nil {
-			logger.Printf("Error scrolling (iteration %d): %v\n", i+1, err)
-			return fmt.Errorf("error scrolling: %v", err)
-		}
-
-		var currentHeight int
-		switch v := height.(type) {
-		case int:
-			currentHeight = v
-		case float64:
-			currentHeight = int(v)
-		default:
-			logger.Printf("Unexpected height type: %T\n", height)
-			return fmt.Errorf("unexpected height type: %T", height)
-		}
-
-		logger.Printf("Scroll iteration %d: height = %d\n", i+1, currentHeight)
-
-		if currentHeight == previousHeight {
-			logger.Println("Reached bottom of the page")
-			break
-		}
-
-		previousHeight = currentHeight
-
-		page.WaitForTimeout(500)
-	}
-
-	logger.Println("Scrolling back to top")
-	_, err := page.Evaluate(`() => { window.scrollTo(0, 0); }`)
-	if err != nil {
-		logger.Printf("Error scrolling back to top: %v\n", err)
-		return fmt.Errorf("error scrolling back to top: %v", err)
-	}
-
-	logger.Println("Page scroll completed")
-	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) {
-	logger.Printf("Extracting content with CSS selector: %s\n", includeSelector)
-
-	doc, err := goquery.NewDocumentFromReader(strings.NewReader(content))
-	if err != nil {
-		return "", fmt.Errorf("error parsing HTML: %v", err)
-	}
-
-	selection := doc.Find(includeSelector)
-	if selection.Length() == 0 {
-		logger.Printf("Warning: No content found with CSS selector: %s. Falling back to body content.\n", includeSelector)
-		selection = doc.Find("body")
-		if selection.Length() == 0 {
-			return "", fmt.Errorf("no content found in body")
-		}
-	}
-
-	for _, excludeSelector := range excludeSelectors {
-		selection.Find(excludeSelector).Remove()
-	}
-
-	selectedContent, err := selection.Html()
-	if err != nil {
-		return "", fmt.Errorf("error extracting content with CSS selector: %v", err)
-	}
-
-	logger.Printf("Extracted content length: %d\n", len(selectedContent))
-	return selectedContent, nil
-}

main.go

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