An implementation of Go tour exercise, https://tour.golang.org/concurrency/9

parallel_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)
}

// 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 bool) {
	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		//fmt.Printf("thread %v exited\n", url)
		// notify parent thread
		ch <- true
		return
	}
	fmt.Printf("found: %s %q\n", url, body)
	
	childCh := make(chan bool)
	threads := 0
	for _, u := range urls {
		if _, visited := track[u]; !visited {
			childDepth := depth - 1
			if childDepth > 0 {
				threads++
				track[u] = true
				go Crawl(u, childDepth, fetcher, childCh)
			}
		}
	}
	for threads > 0{
		//fmt.Println(urls, threads)
		if <- childCh {
			//fmt.Println(url, threads, depth)
			threads--
			//fmt.Println(url, threads, depth)
		}
		//fmt.Println(urls, threads)
	}
	//fmt.Printf("thread %v exited\n", url)
	// notify parent thread
	ch <- true
}

var track = make(map[string]bool)

func main() {
	ch := make(chan bool)
	rootUrl := "http://golang.org/"
	track[rootUrl] = true
	go Crawl(rootUrl, 4, fetcher, ch)
	<- ch
}

// 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/",
		},
	},
}