toyfetcher.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)
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
	var crawl func(url string, depth int)
	var wg sync.WaitGroup

	type cachedResult struct {
		body string
		urls []string
	}

	var crawlerCache = struct {
		fetched_urls map[string]cachedResult
		mux          sync.RWMutex
	}{fetched_urls: make(map[string]cachedResult)}

	crawl = func(url string, depth int) {
		defer wg.Done()

		if depth <= 0 {
			return
		}

		crawlerCache.mux.RLock()
		hot, ok := crawlerCache.fetched_urls[url]
		crawlerCache.mux.RUnlock()

		var urls []string

		if ok {
			body, turls := hot.body, hot.urls
			urls = turls
			fmt.Printf("cached: %s %q\n", url, body)
		} else {
			body, turls, err := fetcher.Fetch(url)
			urls = turls

			if err != nil {
				fmt.Println(err)
				return
			}

			fmt.Printf("fetched: %s %q\n", url, body)

			crawlerCache.mux.Lock()
			crawlerCache.fetched_urls[url] = cachedResult{body, urls}
			crawlerCache.mux.Unlock()
		}

		wg.Add(len(urls))
		for _, u := range urls {
			go crawl(u, depth-1)
		}
	}

	wg.Add(1)
	go crawl(url, depth)
	wg.Wait()

	return
}

func main() {
	Crawl("https://golang.org/", 4, fetcher)
}

// 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/",
		},
	},
}