“Extraia imagens do PDF” Respostas de código

Extrair imagem do PDF Python

import PyPDF2

from PIL import Image

if __name__ == '__main__':
    input1 = PyPDF2.PdfFileReader(open("input.pdf", "rb"))
    page0 = input1.getPage(0)
    xObject = page0['/Resources']['/XObject'].getObject()

    for obj in xObject:
        if xObject[obj]['/Subtype'] == '/Image':
            size = (xObject[obj]['/Width'], xObject[obj]['/Height'])
            data = xObject[obj].getData()
            if xObject[obj]['/ColorSpace'] == '/DeviceRGB':
                mode = "RGB"
            else:
                mode = "P"

            if xObject[obj]['/Filter'] == '/FlateDecode':
                img = Image.frombytes(mode, size, data)
                img.save(obj[1:] + ".png")
            elif xObject[obj]['/Filter'] == '/DCTDecode':
                img = open(obj[1:] + ".jpg", "wb")
                img.write(data)
                img.close()
            elif xObject[obj]['/Filter'] == '/JPXDecode':
                img = open(obj[1:] + ".jp2", "wb")
                img.write(data)
                img.close()
Repulsive Rattlesnake

# Extraia imagens do arquivo PDF

# extract images from pdf file
import fitz
doc = fitz.open("file.pdf")
for i in range(len(doc)):
    for img in doc.getPageImageList(i):
        xref = img[0]
        pix = fitz.Pixmap(doc, xref)
        if pix.n < 5:       # this is GRAY or RGB
            pix.writePNG("p%s-%s.png" % (i, xref))
        else:               # CMYK: convert to RGB first
            pix1 = fitz.Pixmap(fitz.csRGB, pix)
            pix1.writePNG("p%s-%s.png" % (i, xref))
            pix1 = None
        pix = None
Impossible Impala

Extraia imagens do PDF

# STEP 1
# import libraries
import fitz
import io
from PIL import Image
  
# STEP 2
# file path you want to extract images from
file = "/content/pdf_file.pdf"
  
# open the file
pdf_file = fitz.open(file)
  
# STEP 3
# iterate over PDF pages
for page_index in range(len(pdf_file)):
    
    # get the page itself
    page = pdf_file[page_index]
    image_list = page.getImageList()
      
    # printing number of images found in this page
    if image_list:
        print(f"[+] Found a total of {len(image_list)} images in page {page_index}")
    else:
        print("[!] No images found on page", page_index)
    for image_index, img in enumerate(page.getImageList(), start=1):
        
        # get the XREF of the image
        xref = img[0]
          
        # extract the image bytes
        base_image = pdf_file.extractImage(xref)
        image_bytes = base_image["image"]
          
        # get the image extension
        image_ext = base_image["ext"]
joel hao

Respostas semelhantes a “Extraia imagens do PDF”

Perguntas semelhantes a “Extraia imagens do PDF”

Mais respostas relacionadas para “Extraia imagens do PDF” em Python

Procure respostas de código populares por idioma

Procurar outros idiomas de código