I have a batch of student answer sheets saved as PDFs. Each file contains short, text-based responses. I need a single, self-contained Python script that will: • Extract the text from every PDF in a given folder (use a reliable open-source library such as pdfplumber or PyPDF2). • Compare each response against a set of predefined keywords or phrases that I will supply in a separate JSON or CSV answer key. • Assign scores automatically based on keyword matches (simple rule-based grading is fine—no machine-learning needed). • Produce a concise summary report for every file, capturing the overall score and any missed keywords, then save the results to either CSV or JSON. Printing to console as an option is a plus. Acceptance criteria • Script runs from the command line with a clear README explaining required packages and usage. • Works on Python 3.10+ without proprietary dependencies. • Handles at least 100 PDFs in one run without crashing or leaking memory. • Summary report matches my sample output format exactly. If you have experience with text extraction, keyword scoring, and tidy reporting, this should be a quick, straightforward build.