Golang Tutorial: Crawler

crawler.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)
}


// 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:
  type FetchResult struct {
    depth int
    url string
  }
  visited := make(map[string]int)
  ch := make(chan FetchResult)
  var wg sync.WaitGroup

  var goFetch func(url string, depth int, fetcher Fetcher, ch chan FetchResult)
  goFetch = func (url string, depth int, fetcher Fetcher, ch chan FetchResult) {
    if depth <= 0 || visited[url] != 0 {
        wg.Done()
        return
    }
    body, urls, err := fetcher.Fetch(url)

    ch <- FetchResult{depth+1, url}

    if err != nil {
        // fmt.Println(err)
        fmt.Printf("not found: %d: %s %q\n", depth, url, body)
        wg.Done()
        return
    }
    fmt.Printf("found: %d: %s %q\n", depth, url, body)


    for _, u := range urls {
      wg.Add(1)
      go goFetch(u, depth-1, fetcher, ch)
    }
    wg.Done()
    return
  }
  wg.Add(1)
  go goFetch(url, depth, fetcher, ch)
  go func() { wg.Wait(); close(ch) }()
  for fetchedResult := range ch {
    visited[fetchedResult.url] = fetchedResult.depth
  }
}


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/",
        },
    },
}