Go Exercise: Web Crawler

go-exercise-web-crawler.go

package main

import (
	"fmt"
	"sync"
)

type Fetcher interface {
	Fetch(url string) (body string, urls []string, err error)
}

func (c *Crawling) AddCount() {
	c.mux.Lock()
	c.count++
	c.mux.Unlock()
}

func (c *Crawling) SubCount() {
	c.mux.Lock()
	c.count--
	if c.count <= 0 {
		c.quit <- true
	}
	c.mux.Unlock()
}

type Crawling struct {
	visited map[string]bool
	mux sync.Mutex
	count int
	quit chan bool
}

func (c *Crawling) AddUrl(url string) {
	c.mux.Lock()
	c.visited[url] = true
	c.mux.Unlock()
}

func (c *Crawling) Crawl(url string, fetcher Fetcher) {
	body, urls, err := fetcher.Fetch(url)
	c.AddUrl(url)

	if err != nil {
		fmt.Println(err)
		c.SubCount()
		return
	}
	fmt.Printf("found: %s %q\n", url, body)
	for _, u := range urls {
		if !c.visited[u] {
			c.AddCount()
			go c.Crawl(u, fetcher)
		}
	}
	c.SubCount()
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
	quit := make(chan bool)
	crawling_urls := Crawling{visited: make(map[string]bool), quit: quit, count: 1}
	go crawling_urls.Crawl(url, fetcher)
	<- quit
}

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/",
		},
	},
}