https://tour.golang.org/concurrency/9

exercise-web-crawler.go

package main

import (
	"fmt"
)

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)
}

func crawl(url string, fetcher Fetcher, ch chan []string) {
	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		ch<-[]string{}
		return
	}
	fmt.Printf("found: %s %q\n", url, body)
	ch<-urls
}

func Crawl(url string, depth int, fetcher Fetcher) {
	ch := make(chan []string)
	sites := map[string]struct{}{}
	urls := []string{url}
	
	sites[url] = struct{}{}
	for i := 0; i < depth && len(urls) != 0; i++ {
		for _, u := range urls {
			go crawl(u, fetcher, ch)
		}
		
		newURLs := []string{}
		for count := 0; count < len(urls); count++ {
			v, ok := <-ch
			if !ok {
				return
			}
			for _, site := range v {
				if _, ok := sites[site]; !ok {
					sites[site] = struct{}{}
					newURLs = append(newURLs, site)
				}
			}
		}
		urls = newURLs
	}
}

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/",
		},
	},
}