问题

改良原有的网络爬虫是任务的挑战。

• 平行処理でクロールする

クロール済みのページはクロールしない

回答: 只需要一种选择的话，用汉语自然地改写以下内容：

这样可以吗……感觉还可以写得更好一些。
重点是

• fetch済かどうかをChennel(holder)で管理している

子goroutineが終わるまで親のプロセスが待つためのChannel(done)を用意する

package main

import (
    "fmt"
    "time"
)

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) {
    fmt.Printf("start. depth=%d, url=%s\n", depth, url)
    if depth <= 0 {
        return
    }

    history := <-holder
    if _, ok := history[url]; ok {
        fmt.Printf("already fetched: %s \n", url)
        holder <- history
        return
    }
    history[url] = url
    holder <- history

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

    fmt.Printf("found: %s %q\n", url, body)
    done := make(chan bool)
    for _, u := range urls {
        go func(url string) {
            Crawl(url, depth-1, fetcher)
            done <- true
        }(u)
    }

    for _, _ = range urls {
        <-done
    }

    fmt.Printf("end. depth=%d, url=%s\n", depth, url)
    return
}

var holder chan fetchHistory

func init() {
    holder = make(chan fetchHistory, 1)
    holder <- fetchHistory(make(map[string]string))
}

func main() {
    Crawl("http://golang.org/", 4, fetcher)
    fmt.Println("finish!!")
}

var historyHolder chan fetchHistory

type fetchHistory map[string]string

// 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
    }
    // timeout
    time.Sleep(1000 * time.Millisecond)
    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/",
        },
    },
}