Just saying that you need to read/modify XML & HTML (or JSON) doesn't provide enough detail to be able to suggest which tool(s) might be best for the job.  The most important parts that you left out are details like what type of information are you trying to gather (values, calculations, transformations, grouping, etc.), in what format you need it, and any other constraints or restrictions that you may have.  Also, the best tool for processing or reading data, may not be the best tool for mo