I’m looking for a way to extract RSS feeds that I’ve collected from Google News. I’ve parsed out the proper URL (no Google bounce) from my database and I want to have a slick way of extracting the meat of articles and not have to look at the fluff surrounding them. I’m not saving the whole mess into the database, but I want to have the meat that I can summarize or park into a table somewhere.
Anybody have any solutions? Cleaning up pages for content only would save tokens and clarity in workflows.
Cheers