Answers for "python extract data from pdf to text file"

pdf to text python

#!pip install tabula-py
import tabula
#read all table data
df = tabula.read_pdf("sample.pdf",pages=[1,2])
df[1]

#tabula.convert_into("sample.pdf", "sample.csv", output_format="csv")

extract text from pdf python

# using PyMuPDF
import sys, fitz
fname = sys.argv[1]  # get document filename
doc = fitz.open(fname)  # open document
out = open(fname + ".txt", "wb")  # open text output
for page in doc:  # iterate the document pages
    text = page.get_text().encode("utf8")  # get plain text (is in UTF-8)
    out.write(text)  # write text of page
    out.write(bytes((12,)))  # write page delimiter (form feed 0x0C)
out.close()