exercise-web-crawler.go

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)
}

// We put these objects into channel, empty task denotes sequence end
type FetchTask struct {
	url string
	depth int
}

func generate_tasks(task FetchTask, fettcher Fetcher, out chan FetchTask) {
	defer func () { out <- FetchTask{} }() // Put empty task to channel: task generation sequance is complete
	
	if task.depth <= 0 {
		return
	}
	body, urls, err := fetcher.Fetch(task.url)
	if err != nil {
		fmt.Println(err)
		return
	}
	fmt.Printf("found: %s %q\n", task.url, body)
	for _, u := range urls {
		out <- FetchTask{u, task.depth-1} // put new fetch task to channel
	}
	return
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
	// Mark all visited urls
	visited := make(map[string]bool)
	// tasks queue
	out := make(chan FetchTask)
	// count how many task generators are active
	num := 1
	// mark first url as visited and go
	visited[url] = true
	go generate_tasks(FetchTask{url, depth}, fetcher, out)
	
	for {
	  // wait for next task from channel
		task := <-out
		switch {
		  // empty task: a task generator ended
			case task.url == "":
				num-- // decrease generators number
				if num == 0 { // exit all generators are complete
					return 
				}
			case visited[task.url] == false: // if we have task with unvisited url
				visited[task.url] = true // mark as visited
				num++ // increase generators number
				go generate_tasks(task, fetcher, out) // start task generator
		}
	}
}

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/",
		},
	},
}

output

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