Я пытаюсь использовать код здесь:
https://www.geeksforgeeks.org/python-reading-contents-of-pdf-using-ocr-optical-character-recognition/
# Import libraries
from PIL import Image
import pytesseract
import sys
from pdf2image import convert_from_path
import os
# Path of the pdf
PDF_file = "/Users/user1/Desktop/pdf1.pdf"
'''
Part #1 : Converting PDF to images
'''
# Store all the pages of the PDF in a variable
pages = convert_from_path(PDF_file, 500)
# Counter to store images of each page of PDF to image
image_counter = 1
# Iterate through all the pages stored above
for page in pages:
# Declaring filename for each page of PDF as JPG
# For each page, filename will be:
# PDF page 1 -> page_1.jpg
# PDF page 2 -> page_2.jpg
# PDF page 3 -> page_3.jpg
# ....
# PDF page n -> page_n.jpg
filename = "page_" + str(image_counter) + ".jpg"
# Save the image of the page in system
page.save(filename, 'JPEG')
# Increment the counter to update filename
image_counter = image_counter + 1
'''
Part #2 - Recognizing text from the images using OCR
'''
3
# Variable to get count of total number of pages
filelimit = image_counter - 1
# Creating a text file to write the output
outfile = "/Users/user1/Desktop/ocr/pdf1.txt"
# Open the file in append mode so that
# All contents of all images are added to the same file
f = open(outfile, "a")
# Iterate from 1 to total number of pages
for i in range(1, filelimit + 1):
# Set filename to recognize text from
# Again, these files will be:
# page_1.jpg
# page_2.jpg
# ....
# page_n.jpg
filename = "page_" + str(i) + ".jpg"
# Recognize the text as string in image using pytesserct
text = str(((pytesseract.image_to_string(Image.open(filename)))))
# The recognized text is stored in variable text
# Any string processing may be applied on text
# Here, basic formatting has been done:
# In many PDFs, at line ending, if a word can't
# be written fully, a 'hyphen' is added.
# The rest of the word is written in the next line
# Eg: This is a sample text this word here GeeksF-
# orGeeks is half on first line, remaining on next.
# To remove this, we replace every '-\n' to ''.
text = text.replace('-\n', '')
# Finally, write the processed text to the file.
f.write(text)
# Close the file after writing all the text.
f.close()
, но я получаю следующую ошибку:
Traceback (most recent call last):
File "/Users/user1/PycharmProjects/project1/venv/lib/python3.8/site-packages/pdf2image/pdf2image.py", line 409, in pdfinfo_from_path
proc = Popen(command, env=env, stdout=PIPE, stderr=PIPE)
File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/subprocess.py", line 854, in __init__
self._execute_child(args, executable, preexec_fn, close_fds,
File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/subprocess.py", line 1702, in _execute_child
raise child_exception_type(errno_num, err_msg, err_filename)
FileNotFoundError: [Errno 2] No such file or directory: 'pdfinfo'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Users/user1/PycharmProjects/project1/non_parseable.py", line 16, in <module>
pages = convert_from_path(PDF_file, 500)
File "/Users/user1/PycharmProjects/project1/venv/lib/python3.8/site-packages/pdf2image/pdf2image.py", line 89, in convert_from_path
page_count = pdfinfo_from_path(pdf_path, userpw, poppler_path=poppler_path)["Pages"]
File "/Users/user1/PycharmProjects/project1/venv/lib/python3.8/site-packages/pdf2image/pdf2image.py", line 430, in pdfinfo_from_path
raise PDFInfoNotInstalledError(
pdf2image.exceptions.PDFInfoNotInstalledError: Unable to get page count. Is poppler installed and in PATH?
Process finished with exit code 1
а идея как это исправить?