Several examples of deleting html tags using regular expressions in java

Example 1

For news content or blog articles, if the abstract is displayed, you need to remove the html format tag of the content, find a regular expression, and implement:

The code is as follows:

Copy code

/** * Delete the html format in the input string      *  * @ Param input * @ Param length * @ Return */ Public static String splitAndFilterString (String input ){ If (input = null | input. trim (). equals ("")){ Return "";         }  // Remove all html elements, String str = input. replaceAll ("\\& [a-zA-Z] {};", ""). replaceAll ( "<[^>] *>", ""). ReplaceAll ("[(/>) <]", ""); Return str;     } Filter out the regular expressions of all script scripts: Content. replaceAll ("<script [^>] *?> [\ S \ S] *? <\\/ Script> ","") Filter out the regular expressions of all styles: Content. replaceAll ("<[\ s] *? Style [^>] *?> [\ S \ S] *? <[\ S] *? \/[\ S] *? Style [\ s] *?> ",""); Filter all html tags and retain the p and br tags. Content. replaceAll ("</? (?! Br | /? P) [^>] *> ",""); Filter all html tags and keep the p tag. Content. replaceAll ("</? (?! /? P) [^>] *> ","");

Example 2

The code is as follows:

Copy code

Import java. util. regex. Matcher; Import java. util. regex. Pattern;    Public class HtmlUtil { Private static final String regEx_script = "<script [^>] *?> [\ S \ S] *? <\\/ Script> "; // defines the regular expression of the script. Private static final String regEx_style = "<style [^>] *?> [\ S \ S] *? <\\/ Style> "; // defines the regular expression of the style. Private static final String regEx_html = "<[^>] +>"; // defines the regular expression of the HTML tag. Private static final String regEx_space = "\ s * | \ t | \ r | \ n"; // define a space and press enter to enter the line break.        /** * @ Param htmlStr * @ Return * Deleting Html tags */ Public static String delHTMLTag (String htmlStr ){ Pattern p_script = Pattern. compile (regEx_script, Pattern. CASE_INSENSITIVE ); Matcher m_script = p_script.matcher (htmlStr ); HtmlStr = m_script.replaceAll (""); // filter script tags    Pattern p_style = Pattern. compile (regEx_style, Pattern. CASE_INSENSITIVE ); Matcher m_style = p_style.matcher (htmlStr ); HtmlStr = m_style.replaceAll (""); // filter style labels    Pattern p_html = Pattern. compile (regEx_html, Pattern. CASE_INSENSITIVE ); Matcher m_html = p_html.matcher (htmlStr ); HtmlStr = m_html.replaceAll (""); // filter html tags    Pattern p_space = Pattern. compile (regEx_space, Pattern. CASE_INSENSITIVE ); Matcher m_space = p_space.matcher (htmlStr ); HtmlStr = m_space.replaceAll (""); // filter the blank carriage return tag Return htmlStr. trim (); // return a text string     }        Public static String getTextFromHtml (String htmlStr ){ HtmlStr = delHTMLTag (htmlStr ); HtmlStr = htmlStr. replaceAll ("& nbsp ;",""); HtmlStr = htmlStr. substring (0, htmlStr. indexOf (". ") + 1 ); Return htmlStr;     }        Public static void main (String [] args ){ String str = "<div style = 'text-align: center; '> cleaning up the" Four Winds "<br/> <span style = 'font-size: 14px; '> </span> <span style = 'font-size: 18px; '> The company held a mobilization meeting for the party's Mass Line education practices </span> <br/> </div> "; System. out. println (getTextFromHtml (str ));     } }

Example 3

/

The code is as follows:

Copy code

** * Deleting Html tags  * * @ Param inputString * @ Return */ Public static String htmlRemoveTag (String inputString ){ If (inputString = null) Return null; String htmlStr = inputString; // String containing html tags String textStr = ""; Java. util. regex. Pattern p_script; Java. util. regex. Matcher m_script; Java. util. regex. Pattern p_style; Java. util. regex. Matcher m_style; Java. util. regex. Pattern p_html; Java. util. regex. Matcher m_html; Try { // Define the regular expression {or <script [^>] *?> [\ S \ S] *? <\/Script> String regEx_script = "<[\ s] *? Script [^>] *?> [\ S \ S] *? <[\ S] *? \/[\ S] *? Script [\ s] *?> "; // Define the regular expression {or <style [^>] *?> [\ S \ S] *? <\/Style> String regEx_style = "<[\ s] *? Style [^>] *?> [\ S \ S] *? <[\ S] *? \/[\ S] *? Style [\ s] *?> "; String regEx_html = "<[^>] +>"; // defines the regular expression of the HTML tag. P_script = Pattern. compile (regEx_script, Pattern. CASE_INSENSITIVE ); M_script = p_script.matcher (htmlStr ); HtmlStr = m_script.replaceAll (""); // filter script tags P_style = Pattern. compile (regEx_style, Pattern. CASE_INSENSITIVE ); M_style = p_style.matcher (htmlStr ); HtmlStr = m_style.replaceAll (""); // filter style labels P_html = Pattern. compile (regEx_html, Pattern. CASE_INSENSITIVE ); M_html = p_html.matcher (htmlStr ); HtmlStr = m_html.replaceAll (""); // filter html tags TextStr = htmlStr; } Catch (Exception e ){ E. printStackTrace ();  } Return textStr; // return a text string  }