PyMuPDF 1.24.4 中文文档（三）（1）

import sys, pymupdf  # import the bindings
fname = sys.argv[1]  # get filename from command line
doc = pymupdf.open(fname)  # open document
for page in doc:  # iterate through the pages
    pix = page.get_pixmap()  # render page to an image
    pix.save("page-%i.png" % page.number)  # store image as a PNG 

zoom_x = 2.0  # horizontal zoom
zoom_y = 2.0  # vertical zoom
mat = pymupdf.Matrix(zoom_x, zoom_y)  # zoom factor 2 in each dimension
pix = page.get_pixmap(matrix=mat)  # use 'mat' instead of the identity matrix 

mat = pymupdf.Matrix(2, 2)  # zoom factor 2 in each direction
rect = page.rect  # the page rectangle
mp = (rect.tl + rect.br) / 2  # its middle point, becomes top-left of clip
clip = pymupdf.Rect(mp, rect.br)  # the area we want
pix = page.get_pixmap(matrix=mat, clip=clip) 

# WIDTH: width of the GUI window
# HEIGHT: height of the GUI window
# clip: a subrectangle of the document page
# compare width/height ratios of image and window
if clip.width / clip.height < WIDTH / HEIGHT:
    # clip is narrower: zoom to window HEIGHT
    zoom = HEIGHT / clip.height
else:  # clip is broader: zoom to window WIDTH
    zoom = WIDTH / clip.width
mat = pymupdf.Matrix(zoom, zoom)
pix = page.get_pixmap(matrix=mat, clip=clip) 

width = WIDTH / zoom
height = HEIGHT / zoom
clip = pymupdf.Rect(tl, tl.x + width, tl.y + height)
# ensure we still are inside the page
clip &= page.rect
mat = pymupdf.Matrix(zoom, zoom)
pix = pymupdf.Pixmap(matrix=mat, clip=clip) 

>>> pdfbytes = doc.convert_to_pdf()  # this a bytes object
>>> pdf = pymupdf.open("pdf", pdfbytes)  # open it as a PDF document
>>> # now use 'pdf' like any PDF document 

>>> d = page.get_text("dict")
>>> blocks = d["blocks"]  # the list of block dictionaries
>>> imgblocks = [b for b in blocks if b["type"] == 1]
>>> pprint(imgblocks[0])
{'bbox': (100.0, 135.8769989013672, 300.0, 364.1230163574219),
 'bpc': 8,
 'colorspace': 3,
 'ext': 'jpeg',
 'height': 501,
 'image': b'\xff\xd8\xff\xe0\x00\x10JFIF\...',  # CAUTION: LARGE!
 'size': 80518,
 'transform': (200.0, 0.0, -0.0, 228.2460174560547, 100.0, 135.8769989013672),
 'type': 1,
 'width': 439,
 'xres': 96,
 'yres': 96} 

>>> pix1 = pymupdf.Pixmap(doc.extract_image(xref)["image"])    # (1) pixmap of image w/o alpha
>>> mask = pymupdf.Pixmap(doc.extract_image(smask)["image"])   # (2) mask pixmap
>>> pix = pymupdf.Pixmap(pix1, mask)                           # (3) copy of pix1, image mask added 

import os, pymupdf
import PySimpleGUI as psg  # for showing a progress bar
doc = pymupdf.open()  # PDF with the pictures
imgdir = "D:/2012_10_05"  # where the pics are
imglist = os.listdir(imgdir)  # list of them
imgcount = len(imglist)  # pic count
for i, f in enumerate(imglist):
    img = pymupdf.open(os.path.join(imgdir, f))  # open pic as document
    rect = img[0].rect  # pic dimension
    pdfbytes = img.convert_to_pdf()  # make a PDF stream
    img.close()  # no longer needed
    imgPDF = pymupdf.open("pdf", pdfbytes)  # open stream as PDF
    page = doc.new_page(width = rect.width,  # new page with ...
                       height = rect.height)  # pic dimension
    page.show_pdf_page(rect, imgPDF, 0)  # image fills the page
    psg.EasyProgressMeter("Import Images",  # show our progress
        i+1, imgcount)
doc.save("all-my-pics.pdf") 

import os, pymupdf
import PySimpleGUI as psg  # for showing progress bar
doc = pymupdf.open()  # PDF with the pictures
imgdir = "D:/2012_10_05"  # where my files are
imglist = os.listdir(imgdir)  # list of pictures
imgcount = len(imglist)  # pic count
imglist.sort()  # nicely sort them
for i, f in enumerate(imglist):
    img = open(os.path.join(imgdir,f), "rb").read()  # make pic stream
    doc.embfile_add(img, f, filename=f,  # and embed it
                        ufilename=f, desc=f)
    psg.EasyProgressMeter("Embedding Files",  # show our progress
        i+1, imgcount)
page = doc.new_page()  # at least 1 page is needed
doc.save("all-my-pics-embedded.pdf") 

pix = pymupdf.Pixmap("input.xxx")  # any supported input format
pix.save("output.yyy")  # any supported output format 

pix = pymupdf.Pixmap("myfamily.jpg")
pix.save("myfamily.psd") 

import tkinter as tk
pix = pymupdf.Pixmap("input.jpg")  # or any RGB / no-alpha image
tkimg = tk.PhotoImage(data=pix.tobytes("ppm")) 

import tkinter as tk
pix = pymupdf.Pixmap("input.png")  # may have an alpha channel
if pix.alpha:  # we have an alpha channel!
    pix = pymupdf.Pixmap(pix, 0)  # remove it
tkimg = tk.PhotoImage(data=pix.tobytes("ppm")) 

import pymupdf
src = pymupdf.Pixmap("img-7edges.png")      # create pixmap from a picture
col = 3                                  # tiles per row
lin = 4                                  # tiles per column
tar_w = src.width * col                  # width of target
tar_h = src.height * lin                 # height of target
# create target pixmap
tar_pix = pymupdf.Pixmap(src.colorspace, (0, 0, tar_w, tar_h), src.alpha)
# now fill target with the tiles
for i in range(col):
    for j in range(lin):
        src.set_origin(src.width * i, src.height * j)
        tar_pix.copy(src, src.irect) # copy input to new loc
tar_pix.save("tar.png") 

import pymupdf, time
if not list(map(int, pymupdf.VersionBind.split("."))) >= [1, 14, 8]:
    raise SystemExit("need PyMuPDF v1.14.8 for this script")
n = 6                             # depth (precision)
d = 3**n                          # edge length
t0 = time.perf_counter()
ir = (0, 0, d, d)                 # the pixmap rectangle
pm = pymupdf.Pixmap(pymupdf.csRGB, ir, False)
pm.set_rect(pm.irect, (255,255,0)) # fill it with some background color
color = (0, 0, 255)               # color to fill the punch holes
# alternatively, define a 'fill' pixmap for the punch holes
# this could be anything, e.g. some photo image ...
fill = pymupdf.Pixmap(pymupdf.csRGB, ir, False) # same size as 'pm'
fill.set_rect(fill.irect, (0, 255, 255))   # put some color in
def punch(x, y, step):
  """Recursively "punch a hole" in the central square of a pixmap.
 Arguments are top-left coords and the step width.
 Some alternative punching methods are commented out.
 """
    s = step // 3                 # the new step
    # iterate through the 9 sub-squares
    # the central one will be filled with the color
    for i in range(3):
        for j in range(3):
            if i != j or i != 1:  # this is not the central cube
                if s >= 3:        # recursing needed?
                    punch(x+i*s, y+j*s, s)       # recurse
            else:                 # punching alternatives are:
                pm.set_rect((x+s, y+s, x+2*s, y+2*s), color)     # fill with a color
                #pm.copy(fill, (x+s, y+s, x+2*s, y+2*s))  # copy from fill
                #pm.invert_irect((x+s, y+s, x+2*s, y+2*s))       # invert colors
    return
#==============================================================================
# main program
#==============================================================================
# now start punching holes into the pixmap
punch(0, 0, d)
t1 = time.perf_counter()
pm.save("sierpinski-punch.png")
t2 = time.perf_counter()
print ("%g sec to create / fill the pixmap" % round(t1-t0,3))
print ("%g sec to save the image" % round(t2-t1,3)) 

import numpy as np
import pymupdf
#==============================================================================
# create a fun-colored width * height PNG with pymupdf and numpy
#==============================================================================
height = 150
width  = 100
bild = np.ndarray((height, width, 3), dtype=np.uint8)
for i in range(height):
    for j in range(width):
        # one pixel (some fun coloring)
        bild[i, j] = [(i+j)%256, i%256, j%256]
samples = bytearray(bild.tostring())    # get plain pixel data from numpy array
pix = pymupdf.Pixmap(pymupdf.csRGB, width, height, samples, alpha=False)
pix.save("test.png") 

page.insert_image(
    rect,                  # where to place the image (rect-like)
    filename=None,         # image in a file
    stream=None,           # image in memory (bytes)
    pixmap=None,           # image from pixmap
    mask=None,             # specify alpha channel separately
    rotate=0,              # rotate (int, multiple of 90)
    xref=0,                # re-use existing image
    oc=0,                  # control visibility via OCG / OCMD
    keep_proportion=True,  # keep aspect ratio
    overlay=True,          # put in foreground
) 

page.show_pdf_page(
    rect,                  # where to place the image (rect-like)
    src,                   # source PDF
    pno=0,                 # page number in source PDF
    clip=None,             # only display this area (rect-like)
    rotate=0,              # rotate (float, any value)
    oc=0,                  # control visibility via OCG / OCMD
    keep_proportion=True,  # keep aspect ratio
    overlay=True,          # put in foreground
) 
```## 如何使用像素图：检查文本可见性
文本是否实际可见取决于多个因素：
1.  文本没有被其他对象覆盖，但可能与背景色相同，例如白色字体在白色背景上等。
1.  文本可能被图像或矢量图覆盖。检测这一点是一项重要的功能，例如用于揭示不当匿名化的法律文件。
1.  文本是隐藏创建的。这种技术通常由 OCR 工具使用，将识别的文本存储在页面上的不可见层中。
下面展示了如何检测情况 1\. 或者情况 2\. 如果遮盖物是单色的话：
```py
pix = page.get_pixmap(dpi=150)  # make page image with a decent resolution
# the following matrix transforms page to pixmap coordinates
mat = page.rect.torect(pix.irect)
# search for some string "needle"
rlist = page.search_for("needle")
# check the visibility for each hit rectangle
for rect in rlist:
    if pix.color_topusage(clip=rect * mat)[0] > 0.95:
        print("'needle' is invisible here:", rect) 

import sys, pymupdf  # import the bindings
fname = sys.argv[1]  # get filename from command line
doc = pymupdf.open(fname)  # open document
for page in doc:  # iterate through the pages
    pix = page.get_pixmap()  # render page to an image
    pix.save("page-%i.png" % page.number)  # store image as a PNG 

zoom_x = 2.0  # horizontal zoom
zoom_y = 2.0  # vertical zoom
mat = pymupdf.Matrix(zoom_x, zoom_y)  # zoom factor 2 in each dimension
pix = page.get_pixmap(matrix=mat)  # use 'mat' instead of the identity matrix