0

i'm trying to scrape a website with chromedp, at some point there is multiple pages and I need to click on each of them. I successfully click on page 2 (each page is a <a href> element) and scrape it's content but when my code need to click the page 3 I have Could not find node with given id (-32000) error.

For what I have see on other issue it can come from a laggy server, so I have test waitVisible and waitReady on the HTML element which store the result I need to scrape but I still have this issue.

I maybe have an idea of what cause this error, when I click the link to the next page, the page is refreshed but not the url, so I suspect my node array which contain my a href link to be invalid.

Here what I have actually tried

ctxWithTimeOut, cancel := context.WithTimeout(ctx, time.Second*45)
    defer cancel()
    err = chromedp.Run(ctxWithTimeOut, chromedp.WaitVisible(".EnTeteTableau", chromedp.ByQuery))
    if err != nil {
        log.Printf("impossible de trouver l'élément .EnTeteTableau")
        log.Fatal(err)
    } else if numberOfPages > "1" {
        log.Printf("dans le if page > 1")
        err = chromedp.Run(ctx, chromedp.Sleep(time.Second*3))
        if err != nil {
            log.Fatal(err)
        }

        // Récupération des liens <a> des pages
        var pages []*cdp.Node
        err = chromedp.Run(ctx, chromedp.Nodes("td.pagination>a", &pages, chromedp.ByQueryAll))
        if err != nil {
            log.Fatal(err)
        } else {
            log.Printf("a trouvé les éléments paginations")
            var specIDList []string
            for _, v := range pages {
                fmt.Println("nodes pages ", v)
                log.Printf("dans le for, taille de page", len(pages))

                // Récupération de chaques lignes du tableau
                err = chromedp.Run(ctx, chromedp.Nodes(".light a, .dark a", &nodes, chromedp.ByQueryAll))
                if err != nil {
                    log.Fatal(err)
                }

                specIDList = append(specIDList, getSpecID(nodes)...)
                log.Println(specIDList)
                err = chromedp.Run(ctx, chromedp.MouseClickNode(v))
                if err != nil {
                    log.Fatal(err)
                }
                log.Printf("a cliqué")
                // Après le clic sur la page suivante on a besoin d'attendre que le tableau s'affiche à nouveau sinon on déclenche l'erreur
                // Could not find node with given id (-32000)
                err = chromedp.Run(ctxWithTimeOut, chromedp.WaitVisible(".EnTeteTableau", chromedp.ByQuery))
                fmt.Println(v.NodeID)
                if err != nil {
                    log.Printf("impossible de trouver l'élément .EnTeteTableau")
                    log.Fatal(err)
                }
                // err = chromedp.Run(ctx, chromedp.Sleep(time.Second*3))
                // if err != nil {
                //  log.Fatal(err)
                // }
            }
        }
Romain P
  • 55
  • 1
  • 1
  • 11

0 Answers0