按照a tour of Go 中 Crawl 例程提示,改写了 Crawl 函数,但是只能找出一条 url,想不出原因,请教大家,谢谢。
```
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)
}
// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
// TODO: Fetch URLs in parallel.
// TODO: Don't fetch the same URL twice.
// This implementation doesn't do either:
if depth <= 0 {
fmt.Printf("depth <= 0 return")
return
}
body, urls, err := fetcher.Fetch(url)
if err != nil {
fmt.Println(err)
return
}
fmt.Printf("found: %s %q\n", url, body)
crawled.mux.Lock()
crawled.c[url]++
crawled.mux.Unlock()
for _, u := range urls {
//crawled.mux.Lock()
if cnt, ok := crawled.c[u]; ok {
cnt++
} else {
fmt.Println("go ...", u)
go Crawl(u, depth-1, fetcher)
}
//crawled.mux.Unlock()
//Crawl(u, depth-1, fetcher)
}
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/",
},
},
}
type crawledUrl struct {
c map[string]int
mux sync.Mutex
}
var crawled = crawledUrl{c: make(map[string]int)}
```
更多评论
还没执行完,main goroutine 就退出了。
你在 main 中 Sleep 一会。
另外,注释掉的加锁、解锁两行代码得有,否则有 `DATA RACE`
#1
多谢指点!
main goroutine 不会等待其 spawn 的goroutine运行完再退出,所以通过 sync.Wait() 在goroutine间进行同步也能达到效果。
#3