Exercise: 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)
}

// Cache has a map to store visited URLs
// and a mutex to make it safe to use with
// goroutines
type Cache struct {
	l  map[string]bool
	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, c Cache) {
	// When all crawls are done, call Done() on
	// the waitgroup
	defer wg.Done()
	if depth <= 0 {
		return
	}
	// Lock the cache while accessing
	c.mu.Lock()
	// Has this URL already been checked?
	// If so, unlock and return
	if _, ok := c.l[url]; ok {
		c.mu.Unlock()
		return
	}
	// Set the URL to visited, and unlock
	c.l[url] = true
	c.mu.Unlock()
	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		return
	}
	fmt.Printf("found: %s %q\n", url, body)
	for _, u := range urls {
		// Add another goroutine to the waitgroup
		wg.Add(1)
		go Crawl(u, depth-1, fetcher, c)
	}
	return
}

// Need to wait for all goroutines to finish
var wg sync.WaitGroup

func main() {
	c := Cache{l: make(map[string]bool)}
	// Add 1 to waitgroup for the main goroutine
	wg.Add(1)
	Crawl("http://golang.org/", 4, fetcher, c)
	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{
	"http://golang.org/": &fakeResult{
		"The Go Programming Language",
		[]string{
			"http://golang.org/pkg/",
			"http://golang.org/cmd/",
		},
	},
	"http://golang.org/pkg/": &fakeResult{
		"Packages",
		[]string{
			"http://golang.org/",
			"http://golang.org/cmd/",
			"http://golang.org/pkg/fmt/",
			"http://golang.org/pkg/os/",
		},
	},
	"http://golang.org/pkg/fmt/": &fakeResult{
		"Package fmt",
		[]string{
			"http://golang.org/",
			"http://golang.org/pkg/",
		},
	},
	"http://golang.org/pkg/os/": &fakeResult{
		"Package os",
		[]string{
			"http://golang.org/",
			"http://golang.org/pkg/",
		},
	},
}