My solution to A Tour of Go's web crawler exercise.

golang-tour-web-crawler.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 visitedUrls map[string]bool

func (v visitedUrls) contains(url string) bool   { return v[url] }
func (v visitedUrls) add(url string) visitedUrls { v[url] = true; return v }

// 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 visitedUrls)
	defer close(ch)

	var wg sync.WaitGroup

	wg.Add(1)
	go crawl(url, depth, fetcher, ch, &wg)
	ch <- make(visitedUrls)

	wg.Wait()
}

func crawl(url string, depth int, fetcher Fetcher, ch chan visitedUrls, wg *sync.WaitGroup) {
	visited := <-ch
	defer func() { ch <- visited.add(url) }()
	defer wg.Done()

	if visited.contains(url) || depth <= 0 {
		return
	}

	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		return
	}
	fmt.Printf("found: %s %q\n", url, body)
	for _, u := range urls {
		wg.Add(1)
		go crawl(u, depth-1, fetcher, ch, wg)
	}
	return
}

func main() {
	Crawl("http://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{
	"http://golang.org/": &fakeResult{
		"The Go Programming Language",
		[]string{
			"http://golang.org/pkg/",
			"http://golang.org/cmd/",
		},
	},
	"http://golang.org/pkg/": &fakeResult{
		"Packages",
		[]string{
			"http://golang.org/",
			"http://golang.org/cmd/",
			"http://golang.org/pkg/fmt/",
			"http://golang.org/pkg/os/",
		},
	},
	"http://golang.org/pkg/fmt/": &fakeResult{
		"Package fmt",
		[]string{
			"http://golang.org/",
			"http://golang.org/pkg/",
		},
	},
	"http://golang.org/pkg/os/": &fakeResult{
		"Package os",
		[]string{
			"http://golang.org/",
			"http://golang.org/pkg/",
		},
	},
}