A Tour of Go Exercise: Web Crawler

exercise-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)
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
    fetched := make(map[string]bool)
    crawl(url, depth, fetcher, fetched)
    return
}

func crawl(url string, depth int, fetcher Fetcher, fetched map[string]bool) {
    if depth <= 0 {
        return
    }
    if v, ok := fetched[url]; ok && v {
        return
    }

    body, urls, err := fetcher.Fetch(url)
    if err != nil {
        fmt.Println(err)
        return
    }
    fmt.Printf("found: %s %q\n", url, body)
    fetched[url] = true

    var wg sync.WaitGroup
    for _, u := range urls {
        wg.Add(1)
        go func(u string) {
            defer wg.Done()
            crawl(u, depth-1, fetcher, fetched)
        }(u)
    }
    wg.Wait()
    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/",
		},
	},
}

Hi,
I have a question about the code:
What guaranties you that the map fetched won't be accessed conccurently and be corrupted ?

Plus I think your variable var wg sync.WaitGroup will be redeclared everytime crawl is called, even though it won't cause any problem but I think your intent was maybe to use the same wg variable, as it's name suggest it is for waiting for a group of related routines to end their work not for creating a waitGroup for each routine.