xxxxxxxxxx
#Just print the text and copy from console
print(f"A \n B \n C")
#output:
# A
# B
# C
xxxxxxxxxx
from tika import parser
filename = 'myfile.pdf'
# Parse the PDF
parsedPDF = parser.from_file(filename)
# Extract the text content from the parsed PDF
pdf = parsedPDF["content"]
# Convert double newlines into single newlines
pdf = pdf.replace('\n\n', '\n')
#####################################
# Do something with the PDF
#####################################
print (pdf)
xxxxxxxxxx
>>> import re
>>> re.sub('\r?\n', ' $ ', 'a\r\nb\r\nc')
'a $ b $ c'
>>> re.sub('\r?\n', ' $ ', 'a\nb\nc')
'a $ b $ c'