My solution to Go Tour #69 - Web Crawler

gotour-69.go

package main

import (
	"os"
	"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 os.Error)
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
	type moreUrls struct{
		depth int
		urls  []string
	}
	more := make(chan moreUrls)
	
	getPage := func(url string, depth int) {
		body, urls, err := fetcher.Fetch(url)
		if err != nil {
			fmt.Println(err)
		} else {
			fmt.Printf("found[%d:%s] %q\n", depth, url, body)
		}
		more <- moreUrls{depth+1, urls}
	}
	
	outstanding := 1
	go getPage(url, 0)
	
	visited := map[string]bool{url:true}
	for outstanding > 0 {
		next := <-more
		outstanding--
		if next.depth > depth {
			continue
		}
		for _, url := range next.urls {
			if _, seen := visited[url]; seen {
				continue
			}
			visited[url] = true
			outstanding++
			go getPage(url, next.depth)
		}
	}
}

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, os.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/",
		},
	},
}

xoutput.txt

found[0:http://golang.org/] "The Go Programming Language"
found[1:http://golang.org/pkg/] "Packages"
not found: http://golang.org/cmd/
found[2:http://golang.org/pkg/fmt/] "Package fmt"
found[2:http://golang.org/pkg/os/] "Package os"

Really clear, nice code. http://tour.golang.org/#70

Hi, I think there's a race condition in your code.

If you have something like this:

url1 has two links: url2 and url3

Url3 is like url3 -> urla -> urlb

and Url2 is like Url2 -> url4 -> url5 -> url7 -> url3

urla and urlb may not be fetched at all, because url3 may be fetched with a higher depth that it should.