Go Tour Web Crawler Exercise Solution

webcrawler.go

package main

import (
	"fmt"
	"sync"
)

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 StringSet map[string]struct{}

type SafeStringSet struct{
	mu sync.Mutex
	s StringSet
}

func (s StringSet) Has(url string) bool {
	_, ok := s[url]
	return ok
}

func (s StringSet) Add(url string) {
	s[url] = struct{}{}
}

var urlCache = SafeStringSet{s: make(StringSet)}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
	defer wg.Done() 

	if depth <= 0 {
		return
	}
	
	urlCache.mu.Lock()
	hasurl := urlCache.s.Has(url)
	//Saves cpu cycles and uniquely adds to the set. Most common case.
	urlCache.s.Add(url)
	urlCache.mu.Unlock()
	
	if !hasurl {
		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 Crawl(u, depth-1, fetcher)
		}
	}
	
	return
}

var wg sync.WaitGroup

func main() {
	wg.Add(1)
	Crawl("https://golang.org/", 4, fetcher)
	wg.Wait()
	fmt.Println("Done")
}

// 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{
	"https://golang.org/": &fakeResult{
		"The Go Programming Language",
		[]string{
			"https://golang.org/pkg/",
			"https://golang.org/cmd/",
		},
	},
	"https://golang.org/pkg/": &fakeResult{
		"Packages",
		[]string{
			"https://golang.org/",
			"https://golang.org/cmd/",
			"https://golang.org/pkg/fmt/",
			"https://golang.org/pkg/os/",
		},
	},
	"https://golang.org/pkg/fmt/": &fakeResult{
		"Package fmt",
		[]string{
			"https://golang.org/",
			"https://golang.org/pkg/",
		},
	},
	"https://golang.org/pkg/os/": &fakeResult{
		"Package os",
		[]string{
			"https://golang.org/",
			"https://golang.org/pkg/",
		},
	},
}