diff options
Diffstat (limited to 'main.go')
| -rw-r--r-- | main.go | 35 |
1 files changed, 31 insertions, 4 deletions
@@ -2,10 +2,14 @@ package main import ( "flag" + "fmt" "io" "log" "net/http" "time" + + "golang.org/x/net/html" + "golang.org/x/net/html/atom" ) type Link struct { @@ -20,6 +24,7 @@ func main() { // CLI flag configuration. rawURL := flag.String("url", "", "Web address of target HTML") timeoutSecs := flag.Int("timeout", 2, "Number of seconds after which to time out") + flag.Parse() if *rawURL == "" { log.Fatal("Missing -url") @@ -48,12 +53,34 @@ func main() { log.Fatal(err) } - _ = links + fmt.Println(links) } -// findLinks consumes the given reader, scraping it of anchor +// findLinks consumes the given [io.Reader], scraping it of anchor // tags. Each anchor tag is "unmarshalled" into a [Link]. The // resulting slice of Links is returned, along with an error. -func findLinks(_ io.Reader) ([]Link, error) { - return nil, nil +func findLinks(r io.Reader) ([]Link, error) { + doc, err := html.Parse(r) + if err != nil { + return nil, fmt.Errorf("can't parse html reader: %w", err) + } + + var links []Link + for n := range doc.Descendants() { + if n.Type == html.ElementNode && n.DataAtom == atom.A { + var link Link + + // Scan the href. + for _, a := range n.Attr { + if a.Key == "href" { + link.Href = a.Val + } + } + + // FIXME: for now, only scan for hrefs. + links = append(links, link) + } + } + + return links, nil } |