Python操作PDF文件的几种方式

python深色版本from pypdf import PdfReader

# 创建 PDF 读取器对象
reader = PdfReader("example.pdf")

# 获取页数
print(f"文档总页数: {len(reader.pages)}")

# 获取文档元数据
if reader.metadata:
    print(f"作者: {reader.metadata.author}")
    print(f"标题: {reader.metadata.title}")
    print(f"创建日期: {reader.metadata.creation_date}")

# 提取第一页的文本
first_page = reader.pages[0]
text = first_page.extract_text()
print("第一页内容:")
print(text)
ZHIBO.76ZHIBO.CN18丨SOHU.CYDDW.CN42丨ZHIBO.04SZFK.COM78丨MAP.ZKAFX120.COM55
WAP.YUYOUKE.NET35丨WEIBO.XIANGHETL.COM25丨WEIBO.FMMITV.COM81丨FOOTBALL.0318SEO.COM52
WWW.PORTASTYL.COM24丨YES.NJZHONGTONG.COM37丨MOBI.SHOA01.COM26丨LIVE.ENDYEDU.COM10
24K.GZXZDZ.CN55丨MAP.NMFZTD.ORG.CN30丨QQ.QDSKYWGJJNG.COM69丨FREE.QQRJ.CN39
YUSHA168.COM75丨TJBD120.COM44丨TV.FJZB2.COM41丨ZHIBO.SHANTT.CN41
ONLINE.ZZZ-Z.CN85丨FOOTBALL.HASUNSOFT.COM42丨XGLXX.COM42丨SOHU.MINGPEI.NET69
BOLL.HBST123.COM30丨FREE.SHKYBZ.CN58丨CCTV.QZSYHB.CN58丨FOOTBALL.SANACE.COM.CN26
YES.HASUNSOFT.COM11丨SOHU.HNTGNETWORK.COM14丨VIP.CLQMW.COM15丨WAP.BTJZ.NET.CN74
LANQIU.CLQMW.COM33丨CCTV.ZQIPR.COM85丨FOOTBALL.ZQIPR.COM64丨ZHIHU.ZHENGXIANGJINSHU.COM29
VIP.DGBLJZ.COM73丨SINA.GSXZFWZX.COM63丨SHIJIEBEI.HENGHUASZ.COM72丨PRETTY.CHRONOPORTAL.CN83
LVYIN.SJZXHD.CN25丨SHARE.ZHENGXIANGJINSHU.COM97丨M.ZZKFJYZX.COM47丨OUGUAN.YUYOUKE.NET29
YES.XMJIUSHI.CN70丨PRETTY.KSSJ666.COM91丨WEIBO.CTDSBGG.COM11丨SWEET.HZSMC.COM77

python深色版本from pypdf import PdfMerger

merger = PdfMerger()

# 添加多个 PDF 文件
pdf_files = ["file1.pdf", "file2.pdf", "file3.pdf"]
for pdf in pdf_files:
    merger.append(pdf)

# 将合并后的结果写入新文件
merger.write("merged_output.pdf")
merger.close()  # 记得关闭

python深色版本from pypdf import PdfReader, PdfWriter

reader = PdfReader("original.pdf")
writer = PdfWriter()

# 将前5页保存为一个新文件
for page_num in range(min(5, len(reader.pages))):
    page = reader.pages[page_num]
    writer.add_page(page)

with open("first_5_pages.pdf", "wb") as output_file:
    writer.write(output_file)

python深色版本from pypdf import PdfReader, PdfWriter

reader = PdfReader("unencrypted.pdf")
writer = PdfWriter()

# 将所有页面添加到 writer
for page in reader.pages:
    writer.add_page(page)

# 添加加密，设置用户密码和所有者密码
writer.encrypt(user_password="user123", owner_password="owner456")

with open("encrypted.pdf", "wb") as output_file:
    writer.write(output_file)

python深色版本from pypdf import PdfReader, PdfWriter

reader = PdfReader("encrypted.pdf")

# 检查是否加密
if reader.is_encrypted:
    # 提供密码进行解密
    reader.decrypt("user123")  # 或者 "owner456"

writer = PdfWriter()
for page in reader.pages:
    writer.add_page(page)

with open("decrypted.pdf", "wb") as output_file:
    writer.write(output_file)

python深色版本import pdfplumber

with pdfplumber.open("financial_report.pdf") as pdf:
    # 假设表格在第一页
    page = pdf.pages[0]
    
    # 提取页面上的所有表格
    tables = page.extract_tables()
    
    # 遍历每个表格
    for i, table in enumerate(tables):
        print(f"表格 {i+1}:")
        for row in table:
            print(row)  # 每行是一个列表
    
    # 如果只想提取一个特定的表格，可以使用 extract_table()
    # table = page.extract_table()
    
    # 可视化表格边界（用于调试）
    # im = page.to_image()
    # im.draw_rects(page.extract_words())  # 画出单词边界
    # im.show()

python深色版本from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont

# 注册中文字体 (需要有字体文件)
# pdfmetrics.registerFont(TTFont('SimSun', 'simsun.ttc'))

# 创建画布
c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter

# 添加文本
c.setFont("Helvetica", 16)
c.drawString(100, height - 100, "Hello, this is a PDF generated by Python!")

# 添加更多文本
c.setFont("Helvetica", 12)
c.drawString(100, height - 130, "Using the reportlab library.")

# 保存
c.save()
print("PDF 已创建: hello.pdf")