Question

從HTML中提取文本，我用的是完全HTML5-compliant tokenizer and parser，這樣

s := ` 
<p>Links:</p><ul><li><a href="foo">Foo</a><li> 
<a href="/bar/baz">BarBaz</a></ul><span>TEXT <b>I</b> WANT</span> 
<script type='text/javascript'> 
/* <![CDATA[ */ 
var post_notif_widget_ajax_obj = {"ajax_url":"http:\/\/site.com\/wp-admin\/admin-ajax.php","nonce":"9b8270e2ef","processing_msg":"Processing..."}; 
/* ]]> */ 
</script>` 

    domDocTest := html.NewTokenizer(strings.NewReader(s)) 
    for tokenType := domDocTest.Next(); tokenType != html.ErrorToken; { 
     if tokenType != html.TextToken { 
      tokenType = domDocTest.Next() 
      continue 
     } 
     TxtContent := strings.TrimSpace(html.UnescapeString(string(domDocTest.Text()))) 
     if len(TxtContent) > 0 { 
      fmt.Printf("%s\n", TxtContent) 
     } 
     tokenType = domDocTest.Next() 
    } 

，但我得到這個結果

Links: 
Foo 
BarBaz 
TEXT 
I 
WANT 
/* <![CDATA[ */ 
var post_notif_widget_ajax_obj = {"ajax_url":"http:\/\/site.com\/wp-admin\/admin-ajax.php","nonce":"9b8270e2ef","processing_msg":"Processing..."}; 
/* ]]> */ 

我不想CDATA內容。一些想法，如何只獲取文本內容？

Answer 1

正如@Eric波利表示，我看TextTokens & StartTagTokens。 這裏是我的解決方案

s := ` 
<p>Links:</p><ul><li><a href="foo">Foo</a><li> 
<a href="/bar/baz">BarBaz</a></ul><span>TEXT <b>I</b> WANT</span> 
<script type='text/javascript'> 
/* <![CDATA[ */ 
var post_notif_widget_ajax_obj = {"ajax_url":"http:\/\/site.com\/wp-admin\/admin-ajax.php","nonce":"9b8270e2ef","processing_msg":"Processing..."}; 
/* ]]> */ 
</script>` 

    domDocTest := html.NewTokenizer(strings.NewReader(s)) 
    previousStartTokenTest := domDocTest.Token() 
loopDomTest: 
    for { 
     tt := domDocTest.Next() 
     switch { 
     case tt == html.ErrorToken: 
      break loopDomTest // End of the document, done 
     case tt == html.StartTagToken: 
      previousStartTokenTest = domDocTest.Token() 
     case tt == html.TextToken: 
      if previousStartTokenTest.Data == "script" { 
       continue 
      } 
      TxtContent := strings.TrimSpace(html.UnescapeString(string(domDocTest.Text()))) 
      if len(TxtContent) > 0 { 
       fmt.Printf("%s\n", TxtContent) 
      } 
     } 
    } 

Answer 2

如果您使用github.com/PuerkitoBio/goquery實現您想要的功能相當容易。

• 首先，您需要使用document.Find()以確定要刪除，你的情況scripts的元素，所以document.Find(scripts)

• 然後，你需要使用element.Remove()

• 文檔中刪除

  最後，您打印/使用文本document.Text()

所以，最終的代碼將是

package main 

import (
    "fmt" 
    "strings" 
    "github.com/PuerkitoBio/goquery" 
) 

func main(){ 
    s := `<p>Links:</p><ul><li><a href="foo">Foo</a><li><a href="/bar/baz">BarBaz</a></ul><span>TEXT <b>I</b> WANT</span><script type='text/javascript'>/* <![CDATA[ */var post_notif_widget_ajax_obj = {"ajax_url":"http:\/\/site.com\/wp-admin\/admin-ajax.php","nonce":"9b8270e2ef","processing_msg":"Processing..."};/* ]]> */</script>` 

    p := strings.NewReader(s) 
    doc, _ := goquery.NewDocumentFromReader(p) 

    doc.Find("script").Each(func(i int, el *goquery.Selection) { 
     el.Remove() 
    }) 

    fmt.Println(doc.Text()) // Links:FooBarBazTEXT I WANT 

}