https://tour.golang.org/concurrency/10

exercise_web_crawler.go

package main

import (
	"fmt"
	"sync"
)

type Cache struct {
	data map[string]string
	m    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)
}

func (c *Cache) Add(url, body string) {
	c.m.Lock()
	c.data[url] = body
	c.m.Unlock()
}

func (c *Cache) Present(url string) bool {
	c.m.Lock()
	defer c.m.Unlock()

	_, ok := c.data[url]
	return ok
}

// 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:

	var wg sync.WaitGroup

	if depth <= 0 {
		return
	}

	if cache.Present(url) {
		fmt.Printf("Already fetched: %s\n", url)
	} else {
		body, urls, err := fetcher.Fetch(url)
		if err != nil {
			fmt.Println(err)
			return
		}

		cache.Add(url, body)

		fmt.Printf("found: %s %q\n", url, body)
		for _, u := range urls {
			wg.Add(1)
			go func(u string) {
				defer wg.Done()
				Crawl(u, depth-1, fetcher, cache)
			}(u)
		}

	}
	wg.Wait()
}

func main() {
	cache := &Cache{data: make(map[string]string)}
	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/",
		},
	},
}