Exercise: Web Crawler

gistfile1.txt

/*
Exercise: Web Crawler
In this exercise you'll use Go's concurrency features to parallelize a web crawler.

Modify the Crawl function to fetch URLs in parallel without fetching the same URL twice.

Hint: you can keep a cache of the URLs that have been fetched on a map, but maps alone are not safe for concurrent use!
*/

package main

import (
	"fmt"
	"sync"
	"time"
)

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 Response struct {
	url  string
	urls []string
	body string
	err  error
}

var ch chan Response = make(chan Response)
var fetched map[string]bool = make(map[string]bool)
var wg sync.WaitGroup
var mu sync.Mutex

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
	// TODO: Fetch URLs in parallel.
	// TODO: Don't fetch the same URL twice.
	// This implementation doesn't do either:
	var fetch func(url string, depth int, fetcher Fetcher)
	wg.Add(1)
	recv := func() {
		for res := range ch {
			body, _, err := res.body, res.urls, res.err
			if err != nil {
				fmt.Println(err)
				continue
			}
			fmt.Printf("found: %s %q\n", url, body)
		}
	}

	fetch = func(url string, depth int, fetcher Fetcher) {
		time.Sleep(time.Second / 2)
		defer wg.Done()
		if depth <= 0 || fetched[url] {
			return
		}
		mu.Lock()
		fetched[url] = true
		mu.Unlock()
		body, urls, err := fetcher.Fetch(url)
		for _, u := range urls {
			wg.Add(1)
			go fetch(u, depth-1, fetcher)
		}
		ch <- Response{url, urls, body, err}
	}

	go fetch(url, depth, fetcher)
	go recv()
	return
}

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

// 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/cmd1/",
		},
	},
	"https://golang.org/pkg/": &fakeResult{
		"Packages",
		[]string{
			"https://golang.org/",
			"https://golang.org/cmd2/",
			"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/",
		},
	},
}