[Go语言]我的第十一个Go语言程序

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

var fetched = Fetched{v : make(map[string]bool)}

// 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
}

fetched.mux.Lock()
defer fetched.mux.Unlock()
if _, ok := fetched.v[url]; !ok {
body, urls, err := fetcher.Fetch(url)
fetched.v[url] = true;
if err != nil {
fmt.Println(err)
return
}
fmt.Printf("found: %s %q\n", url, body)
for _, u := range urls {
go Crawl(u, depth-1, fetcher)
}
}

return
}

func main() {
Crawl("http://golang.org/", 4, fetcher)
time.Sleep(time.Second)
}

// 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/",
},
},
}