Exercise: Web Crawler

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!

练习：Web 爬虫
在这个练习中，我们将会使用 Go 的并发特性来并行化一个 Web 爬虫。

修改 Crawl 函数来并行地抓取 URL，并且保证不重复。

提示：你可以用一个 map 来缓存已经获取的 URL，但是要注意 map 本身并不是并发安全的！

原始代码为

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("https://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{
	"https://golang.org/": &fakeResult{
		"The Go Programming Language",
		[]string{
			"https://golang.org/pkg/",
			"https://golang.org/cmd/",
		},
	},
	"https://golang.org/pkg/": &fakeResult{
		"Packages",
		[]string{
			"https://golang.org/",
			"https://golang.org/cmd/",
			"https://golang.org/pkg/fmt/",
			"https://golang.org/pkg/os/",
		},
	},
	"https://golang.org/pkg/fmt/": &fakeResult{
		"Package fmt",
		[]string{
			"https://golang.org/",
			"https://golang.org/pkg/",
		},
	},
	"https://golang.org/pkg/os/": &fakeResult{
		"Package os",
		[]string{
			"https://golang.org/",
			"https://golang.org/pkg/",
		},
	},
}

可以看到原始的Crawl函数已经写好了，我们需要做的是
1.要将Crawl中Fetch URL的过程变成并行
2.不能重复Fetch相同的URL

1.并行化Fetch URL

要完成第一点，简单的做法就是直接使用协程，将

for _, u := range urls {
	Crawl(u, depth-1, fetcher)
}

改成

for _, u := range urls {
	go Crawl(u, depth-1, fetcher)
}

但是这样做有一个问题，就是后续的所有Crawl都用协程进行，主程序没有阻塞，会直接结束。为了让主程序等待所有的协程都结束，利用一个通道done来判断协程结束与否，每当有一个协程结束后就往通道中发送一次数据，改写为

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

for _, _ = range urls {
	<- done
}

2.不重复Fetch相同的URL

要完成第二点，考虑使用一个map来判断url是否已经Fetch过，但是map并不是并发安全的，因此使用一个锁来实现并发安全的map，结构体如下所示

type SafeMap struct{
	mp map[string] bool
	mu sync.Mutex
} 

var sm SafeMap = SafeMap{mp: make( map[string] bool )}

在Crawl函数中，每次判断url是否在map中都需要加锁，并且修改map的代码也要放到临界区内，当这些都结束后，释放锁，如果url在map中，ok会为true，也就是已经Fetch过了这个url，直接返回即可。

sm.mu.Lock()
_, ok := sm.mp[url]
sm.mp[url] = true
sm.mu.Unlock()

if ok || depth <= 0 {
	return
}

最后整合上述代码

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 SafeMap struct{
	mp map[string] bool
	mu sync.Mutex
} 

var sm SafeMap = SafeMap{mp: 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) {
	// TODO: Fetch URLs in parallel.
	// TODO: Don't fetch the same URL twice.
	// This implementation doesn't do either:
	sm.mu.Lock()
	_, ok := sm.mp[url]
	sm.mp[url] = true
	sm.mu.Unlock()

	if ok || depth <= 0 {
		return
	}
	
	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		return
	}
	fmt.Printf("found: %s %q\n", url, body)
	done := make(chan bool, len(urls) )
	for _, u := range urls {
		go func(url string){
			Crawl(url, depth-1, fetcher)
			done <- true
		}(u)
		//go Crawl(u, depth-1, fetcher)
		
	}
	for _, _ = range urls {
		<- done
	}
	return
}

func main() {
	Crawl("https://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{
	"https://golang.org/": &fakeResult{
		"The Go Programming Language",
		[]string{
			"https://golang.org/pkg/",
			"https://golang.org/cmd/",
		},
	},
	"https://golang.org/pkg/": &fakeResult{
		"Packages",
		[]string{
			"https://golang.org/",
			"https://golang.org/cmd/",
			"https://golang.org/pkg/fmt/",
			"https://golang.org/pkg/os/",
		},
	},
	"https://golang.org/pkg/fmt/": &fakeResult{
		"Package fmt",
		[]string{
			"https://golang.org/",
			"https://golang.org/pkg/",
		},
	},
	"https://golang.org/pkg/os/": &fakeResult{
		"Package os",
		[]string{
			"https://golang.org/",
			"https://golang.org/pkg/",
		},
	},
}