Created
March 19, 2015 17:22
-
-
Save kyrre/c19f94f8662194be1c3d to your computer and use it in GitHub Desktop.
convert pdf files to text
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def pdf_to_str(filename, resolution=600): | |
try: | |
with wand.image.Image(filename=filename, resolution=resolution) as img: | |
img.type = 'grayscale' | |
img.format = 'jpeg' | |
img.compression_quality = 100 | |
directory = tempfile.mkdtemp() | |
output_path = os.path.join(directory, filename[:-4] + '.jpg') | |
with img.convert('jpeg') as converted: | |
converted.save(filename=output_path) | |
text = ocr_directory(directory) | |
shutil.rmtree(directory) | |
return text | |
except: | |
return None | |
def img_to_str(img_path): | |
try: | |
return pytesseract.image_to_string(Image.open(img_path)) | |
except: | |
return None | |
def ocr_directory(directory): | |
filenames = glob.glob(os.path.join(directory, '*')) | |
return '\n'.join((img_to_str(image) for image in filenames)) | |
print pdf_to_str('all.pdf') | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment