Modify the Crawl function to fetch URLs in parallel without fetching the same URL twice.

go_tour_ex_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)
}

var crawled = 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) {
    // Fetch URLs in parallel.
    // Don't fetch the same URL twice.
    if crawled[url] {
        fmt.Printf("already fetched: %s\n", url)
        return
    }
    // This implementation doesn't do either:
    if depth <= 0 {
        return
    }
    body, urls, err := fetcher.Fetch(url)
    // save crawled urls
    crawled[url] = true
    if err != nil {
        fmt.Println(err)
        return
    }
    
    fmt.Printf("found: %s %q\n", url, body)
    stat := make(chan bool)
    for _, u := range urls {
        go func() {
            Crawl(u, depth-1, fetcher)
            stat <- true
        }()
        <- stat
    }
    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/",
        },
    },
}