A Tour of Go Exercise: Web Crawler

exercise-web-crawler-slution1.go

package main

import (
	"fmt"
	"sync"
)

/*
This solution uses channels to force each gorountines to wait for its child gorountines to exit.
*/

type SafeCounter struct {
	v   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)
}

var cnt SafeCounter = SafeCounter{v: 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, exit chan bool) {
	// Fetch URLs in parallel.
	// Don't fetch the same URL twice.

	if depth <= 0 {
		exit <- true
		return
	}

	cnt.mux.Lock()
	_, ok := cnt.v[url]
	if ok == false {
		cnt.v[url] = true
		cnt.mux.Unlock()
	} else {
		exit <- true
		cnt.mux.Unlock()
		return
	}

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

	e := make(chan bool)
	for _, u := range urls {
		go Crawl(u, depth-1, fetcher, e)
	}
  
  // wait for all child gorountines to exit
	for i := 0; i < len(urls); i++ {
		<-e
	}
	exit <- true
}

func main() {
	exit := make(chan bool)
	go Crawl("https://golang.org/", 4, fetcher, exit)
	<-exit
}

// 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/",
		},
	},
}

exercise-web-crawler-slution2.go

package main

import (
	"fmt"
	"sync"
)

/*
This solution uses WaitGroup to force each gorountines to wait for its child gorountines to exit.
*/


type SafeCounter struct {
	v   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)
}

var cnt SafeCounter = SafeCounter{v: 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, wg *sync.WaitGroup) {
	// Fetch URLs in parallel.
	// Don't fetch the same URL twice.

	if depth <= 0 {
		wg.Done()
		return
	}

	cnt.mux.Lock()
	_, ok := cnt.v[url]
	if ok == false {
		cnt.v[url] = true
		cnt.mux.Unlock()
	} else {
		wg.Done()
		cnt.mux.Unlock()
		return
	}

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

	var wg_ sync.WaitGroup
	for _, u := range urls {
		wg_.Add(1)
		go Crawl(u, depth-1, fetcher, &wg_)
	}
	
	wg_.Wait()
	wg.Done()
}

func main() {
	var wg sync.WaitGroup
	go Crawl("https://golang.org/", 4, fetcher, &wg)
	wg.Add(1)
	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/",
		},
	},
}

Just structure with map + mutex and populating channel

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 SafeCrawl struct {
	crawled map[string]int
	mu sync.Mutex
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func CrawlRecursive(url string, depth int, fetcher Fetcher, ch chan string, sc SafeCrawl) {
	sc.mu.Lock()
	if depth <= 0 || sc.crawled[url] != 0 {
		return
	}
	sc.crawled[url] = 1
	sc.mu.Unlock()
	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		return
	}
	ch <- fmt.Sprintf("found: %s %q", url, body)
	for _, u := range urls {
		CrawlRecursive(u, depth-1, fetcher, ch, sc)
	}
}

func Crawl(url string, depth int, fetcher Fetcher, ch chan string) {
	sc := SafeCrawl{crawled : make(map[string]int)}
	CrawlRecursive(url, depth, fetcher, ch, sc)
	close(ch)
}

func main() {
	ch := make(chan string)
	go Crawl("https://golang.org/", 4, fetcher, ch)
	for crawled := range ch {
		fmt.Println(crawled)
	}
}

// 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/",
		},
	},
}

@Fleyderer
i'd say you need to call CrawlRecursive with go every time in order to properly make it concurrent

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 urlCache struct {
	sync.RWMutex
	m 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, wg *sync.WaitGroup, cache *urlCache) {
	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 {
		cache.RLock()
		_, ok := cache.m[u]
		cache.RUnlock()
		if ok {
			continue
		}
		cache.Lock()
		cache.m[u] = true
		cache.Unlock()
		wg.Add(1)
		go func() {
			defer wg.Done()
			Crawl(u, depth-1, fetcher, wg, cache)
		}()

	}
	return
}

func main() {
	wg := sync.WaitGroup{}
	cache := urlCache{m: make(map[string]bool)}
	wg.Add(1)
	go func() {
		defer wg.Done()
		Crawl("https://golang.org/", 4, fetcher, &wg, &cache)
	}()
	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/",
		},
	},
}

re: https://gist.github.com/SaoYan/32cf28b4689d3d9b077cc96d105a31df?permalink_comment_id=4667391#gistcomment-4667391
there is a race condition in get/set.. think about it