My Solution to Go Tour #70 - Web Crawler

crawler.go

// GistID: 4601612
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 Response struct {
	*Request
	body string
	urls []string
	err  error
}

type Request struct {
	url   string
	depth int
}

func fetcherPool(fetcher Fetcher, size int) (chan *Request, chan *Response) {
	requests := make(chan *Request)
	responses := make(chan *Response)
	for i := 0; i < size; i++ {
		go func() {
			for {
				req := <-requests
				body, urls, err := fetcher.Fetch(req.url)
				responses <- &Response{req, body, urls, err}
			}
		}()
	}
	return requests, responses
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
	requests, responses := fetcherPool(fetcher, 10)
	seen := map[string]bool{url: true}

	schedule := func(d int, urls ...string) {
		for _, u := range urls {
			requests <- &Request{u, d}
		}
	}
	unique := func(urls []string) []string {
		output := make([]string, 0, len(urls))
		for _, u := range urls {
			if !seen[u] {
				seen[u] = true
				output = append(output, u)
			}
		}
		return output
	}

	schedule(depth, url)
	for active := 1; active > 0; active-- {
		res := <-responses
		if res.err != nil {
			fmt.Println(res.err)
			continue
		}

		fmt.Printf("found: %s %q\n", res.url, res.body)
		if d := res.depth - 1; d > 0 {
			notseen := unique(res.urls)
			if len(notseen) > 0 {
				active += len(notseen)
				go schedule(d, notseen...)
			}
		}
	}
}

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/",
		},
	},
}