Last active
May 27, 2024 07:52
-
-
Save obutora/da3ef5d943e782f5f2c398fea6117875 to your computer and use it in GitHub Desktop.
Collyを使ったCrawler
This file contains hidden or 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" | |
"github.com/go-rod/rod" | |
"github.com/go-rod/rod/lib/proto" | |
"github.com/gocolly/colly/v2" | |
) | |
func main() { | |
url := "https://www.amazon.co.jp/gp/bestsellers/fashion/" | |
// url := "https://www.amazon.co.jp/gp/bestsellers/fashion/?pg=2" | |
c := colly.NewCollector() | |
// Find and visit all links | |
c.OnHTML(".a-container", func(e *colly.HTMLElement) { | |
var ( | |
name string | |
imgUrl string | |
) | |
e.ForEach("#gridItemRoot", func(i int, h *colly.HTMLElement) { | |
// urlString = h.Attr("href") | |
// title = strings.ReplaceAll(h.Text, "\n", "") | |
// imgUrl := | |
h.ForEach("img", func(i int, h *colly.HTMLElement) { | |
imgUrl = h.Attr("src") | |
name = h.Attr("alt") | |
}) | |
fmt.Printf("name: %v, imgUrl: %v\n", name, imgUrl) | |
}) | |
}) | |
c.OnRequest(func(r *colly.Request) { | |
fmt.Println("Visiting", r.URL) | |
}) | |
c.Visit(url) | |
c.Wait() | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment