// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher crawler.Fetcher, visitUrl func(string, string)) {
// TODO: Fetch URLs in parallel.
// TODO: Don't fetch the same URL twice.
// This implementation doesn't do either:
if depth <= 0 {
return
}
body, urls, err := fetcher.Fetch(url)
if err != nil {
fmt.Println(err)
return
}
visitUrl(url, body)
for _, u := range urls {
Crawl(u, depth-1, fetcher, visitUrl)
}
return
}
// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher crawler.Fetcher, visitUrl func(string, string)) {
if depth <= 0 {
fmt.Printf("<- Done with %v, depth 0.\n", url)
return
}
fetched.Lock()
if _, ok := fetched.m[url]; ok {
fetched.Unlock()
fmt.Printf("<- Done with %v, already fetched.\n", url)
return
}
// We mark the url to be loading to avoid others reloading it at the same time.
fetched.m[url] = loading
fetched.Unlock()
// We load it concurrently.
body, urls, err := fetcher.Fetch(url)
// And update the status in a synced zone.
fetched.Lock()
fetched.m[url] = err
fetched.Unlock()
if err != nil {
fmt.Printf("<- Error on %v: %v\n", url, err)
return
}
visitUrl(url, body)
done := make(chan bool)
for i, u := range urls {
fmt.Printf("-> Crawling child %v/%v of %v : %v.\n", i, len(urls), url, u)
go func(url string) {
Crawl(url, depth-1, fetcher, visitUrl)
done <- true
}(u)
}
for i, u := range urls {
fmt.Printf("<- [%v] %v/%v Waiting for child %v.\n", url, i, len(urls), u)
<-done
}
fmt.Printf("<- Done with %v\n", url)
}
