Crawl from go tour

crawl.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)
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher, res *safeResults, q chan int) {
	//fmt.Println("start Crawl depth", depth)
	if depth <= 0 {
		q <- 1
		return
	}
	res.mux.Lock()
	_, ok := res.v[url]
	if ok != true {
		//	fmt.Println("Add", url)
		res.v[url] = true
	}
	res.mux.Unlock()
	if ok == true {
		//	fmt.Println("Skip", url)
		q <- 1
		return
	}
	body, urls, err := fetcher.Fetch(url)

	if err != nil {
		//	fmt.Println(err)
		q <- 1
		return
	}
	fmt.Printf("found: %s %q\n", url, body)
	nq := make(chan int)
	for _, u := range urls {
		//	fmt.Println("Next url", u, depth-1)
		go Crawl(u, depth-1, fetcher, res, nq)
	}
	for _, v := range urls {
		fmt.Println("done", v, <-nq)
	}
	q <- 1
	return
}

func main() {
	q := make(chan int, 100)
	res := safeResults{v: make(map[string]bool)}
	go Crawl("http://golang.org/", 4, fetcher, &res, q)
	fmt.Println("Global done", <-q)
}

// fakeFetcher is Fetcher that returns canned results.
type fakeFetcher map[string]*fakeResult

type fakeResult struct {
	body string
	urls []string
}

type safeResults struct {
	v   map[string]bool
	mux sync.Mutex
}

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/",
		},
	},
}