golang tutorial web crawler

webcrawler.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 Cache struct{
	urlMap map[string]bool
	mux sync.Mutex
}

func (c *Cache) Add(url string) {
	c.mux.Lock()
	c.urlMap[url] = true
	c.mux.Unlock()
}

func (c *Cache) Has(url string) bool {
	c.mux.Lock()
	defer c.mux.Unlock()
	return c.urlMap[url]
}

type result struct {
	url string
	depth int
	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 c = Cache{urlMap: make(map[string]bool)}
	queue := make(chan result, 1)

	fetch := func (url string, depth int, queue chan<- result) {
		body, urls, err := fetcher.Fetch(url)
		queue <- result{url, depth, body, urls, err}
	}

	go fetch(url, depth, queue)
	c.Add(url)

	for fetching := 1;fetching > 0;fetching-- {

		res := <- queue

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

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

		if res.depth <= 0 {
			continue
		}

		for _, u := range res.urls {
			if c.Has(u) {
				continue
			}
			
			go fetch(u, res.depth-1, queue)
			fetching++
			c.Add(u)
		}

	}
	close(queue)

	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/",
		},
	},
}