PyMuPDF 1.24.4 中文文档（一）（4）

import pymupdf
doc = pymupdf.open("a.pdf") # open a document
out = open("output.txt", "wb") # create a text output
for page in doc: # iterate the document pages
    text = page.get_text().encode("utf8") # get plain text (is in UTF-8)
    out.write(text) # write text of page
    out.write(bytes((12,))) # write page delimiter (form feed 0x0C)
out.close() 

tp = page.get_textpage_ocr()
text = page.get_text(textpage=tp) 

import pymupdf
doc = pymupdf.open("test.pdf") # open a document
for page_index in range(len(doc)): # iterate over pdf pages
    page = doc[page_index] # get the page
    image_list = page.get_images()
    # print the number of images found on the page
    if image_list:
        print(f"Found {len(image_list)} images on page {page_index}")
    else:
        print("No images found on page", page_index)
    for image_index, img in enumerate(image_list, start=1): # enumerate the image list
        xref = img[0] # get the XREF of the image
        pix = pymupdf.Pixmap(doc, xref) # create a Pixmap
        if pix.n - pix.alpha > 3: # CMYK: convert to RGB first
            pix = pymupdf.Pixmap(pymupdf.csRGB, pix)
        pix.save("page_%s-image_%s.png" % (page_index, image_index)) # save the image as png
        pix = None 

doc = pymupdf.open("some.file")
page = doc[0]
paths = page.get_drawings() 

import pymupdf
doc_a = pymupdf.open("a.pdf") # open the 1st document
doc_b = pymupdf.open("b.pdf") # open the 2nd document
doc_a.insert_pdf(doc_b) # merge the docs
doc_a.save("a+b.pdf") # save the merged document with a new filename 

import pymupdf
doc_a = pymupdf.open("a.pdf") # open the 1st document
doc_b = pymupdf.open("b.svg") # open the 2nd document
doc_a.insert_file(doc_b) # merge the docs
doc_a.save("a+b.pdf") # save the merged document with a new filename 

import pymupdf
doc_a = pymupdf.open("a.pdf") # open the 1st document
doc_b = pymupdf.open("b.svg") # open the 2nd document
doc_a.insert_file(doc_b) # merge the docs
doc_a.save("a+b.pdf") # save the merged document with a new filename 

import pymupdf
doc = pymupdf.open("document.pdf") # open a document
for page_index in range(len(doc)): # iterate over pdf pages
    page = doc[page_index] # get the page
    # insert an image watermark from a file name to fit the page bounds
    page.insert_image(page.bound(),filename="watermark.png", overlay=False)
doc.save("watermarked-document.pdf") # save the document with a new filename 

import pymupdf
doc = pymupdf.open("document.pdf") # open a document
for page_index in range(len(doc)): # iterate over pdf pages
    page = doc[page_index] # get the page
    # insert an image logo from a file name at the top left of the document
    page.insert_image(pymupdf.Rect(0,0,50,50),filename="my-logo.png")
doc.save("logo-document.pdf") # save the document with a new filename 

import pymupdf
doc = pymupdf.open("test.pdf") # open document
page = doc[0] # get the 1st page of the document
page.set_rotation(90) # rotate the page
doc.save("rotated-page-1.pdf") 

import pymupdf
doc = pymupdf.open("test.pdf") # open document
page = doc[0] # get the 1st page of the document
page.set_cropbox(pymupdf.Rect(100, 100, 400, 400)) # set a cropbox for the page
doc.save("cropped-page-1.pdf") 

import pymupdf
doc = pymupdf.open("test.pdf") # open main document
attachment = pymupdf.open("my-attachment.pdf") # open document you want to attach
page = doc[0] # get the 1st page of the document
point = pymupdf.Point(100, 100) # create the point where you want to add the attachment
attachment_data = attachment.tobytes() # get the document byte data as a buffer
# add the file annotation with the point, data and the file name
file_annotation = page.add_file_annot(point, attachment_data, "attachment.pdf")
doc.save("document-with-attachment.pdf") # save the document 

import pymupdf
doc = pymupdf.open("test.pdf") # open main document
embedded_doc = pymupdf.open("my-embed.pdf") # open document you want to embed
embedded_data = embedded_doc.tobytes() # get the document byte data as a buffer
# embed with the file name and the data
doc.embfile_add("my-embedded_file.pdf", embedded_data)
doc.save("document-with-embed.pdf") # save the document 

import pymupdf
doc = pymupdf.open("test.pdf") # open a document
doc.delete_page(0) # delete the 1st page of the document
doc.save("test-deleted-page-one.pdf") # save the document 

import pymupdf
doc = pymupdf.open("test.pdf") # open a document
doc.delete_pages(from_page=9, to_page=14) # delete a page range from the document
doc.save("test-deleted-pages.pdf") # save the document 

import pymupdf
doc = pymupdf.open("test.pdf") # open a document
doc.move_page(1,0) # move the 2nd page of the document to the start of the document
doc.save("test-page-moved.pdf") # save the document