http://go-tour-jp.appspot.com/#71

go-tour-71.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)
}

var history = make(map[string]bool)

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
	// TODO: Fetch URLs in parallel.
	// TODO: Don't fetch the same URL twice.
	// This implementation doesn't do either:
	ch := make(chan crwalResult)
	quit := make(chan int)
	history[url] = true
    // fetch中の数を管理して、無い場合にCrwal全体を完了とする
    // rangeにすると、残りのURLが無いことはわかるが、
    // いつチャンネルを閉じてよい分からない(開きっぱなしになる)
    // そもそも、チャンネルはロックし続けないなら閉じなくて良い
	fetch := 1
	go crawlInner(url, depth, fetcher, ch, quit)
	for {
		select {

		case res := <-ch:
			for _, u := range res.urls {
				if history[u] != true {
					history[u] = true
					fetch++
					go crawlInner(u, res.depth, fetcher, ch, quit)
				}
			}
		case <-quit:
			if fetch--; fetch == 0 {
				return
			}
		}
	}

	return
}

func crawlInner(
	url string, depth int, fetcher Fetcher,
	ch chan crwalResult, quit chan int) {

	if depth <= 0 {
		quit <- 0
		return
	}

	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		quit <- 0
		return
	}

	fmt.Printf("found: %s %q\n", url, body)

	ch <- crwalResult{
		depth - 1,
		urls,
	}
	quit <- 0
}

type crwalResult struct {
	depth int
	urls  []string
}

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/",
		},
	},
}