Solution for Web Crawler exercise of Go's Tour

web-crawler.go

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 map[string]*fakeResult

// Safe-n-Cached wrapper for Fetcher
type cachedFetcher struct {
	mutex sync.Mutex
	cache   urlCache
	fetcher Fetcher
}

func (self *cachedFetcher) Fetch(url string) (string, []string, error) {
	defer self.mutex.Unlock()
	self.mutex.Lock()
	if res, ok := self.cache[url]; ok {
		return res.body, res.urls, nil
	}

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

	if err == nil {
		self.cache[url] = &fakeResult{
			"[cached] " + body,
			urls,
		}
	}

	return body, urls, err
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher, resultChan chan string) {
	// This implementation doesn't do either:
	if depth <= 0 {
		return
	}

	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		resultChan <- fmt.Sprintf("%s", err)
		return
	}

	resultChan <- fmt.Sprintf("found: %s %q", url, body)
	
	var wg sync.WaitGroup
	for _, u := range urls {
		wg.Add(1)
		// try to remove passing url to the closure :) 
		go func(url string) {
			defer wg.Done()
			Crawl(url, depth-1, fetcher, resultChan)
		}(u)
	}
	wg.Wait()
}

func main() {
	resultChan := make(chan string)
	
	go func() {
		Crawl("https://golang.org/", 4, &cachedFetcher{
			cache:   make(urlCache),
			fetcher: &fetcher,
		}, resultChan)
		close(resultChan)
	}()
	
	for result := range resultChan {
		fmt.Println(result)
	}
}

// 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/",
		},
	},
}