npx skills add https://github.com/anthropics/skills --skill pdf本指南涵盖了使用 Python 库和命令行工具进行 PDF 处理的基本操作。如需了解高级功能、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 并遵循其说明。
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()
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)
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)
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者，精准高效
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}")
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)
import pdfplumber
with pdfplumber.open("document.pdf") as pdf:
for page in pdf.pages:
text = page.extract_text()
print(text)
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)
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: # 检查表格是否非空
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)
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")
# 添加一条线
c.line(100, height - 140, 400, height - 140)
# 保存
c.save()
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)
重要提示：切勿在 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，会导致它们渲染为实心黑框。
相反，请在 Paragraph 对象中使用 ReportLab 的 XML 标记标签：
from reportlab.platypus import Paragraph
from reportlab.lib.styles import getSampleStyleSheet
styles = getSampleStyleSheet()
# 下标：使用 <sub> 标签
chemical = Paragraph("H<sub>2</sub>O", styles['Normal'])
# 上标：使用 <super> 标签
squared = Paragraph("x<super>2</super> + y<super>2</super>", styles['Normal'])
对于使用 canvas 绘制的文本（非 Paragraph 对象），请手动调整字体大小和位置，而不是使用 Unicode 下标/上标。
# 提取文本
pdftotext input.pdf output.txt
# 提取文本并保留布局
pdftotext -layout input.pdf output.txt
# 提取特定页面
pdftotext -f 1 -l 5 input.pdf output.txt # 第 1-5 页
# 合并 PDF
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf
# 拆分页面
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
qpdf input.pdf --pages . 6-10 -- pages6-10.pdf
# 旋转页面
qpdf input.pdf output.pdf --rotate=+90:1 # 将第 1 页旋转 90 度
# 移除密码
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf
# 合并
pdftk file1.pdf file2.pdf cat output merged.pdf
# 拆分
pdftk input.pdf burst
# 旋转
pdftk input.pdf rotate 1east output rotated.pdf
# 需要：pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path
# 将 PDF 转换为图像
images = convert_from_path('scanned.pdf')
# 对每一页进行 OCR
text = ""
for i, image in enumerate(images):
text += f"Page {i+1}:\n"
text += pytesseract.image_to_string(image)
text += "\n\n"
print(text)
from pypdf import PdfReader, PdfWriter
# 创建水印（或加载现有的）
watermark = PdfReader("watermark.pdf").pages[0]
# 应用到所有页面
reader = PdfReader("document.pdf")
writer = PdfWriter()
for page in reader.pages:
page.merge_page(watermark)
writer.add_page(page)
with open("watermarked.pdf", "wb") as output:
writer.write(output)
# 使用 pdfimages (poppler-utils)
pdfimages -j input.pdf output_prefix
# 这将提取所有图像为 output_prefix-000.jpg, output_prefix-001.jpg 等。
from pypdf import PdfReader, PdfWriter
reader = PdfReader("input.pdf")
writer = PdfWriter()
for page in reader.pages:
writer.add_page(page)
# 添加密码
writer.encrypt("userpassword", "ownerpassword")
with open("encrypted.pdf", "wb") as output:
writer.write(output)
| 任务 | 最佳工具 | 命令/代码 |
|---|---|---|
| 合并 PDF | pypdf | writer.add_page(page) |
| 拆分 PDF | pypdf | 每页一个文件 |
| 提取文本 | pdfplumber | page.extract_text() |
| 提取表格 | pdfplumber | page.extract_tables() |
| 创建 PDF | reportlab | Canvas 或 Platypus |
| 命令行合并 | qpdf | qpdf --empty --pages ... |
| OCR 扫描的 PDF | pytesseract | 先转换为图像 |
| 填写 PDF 表单 | pdf-lib 或 pypdf (见 FORMS.md) | 参见 FORMS.md |
每周安装量
48.0K
代码仓库
GitHub 星标数
101.0K
首次出现
2026年1月20日
安全审计
安装于
opencode38.4K
gemini-cli36.6K
codex36.3K
github-copilot33.9K
cursor32.8K
amp30.9K
This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see REFERENCE.md. If you need to fill out a PDF form, read FORMS.md and follow its instructions.
from pypdf import PdfReader, PdfWriter
# Read a PDF
reader = PdfReader("document.pdf")
print(f"Pages: {len(reader.pages)}")
# Extract text
text = ""
for page in reader.pages:
text += page.extract_text()
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)
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)
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}")
reader = PdfReader("input.pdf")
writer = PdfWriter()
page = reader.pages[0]
page.rotate(90) # Rotate 90 degrees clockwise
writer.add_page(page)
with open("rotated.pdf", "wb") as output:
writer.write(output)
import pdfplumber
with pdfplumber.open("document.pdf") as pdf:
for page in pdf.pages:
text = page.extract_text()
print(text)
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)
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: # Check if table is not empty
df = pd.DataFrame(table[1:], columns=table[0])
all_tables.append(df)
# Combine all tables
if all_tables:
combined_df = pd.concat(all_tables, ignore_index=True)
combined_df.to_excel("extracted_tables.xlsx", index=False)
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter
# Add text
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "This is a PDF created with reportlab")
# Add a line
c.line(100, height - 140, 400, height - 140)
# Save
c.save()
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 = []
# Add content
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())
# Page 2
story.append(Paragraph("Page 2", styles['Heading1']))
story.append(Paragraph("Content for page 2", styles['Normal']))
# Build PDF
doc.build(story)
IMPORTANT : Never use Unicode subscript/superscript characters (₀₁₂₃₄₅₆₇₈₉, ⁰¹²³⁴⁵⁶⁷⁸⁹) in ReportLab PDFs. The built-in fonts do not include these glyphs, causing them to render as solid black boxes.
Instead, use ReportLab's XML markup tags in Paragraph objects:
from reportlab.platypus import Paragraph
from reportlab.lib.styles import getSampleStyleSheet
styles = getSampleStyleSheet()
# Subscripts: use <sub> tag
chemical = Paragraph("H<sub>2</sub>O", styles['Normal'])
# Superscripts: use <super> tag
squared = Paragraph("x<super>2</super> + y<super>2</super>", styles['Normal'])
For canvas-drawn text (not Paragraph objects), manually adjust font the size and position rather than using Unicode subscripts/superscripts.
# Extract text
pdftotext input.pdf output.txt
# Extract text preserving layout
pdftotext -layout input.pdf output.txt
# Extract specific pages
pdftotext -f 1 -l 5 input.pdf output.txt # Pages 1-5
# Merge PDFs
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf
# Split pages
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
qpdf input.pdf --pages . 6-10 -- pages6-10.pdf
# Rotate pages
qpdf input.pdf output.pdf --rotate=+90:1 # Rotate page 1 by 90 degrees
# Remove password
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf
# Merge
pdftk file1.pdf file2.pdf cat output merged.pdf
# Split
pdftk input.pdf burst
# Rotate
pdftk input.pdf rotate 1east output rotated.pdf
# Requires: pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path
# Convert PDF to images
images = convert_from_path('scanned.pdf')
# OCR each page
text = ""
for i, image in enumerate(images):
text += f"Page {i+1}:\n"
text += pytesseract.image_to_string(image)
text += "\n\n"
print(text)
from pypdf import PdfReader, PdfWriter
# Create watermark (or load existing)
watermark = PdfReader("watermark.pdf").pages[0]
# Apply to all pages
reader = PdfReader("document.pdf")
writer = PdfWriter()
for page in reader.pages:
page.merge_page(watermark)
writer.add_page(page)
with open("watermarked.pdf", "wb") as output:
writer.write(output)
# Using pdfimages (poppler-utils)
pdfimages -j input.pdf output_prefix
# This extracts all images as output_prefix-000.jpg, output_prefix-001.jpg, etc.
from pypdf import PdfReader, PdfWriter
reader = PdfReader("input.pdf")
writer = PdfWriter()
for page in reader.pages:
writer.add_page(page)
# Add password
writer.encrypt("userpassword", "ownerpassword")
with open("encrypted.pdf", "wb") as output:
writer.write(output)
| Task | Best Tool | Command/Code |
|---|---|---|
| Merge PDFs | pypdf | writer.add_page(page) |
| Split PDFs | pypdf | One page per file |
| Extract text | pdfplumber | page.extract_text() |
| Extract tables | pdfplumber | page.extract_tables() |
| Create PDFs | reportlab | Canvas or Platypus |
| Command line merge | qpdf | qpdf --empty --pages ... |
Weekly Installs
48.0K
Repository
GitHub Stars
101.0K
First Seen
Jan 20, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykFail
Installed on
opencode38.4K
gemini-cli36.6K
codex36.3K
github-copilot33.9K
cursor32.8K
amp30.9K
97,600 周安装
| OCR scanned PDFs | pytesseract | Convert to image first |
| Fill PDF forms | pdf-lib or pypdf (see FORMS.md) | See FORMS.md |