Exercise: Web Crawler - A Tour of Go

exercise-web-crawler.go

package main

import (
	"fmt"
	"sync"
)

type Cache struct {
	v map[string]int
	mux 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)
}


// 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, quit chan bool) {
	// TODO: Fetch URLs in parallel.
	// TODO: Don't fetch the same URL twice.
	// This implementation doesn't do either:
	
	if depth <= 0 {
		quit <- true
		return
	}
	
	cache.mux.Lock()
	if _, ok := cache.v[url]; ok {
		cache.mux.Unlock()
		quit <- true
		return
	}
	cache.v[url]++
	cache.mux.Unlock()
		
	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		quit <- true
		return
	}
	fmt.Printf("found: %s %q\n", url, body)
	
	chs := make([]chan bool,len(urls))
	//fmt.Println(len(chs))
	for i, u := range urls {
		chs[i] = make(chan bool)
		go Crawl(u, depth-1, fetcher, cache,chs[i])
		
	}
	for _, ch := range chs {
		<- ch
	}
	quit <-true
	return
}

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

// 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/",
		},
	},
}