Extract HTML data from csv or html docs into Spreadsheet

I have approximately 9000 csv files containing html code(I can provide unconverted html docs if preferred). I would prefer to have them programmatically imported into Open Office Spreadsheet(version [login to view URL]) but can live with Excel if that's all you can do, or a tab separated csv. I need each csv file to be imported into it's own row within the spreadsheet(or tab separated csv). So row 1 would be header names. Row 2 would be the data from the first csv. Row 3 would be the data from the second csv and so on. The HTML source code must be what shows up in the spreadsheet. There will be 4 columns of data for each csv. I only want certain parts of the html code and its contents from within the csv files inserted into the 4 columns which are: Data from the Title Tag, a block of html between consistently named h3 and p tags(but may have varying length), a section of code with consistent named opening and ending comments plus a set of h3 tags with its following p tag data, lastly a two consistently named words followed by a number.