without_line_breaks = a_string.replace("
", " ")
s_lines = 'one
two
three'
print(s_lines)
# one
# two
# three
print(s_lines.replace('
', '-'))
# one-two-three
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('
', '
')
#####################################
# Do something with the PDF
#####################################
print (pdf)