Exercise: Web Crawler

gista-file

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 UrlMapper struct {
	v   map[string]string
	mux sync.Mutex
}

func (t *UrlMapper) Set(key string, value string) {
	t.mux.Lock()
	if _, ok := t.v[key]; !ok {
		t.v[key] = value
	}
	t.mux.Unlock()
}

func (t *UrlMapper) Get(key string) string {
	t.mux.Lock()
	var v string
	if _, ok := t.v[key]; ok {
		v = t.v[key]
	}
	t.mux.Unlock()
	return v
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher, ret chan string, mapper UrlMapper) {
	defer close(ret)

	var _crawl func(string, int, Fetcher, chan string, UrlMapper)
	_crawl = func(url string, depth int, fetcher Fetcher, ret chan string, mapper UrlMapper) {
		if depth <= 0 {
			return
		}

		if mapper.Get(url) != "" {
			return
		}

		body, urls, err := fetcher.Fetch(url)
		if err != nil {
			//fmt.Println(err)
			return
		}
		ret <- url
		mapper.Set(url, body)
		//fmt.Printf("found: %s %q\n", url, body)
		for _, u := range urls {
			_crawl(u, depth-1, fetcher, ret, mapper)
		}
	}
	_crawl(url, depth, fetcher, ret, mapper)
	return
}

func main() {
	mapper := UrlMapper{v: make(map[string]string)}
	result := make(chan string)
	go Crawl("http://golang.org/", 4, fetcher, result, mapper)
	for s := range result {
		fmt.Println(s)
	}
}

// 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/",
		},
	},
}