import fitz
import numpy as np
from PIL import Image
import cv2
from tqdm import tqdm
import io

pdf_doc = fitz.open('/Users/linql/Desktop/11.pdf')
output_doc = fitz.open()
for orig_page in tqdm(pdf_doc):
    zoom = 2
    mat = fitz.Matrix(zoom, zoom)
    pix = orig_page.get_pixmap(matrix=mat)
    img = Image.frombytes("RGB",
                          [pix.width, pix.height],
                          pix.samples)
    img = img.convert('L')
    cleaned_page_array = cv2.adaptiveThreshold(np.array(img),
                                               255,
                                               # cv2.ADAPTIVE_THRESH_MEAN_C, #基于邻域均值的自适应阈值。
                                               cv2.ADAPTIVE_THRESH_GAUSSIAN_C,#基于邻域加权平均的自适应阈值。
                                               cv2.THRESH_BINARY,
                                               19,
                                               15)
    new_image = Image.fromarray(cleaned_page_array)
    fp = io.BytesIO()
    new_image.save(fp, "JPEG")
    page = output_doc.new_page(width=new_image.size[0], height=new_image.size[1])
    page.insert_image(page.rect, stream=fp.getvalue())

output_doc.save("output_file.pdf")