You need to convert HTML to readable, formatted plain text.
Use the html2text class available from http://www.chuggnutt.com/html2text.php. Example 13-51 shows it in action.
Converting HTML to plain text
The html2text class has a large number of formatting rules built in so your generated plain text has some visual layout for headings, paragraphs, and so on. It also includes a list of all the links in the HTML at the bottom of the text it generates.
13.13.4. See Also
http://www.chuggnutt.com/html2text.php for more information on html2text and links to download it.