Certainly! Here's the reformatted answer in HTML:
<p>So for the start, we have a file with the following lines, calleddatafile.txt</p> <pre>1 some test lines here but not all lines contain nubers 3 and here is the last one</pre> <p>and we have one bash variable$ADDEDwith the line content what want add</p> <pre>ADDED="==This is the new line=="</pre> <h2>So, add line after the first line</h2> <pre>ADDED="==This is the new line==" < datafile.txt sed "1a \\ $ADDED "</pre> <p>the result:</p> <pre>1 some test lines here ==This is the new line== but not all lines contain nubers 3 and here is the last line</pre> <h2>Add line after all lines what are starts with a number</h2> <pre>< datafile.txt sed "/^[0-9]/a \\ $ADDED "</pre> <p>the result:</p> <pre>1 some test lines here ==This is the new line== but not all lines contain nubers 3 and here is the last line ==This is the new line==</pre> <h2>Add line to the start, so insert before first line</h2> <pre>< datafile.txt sed "1i \\ $ADDED "</pre> <p>result</p> <pre>==This is the new line== 1 some test lines here but not all lines contain nubers 3 and here is the last line</pre> <h2>You can "substitute" the end of the line for adding a new one</h2> <pre>< datafile.txt sed "/all/s/$/\\ $ADDED/"</pre> <p>the above example add line after the line what contains word "all" by substitution</p> <pre>1 some test lines here but not all lines contain nubers ==This is the new line== 3 and here is the last line</pre> <h2>You can even split line and add between</h2> <pre>< datafile.txt sed "/all/s/\(.*lines \)\(.*\)/\1\\ $ADDED\\ \2/"</pre> <p>the above will search for the line what contains the word "all" and split it after the word "lines". The result:</p> <pre>1 some test lines here but not all lines ==This is the new line== contain nubers 3 and here is the last line</pre> <p>Last thing. It is impossible to parsing HTML with regural expressions, check the link in sputnik's comment.</p> <p>BUT, that's not mean than it is impossible match some parts of HTML files. If you know what you want match (and not parse) - you can safely use regular expression for HTML too. Simply, many peoples here don't know the difference between parsing and matching.</p> <p>So, if your html files has well known structure, e.g. you are sure than your html will the above structure all times, you can safely write:</p> <pre><your_file.html sed "/^<tr><th>/a \\ <tr><td>new Row:1 Cell:1</td><td>Row:1 Cell:2</td><td>Row:1 Cell:3</td><td>Row:1 Cell:4</td> "</pre> <p>and you will get</p> <pre><table id="tfhover" class="tftable" border="1"> <tr><th>HEADER1</th><th>HEADER2</th><th>HEADER3</th><th>HEADER4</th></tr> <tr><td>new Row:1 Cell:1</td><td>Row:1 Cell:2</td><td>Row:1 Cell:3</td><td>Row:1 Cell:4</td> <tr><td>Row:1 Cell:1</td><td>Row:1 Cell:2</td><td>Row:1 Cell:3</td><td>Row:1 Cell:4</td></tr> </table></pre> <p>simply because we NOT PARSING the html code, we are only MATCHING some line patterns..</p> </div> Remember to remove the ``` tags when adding this to your blog post. If you have any further questions or need assistance with something else, feel free to ask.