Use this command to obtaine txt version from pdf.. 47 is first page where the transaction begins, It will create a text file named celsius.txt.. It takes around 10 minutes for conversion to complete.
pdftotext -layout -f 47 -l 14384 celsius.pdf
For MAC/Windows download and install poppler
OR
Uncompress celsius.zip file: It contains pdf data in text format that is used for analysis. Txt file is of approximately 1 GB.