pip install pymupdf

import fitz  # PyMuPDF 的導(dǎo)入名稱

# 打開 PDF 文件
doc = fitz.open("example.pdf")

# 獲取文檔信息
print(f"頁數(shù): {doc.page_count}")
print(f"元數(shù)據(jù): {doc.metadata}")

# 讀取第一頁文本
page = doc.load_page(0)  # 0 表示第一頁
text = page.get_text()
print(text)

# 關(guān)閉文檔
doc.close()

# 提取所有頁面文本
for page_num in range(doc.page_count):
    page = doc.load_page(page_num)
    print(f"第 {page_num+1} 頁內(nèi)容:")
    print(page.get_text())

# 將第一頁渲染為圖像
page = doc.load_page(0)
pix = page.get_pixmap(matrix=fitz.Matrix(2, 2))  # 2倍縮放提高清晰度
pix.save("page0.png")  # 保存為PNG

# 在整個(gè)文檔中搜索特定文本
for page_num in range(doc.page_count):
    page = doc.load_page(page_num)
    text_instances = page.search_for("搜索關(guān)鍵詞")
    
    for inst in text_instances:
        print(f"在第 {page_num+1} 頁找到匹配:")
        print(f"位置: {inst}")

# 提取帶格式的文本（保留布局）
text = page.get_text("blocks")  # 返回文本塊列表
for block in text:
    print(block[4])  # 文本內(nèi)容在元組的第5個(gè)位置

# 獲取所有鏈接
links = page.get_links()
for link in links:
    if link["kind"] == fitz.LINK_URI:  # 網(wǎng)頁鏈接
        print(f"找到URL鏈接: {link['uri']}")

# 獲取文檔書簽
toc = doc.get_toc()  # 獲取目錄
for item in toc:
    print(f"層級(jí) {item[0]}, 標(biāo)題: {item[1]}, 頁碼: {item[2]}")

# 創(chuàng)建新文檔
new_doc = fitz.open()

# 從原文檔復(fù)制頁面
new_doc.insert_pdf(doc, from_page=0, to_page=2)  # 復(fù)制前3頁

# 添加新頁面
new_page = new_doc.new_page(width=595, height=842)  # A4尺寸
new_page.insert_text((100, 100), "這是新添加的文本")

# 保存修改后的文檔
new_doc.save("modified.pdf")
new_doc.close()

# 高效處理多頁
with fitz.open("large.pdf") as doc:
    for page in doc:  # 直接迭代比load_page更快
        text = page.get_text()

from concurrent.futures import ThreadPoolExecutor

def process_page(page_num):
    with fitz.open("large.pdf") as doc:
        page = doc.load_page(page_num)
        return page.get_text()

with ThreadPoolExecutor() as executor:
    results = list(executor.map(process_page, range(doc.page_count)))

# 只加載需要的頁面
doc = fitz.open("large.pdf")
page = doc[10]  # 直接訪問第11頁

# 確保系統(tǒng)有中文字體
text = page.get_text("text", flags=fitz.TEXT_PRESERVE_LIGATURES)

doc = fitz.open("encrypted.pdf", password="123456")

if doc.can_save_incrementally():
    print("支持增量保存")