def main(directory, file_name,out_dir, file_type='.pdf', dpi=500, verbose=True):
"""
Walks through all the pages in a file, converts to image, and uses OCR to
convert image to .txt files. It then deletes the image files and merges the
individual page .txt files. After it deletes the individual page .txt files
Params:
directory: str where the files are stored
file_name: str name of file
out_dir: str the directory where the text files are going
file_type:str default '.pdf'
dpi: int dots per inch
verbose: bool default is True
"""
da = DirectoryAssistor()
out_dir = out_dir
image_list = convert_to_img(directory=directory, file_name=file_name)
page_lst = []
with concurrent.futures.ProcessPoolExecutor(max_workers=6) as executor:
for img_path,out_file in zip(image_list,executor.map(ocr,image_list)):
print(img_path.split("\\")[-1],',',out_file,', processed')
page_lst.append(out_file)
for img in image_list:
da.delete_files(img)
merge_pages(page_lst=page_lst, out_dir=out_dir, file_name=file_name)
for page in page_lst:
da.delete_files(out_dir+page)
class ImageConverter():
def __init__(self, directory):
self.directory = directory
self.ds = DirectoryAssistor()
def convert_image(self, file_name, file_type='.pdf', dpi=500):
'''
Converts a file of type file_type to .txt using OCR
Params
file_name: string that is the name of the file that needs to be read in
file_type: str that is the type of file being read in
dpi: int that is the dots per inch of the file being read in
'''
pages = convert_from_path(self.directory + file_name, dpi=dpi)
image_counter = 1
image_names = []
for page in pages:
image_name = 'page_' + str(image_counter) + '.jpg'
image_names.append(image_name)
page.save(image_name, 'JPEG')
image_counter += 1
new_file_name = file_name.replace(file_type, '.txt')
filelimit = image_counter - 1
outfile = self.directory + new_file_name
f = open(outfile, 'a')
for i in range(1, filelimit + 1):
image_name = "page_" + str(i) + ".jpg"
text = str(((pytesseract.image_to_string(Image.open(image_name)))))
text = text.replace('-\n', '')
f.write(text)
f.close()
for img in image_names:
self.ds.delete_files(img)
self.ds.delete_files(directory + file_name)
def convert_txt_to_doc(self, text_file):
'''
Converts a .txt document to a .doc format
Params
text_file: name of .txt file stored in the directory for the object
'''
document = Document()
new_name = text_file.replace('.txt', '')
document.add_heading(new_name, 0)
myfile = open(self.directory + text_file).read()
myfile = re.sub(r'[^\x00-\x7F]+|\x0c', ' ', myfile)
p = document.add_paragraph(myfile)
document.save(directory + new_name + '.doc')