递归 Goroutines，告诉 Go 停止从通道读取的最简洁的方法是什么

您可以扩展解析url上发送的结果，并包括找到的新url的数量，而不是涉及sync.WaitGroup个.在主循环中，只要有东西要收集，你就会继续阅读结果.

在您的示例中，找到的URL数量将是生成的GO routine 的数量，但它不一定是.我个人或多或少会产生固定数量的获取 routine ，这样您就不会打开太多HTTP请求(或者至少您可以控制它).那么您的主循环不会改变，因为它并不关心如何执行抓取.这里重要的事实是，您需要 for each url发送一个结果或错误-我已经修改了这里的代码，所以当深度已经是1时，它不会产生新的 routine .

此解决方案的一个副作用是，您可以轻松地在主循环中打印进度.

以下是操场上的示例:

http://play.golang.org/p/BRlUc6bojf个

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)
}

type Res struct {
    url string
    body string
    found int // Number of new urls found
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher, ch chan Res, errs chan error, visited map[string]bool) {
    body, urls, err := fetcher.Fetch(url)
    visited[url] = true
    if err != nil {
        errs <- err
        return
    }

    newUrls := 0    
    if depth > 1 {
        for _, u := range urls {
            if !visited[u] {
                newUrls++
                go Crawl(u, depth-1, fetcher, ch, errs, visited)
            }
        }
    }

    // Send the result along with number of urls to be fetched
    ch <- Res{url, body, newUrls}

    return
}

func main() {
    ch := make(chan Res)
    errs := make(chan error)
    visited := map[string]bool{}
    go Crawl("http://golang.org/", 4, fetcher, ch, errs, visited)
    tocollect := 1
    for n := 0; n < tocollect; n++ {
        select {
        case s := <-ch:
            fmt.Printf("found: %s %q\n", s.url, s.body)
            tocollect += s.found
        case e := <-errs:
            fmt.Println(e)
        }
    }

}

// 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/",
        },
    },
}

是的，遵循@jimt建议，并确保访问 map 线程安全.