fix: Resolve playwright function deprecations and io/ioutil function deprecations.

README.md

@@ -4,16 +4,18 @@ Rollup aggregates the contents of text-based files and webpages into a markdown
 
 ## Features
 
-- File type filtering
+- File type filtering for targeted content aggregation
-- Ignore patterns for excluding files
+- Ignore patterns for excluding specific files or directories
-- Support for code-generated file detection
+- Support for code-generated file detection and exclusion
-- Advanced web scraping functionality
+- Advanced web scraping functionality with depth control
-- Verbose logging option for detailed output
+- Verbose logging option for detailed operation insights
-- Exclusionary CSS selectors for web scraping
+- Exclusionary CSS selectors for precise web content extraction
-- Support for multiple URLs in web scraping
+- Support for multiple URLs in web scraping operations
 - Configurable output format for web scraping (single file or separate files)
-- Configuration file support (YAML)
+- Flexible configuration file support (YAML)
-- Generation of default configuration file
+- 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:
+  sites:
-    - url: https://example.com
+    - 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/web.go

@@ -2,7 +2,7 @@ package cmd
 
 import (
 	"fmt"
-	"io/ioutil"
+	"io"
 	"log"
 	"net/url"
 	"os"
@@ -44,7 +44,7 @@ func runWeb(cmd *cobra.Command, args []string) error {
 	scraper.SetupLogger(verbose)
 	logger := log.New(os.Stdout, "WEB: ", log.LstdFlags)
 	if !verbose {
-        logger.SetOutput(ioutil.Discard)
+		logger.SetOutput(io.Discard)
 	}
 	logger.Printf("Starting web scraping process with verbose mode: %v", verbose)
 	scraperConfig.Verbose = verbose
@@ -139,7 +139,7 @@ func writeSingleFile(content map[string]string) error {
 	defer file.Close()
 
 	for url, c := range content {
-		_, err = fmt.Fprintf(file, "# Content from %s\n\n%s\n\n---\n\n", url, c)
+		_, err = fmt.Fprintf(file, "# ::: Content from %s\n\n%s\n\n---\n\n", url, c)
 		if err != nil {
 			return fmt.Errorf("error writing content to file: %v", err)
 		}
@@ -161,7 +161,7 @@ func writeMultipleFiles(content map[string]string) error {
 			return fmt.Errorf("error creating output file %s: %v", filename, err)
 		}
 
-		_, err = file.WriteString(fmt.Sprintf("# Content from %s\n\n%s\n", url, c))
+		_, err = file.WriteString(fmt.Sprintf("# ::: Content from %s\n\n%s\n", url, c))
 		if err != nil {
 			file.Close()
 			return fmt.Errorf("error writing content to file %s: %v", filename, err)
@@ -215,8 +215,10 @@ func scrapeURL(urlStr string, depth int, visited map[string]bool) (string, error
 	return content, nil
 }
 
-var testExtractAndConvertContent = extractAndConvertContent
+var (
-var testExtractLinks = scraper.ExtractLinks
+	testExtractAndConvertContent = extractAndConvertContent
+	testExtractLinks             = scraper.ExtractLinks
+)
 
 func extractAndConvertContent(urlStr string) (string, error) {
 	content, err := scraper.FetchWebpageContent(urlStr)
@@ -240,7 +242,7 @@ func extractAndConvertContent(urlStr string) (string, error) {
 	if err != nil {
 		return "", fmt.Errorf("error parsing URL: %v", err)
 	}
-	header := fmt.Sprintf("# Content from %s\n\n", parsedURL.String())
+	header := fmt.Sprintf("# ::: Content from %s\n\n", parsedURL.String())
 
 	return header + markdown + "\n\n", nil
 }

cmd/web_test.go

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

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

internal/config/config_test.go

@@ -45,10 +45,10 @@ scrape:
 	}
 	defer os.Remove(tmpfile.Name())
 
-	if _, err := tmpfile.Write(content); err != nil {
+	if _, err = tmpfile.Write(content); err != nil {
 		t.Fatalf("Failed to write to temp file: %v", err)
 	}
-	if err := tmpfile.Close(); err != nil {
+	if err = tmpfile.Close(); err != nil {
 		t.Fatalf("Failed to close temp file: %v", err)
 	}
 

internal/scraper/scraper.go

@@ -1,21 +1,21 @@
 package scraper
 
 import (
+	"context"
 	"fmt"
-	"io/ioutil"
+	"io"
 	"log"
 	"math/rand"
 	"net/url"
 	"os"
 	"regexp"
 	"strings"
-	"time"
 	"sync"
-	"context"
+	"time"
 
+	md "github.com/JohannesKaufmann/html-to-markdown"
 	"github.com/PuerkitoBio/goquery"
 	"github.com/playwright-community/playwright-go"
-	md "github.com/JohannesKaufmann/html-to-markdown"
 	"golang.org/x/time/rate"
 )
 
@@ -81,7 +81,7 @@ func ScrapeSites(config Config) (map[string]string, error) {
 				fullURL := site.BaseURL + path
 				totalURLs++
 				logger.Printf("Queueing URL for scraping: %s\n", fullURL)
-                scrapeSingleURL(fullURL, site, config, results, limiter)
+				scrapeSingleURL(fullURL, site, results, limiter)
 			}
 		}(site)
 	}
@@ -108,11 +108,12 @@ func ScrapeSites(config Config) (map[string]string, error) {
 	return scrapedContent, nil
 }
 
-func scrapeSingleURL(url string, site SiteConfig, config Config, results chan<- struct {
+func scrapeSingleURL(url string, site SiteConfig, results chan<- struct {
 	url     string
 	content string
 	err     error
-}, limiter *rate.Limiter) {
+}, limiter *rate.Limiter,
+) {
 	logger.Printf("Starting to scrape URL: %s\n", url)
 
 	// Wait for rate limiter before making the request
@@ -155,11 +156,12 @@ func scrapeSingleURL(url string, site SiteConfig, config Config, results chan<-
 	}{url, content, nil}
 }
 
-func scrapeSite(site SiteConfig, config Config, results chan<- struct {
+func scrapeSite(site SiteConfig, results chan<- struct {
 	url     string
 	content string
 	err     error
-}, limiter *rate.Limiter) {
+}, limiter *rate.Limiter,
+) {
 	visited := make(map[string]bool)
 	queue := []string{site.BaseURL}
 
@@ -296,7 +298,7 @@ func SetupLogger(verbose bool) {
 	if verbose {
 		logger = log.New(os.Stdout, "SCRAPER: ", log.LstdFlags)
 	} else {
-		logger = log.New(ioutil.Discard, "", 0)
+		logger = log.New(io.Discard, "", 0)
 	}
 }
 
@@ -387,7 +389,9 @@ func FetchWebpageContent(urlStr string) (string, error) {
 	}
 
 	logger.Println("Waiting for body element")
-	_, err = page.WaitForSelector("body", playwright.PageWaitForSelectorOptions{
+	
+	bodyElement := page.Locator("body")
+	err = bodyElement.WaitFor(playwright.LocatorWaitForOptions{
 		State: playwright.WaitForSelectorStateVisible,
 	})
 	if err != nil {
@@ -404,7 +408,7 @@ func FetchWebpageContent(urlStr string) (string, error) {
 
 	if content == "" {
 		logger.Println(" content is empty, falling back to body content")
-		content, err = page.InnerHTML("body")
+		content, err = bodyElement.InnerHTML()
 		if err != nil {
 			logger.Printf("Error getting body content: %v\n", err)
 			return "", fmt.Errorf("could not get body content: %v", err)
@@ -457,6 +461,8 @@ func scrollPage(page playwright.Page) error {
 		() => {
 			window.scrollTo(0, document.body.scrollHeight);
 			return document.body.scrollHeight;
+			// wait for 500 ms
+			new Promise(resolve => setTimeout(resolve, 500));
 		}
 	`
 
@@ -488,7 +494,9 @@ func scrollPage(page playwright.Page) error {
 
 		previousHeight = currentHeight
 
-		page.WaitForTimeout(500)
+		// Wait for a while before scrolling again
+		
+		
 	}
 
 	logger.Println("Scrolling back to top")

internal/scraper/scraper_test.go

@@ -1,13 +1,13 @@
 package scraper
 
 import (
-	"testing"
+	"io"
+	"log"
 	"net/http"
 	"net/http/httptest"
-	"strings"
 	"reflect"
-	"log"
+	"strings"
-	"io/ioutil"
+	"testing"
 )
 
 func TestIsAllowedURL(t *testing.T) {
@@ -73,7 +73,7 @@ func TestGetOverrides(t *testing.T) {
 
 func TestExtractContentWithCSS(t *testing.T) {
 	// Initialize logger for testing
-	logger = log.New(ioutil.Discard, "", 0)
+	logger = log.New(io.Discard, "", 0)
 
 	html := `
 		<html>