Created
October 22, 2013 01:14
-
-
Save yanolab/7093679 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package main | |
import ( | |
"fmt" | |
"sync" | |
) | |
var workerSize = 4 | |
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 task struct { | |
url string | |
depth int | |
} | |
type cache struct { | |
m map[string]bool | |
mu sync.Mutex | |
} | |
func (c *cache) visited(url string) bool { | |
c.mu.Lock() | |
defer c.mu.Unlock() | |
if _, visited := c.m[url]; visited { | |
return true | |
} | |
c.m[url] = true | |
return false | |
} | |
func fetchTask(url string, depth int, tasks chan task, wg *sync.WaitGroup) { | |
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 { | |
wg.Add(1) | |
tasks <- task{u, depth - 1} | |
} | |
} | |
func wakeupWorker(c *cache, tasks chan task, wg *sync.WaitGroup) { | |
for t := range tasks { | |
if !c.visited(t.url) { | |
fetchTask(t.url, t.depth, tasks, wg) | |
} | |
wg.Done() | |
} | |
} | |
// Crawl uses fetcher to recursively crawl | |
// pages starting with url, to a maximum of depth. | |
func Crawl(url string, depth int, fetcher Fetcher) { | |
tasks := make(chan task, workerSize) | |
// Shutdown workers | |
defer close(tasks) | |
var wg sync.WaitGroup | |
cache := &cache{m:map[string]bool{url: true}} | |
// Create worker pool | |
for i := 0; i < workerSize; i++ { | |
go wakeupWorker(cache, tasks, &wg) | |
} | |
// Run the first fetch task | |
fetchTask(url, depth, tasks, &wg) | |
wg.Wait() | |
} | |
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/", | |
}, | |
}, | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment