Created
October 18, 2017 01:47
-
-
Save pandaman64/20c7f47551afaa2ff69dd5352eeecf3b to your computer and use it in GitHub Desktop.
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" | |
"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) | |
} | |
type SharedState struct { | |
messages chan string | |
visited map[string]interface{} | |
mux sync.Mutex | |
wg sync.WaitGroup | |
} | |
func CrawlImpl(state *SharedState, url string, depth int, fetcher Fetcher) { | |
defer state.wg.Done() | |
if depth <= 0 { | |
return | |
} | |
state.mux.Lock() | |
if _, ok := state.visited[url]; !ok { | |
state.visited[url] = nil | |
body, urls, err := fetcher.Fetch(url) | |
if err != nil { | |
state.mux.Unlock() | |
return | |
} | |
state.messages <- fmt.Sprintf("%s found: %s", url, body) | |
state.mux.Unlock() | |
for _, url = range urls { | |
if _, ok = state.visited[url]; !ok { | |
state.wg.Add(1) | |
go CrawlImpl(state, url, depth - 1, fetcher) | |
} | |
} | |
} else { | |
state.mux.Unlock() | |
} | |
} | |
// Crawl uses fetcher to recursively crawl | |
// pages starting with url, to a maximum of depth. | |
func Crawl(url string, depth int, fetcher Fetcher) { | |
state := SharedState { | |
messages: make(chan string), | |
visited: make(map[string]interface{}), | |
} | |
state.wg.Add(1) | |
go func() { | |
state.wg.Wait() | |
close(state.messages) | |
}() | |
go CrawlImpl(&state, url, depth, fetcher) | |
for m := range state.messages { | |
fmt.Println(m) | |
} | |
} | |
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/", | |
}, | |
}, | |
"http://golang.org/cmd/": &fakeResult{ | |
"Commands", | |
[]string{ | |
"http://golang.org/", | |
}, | |
}, | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment