A Tour of Go - Exercise: Web Crawler

main.go

package main

import (
	"fmt"
	"sync"
)

type Fetcher interface {
	// Fetch returns the body of URL and
	// a slice of URLs found on that page.
	Fetch(url string) (body string, urls []string, err error)
}

type crawlResponse struct {
	url string
	depth int
	
	body string
	urls []string
	err error
}

type crawlState struct {
	mu sync.Mutex
	found map[string]any
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
	ch := make(chan crawlResponse, 10)
	state := crawlState{
		found: map[string]any{url:true},
	}
	
	var wg sync.WaitGroup
	wg.Add(1)
	go ReadUrl(url, depth, fetcher, ch)
	
	go func() {
		for r := range ch {
			if r.err != nil {
				fmt.Println(r.err)
			}
			fmt.Printf("found: %s %q\n", r.url, r.body)

			if r.depth > 0 {
				for _, u := range r.urls {
					_, ok := state.found[u]
					if ok {
						continue
					}
					state.mu.Lock()
					state.found[u] = true
					state.mu.Unlock()

					wg.Add(1)
					go ReadUrl(u, r.depth - 1, fetcher, ch)
				}
			}
			wg.Done()
		}
	}()
	
	wg.Wait()
	close(ch)
}

func ReadUrl(url string, depth int, fetcher Fetcher, ch chan crawlResponse) {
	body, urls, err := fetcher.Fetch(url)
	ch <- crawlResponse{url, depth, body, urls, err}
}

func main() {
	Crawl("https://golang.org/", 4, fetcher)
}

// fakeFetcher is Fetcher that returns canned results.
type fakeFetcher map[string]*fakeResult

type fakeResult struct {
	body string
	urls []string
}

func (f fakeFetcher) Fetch(url string) (string, []string, error) {
	if res, ok := f[url]; ok {
		return res.body, res.urls, nil
	}
	return "", nil, fmt.Errorf("not found: %s", url)
}

// fetcher is a populated fakeFetcher.
var fetcher = fakeFetcher{
	"https://golang.org/": &fakeResult{
		"The Go Programming Language",
		[]string{
			"https://golang.org/pkg/",
			"https://golang.org/cmd/",
		},
	},
	"https://golang.org/pkg/": &fakeResult{
		"Packages",
		[]string{
			"https://golang.org/",
			"https://golang.org/cmd/",
			"https://golang.org/pkg/fmt/",
			"https://golang.org/pkg/os/",
		},
	},
	"https://golang.org/pkg/fmt/": &fakeResult{
		"Package fmt",
		[]string{
			"https://golang.org/",
			"https://golang.org/pkg/",
		},
	},
	"https://golang.org/pkg/os/": &fakeResult{
		"Package os",
		[]string{
			"https://golang.org/",
			"https://golang.org/pkg/",
		},
	},
}

The exercise can be found here

My goals were to not change the original function signatures or the main() function and to not use recursion.