http://tour.golang.org/#73

73.go

// http://tour.golang.org/#73

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 CrawlLog struct {
    urls map[string]bool
    lock 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) {
    log := &CrawlLog{urls: make(map[string]bool)}
    wg := new(sync.WaitGroup)

    wg.Add(1)
    go CrawlImpl(url, depth, fetcher, log, wg)
    wg.Wait()
}

func CrawlImpl(url string, depth int, fetcher Fetcher, log *CrawlLog, wg *sync.WaitGroup) {
    defer wg.Done()
    if depth <= 0 {
        return
    }
    if log.urls[url] == true {
        fmt.Printf("skip: %s\n", url)
    }

    body, urls, err := fetcher.Fetch(url)
    if err != nil {
        fmt.Println(err)
        return
    }
    fmt.Printf("found: %s %q\n", url, body)
    
    log.lock.Lock()
    log.urls[url] = true
    log.lock.Unlock()
    for _, u := range urls {
        wg.Add(1)
        go CrawlImpl(u, depth-1, fetcher, log, wg)
    }
    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/",
        },
    },
}