Go Tour Exercise

web_crawler.go

package main

// Exercise: Web Crawler
// https://tour.golang.org/concurrency/10
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)
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher, urlStorage *UrlStorage, urlChannel chan string) {
	// TODO: Fetch URLs in parallel.
	// TODO: Don't fetch the same URL twice.
	// This implementation doesn't do either:
	defer func() {
		urlChannel <- url
	}()
	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)
	subUrlChannel := make(chan string, len(urls))
	validUrl := 0
	for _, u := range urls {
		if !urlStorage.AddUrl(u) {
			continue
		}
		validUrl += 1
		go Crawl(u, depth-1, fetcher, urlStorage, subUrlChannel)
	}
	for i := 0; i < validUrl; i += 1 {
		url := <- subUrlChannel
		fmt.Printf("Finish process url %s", url)
	}
	return
}

type UrlStorage struct {
    urls map[string]bool
	mutex sync.Mutex
}

func NewUrlStorage() *UrlStorage {
    return &UrlStorage{urls: make(map[string]bool, 1000)}
}

func (this *UrlStorage) AddUrl(url string) bool {
    this.mutex.Lock()
	defer this.mutex.Unlock()
	if _, hasUrl := this.urls[url]; hasUrl {
		return false
	}
	this.urls[url] = true
	return true
}

func main() {
    urlStorage := NewUrlStorage()
	urlChannel := make(chan string, 1)
	Crawl("https://golang.org/", 4, fetcher, urlStorage, urlChannel)
}

// 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/",
		},
	},
}