Solution to Exercise: Web Crawler https://tour.golang.org/concurrency/10

exercise-web-crawler.go

package main

import (
	"fmt"
	"time"
	"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 SafeCounter struct {
	v   map[string]bool
	mux sync.Mutex
}
var c SafeCounter = SafeCounter{v: make(map[string]bool)}
func (s SafeCounter)checkvisited(url string)bool{
	s.mux.Lock()
	defer s.mux.Unlock()
	_,ok:=s.v[url]
	if ok==false {
		s.v[url]=true
		return false
	}
	return true
	
}


// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
	// TODO: Fetch URLs in parallel.
	// TODO: Don't fetch the same URL twice.
	// This implementation doesn't do either:
	if depth <= 0 {
		return
	}
	if c.checkvisited(url) {
		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 {
		go Crawl(u, depth-1, fetcher)
	}
	return
}

func main() {
	Crawl("http://golang.org/", 4, fetcher)
	time.Sleep(5*time.Second)
}

// 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/",
		},
	},
}

package main

import (
	"fmt"
	"sync"
	"time"
)

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 safemap struct {
	m sync.Mutex
	mm map[string]bool
}
var safe safemap = safemap{mm:make(map[string]bool)}
// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
	// TODO: Fetch URLs in parallel.
	// TODO: Don't fetch the same URL twice.
	safe.m.Lock()
	safe.mm[url] = true
	safe.m.Unlock()
	// This implementation doesn't do either:
	if 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 {
		if _, visited := safe.mm[u]; !visited {
			go Crawl(u, depth-1, fetcher)
		}
	}
	return
}

func main() {
	Crawl("https://golang.org/", 4, fetcher)
	time.Sleep(time.Second)
}

// 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/",
		},
	},
}

could you guys give me some feedback on this code?

here is my answer, using channels.

package main

import (
	"fmt"
	"sync"
)

type Fetcher interface {
	Fetch(url string) (body string, urls []string, err error)
}

type SafeCounter struct {
	mu sync.Mutex
	v  map[string]bool
}

func (c *SafeCounter) Inc(key string) {
	c.mu.Lock()
	defer c.mu.Unlock()
	c.v[key] = true
}

func (c *SafeCounter) Visited(key string) bool {
	c.mu.Lock()
	defer c.mu.Unlock()
	return c.v[key]
}

func Crawl(url string, depth int, fetcher Fetcher, ch chan string, wg *sync.WaitGroup, c *SafeCounter) error {
	defer func() {
		if r := recover(); r != nil {
			fmt.Println("Recovered in Crawl:", r)
		}
	}()

	if depth <= 0 || c.Visited(url) {
		return nil
	}

	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		return err
	}
	//body, urls, err := fetcher.Fetch(url)
	//fmt.Printf("found: %s %q\n", url, body)
	wg.Add(len(urls)) // Add the number of URLs to crawl before starting to crawl them

	ch <- url + " " + "'" + body + "'"
	c.Inc(url)

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

	return nil
}

func main() {
	ch := make(chan string)
	c := SafeCounter{v: make(map[string]bool)}
	var wg sync.WaitGroup

	// Increment the WaitGroup before starting the crawl
	wg.Add(1)
	go func() {
		defer wg.Done()
		if err := Crawl("https://golang.org/", 4, fetcher, ch, &wg, &c); err != nil {
			fmt.Println(err)
		}
	}()

	go func() {
		wg.Wait()
		close(ch)
	}()

	for result := range ch {
		fmt.Printf("found: %s \n", result)
	}

	wg.Wait() // Wait for all goroutines to finish before exiting
	//fmt.Println(c.v)
}

// 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/",
		},
	},
}

Here's my solution. Pretty neat imo!

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 SafeMap struct {
	mu sync.Mutex
	m  map[string]string
}

func (sm *SafeMap) addCache(url string) {
	sm.mu.Lock()
	defer sm.mu.Unlock()

	sm.m[url] = url
}

func (sm *SafeMap) checkCache(url string) bool {
	sm.mu.Lock()
	defer sm.mu.Unlock()

	_, ok := sm.m[url]
	return ok
}

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

	if depth <= 0 {
		return
	}

	if sm.checkCache(url) {
		return
	}

	sm.addCache(url)

	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, sm)
	}
}

var wg sync.WaitGroup

func main() {
	sm := SafeMap{m: make(map[string]string)}

	wg.Add(1)
	Crawl("https://golang.org/", 4, fetcher, &sm)
	wg.Wait()
}

// 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/",
		},
	},
}