Exercise: Web Crawler

exercise-web-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)
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {

	ch := make(chan bool)
	type SafeAssignments struct {
		v   map[string] int
		mux sync.Mutex
	}
	sa := &SafeAssignments{v: make(map[string]int)}

	assign := func(url string) bool {
		sa.mux.Lock()
		defer sa.mux.Unlock()
		_, ok := sa.v[url]
		if ok {
			return false
		}
		sa.v[url] = 1
		return true
	}

	notifyIfCompleted := func() {
		sa.mux.Lock()
		defer sa.mux.Unlock()
		for _, v := range sa.v {
			if v != 2 {
				return
			}
		}
		ch <- true
	}
	
	complete := func(url string) {
		sa.v[url] = 2
		notifyIfCompleted()
	}

	var impl func(url string, d int)
	impl = func(url string, d int) {
		if depth <= 0 {
			return
		}
		body, urls, err := fetcher.Fetch(url)
		defer complete(url)
		if err != nil {
			fmt.Println(err)
			return
		}
		fmt.Printf("found: %s %q\n", url, body)
		for _, u := range urls {
			if assign(u) {
				go impl(u, depth-1)
			}
		}
	}

	go impl(url, depth)
	fmt.Printf("Success? %v\n", <- ch)		
}

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/",
		},
	},
}

This result

found: http://golang.org/ "The Go Programming Language"
not found: http://golang.org/cmd/
found: http://golang.org/pkg/ "Packages"
found: http://golang.org/pkg/os/ "Package os"
found: http://golang.org/pkg/fmt/ "Package fmt"
Success? true