crawler.go

// My primitive solution to the web crawler exercise in the go tool tour
// Definitely need more practice on concurrency patterns and error package usage
//
// After much frustration, I ended up peeking at the official solution:
// https://github.com/golang/tour/blob/master/solutions/webcrawler.go
// so, I stole these ideas:
// the use of a concurrent closure
// iterating through the done channel

package main

import (
	"fmt"
	"sync"
)

var mux sync.Mutex
var visited = make(map[string]bool)

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) {

	if depth <= 0 {
		return
	}

	mux.Lock()
	if visited[url] {
		mux.Unlock()
		fmt.Println("already visited: " + url)
		return
	}
	visited[url] = true
	mux.Unlock()

	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		return
	}
	fmt.Println("found "+body, url)

	done := make(chan bool)
  
	for _, url := range urls {
		go func(url string) {
			Crawl(url, depth-1, fetcher)
			done <- true
		}(url)
	}
	for _ = range urls {
		<-done
	}
	return
}

func main() {
	Crawl("http://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{
	"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/",
		},
	},
}