A Tour of Go - Exercise: Web Crawler

sqlxx · · 1948 次点击 · · 开始浏览    
这是一个创建于 的文章,其中的信息可能已经有所发展或是发生改变。


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.


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, out chan string, mutuex chan map[string]bool, end chan bool) {
	// TODO: Fetch URLs in parallel.
	// TODO: Don't fetch the same URL twice.
	// This implementation doesn't do either:
	if depth <= 0 {
		end <- true
		return
	}
	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		out <- err.Error()
		end <- true
		return
	}
	fmt.Printf("found: %s %q\n", url, body)
	visited := <- mutuex
	subEnd := make(chan bool)
	i := 0
	for _, u := range urls {
		if !visited[u] {
			visited[u] = true
			i ++
			go Crawl(u, depth-1, fetcher, out, mutuex, subEnd)
		}
	}
	mutuex <- visited
	for ; i == 0 ; i-- {
		<- subEnd
	}
	
	end <- true
	
	
	return
}


func main() {
	out := make(chan string)
	mutuex := make(chan map[string]bool) 
	visited := make(map[string]bool)
	end := make(chan bool)
	visited["http://golang.org/"] = true
	go Crawl("http://golang.org/", 4, fetcher, out, mutuex, end)
	mutuex <- visited

	
	for {
		select {
		case t:= <- out:
			fmt.Println(t)
		case <- end:
			return
		}
	}
}


// 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/",
		},
	},
}



有疑问加站长微信联系(非本文作者)

本文来自:CSDN博客

感谢作者:sqlxx

查看原文:A Tour of Go - Exercise: Web Crawler

入群交流(和以上内容无关):加入Go大咖交流群,或添加微信:liuxiaoyan-s 备注:入群;或加QQ群:692541889

1948 次点击  
加入收藏 微博
0 回复
暂无回复
添加一条新回复 (您需要 登录 后才能回复 没有账号 ?)
  • 请尽量让自己的回复能够对别人有帮助
  • 支持 Markdown 格式, **粗体**、~~删除线~~、`单行代码`
  • 支持 @ 本站用户;支持表情(输入 : 提示),见 Emoji cheat sheet
  • 图片支持拖拽、截图粘贴等方式上传