Spaces:
Running
Running
File size: 3,445 Bytes
f8afc9b e709d2a f8afc9b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
import fitz
from PIL import Image
class doc_processing:
def __init__(self, name, id_type, doc_type, f_path):
self.name = name
self.id_type = id_type
self.doc_type = doc_type
self.f_path = f_path
# self.o_path = o_path
def pdf_to_image_scale(self):
pdf_document = fitz.open(self.f_path)
if self.id_type == "gst":
page_num = 2
else:
page_num = 0
page = pdf_document.load_page(page_num)
pix = page.get_pixmap() # Render page as a pixmap (image)
# Convert pixmap to PIL Image
image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
original_width, original_height = image.size
print("original_width",original_width)
print("original_height",original_height)
new_width = (1000 / original_width) * original_width
new_height = (1000 / original_height) * original_height
print("new_width",new_width)
print("new_height",new_height)
# new_width =
# new_height =
image.resize((int(new_width), int(new_height)), Image.Resampling.LANCZOS)
output_path = "processed_images/{}/{}.jpeg".format(self.id_type,self.name)
image.save(output_path)
return {"success":200,"output_p":output_path}
def scale_img(self):
print("path of file",self.f_path)
image = Image.open(self.f_path).convert("RGB")
original_width, original_height = image.size
print("original_width",original_width)
print("original_height",original_height)
new_width = (1000 / original_width) * original_width
new_height = (1000 / original_height) * original_height
print("new_width",new_width)
print("new_height",new_height)
# new_width =
# new_height =
image.resize((int(new_width), int(new_height)), Image.Resampling.LANCZOS)
output_path = "processed_images/{}/{}.jpeg".format(self.id_type,self.name)
image.save(output_path)
return {"success":200,"output_p":output_path}
def process(self):
if self.doc_type == "pdf":
response = self.pdf_to_image_scale()
else:
response = self.scale_img()
return response
# files = {
# "aadhar_file": "/home/javmulla/model_one/test_images_aadhar/test_two.jpg",
# "pan_file": "/home/javmulla/model_one/test_images_pan/6ea33087.jpeg",
# "cheque_file": "/home/javmulla/model_one/test_images_cheque/0f81678a.jpeg",
# "gst_file": "/home/javmulla/model_one/test_images_gst/0a52fbcb_page3_image_0.jpg"
# }
# files = {
# "aadhar_file": "/home/javmulla/model_one/test_images_aadhar/test_two.jpg",
# "pan_file": "/home/javmulla/model_one/test_images_pan/6ea33087.jpeg",
# "cheque_file": "/home/javmulla/model_one/test_images_cheque/0f81678a.jpeg",
# "gst_file": "test_Images_folder/gst/e.pdf"
# }
# for key, value in files.items():
# name = value.split("/")[-1].split(".")[0]
# id_type = key.split("_")[0]
# doc_type = value.split("/")[-1].split(".")[1]
# f_path = value
# preprocessing = doc_processing(name,id_type,doc_type,f_path)
# response = preprocessing.process()
# print("response",response)
# id_type, doc_type, f_path
|