Created
September 29, 2012 17:32
-
-
Save fanzeyi/3804668 to your computer and use it in GitHub Desktop.
My solution for `Exercise: Web Crawler`
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" | |
var visited = map[string]bool { | |
} | |
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, ch chan bool) { | |
// DONE: Fetch URLs in parallel. | |
// DONE: Don't fetch the same URL twice. | |
// This implementation doesn't do either: | |
fmt.Println("Fetching:",url) | |
if depth <= 0 { | |
ch <- true | |
return | |
} | |
if visited[url] { | |
ch <- true | |
return | |
} | |
body, urls, err := fetcher.Fetch(url) | |
visited[url] = true | |
if err != nil { | |
fmt.Println(err) | |
ch <- true | |
return | |
} | |
fmt.Printf("found: %s %q\n", url, body) | |
c := make(chan bool, 100) | |
for _, u := range urls { | |
go Crawl(u, depth-1, fetcher, c) | |
} | |
count := 0 | |
for { | |
if _,ok := <- c; ok { | |
count = count + 1 | |
} | |
if count == len(urls) { | |
break | |
} | |
} | |
ch <- true | |
return | |
} | |
func main() { | |
ch := make(chan bool, 100) | |
go Crawl("http://golang.org/", 4, fetcher, ch) | |
count := 0 | |
for { | |
if _,ok := <- ch; ok { | |
count = count + 1 | |
} | |
if count == 1 { | |
break | |
} | |
} | |
} | |
// 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