PyMuPDF 1.24.4 中文文档（二）（4）

"""
How to use a pymupdf font with method Page.insert_htmlbox().
"""
import pymupdf
# Example text
text = """Lorem ipsum dolor sit amet, consectetur adipisici elit, sed
 eiusmod tempor incidunt ut labore et dolore magna aliqua. Ut enim ad
 minim veniam, quis nostrud exercitation <b>ullamco <i>laboris</i></b>
 nisi ut aliquid ex ea commodi consequat. Quis aute iure
 <span style="color: red;">reprehenderit</span>
 in <span style="color: green;font-weight:bold;">voluptate</span> velit
 esse cillum dolore eu fugiat nulla pariatur. Excepteur sint obcaecat
 cupiditat non proident, sunt in culpa qui
 <a href="https://www.artifex.com">officia</a> deserunt mollit anim id
 est laborum."""
"""
This is similar to font file support. However, we can use a convenience
function for creating required CSS definitions.
We still need an Archive for finding the font binaries.
"""
arch = pymupdf.Archive()
# We request to use "myfont" throughout the text.
css = pymupdf.css_for_pymupdf_font("ubuntu", archive=arch, name="myfont")
css += "* {font-family: myfont;text-align: justify;}"
doc = pymupdf.Document()
page = doc.new_page(width=150, height=150)
page.insert_htmlbox(page.rect, text, css=css, archive=arch, rotate=90)
doc.subset_fonts(verbose=True)
doc.ez_save(__file__.replace(".py", ".pdf")) 

for page in doc:
    text_blocks = page.get_text("dict", flags=pymupdf.TEXTFLAGS_TEXT)["blocks"]
    for block in text_blocks:
        for line in block["lines"]:
            for span in line["spans"]:
                text = span["text"]
                color = pymupdf.sRGB_to_rgb(span["color"])
                print(f"Text: {text}, Color: {color}")

import sys, pathlib, pymupdf
fname = sys.argv[1]  # get document filename
with pymupdf.open(fname) as doc:  # open document
    text = chr(12).join([page.get_text() for page in doc])
# write as a binary file to support non-ASCII characters
pathlib.Path(fname + ".txt").write_bytes(text.encode()) 

key1               value1
key2
value2
key3
       value3 blah, blah, blah key4 value4 some other text key5 value5 ... 

doc = pymupdf.open("some.pdf")
header = "Header"  # text in header
footer = "Page %i of %i"  # text in footer
for page in doc:
    page.insert_text((50, 50), header)  # insert header
    page.insert_text(  # insert footer 50 points above page bottom
        (50, page.rect.height - 50),
        footer % (page.number + 1, doc.page_count),
    )

import sys
import pymupdf
def mark_word(page, text):
  """Underline each word that contains 'text'.
 """
    found = 0
    wlist = page.get_text("words", delimiters=None)  # make the word list
    for w in wlist:  # scan through all words on page
        if text in w[4]:  # w[4] is the word's string
            found += 1  # count
            r = pymupdf.Rect(w[:4])  # make rect from word bbox
            page.add_underline_annot(r)  # underline
    return found
fname = sys.argv[1]  # filename
text = sys.argv[2]  # search string
doc = pymupdf.open(fname)
print("underlining words containing '%s' in document '%s'" % (word, doc.name))
new_doc = False  # indicator if anything found at all
for page in doc:  # scan through the pages
    found = mark_word(page, text)  # mark the page's words
    if found:  # if anything found ...
        new_doc = True
        print("found '%s' %i times on page %i" % (text, found, page.number + 1))
if new_doc:
    doc.save("marked-" + doc.name) 

# -*- coding: utf-8 -*-
import pymupdf
# the document to annotate
doc = pymupdf.open("tilted-text.pdf")
# the text to be marked
needle = "¡La práctica hace el campeón!"
# work with first page only
page = doc[0]
# get list of text locations
# we use "quads", not rectangles because text may be tilted!
rl = page.search_for(needle, quads=True)
# mark all found quads with one annotation
page.add_squiggly_annot(rl)
# save to a new PDF
doc.save("a-squiggly.pdf") 

span_quad = pymupdf.recover_quad(line["dir"], span)
annot = page.add_highlight_annot(span_quad)  # this will mark the complete span text 

line_quad = pymupdf.recover_line_quad(line, spans=line["spans"][1:-1])
page.add_highlight_annot(line_quad) 

import sys
import pymupdf
def flags_decomposer(flags):
  """Make font flags human readable."""
    l = []
    if flags & 2 ** 0:
        l.append("superscript")
    if flags & 2 ** 1:
        l.append("italic")
    if flags & 2 ** 2:
        l.append("serifed")
    else:
        l.append("sans")
    if flags & 2 ** 3:
        l.append("monospaced")
    else:
        l.append("proportional")
    if flags & 2 ** 4:
        l.append("bold")
    return ", ".join(l)
doc = pymupdf.open(sys.argv[1])
page = doc[0]
# read page text as a dictionary, suppressing extra spaces in CJK fonts
blocks = page.get_text("dict", flags=11)["blocks"]
for b in blocks:  # iterate through the text blocks
    for l in b["lines"]:  # iterate through the text lines
        for s in l["spans"]:  # iterate through the text spans
            print("")
            font_properties = "Font: '%s' (%s), size %g, color #%06x" % (
                s["font"],  # font name
                flags_decomposer(s["flags"]),  # readable font flags
                s["size"],  # font size
                s["color"],  # font color
            )
            print("Text: '%s'" % s["text"])  # simple print of text
            print(font_properties) 

import pymupdf
doc = pymupdf.open(...)  # new or existing PDF
page = doc.new_page()  # new or existing page via doc[n]
p = pymupdf.Point(50, 72)  # start point of 1st line
text = "Some text,\nspread across\nseveral lines."
# the same result is achievable by
# text = ["Some text", "spread across", "several lines."]
rc = page.insert_text(p,  # bottom-left of 1st char
                     text,  # the text (honors '\n')
                     fontname = "helv",  # the default font
                     fontsize = 11,  # the default font size
                     rotate = 0,  # also available: 90, 180, 270
                     )
print("%i lines printed on page %i." % (rc, page.number))
doc.save("text.pdf") 

import pymupdf
doc = pymupdf.open()
page = doc.new_page()
# the text strings, each having 3 lines
text1 = "rotate=0\nLine 2\nLine 3"
text2 = "rotate=90\nLine 2\nLine 3"
text3 = "rotate=-90\nLine 2\nLine 3"
text4 = "rotate=180\nLine 2\nLine 3"
red = (1, 0, 0) # the color for the red dots
# the insertion points, each with a 25 pix distance from the corners
p1 = pymupdf.Point(25, 25)
p2 = pymupdf.Point(page.rect.width - 25, 25)
p3 = pymupdf.Point(25, page.rect.height - 25)
p4 = pymupdf.Point(page.rect.width - 25, page.rect.height - 25)
# create a Shape to draw on
shape = page.new_shape()
# draw the insertion points as red, filled dots
shape.draw_circle(p1,1)
shape.draw_circle(p2,1)
shape.draw_circle(p3,1)
shape.draw_circle(p4,1)
shape.finish(width=0.3, color=red, fill=red)
# insert the text strings
shape.insert_text(p1, text1)
shape.insert_text(p3, text2, rotate=90)
shape.insert_text(p2, text3, rotate=-90)
shape.insert_text(p4, text4, rotate=180)
# store our work to the page
shape.commit()
doc.save(...) 

import pymupdf
doc = pymupdf.open()  # new or existing PDF
page = doc.new_page()  # new page, or choose doc[n]
# write in this overall area
rect = pymupdf.Rect(100, 100, 300, 150)
# partition the area in 4 equal sub-rectangles
CELLS = pymupdf.make_table(rect, cols=4, rows=1)
t1 = "text with rotate = 0."  # these texts we will written
t2 = "text with rotate = 90."
t3 = "text with rotate = 180."
t4 = "text with rotate = 270."
text = [t1, t2, t3, t4]
red = pymupdf.pdfcolor["red"]  # some colors
gold = pymupdf.pdfcolor["gold"]
blue = pymupdf.pdfcolor["blue"]
"""
We use a Shape object (something like a canvas) to output the text and
the rectangles surrounding it for demonstration.
"""
shape = page.new_shape()  # create Shape
for i in range(len(CELLS[0])):
    shape.draw_rect(CELLS[0][i])  # draw rectangle
    shape.insert_textbox(
        CELLS[0][i], text[i], fontname="hebo", color=blue, rotate=90 * i
    )
shape.finish(width=0.3, color=red, fill=gold)
shape.commit()  # write all stuff to the page
doc.ez_save(__file__.replace(".py", ".pdf")) 

import pymupdf
rect = pymupdf.Rect(100, 100, 400, 300)
text = """Lorem ipsum dolor sit amet, consectetur adipisici elit, sed
 eiusmod tempor incidunt ut labore et dolore magna aliqua. Ut enim ad
 minim veniam, quis nostrud exercitation <b>ullamco <i>laboris</i></b>
 nisi ut aliquid ex ea commodi consequat. Quis aute iure
 <span style="color: #f00;">reprehenderit</span>
 in <span style="color: #0f0;font-weight:bold;">voluptate</span> velit
 esse cillum dolore eu fugiat nulla pariatur. Excepteur sint obcaecat
 cupiditat non proident, sunt in culpa qui
 <a href="https://www.artifex.com">officia</a> deserunt mollit anim id
 est laborum."""
doc = pymupdf.Document()
page = doc.new_page()
page.insert_htmlbox(rect, text, css="* {font-family: sans-serif;font-size:14px;}")
doc.ez_save(__file__.replace(".py", ".pdf")) 

import pymupdf
import os
filedir = os.path.dirname(__file__)
text = """
<style>
body {
 font-family: sans-serif;
}
td,
th {
 border: 1px solid blue;
 border-right: none;
 border-bottom: none;
 padding: 5px;
 text-align: center;
}
table {
 border-right: 1px solid blue;
 border-bottom: 1px solid blue;
 border-spacing: 0;
}
</style>
<body>
<p><b>Some Colors</b></p>
<table>
 <tr>
 <th>Lime</th>
 <th>Lemon</th>
 <th>Image</th>
 <th>Mauve</th>
 </tr>
 <tr>
 <td>Green</td>
 <td>Yellow</td>
 <td><img src="img-cake.png" width=50></td>
 <td>Between<br>Gray and Purple</td>
 </tr>
</table>
</body>
"""
doc = pymupdf.Document()
page = doc.new_page()
rect = page.rect + (36, 36, -36, -36)
# we must specify an Archive because of the image
page.insert_htmlbox(rect, text, archive=pymupdf.Archive("."))
doc.ez_save(__file__.replace(".py", ".pdf")) 

import pymupdf
greetings = (
    "Hello, World!",  # english
    "Hallo, Welt!",  # german
    "سلام دنیا!",  # persian
    "வணக்கம், உலகம்!",  # tamil
    "สวัสดีชาวโลก!",  # thai
    "Привіт Світ!",  # ucranian
    "שלום עולם!",  # hebrew
    "ওহে বিশ্ব!",  # bengali
    "你好世界！",  # chinese
    "こんにちは世界！",  # japanese
    "안녕하세요, 월드!",  # korean
    "नमस्कार, विश्व !",  # sanskrit
    "हैलो वर्ल्ड!",  # hindi
)
doc = pymupdf.open()
page = doc.new_page()
rect = (50, 50, 200, 500)
# join greetings into one text string
text = " ... ".join([t for t in greetings])
# the output of the above is simple:
page.insert_htmlbox(rect, text)
doc.save(__file__.replace(".py", ".pdf"))