def ocr_image(file_name: str):
"""Ocr an image"""
img_ = wand_img(filename=file_name, resolution=300)
wnd_img = wand_img(image=img_).make_blob("jpg")
im = Image.open(io.BytesIO(wnd_img))
text = pytesseract.image_to_string(im, lang='eng')
print(text)
def ocr_image_file(self, current_img_file: str):
"""ocr the extracted pdf image files"""
try:
if os.path.isdir(self.write_path):
img_ = wand_img(filename=os.path.join(self.write_path,
current_img_file),
resolution=300)
wnd_img = wand_img(image=img_).make_blob(format='jpeg')
print("In ocr_image_file")
im = Image.open(io.BytesIO(wnd_img))
# extract and clean the text
text = pytesseract.image_to_string(im, lang='eng')
text = ''.join(text) \
.translate(str.maketrans('', '', string.punctuation)) \
.lower()
text = SPACES.sub(" ", text)
# text = NEWLINE.sub("", text)
# text = TABS.sub("", text)
# text = ''.join([i if ord(i) < 128 else ' ' for i in text])
return text
except Exception as e:
print(e)
print(
f"An error has occurred while trying to ocr img file: {current_img_file}"
)
def make_gif_app_caller(frame, effect):
frame.transform(resize='400x400>')
proc = subprocess.Popen(["gif", effect],
stdin=subprocess.PIPE,
stdout=subprocess.PIPE)
out = proc.communicate(wand_img(frame).make_blob("png"))[0]
result = wand_img(blob=out)
return result
def make_imgtext(frame, text):
frame.transform(resize='400x400>')
proc = subprocess.Popen(["gif", "text", text],
stdin=subprocess.PIPE,
stdout=subprocess.PIPE)
out = proc.communicate(wand_img(frame).make_blob("png"))[0]
result = wand_img(blob=out)
return result
def ocr_image_file(self, img_file_path: str):
try:
if os.path.isdir(img_file_path):
for f in os.listdir(img_file_path):
print(f'Extracting text from file: {f}')
try:
img_ = wand_img(filename=os.path.join(
img_file_path, f),
resolution=300)
wnd_img = wand_img(image=img_).make_blob(
os.path.splitext(f)[-1].lstrip('.'))
im = Image.open(io.BytesIO(wnd_img))
text = pytesseract.image_to_string(im, lang='eng')
self.extracted_pdfs.append(text)
except:
print(f'An error occurred while ocring image: {f}')
else:
raise OSError(f'OSError: Path, {img_file_path} not found.')
except OSError as e:
print(e)
def ocr_image_file(self, img_file_path: str):
try:
if os.path.isdir(img_file_path):
for f in os.listdir(img_file_path):
self.pdf_img_content.append(
os.path.splitext(os.path.split(img_file_path)[1])[0])
pdf_file_number = os.path.splitext(f)[0][-3]
print(f"PDF FILE NUMBER: {pdf_file_number}")
try:
if self.img_format is 'tiff':
tiff_img = os.path.join(img_file_path, f)
img_ = Image.open(tiff_img).convert("RGBA")
# extract and clean the text
text = pytesseract.image_to_string(img_,
lang='eng')
text = ''.join(text) \
.translate(str.maketrans('', '', string.punctuation)) \
.lower()
text = SPACES.sub(" ", text)
text = NEWLINE.sub("", text)
text = TABS.sub("", text)
# attempt to remove special characters
text = ''.join(
[i if ord(i) < 128 else ' ' for i in text])
# update pdf dictionaries
self.extracted_pdfs.append(text)
self.pdf_img_content.append(text)
else:
img_ = wand_img(filename=os.path.join(
img_file_path, f),
resolution=300)
wnd_img = wand_img(image=img_).make_blob(
os.path.splitext(f)[-1].lstrip('.'))
im = Image.open(io.BytesIO(wnd_img))
# extract and clean the text
text = pytesseract.image_to_string(im, lang='eng')
text = ' '.join(text) \
.translate(str.maketrans('', '', string.punctuation)) \
.lower()
text = SPACES.sub("", text)
text = NEWLINE.sub("", text)
text = TABS.sub("", text)
# attempt to remove special characters
text = ''.join(
[i if ord(i) < 128 else ' ' for i in text])
# update pdf dictionaries
self.extracted_pdfs.append(text)
self.pdf_img_content.append(text)
except:
print(f'An error occurred while ocring image: {f}')
else:
raise OSError(f'OSError: Path, {img_file_path} not found.')
except OSError as e:
print(e)