In this tutorial, we will use Python and pdfminer library to extract or read text content from a PDF file. The full source code of the PDFMiner Extract Text example is given below.
PDFMiner Extract Text Source Code
Install PDFMiner
pip install pdfminer
code.py
import io
from pdfminer.converter import TextConverter
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfpage import PDFPage
def extract_text_by_page(pdf_path):
with open(pdf_path, 'rb') as fh:
for page in PDFPage.get_pages(fh,
caching=True,
check_extractable=True):
resource_manager = PDFResourceManager()
fake_file_handle = io.StringIO()
converter = TextConverter(resource_manager,
fake_file_handle)
page_interpreter = PDFPageInterpreter(resource_manager,
converter)
page_interpreter.process_page(page)
text = fake_file_handle.getvalue()
yield text
# close open handles
converter.close()
fake_file_handle.close()
def extract_text(pdf_path):
for page in extract_text_by_page(pdf_path):
print(page)
print()
# Driver code
if __name__ == '__main__':
print(extract_text('###pathofpdffile###'))Run PDFMiner Extract Text Project
python code.py