linkchecker/linkchecker.go

package main

import (
	"fmt"
	"net/http"
	"net/url"
	"strings"

	"golang.org/x/net/html"
)

type LinkChecker struct {
	client *http.Client
}

func NewLinkChecker() *LinkChecker {
	return &LinkChecker{
		client: &http.Client{},
	}
}

func (lc *LinkChecker) CheckLinks(baseURL string) ([]string, error) {
	// Get all links from the page
	links, err := lc.getLinks(baseURL)
	if err != nil {
		return nil, fmt.Errorf("error getting links: %w", err)
	}

	var brokenLinks []string

	// Check each link
	for _, link := range links {
		if !lc.isLinkValid(link) {
			brokenLinks = append(brokenLinks, link)
		}
	}

	return brokenLinks, nil
}

func (lc *LinkChecker) getLinks(pageURL string) ([]string, error) {
	resp, err := lc.client.Get(pageURL)
	if err != nil {
		return nil, err
	}
	defer resp.Body.Close()

	if resp.StatusCode != http.StatusOK {
		return nil, fmt.Errorf("failed to fetch page: %s", resp.Status)
	}

	doc, err := html.Parse(resp.Body)
	if err != nil {
		return nil, err
	}

	var links []string
	baseURL, err := url.Parse(pageURL)
	if err != nil {
		return nil, err
	}

	var traverse func(*html.Node)
	traverse = func(n *html.Node) {
		if n.Type == html.ElementNode && n.Data == "a" {
			for _, attr := range n.Attr {
				if attr.Key == "href" {
					link := attr.Val
					if !strings.HasPrefix(link, "http") {
						// Convert relative URLs to absolute
						if absURL, err := baseURL.Parse(link); err == nil {
							link = absURL.String()
						}
					}
					if strings.HasPrefix(link, "http") {
						links = append(links, link)
					}
				}
			}
		}
		for c := n.FirstChild; c != nil; c = c.NextSibling {
			traverse(c)
		}
	}
	traverse(doc)

	return links, nil
}

func (lc *LinkChecker) isLinkValid(link string) bool {
	resp, err := lc.client.Get(link)
	if err != nil {
		return false
	}
	defer resp.Body.Close()

	return resp.StatusCode >= 200 && resp.StatusCode < 400
}