go_tour_web_crawler.go

package main

import (
    "fmt"
    "sync"
)

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

// A WebMap is a safe map of url and body.
type WebMap struct {
    m   map[string]string
    mux sync.Mutex
}

func (m *WebMap) Inc(url string) (ret bool) {
    m.mux.Lock()
    defer m.mux.Unlock()
    _, ret = m.m[url]
    return
}

func (m *WebMap) Add(url, body string) {
    if !m.Inc(url) {
        m.mux.Lock()
        defer m.mux.Unlock()
        m.m[url] = body
    }
}

// crawler is the class which actually recurses the the web.
type crawler struct {
    wm  WebMap
    wg  sync.WaitGroup
    f   Fetcher
}

func (c *crawler) crawl(url string, d int) {

    // Defering done to the wait group
    defer c.wg.Done()

    // Fetching all urls
    body, urls, err := c.f.Fetch(url)
    if err != nil {
        fmt.Println(err)
        return
    }

    c.wm.Add(url, body) // Adds the url to the WebMap
    fmt.Printf("found: %s %q\n", url, body) // Report

    // Put here your processing code for the url.

    // Spawn new goroutines to continue the job.
    for _, u := range urls {
        if ! c.wm.Inc(u) && d > 0 {
            c.wg.Add(1)
            go c.crawl(u, d-1)
        }
    }
    return
}

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

    wm := WebMap{
        m: make(map[string]string),
    }
    c := crawler{
        wm:  wm,
        f:   fetcher,
    }

    c.wg.Add(1)
    go c.crawl(url, depth)
    c.wg.Wait()
    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/",
        },
    },
}