golang tour web crawler exercise

web_crawler.go

package main

import (
	"fmt"
	"sync"
	// since we use waitgroup instead, no need for time anymore
	// "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 SafeCache struct {
	v   map[string]bool
	mux sync.Mutex
}

func (sc SafeCache) checkCache(key string) bool {
	sc.mux.Lock()
	defer sc.mux.Unlock()
	_, ok := sc.v[key]
	return ok == true
}
func (sc SafeCache) addCache(key string) {
	sc.mux.Lock()
	defer sc.mux.Unlock()
	sc.v[key] = true
}

var sc = SafeCache{v: make(map[string]bool)}
var wg sync.WaitGroup

// 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:

	defer wg.Done()
	if depth <= 0 {
		return
	}
	// check cache to avoid double fetch
	if sc.checkCache(url) {
		return
	}
	sc.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)
	}
	return
}

func main() {
	wg.Add(1)
	Crawl("https://golang.org/", 4, fetcher)
	// I really didn't get this by myself, we need to wait for goroutines to run in this case
	// but wait in main thread is not ideal
	// time.Sleep(5 * time.Second)

	// instead a better way is using sync.WaitGroup
	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/",
		},
	},
}