Last active
August 29, 2015 14:05
-
-
Save alexvictoor/297b3fd3cb5016effe99 to your computer and use it in GitHub Desktop.
My solution to the golang webcrawler exercise
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" | |
) | |
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 TaskResult struct { | |
url string | |
depth int | |
error error | |
body string | |
urls []string | |
} | |
func Crawl(url string, depth int, fetcher Fetcher) { | |
results := make(chan TaskResult) | |
ongoingTasks := 0 | |
fetchedUrls := make(map[string]bool) | |
crawl := func(t Task) { | |
if t.depth > 0 && !fetchedUrls[t.url] { | |
ongoingTasks++ | |
fetchedUrls[t.url] = true | |
go func() { | |
body, urls, err := fetcher.Fetch(t.url) | |
results <- TaskResult{t.url, t.depth, err, body, urls} | |
}() | |
} | |
} | |
crawl(Task{url, depth}) | |
for { | |
select { | |
case r := <-results: | |
ongoingTasks-- | |
if r.error != nil { | |
fmt.Println(r.error) | |
} else { | |
fmt.Printf("found: %s %q\n", r.url, r.body) | |
for _, u := range r.urls { | |
crawl(Task{u, r.depth - 1}) | |
} | |
} | |
default: | |
if ongoingTasks == 0 { | |
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/", | |
}, | |
}, | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment