use_pdf — 使用PDF

PDF 处理指南概述 本指南涵盖使用 Python 库和命令行工具进行基本的 PDF 处理操作。有关高级功能、JavaScript 库和详细示例，请参阅 REFERENCE.md。如果您需要填写 PDF 表单，请阅读 FORMS.md 并按照其说明进行操作。

快速入门

from pypdf import PdfReader, PdfWriter
# 读取 PDF
reader = PdfReader("document.pdf")
print(f"Pages: {len(reader.pages)}")
# 提取文本
text = ""
for page in reader.pages:
    text += page.extract_text()

Python 库 pypdf - 基本操作 合并 PDF

from pypdf import PdfWriter, PdfReader
writer = PdfWriter()
for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
    reader = PdfReader(pdf_file)
    for page in reader.pages:
        writer.add_page(page)
with open("merged.pdf", "wb") as output:
    writer.write(output)

拆分 PDF

reader = PdfReader("input.pdf")
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    with open(f"page_{i+1}.pdf", "wb") as output:
        writer.write(output)

提取元数据

reader = PdfReader("document.pdf")
meta = reader.metadata
print(f"Title: {meta.title}")
print(f"Author: {meta.author}")
print(f"Subject: {meta.subject}")
print(f"Creator: {meta.creator}")

旋转页面

reader = PdfReader("input.pdf")
writer = PdfWriter()
page = reader.pages[0]
page.rotate(90)  # 顺时针旋转 90 度
writer.add_page(page)
with open("rotated.pdf", "wb") as output:
    writer.write(output)

pdfplumber - 文本和表格提取 提取文本

import pdfplumber
with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

提取表格

with pdfplumber.open("document.pdf") as pdf:
    for i, page in enumerate(pdf.pages):
        tables = page.extract_tables()
        for j, table in enumerate(tables):
            print(f"Table {j+1} on page {i+1}:")
            for row in table:
                print(row)

高级表格提取

import pandas as pd
with pdfplumber.open("document.pdf") as pdf:
    all_tables = []
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            if table:  # 检查表格是否不为空
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)
    # 合并所有表格
    if all_tables:
        combined_df = pd.concat(all_tables, ignore_index=True)
        combined_df.to_excel("extracted_tables.xlsx", index=False)

reportlab - 创建 PDF 基本 PDF 创建

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter
# 添加文本
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "This is a PDF created with reportlab")
# 添加线
c.line(100, height - 140, 400, height - 140)
# 保存
c.save()

创建多页 PDF

from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
from reportlab.lib.styles import getSampleStyleSheet
doc = SimpleDocTemplate("report.pdf", pagesize=letter)
styles = getSampleStyleSheet()
story = []
# 添加内容
title = Paragraph("Report Title", styles['Title'])
story.append(title)
story.append(Spacer(1, 12))
body = Paragraph("This is the body of the report. " * 20, styles['Normal'])
story.append(body)
story.append(PageBreak())
# 第 2 页
story.append(Paragraph("Page 2", styles['Heading1']))
story.append(Paragraph("Content for page 2", styles['Normal']))
# 构建 PDF
doc.build(story)

下标和上标 重要：永远不要在 ReportLab PDF 中使用 Unicode 下标/上标字符（₀₁₂₃₄₅₆₇₈₉，⁰¹²³⁴⁵⁶⁷⁸⁹）。内置字体不包含这些字形，导致它们渲染为实心黑色框。相反，使用 ReportLab 的 XML 标记标签在段落对象中：

from reportlab.platypus import Paragraph
from reportlab.lib.styles import getSampleStyleSheet
styles = getSampleStyleSheet()
# 下标：使用  标签
chemical = Paragraph("H2O", styles['Normal'])
# 上标：使用  标签
squared = Paragraph("x2 + y2", styles['Normal'])

对于 canvas 绘制的文本（不适用于段落对象），手动调整字体大小和位置，而不是使用 Unicode 下标/上标。

命令行工具 pdftotext (poppler-utils) # 提取文本 pdftotext input.pdf output.txt # 保留布局提取文本 pdftotext -layout input.pdf output.txt # 提取特定页 pdftotext -f 1 -l 5 input.pdf output.txt # 页 1-5 qpdf # 合并 PDF qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf # 拆分页 qpdf input.pdf --pages . 1-5 -- pages1-5.pdf qpdf input.pdf --pages . 6-10 -- pages6-10.pdf # 旋转页 qpdf input.pdf output.pdf --rotate=+90:1 # 将第 1 页旋转 90 度 # 删除密码 qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf pdftk (如果可用)