A Tour of Go
Exercise: Web Crawler
In this exercise you'll use Go's concurrency features to parallelize a web crawler.
Modify theCrawl
function to fetch URLs in parallel without fetching the same URL twice.
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)
}
// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher, out chan string, mutuex chan map[string]bool, end chan bool) {
// TODO: Fetch URLs in parallel.
// TODO: Don't fetch the same URL twice.
// This implementation doesn't do either:
if depth <= 0 {
end <- true
return
}
body, urls, err := fetcher.Fetch(url)
if err != nil {
out <- err.Error()
end <- true
return
}
fmt.Printf("found: %s %q\n", url, body)
visited := <- mutuex
subEnd := make(chan bool)
i := 0
for _, u := range urls {
if !visited[u] {
visited[u] = true
i ++
go Crawl(u, depth-1, fetcher, out, mutuex, subEnd)
}
}
mutuex <- visited
for ; i == 0 ; i-- {
<- subEnd
}
end <- true
return
}
func main() {
out := make(chan string)
mutuex := make(chan map[string]bool)
visited := make(map[string]bool)
end := make(chan bool)
visited["http://golang.org/"] = true
go Crawl("http://golang.org/", 4, fetcher, out, mutuex, end)
mutuex <- visited
for {
select {
case t:= <- out:
fmt.Println(t)
case <- end:
return
}
}
}
// 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/",
},
},
}