Web crawler from the tour of go.

main.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)
}

func PFetch(url string, ch chan []string) {
	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		ch <- nil
		return
	}
	fmt.Printf("found: %s %q\n", url, body)
	ch <- urls
}


func Crawl(url string, depth int, fetcher Fetcher) {
  // crawl that waits for the go routines to finish...
  // suppose I break when depth == 0; the other go routines might not have
  // finished before this function returns. In this case it's PFetch that
  // prints the data, but if Crawl needed what PFetch send it might loose

	if depth <= 0 {
	        return
    	}

	var urls []string
	var visited map[string]bool
	var waiting_on int
	
	ch := make(chan []string)
	visited = make(map[string]bool)
	
	go PFetch(url, ch)
	waiting_on += 1
	visited[url] = true
	depth -= 1
	
	for {
		if depth <= 0 && waiting_on > 0 {
			urls = <- ch
			waiting_on -= 1
			continue
		} else if waiting_on <= 0 {
			break
		}
        	urls = nil
        	for waiting_on > 0; waiting_on -- {
            		u := <- ch
	    		if u == nil {
		    		continue
		    	}
    			append(urls, u...)
        	}
		all := true
		for _, u := range urls {
			all = all && visited[u]
			if !visited[u] {
				go PFetch(u, depth, ch)
				waiting_on += 1
				visited[u] = true
			}
		}
		
		if all {
			break
		}
		depth -= 1 
	}
}

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/",
		},
	},
}