Last active
December 2, 2020 19:35
-
-
Save beeekind/a7c5ac1303626af3d70c4106e9c7dd08 to your computer and use it in GitHub Desktop.
Simple intuitive way to scrape single page applications in golang
This file contains 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" | |
"context" | |
"github.com/PuerkitoBio/goquery" | |
"github.com/chromedp/cdproto/dom" | |
"github.com/chromedp/chromedp" | |
) | |
func main(){ | |
doc, err := ParseWebApp("youtube.com") | |
if err != nil { | |
// ... | |
} | |
fmt.Println(doc.Find("h1").First().Text()) | |
} | |
// ParseWebApp ... | |
func ParseWebApp(url string) (*goquery.Document, error) { | |
var outterHTML string | |
ctx, cancel := chromedp.NewContext(context.Background()) | |
defer cancel() | |
if err := chromedp.Run(ctx, chromedp.Tasks{ | |
chromedp.Navigate(url), | |
// js rendering happens asynchronously and this call seems to be enough to account for that | |
chromedp.WaitReady(":root"), | |
chromedp.ActionFunc(func(ctx context.Context) error { | |
node, err := dom.GetDocument().Do(ctx) | |
if err != nil { | |
return err | |
} | |
outterHTML, err = dom.GetOuterHTML().WithNodeID(node.NodeID).Do(ctx) | |
return err | |
}), | |
}); err != nil { | |
return nil, fmt.Errorf("ParseWebApp(): ActionFunc(): %w", err) | |
} | |
doc, err := goquery.NewDocumentFromReader(strings.NewReader(outterHTML)) | |
if err != nil { | |
return nil, fmt.Errorf("ParseWebApp(): goquery.NewDocumentFromReader(): %w", err) | |
} | |
return doc, nil | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment