Exercise: Web Crawler In this exercise you'll use Go's concurrency features to parallelize a web crawler. Modify the Crawl function to fetch URLs in parallel without fetching the same URL twice. http://tour.golang.org/#71

tour71.golang.go

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, vis map[string]bool, urlsc chan string) {
	// TODO: Fetch URLs in parallel.
	// TODO: Don't fetch the same URL twice.
	// This implementation doesn't do either:
	if depth <= 0 {
		return
	}
	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		return
	}

	fmt.Printf("found: %s %q\n", url, body)
	go func() {
		for _, u := range urls {

			if !vis[u] {
				vis[u] = true
				urlsc <- u
			}
		}

	}()

	for {
        select {
		case v := <-urlsc:
            go Crawl(v, depth-1, fetcher, vis, urlsc)
		
        case <-time.After(1 * time.Millisecond):
            return
		}
    }
	return
}

func main() {
    root := "http://golang.org/"

	vis := make(map[string]bool)
	urls := make(chan string)

	vis[root] = true
	Crawl(root, 4, fetcher, vis, urls)
}

// 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/",
		},
	},

}