漫游Go语言（八）之sync.Mutex

Contents

1. 1. sync.Mutex
2. 2. 练习：网页爬虫

sync.Mutex

Go为mutual exclusion提供sync.Mutex库的两个方法

Lock
Unlock

我们可以将一块代码用Lock和Unlock包围以实现互斥运行，还可以用defer关键字来确保mutex会被释放。

练习：网页爬虫

在练习将使用Go并发特性来实现并行爬虫。修改Crawl方法并行但不重复地获取URL。
提示，可用一个Map来保存已获取的URL，但Map本身并不是线程安全的。

package main

import (
	"fmt"
)

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) {
	// TODO: Fetch URLs in parallel.
	// TODO: Don't fetch the same URL twice.
	// This implementation doesn't do either:
	if depth <= 0 {
		return
	}
	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 {
		Crawl(u, depth-1, fetcher)
	}
	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/",
		},
	},
}

题目很长，但是需要修改的部分只是Crawl函数

var m = make(map[string]int)
var mtx 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:

	if depth <= 0 {
		return
	}
	mtx.Lock()
	if m[url] == 0 {
		body, urls, err := fetcher.Fetch(url)
		m[url] = 1
		mtx.Unlock()
		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)
		}
	}else{
		mtx.Unlock()
	}
	return
}

在函数外部定义了一个map和mutex用来保存url是否被访问过，并确保其操作的互斥。
在访问下级url时，使用go语句实现并行。

found: http://golang.org/ "The Go Programming Language"
found: http://golang.org/pkg/ "Packages"
found: http://golang.org/pkg/os/ "Package os"
not found: http://golang.org/cmd/
found: http://golang.org/pkg/fmt/ "Package fmt"

至此基本的教程就已经结束了，接下来就应该开始实战提高了。