fake_web_crawler.go

package main

import (
	"fmt"
	"sync"
	"time"
)

type Fetcher interface {
	Fetch(url string) (body string, urls []string, err error)
}

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)
}

func addToMap(url string) {
	mux.Lock()
	crawlMap[url] = url
	mux.Unlock()
}

func Crawl(url string, depth int, fetcher Fetcher) {
	if depth <= 0 {
		return
	}

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

	addToMap(url)

	fmt.Printf("found: %s %q\n", url, body)
	for _, u := range urls {
		if _, ok := crawlMap[u]; !ok {
			addToMap(u)
			go Crawl(u, depth-1, fetcher)
		}
	}

	return
}

func main() {
	go Crawl("http://golang.org/", 4, fetcher)
	time.Sleep(time.Second * 5)
	fmt.Println("Crawling finished")
}

var mux = sync.Mutex{}
var crawlMap = make(map[string]string)
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/",
		},
	},
}