Parse your PDF and DOC format documents into fields and tables for cheap. You know you want to 
I am offering automated outsourced extraction of text fields and table contents from text based documents, e.g. the filing forms from financial industry, healthcare related paperwork and similar. Thanks to my nifty proprietary parsing framework I can make parsers for new document formats fairly quickly, and ambiguity problems associated with missing fields in tables are minimized.
I will only work with not-very-confidential documents because I don’t currently distribute my framework. So if your stuff is sufficiently confidential to require you to run the parser on your machine instead of transmitting it to me for parsing, unfortunately I cannot be of service.