A Tour of Go: Web Crawler Solution

main.go

package main

import (
	"fmt"
	"sync"
)

type Crawler struct {
	crawled map[string]bool
	mux     sync.Mutex
}

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 New() *Crawler {
	return &Crawler{
		crawled: make(map[string]bool),
	}
}

func (c *Crawler) visit(url string) bool {
	c.mux.Lock()
	defer c.mux.Unlock()
	
	_, ok := c.crawled[url]
	if ok {
		return true
	}
	c.crawled[url] = true

	return false
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func (c *Crawler) Crawl(url string, depth int, fetcher Fetcher) {
	var wg sync.WaitGroup

	v := c.visit(url)
	if v || depth <= 0 {
		return
	}

	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		return
	}
	fmt.Printf("found: %s %q\n", url, body)

	for _, u := range urls {
		wg.Add(1)
		go func(u string) {
			defer wg.Done()
			c.Crawl(u, depth-1, fetcher)
		}(u)
	}
	wg.Wait()
	return
}

func main() {
	crawler := New()
	crawler.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/",
		},
	},
}

Calling c.visit before checking for depth might end up not crawling pages that are also linked at at less depth but where the responsible crawler hasn't picked up on in yet