-
-
Save theanine/b178f1568256a606433d5347aa7db02b to your computer and use it in GitHub Desktop.
Goquery Remove Child Elements
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
| // Stackoverflow Answer | |
| // Original Question: http://stackoverflow.com/questions/32635943/get-text-from-div-without-child-elements/32640258#32640258 | |
| package main | |
| import ( | |
| "fmt" | |
| "strings" | |
| "github.com/PuerkitoBio/goquery" | |
| ) | |
| var ( | |
| html = `<html><body><div class="outter-class"> | |
| <h1 class="inner-class"> | |
| The string I need | |
| <span class="other-class" >Some value I don't need</span> | |
| <span class="other-class2" title="sometitle"></span> | |
| </h1> | |
| <div class="other-class3"> | |
| <h3>Some heading i don't need</h3> | |
| </div> | |
| </div></body></html>` | |
| ) | |
| func main() { | |
| r := strings.NewReader(html) | |
| doc, err := goquery.NewDocumentFromReader(r) | |
| if err != nil { | |
| panic(err) | |
| } | |
| // h1 := doc.Find("h1") | |
| // h1.Children().Remove() | |
| // text := h1.Text() | |
| text := doc.Find("h1").Children().Remove().End().Text() | |
| text = strings.TrimSpace(text) | |
| fmt.Println(text) | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment