Skip to content

Instantly share code, notes, and snippets.

@SaoYan

SaoYan/exercise-web-crawler-slution1.go

Last active December 7, 2024 22:01
Show Gist options
  • Save SaoYan/32cf28b4689d3d9b077cc96d105a31df to your computer and use it in GitHub Desktop.
Save SaoYan/32cf28b4689d3d9b077cc96d105a31df to your computer and use it in GitHub Desktop.
Download ZIP
A Tour of Go Exercise: Web Crawler
Raw
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/",
},
},
}
Raw
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/",
},
},
}
@carolinux
Copy link

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

@hsnice16
Copy link

hsnice16 commented Aug 2, 2024 •
edited
Loading

This is what I have done

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 Cache struct {
	mu          sync.Mutex
	fetchedUrls map[string]bool
}

var end = make(chan int)

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher, cache *Cache) {
	// TODO: Fetch URLs in parallel.
	// TODO: Don't fetch the same URL twice.
	// This implementation doesn't do either:

	if depth <= 0 {
		return
	}

	body, urls, err := fetcher.Fetch(url)

	(*cache).mu.Lock()
	(*cache).fetchedUrls[url] = true
	(*cache).mu.Unlock()

	if err != nil {
		fmt.Println(err)
		return
	}

	fmt.Printf("found: %s %q\n", url, body)
	for _, url := range urls {

		if _, ok := (*cache).fetchedUrls[url]; ok {
			continue
		}

		go func() {
			end <- 1
			Crawl(url, depth-1, fetcher, cache)
		}()
		<-end
	}

	return
}

func main() {
	cache := Cache{
		fetchedUrls: make(map[string]bool),
	}
	Crawl("https://golang.org/", 4, fetcher, &cache)
}

// 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/",
		},
	},
}

@channyeintun
Copy link

You just need to the semantics of defer. No need WaitGroup. No need Channel.

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 UrlCache struct {
	mu    sync.Mutex
	cache map[string]string
}

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

	urlCache.mu.Lock()
	_, ok := urlCache.cache[url]
	defer urlCache.mu.Unlock()
	if ok {
		return
	}
	body, urls, err := fetcher.Fetch(url)
	urlCache.cache[url] = 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, urlCache)
	}
	return
}

func main() {
	cache := UrlCache{cache: make(map[string]string)}
	go Crawl("https://golang.org/", 4, fetcher, &cache)
	
	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/",
		},
	},
}

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment