Automated procedure to TL;DR text reports in batch

General aim:
How to pick out possible salient info from long tedious text reports without reading them line by line.
aka How to TL;DR in batch
Alternative to hurling the text into a web-based TagCloud

linux bash:
uses
pdftotext
pdftotext version 0.62.0
Copyright 2005-2017 The Poppler Developers - http://poppler.freedesktop.org
Copyright 1996-2011 Glyph & Cog, LLC

How to install:
sudo apt-get install poppler-utils

(o) Fetch the raw PDF data
Download all pdf files from Rep. Doug Collins' in batch
List and one line shell script is here:
https://pastebin.com/KMiAAUkE

(o) Convert the pdfs to flat text files
sed 's/^/pdftotext /g' list > t
chmod 755
./t

(o) Make list of txt files to process
sed 's/pdf/txt/g' list > list2

(o) Process those text files using bash shell script "check"
available here:
https://pastebin.com/H9LSEAFp

while IFS= read f; do echo $f; ./check "$f"; done < list2

(o) List all ".out" result files from the above and dig if necessary
more *.out

TL;DR:
What you get:
https://pastebin.com/qTbHPbVG