Web Crawler – avec solutions

Dans cet exercice, vous utiliserez les fonctionnalités de concurrence de Go pour paralléliser un crawler web.

Modifiez la fonction Crawl ci-dessous pour récupérer les URLs en parallèle sans récupérer la même URL deux fois.

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) {
    // TODO: Fetch URLs in parallel.
    // TODO: Don't fetch the same URL twice.
    // This implementation doesn't do either:
    if depth <= 0 {
        return
    }
    body, urls, err := fetcher.Fetch(url)
    if err != nil {
        fmt.Println(err)
        return
    }
    fmt.Printf("found: %s %q\n", url, body)
    for _, u := range urls {
        Crawl(u, depth-1, fetcher)
    }
    return
}

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/",
        },
    },
}

Astuce

vous pouvez garder un cache des URLs qui ont été récupérées dans une map, mais les map seules ne sont pas sûres pour une utilisation concurrente !

Solution

main.go

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)
}

// Visited is a thread-safe cache of visited URLs.
type Visited struct {
    cache map[string]bool
    mutex sync.Mutex
}

// IsPresent returns true if the URL is present in the cache.
func (v *Visited) IsPresent(url string) bool {
    v.mutex.Lock()
    defer v.mutex.Unlock()
    if _, ok := v.cache[url]; ok {
        return true
    }

    v.cache[url] = true
    return false
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {

    var wg sync.WaitGroup

    var visited = Visited{cache: make(map[string]bool)}
    // recCrawl is a closure that recursively crawls in parallel
    // using goroutines.
    // WARNING : make sure that recCrawl itself is called as a goroutine.
    var recCrawl func(url string, depth int)
    recCrawl = func(url string, depth int) {
        defer wg.Done()

        if depth <= 0 || visited.IsPresent(url) {
            return
        }
        body, urls, err := fetcher.Fetch(url)
        if err != nil {
            fmt.Println(err)
            return
        }
        fmt.Printf("found: %s %q\n", url, body)
        for _, u := range urls {
            wg.Add(1)
            go recCrawl(u, depth-1)
        }
    }

    wg.Add(1)
    go recCrawl(url, depth)
    wg.Wait()
}

func main() {
    Crawl("https://golang.org/", 4, fetcher)
}

fetcher.go

package main

import "fmt"

// 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/",
        },
    },
}