Conversion Tool Offline

Need to build a conversion tool which extract the data from PDF as it is and convert into a well formatted HTML files with a button click on a bulk data. While conversion following things must be considered: -100% automation required -Emphasis to be maintained as it is. -Indentation/ Block-quoting to be maintained in its hierarchy -Multiple Entity Extraction and placement in right tags -Standard HTML formatting based on Rules -Removal of all junk characters and unwanted data Note : Patterns in the files may differ from each other so program must be trained enough to identify the patterns and act accordingly.