PyMuPDF 1.24.4 中文文档（一）（5）

import pymupdf
doc = pymupdf.open("test.pdf") # open a document
doc.copy_page(0) # copy the 1st page and puts it at the end of the document
doc.save("test-page-copied.pdf") # save the document 

import pymupdf
doc = pymupdf.open("test.pdf") # open a document
doc.select([0, 1]) # select the 1st & 2nd page of the document
doc.save("just-page-one-and-two.pdf") # save the document 

doc.select([1, 1, 1, 5, 4, 9, 9, 9, 0, 2, 2, 2]) 

p_even = [p in range(doc.page_count) if p % 2 == 0]
p_odd  = [p in range(doc.page_count) if p % 2 == 1] 

doc.select(p_even) # only the even pages left over
doc.save("even.pdf") # save the "even" PDF
doc.close() # recycle the file
doc = pymupdf.open(doc.name) # re-open
doc.select(p_odd) # and do the same with the odd pages
doc.save("odd.pdf") 

lastPage = doc.page_count - 1
for i in range(lastPage):
    doc.move_page(lastPage, i) # move current last page to the front 

page_count = len(doc)
for i in range(page_count):
    doc.copy_page(i) # copy this page to after last page 

import pymupdf
doc = pymupdf.open(...) # some new or existing PDF document
page = doc.new_page(-1, # insertion point: end of document
                    width = 595, # page dimension: A4 portrait
                    height = 842)
doc.save("doc-with-new-blank-page.pdf") # save the document 

w, h = pymupdf.paper_size("letter-l")  # 'Letter' landscape
page = doc.new_page(width = w, height = h) 

doc = pymupdf.open()
doc.new_page()
doc.save("A4.pdf") 

import pymupdf
doc = pymupdf.open(...)  # some new or existing PDF document
n = doc.insert_page(-1, # default insertion point
                    text = "The quick brown fox jumped over the lazy dog",
                    fontsize = 11,
                    width = 595,
                    height = 842,
                    fontname = "Helvetica", # default font
                    fontfile = None, # any font file name
                    color = (0, 0, 0)) # text color (RGB) 

import pymupdf
src = pymupdf.open("test.pdf")
doc = pymupdf.open()  # empty output PDF
for spage in src:  # for each page in input
    r = spage.rect  # input page rectangle
    d = pymupdf.Rect(spage.cropbox_position,  # CropBox displacement if not
                  spage.cropbox_position)  # starting at (0, 0)
    #--------------------------------------------------------------------------
    # example: cut input page into 2 x 2 parts
    #--------------------------------------------------------------------------
    r1 = r / 2  # top left rect
    r2 = r1 + (r1.width, 0, r1.width, 0)  # top right rect
    r3 = r1 + (0, r1.height, 0, r1.height)  # bottom left rect
    r4 = pymupdf.Rect(r1.br, r.br)  # bottom right rect
    rect_list = [r1, r2, r3, r4]  # put them in a list
    for rx in rect_list:  # run thru rect list
        rx += d  # add the CropBox displacement
        page = doc.new_page(-1,  # new output page with rx dimensions
                           width = rx.width,
                           height = rx.height)
        page.show_pdf_page(
                page.rect,  # fill all new page with the image
                src,  # input document
                spage.number,  # input page number
                clip = rx,  # which part to use of input page
            )
# that's it, save output file
doc.save("poster-" + src.name,
         garbage=3,  # eliminate duplicate objects
         deflate=True,  # compress stuff where possible
) 

import pymupdf
src = pymupdf.open("test.pdf")
doc = pymupdf.open()  # empty output PDF
width, height = pymupdf.paper_size("a4")  # A4 portrait output page format
r = pymupdf.Rect(0, 0, width, height)
# define the 4 rectangles per page
r1 = r / 2  # top left rect
r2 = r1 + (r1.width, 0, r1.width, 0)  # top right
r3 = r1 + (0, r1.height, 0, r1.height)  # bottom left
r4 = pymupdf.Rect(r1.br, r.br)  # bottom right
# put them in a list
r_tab = [r1, r2, r3, r4]
# now copy input pages to output
for spage in src:
    if spage.number % 4 == 0:  # create new output page
        page = doc.new_page(-1,
                      width = width,
                      height = height)
    # insert input page into the correct rectangle
    page.show_pdf_page(r_tab[spage.number % 4],  # select output rect
                     src,  # input document
                     spage.number)  # input page number
# by all means, save new file using garbage collection and compression
doc.save("4up.pdf", garbage=3, deflate=True) 

import pymupdf
text = "some secret information" # keep this data secret
perm = int(
    pymupdf.PDF_PERM_ACCESSIBILITY # always use this
    | pymupdf.PDF_PERM_PRINT # permit printing
    | pymupdf.PDF_PERM_COPY # permit copying
    | pymupdf.PDF_PERM_ANNOTATE # permit annotations
)
owner_pass = "owner" # owner password
user_pass = "user" # user password
encrypt_meth = pymupdf.PDF_ENCRYPT_AES_256 # strongest algorithm
doc = pymupdf.open() # empty pdf
page = doc.new_page() # empty page
page.insert_text((50, 72), text) # insert the data
doc.save(
    "secret.pdf",
    encryption=encrypt_meth, # set the encryption method
    owner_pw=owner_pass, # set the owner password
    user_pw=user_pass, # set the user password
    permissions=perm, # set permissions
) 

import pymupdf
from pprint import pprint
doc = pymupdf.open("test.pdf") # open document
page = doc[0] # get the 1st page of the document
tabs = page.find_tables() # locate and extract any tables on page
print(f"{len(tabs.tables)} found on {page}") # display number of found tables
if tabs.tables:  # at least one table found?
   pprint(tabs[0].extract())  # print content of first table 

import pymupdf
for page in doc: # iterate the document pages
    link = page.first_link  # a `Link` object or `None`
    while link: # iterate over the links on page
        # do something with the link, then:
        link = link.next # get next link, last one has `None` in its `next` 

import pymupdf
for page in doc:
    for annot in page.annots():
        print(f'Annotation on page: {page.number} with type: {annot.type} and rect: {annot.rect}') 

import pymupdf
# Open the PDF document
doc = pymupdf.open('test.pdf')
# Iterate over each page of the document
for page in doc:
    # Find all instances of "Jane Doe" on the current page
    instances = page.search_for("Jane Doe")
    # Redact each instance of "Jane Doe" on the current page
    for inst in instances:
        page.add_redact_annot(inst)
    # Apply the redactions to the current page
    page.apply_redactions()
# Save the modified document
doc.save('redacted_document.pdf')
# Close the document
doc.close() 

import pymupdf
# Open the PDF document
doc = pymupdf.open('test.pdf')
# Get the first page
page = doc[0]
# Add an area to redact
rect = [0,0,200,200]
# Add a redacction annotation which will have a red fill color
page.add_redact_annot(rect, fill=(1,0,0))
# Apply the redactions to the current page, but ignore vector graphics
page.apply_redactions(graphics=0)
# Save the modified document
doc.save('redactied_document.pdf')
# Close the document
doc.close()