Exercise: Web Crawler https://tour.golang.org/concurrency/10

exercise-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 Cacher struct {
	v map[string]*fakeResult
	m sync.Mutex
}

func (c *Cacher) get(url string) *fakeResult {
	c.m.Lock()
	defer c.m.Unlock()
	return c.v[url]
}

func (c *Cacher) set(url string, result *fakeResult) {
	c.m.Lock()
	defer c.m.Unlock()
	c.v[url] = result
	fmt.Println("  set cache: " + url)
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher, ch chan int, cache *Cacher) {
	if depth <= 0 {
		ch <- 0
		return
	}
	result := cache.get(url)
	var body string
	var urls []string
	if result != nil {
		fmt.Println("  got from cache :" + url)
		body, urls = result.body, result.urls
	} else {
		var err error
		body, urls, err = fetcher.Fetch(url)
		if err != nil {
			fmt.Println(err)
			ch <- -1
			return
		}
		cache.set(url, &fakeResult{body, urls})
	}
	fmt.Printf("found: %s %q\n", url, body)
	ch_children := make(chan int)
	for _, u := range urls {
		go Crawl(u, depth-1, fetcher, ch_children, cache)
	}
	for i := 0; i < len(urls); i++ {
		<-ch_children
	}
	ch <- 0
}

func main() {
	ch := make(chan int)
	cache := Cacher{v: make(map[string]*fakeResult)}
	go Crawl("https://golang.org/", 4, fetcher, ch, &cache)
	<-ch
}

// 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/",
		},
	},
}