A Tour of Go: Concurrency #9 - Web Crawler

exercise-web-crawler.go

package main

import (
	"fmt"
)

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 URLInfo struct {
	URL   string
	Depth int
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
// Fetch URLs in parallel.
// Don't fetch the same URL twice.
func Crawl(url string, depth int, fetcher Fetcher) {
	done := make(map[string]bool) // urls previously crawled
	urlsch := make(chan URLInfo)  // urls found
	donech := make(chan bool)     // control channel
	loop := true
	live := 1

	// goroutine for fetch an url
	fetch := func(url string, depth int, fetcher Fetcher, uch chan URLInfo, dch chan bool) {
		if depth <= 0 {
			return
		}
		body, urls, err := fetcher.Fetch(url)
		if err != nil {
			fmt.Println(err)
			dch <- true
			return
		}
		fmt.Printf("found: %s %q\n", url, body)
		for _, v := range urls {
			uch <- URLInfo{v, depth}
		}
		dch <- true
		return
	}

	// fetches the first url
	done[url] = true
	go fetch(url, depth, fetcher, urlsch, donech)

	// fetches found urls
	for loop {
		select {
		case <-donech:
			live--
		case u := <-urlsch:
			if _, ok := done[u.URL]; !ok {
				done[u.URL] = true
				live++
				go fetch(u.URL, u.Depth-1, fetcher, urlsch, donech)
			}
		default:
			if live == 0 {
				loop = false
				fmt.Println("Bye!")
			}
		}
	}

	return
}

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/",
		},
	},
}