A Tour of Go: exercise-web-crawler.go

exercise-web-crawler.go

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 fetchResult struct {
	body string
	urls []string
	err  error
}

type cachingFetcher struct {
	urlMap  map[string]fetchResult
	mux     *sync.Mutex
	fetcher Fetcher
}

func (cachingFetcher cachingFetcher) fetch(url string) fetchResult {
	cachingFetcher.mux.Lock()
	defer cachingFetcher.mux.Unlock()

	if value, ok := cachingFetcher.urlMap[url]; ok {
		fmt.Printf("found in cache: %s\n", url)
		return value
	}

	body, urls, err := cachingFetcher.fetcher.Fetch(url)
	value := fetchResult{body, urls, err}
	cachingFetcher.urlMap[url] = value
	return value
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher cachingFetcher) {
	if depth <= 0 {
		return
	}
	fetchResult := fetcher.fetch(url)
	// fmt.Println(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>", fetchResult)
	if fetchResult.err != nil {
		fmt.Println(fetchResult.err)
		return
	}
	fmt.Printf("found: %s %q\n", url, fetchResult.body)
	for _, u := range fetchResult.urls {
		go Crawl(u, depth-1, fetcher)
	}
	return
}

func main() {
	var myFetcher = cachingFetcher{make(map[string]fetchResult), &sync.Mutex{}, fetcher}
	go Crawl("https://golang.org/", 4, myFetcher)
	time.Sleep(1 * 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/",
		},
	},
}