tour_crawler.go

package main

import (
	"fmt"
	"sync"
)

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 Result struct {
	url string
	depth int
}
func crawlUrl (url string, found_url chan(Result), depth int, wg *sync.WaitGroup) {
	defer wg.Done()
	fmt.Println("Start to crawl ", url, " with depth ",depth)
	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)
	for _, u := range urls {
		found_url <- Result{u, depth-1}
	}

}

func Crawl(url string, depth int, fetcher Fetcher) {
    wg := &sync.WaitGroup{}
	foundUrls := make(map[string]bool)
	newUrlFound := make(chan(Result))
	go func() {
		for r := range newUrlFound {
			fmt.Println("Looping over", r.url)
			if _, ok := foundUrls[r.url]; ok {
				fmt.Println(r.url, " already found")
			} else {
				foundUrls[r.url] = true
			    wg.Add(1)
				go crawlUrl(r.url, newUrlFound, r.depth, wg)
			}
		}
	}()
	newUrlFound <- Result{url, depth}
    wg.Wait()
}


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/",
		},
	},
}