The text appears correct, but the encoding is incorrect.

[weirman]

Many thanks to the excellent PyMuPDF. However, I encountered some issues during my process and hope to receive help from the community.
I followed this approach and obtained the correctly rendered text, but when I copy it, I find that the text content’s encoding is incorrect.

import fitz
import pathlib
import io
import time
def extract_text_from_pdf(pdf_path):
    try:
        doc = fitz.open(pdf_path)
        extracted_text = ""

        for page_num in range(len(doc)):
            page = doc[page_num]
            extracted_text += page.get_text("text") + "\n"
        return extracted_text
    except Exception as e:
        print(f"Read PDF ERROR: {e}")

def insert_htmlbox( page, rect, text, rotate=0, oc=0, adjust=True, overlay=True, morph=None, css=None ):
    def story_maker(clip, text, adjust=True, rotate=0, css=css):
        rect = fitz.Rect(clip)  # copy to rect
        rect += (-clip.x0, -clip.y0, -clip.x0, -clip.y0)
        if rotate in (90, 270):
            rect.x1, rect.y1 = rect.y1, rect.x1
        orig_height = rect.y1
        mycss = "body {margin:1px;}" + css
        more = True
        while more:
            fp = io.BytesIO()  # use for file output
            writer = fitz.DocumentWriter(fp)
            story = fitz.Story(html=text, user_css=mycss)
            dev = writer.begin_page(rect)
            more, filled = story.place(rect)
            if more:  # text did not fit in this clip, so enlarge and try again
                rect *= 1.01  # enlarge by 1%
                continue
            story.draw(dev)  # good, we stayed inside the clip
            writer.end_page()  # end the page
            writer.close()  # close the writer
            break  # leave the loop

        try:
            doc = fitz.open("pdf", fp)  # make a PDF from memory
        except:
            fitz.FZ_MAX_INF_RECT
            return None, fitz.FZ_MAX_INF_RECT
        if adjust is False and rect.y1 > orig_height:
            doc.close()
            return None, rect.y1
        return doc, filled[3] - filled[1]

    while rotate < 0:
        rotate += 360
    while rotate >= 360:
        rotate -= 360
    rect = fitz.Rect(rect)
    if css is None:
        css = ""
    doc, height = story_maker(rect, text, adjust=adjust, rotate=rotate, css=css)

    rc = rect.height - height if rotate in (0, 180) else rect.width - height
    if doc is not None:
        page.show_pdf_page(
            rect, doc, 0, rotate=rotate, oc=oc, overlay=overlay
        )
    return rc

### End of custom function
fitz.Page.insert_htmlbox = insert_htmlbox  # mix it into the Page object


text = "དབུས་གཙང་གནས་ཡིག་ཅེས་པའི་དེབ་དེའི་རྩོམ་པ་པོ་ནི་རྗེ་བཙུན་བླ་"
doc = fitz.open()
page = doc.new_page()
clip = fitz.Rect(200, 200, 500, 400)
css = "body {font-family: sans-serif;}"  # example extra styling
pdf_name = 'output.pdf'
rc = page.insert_htmlbox(clip, text,
    css=None,
    rotate=0,  # one of 0, 90, 180, 270
    adjust=True,  # whether to reduce font size until text fits in clip
    morph=None,
    overlay=True,
)
print(rc)  # float as in insert_textbox
print("Text written to PDF:", text)
doc.subset_fonts()  # recommended
doc.ez_save(pdf_name)
print("Extracted text from PDF:",extract_text_from_pdf(pdf_name))

183.5999984741211
Text written to PDF: དབུས་གཙང་གནས་ཡིག་ཅེས་པའི་དེབ་དེའི་རྩོམ་པ་པོ་ནི་རྗེ་བཙུན་བླ་
Extracted text from PDF: དʐས་གཙང་གནས་ཡིག་ཅེས་པའི་དེབ་དེའི་Πོམ་པ་པོ་ནི་ེ͛་བ˦ན་ʪ་