Python对PDF文档和PPT文档的操作详解

def __init__(self, filename, pagesize=(595.27,841.89), bottomup=1, pageCompression=0, encoding=rl_config.defaultEncoding, verbosity=0, encrypt=None)

pip install reportlab

from reportlab.lib.pagesizes import letter
# canvas模块有个Canvas类，是创建PDF文档的入口。通过help函数可以查询它的用法。
from reportlab.pdfgen import canvas  
# 创建⼀个PDF⽂件
c = canvas.Canvas("example.pdf", pagesize=letter)
# 添加⽂本到PDF
c.drawString(100, 750, "Hello, World!")
# 添加图片到pdf
c.drawImage("image.jpg", 200, 200, width=100, height=100)
c.showPage()
# 保存PDF
c.save()

import pdfkit

# 将HTML内容转换为PDF
pdfkit.from_file('input.html', 'output.pdf')

# 将URL转换为PDF
pdfkit.from_url('http://example.com', 'output.pdf')

# 将字符串转换为PDF
pdfkit.from_string('Hello, world!', 'output.pdf')

from fpdf import FPDF

# 创建PDF对象
pdf = FPDF()

# 添加页面
pdf.add_page()

# 设置字体和字号
pdf.set_font('Arial', size=12)

# 添加文本
pdf.cell(0, 10, 'Hello, world!', ln=True)

# 保存PDF
pdf.output('output.pdf')

from PyPDF2 import PdfFileReader, PdfFileWriter

# 读取PDF文件
pdf = PdfFileReader('input.pdf')

# 获取页面数量
num_pages = pdf.getNumPages()

# 获取第一页内容
page1 = pdf.getPage(0)

# 旋转页面
page1.rotateClockwise(90)

# 创建新的PDF文件
output_pdf = PdfFileWriter()

# 添加页面
output_pdf.addPage(page1)

# 保存新的PDF文件
with open('output.pdf', 'wb') as f:
    output_pdf.write(f)

pip install reportlab

import PyPDF2
# 打开PDF⽂件
pdf_file = open('example.pdf', 'rb')
# 创建⼀个PDF⽂件阅读器对象
pdf_reader = PyPDF2.PdfFileReader(pdf_file)
# 获取PDF⽂件的总⻚数
total_pages = pdf_reader.numPages
# 读取每⼀⻚的⽂本内容
for page_num in range(total_pages):
	page = pdf_reader.getPage(page_num)
	page_text = page.extractText()
	print(f"第 {page_num + 1} ⻚内容：")
	print(page_text)
	print("\n")
# 关闭PDF⽂件
pdf_file.close()

import slate3k as slate

# 打开PDF文件
with open('example.pdf', 'rb') as pdf_file:
    # 创建PDF解析器对象
    pdf_text = slate.PDF(pdf_file)

# 提取PDF文件的文本内容
text = ' '.join(pdf_text)
print("Text in PDF:", text)

pip install python-pptx

from pptx import Presentation
# 创建⼀个新的演⽰⽂稿对象
prs = Presentation()
# 添加⼀张幻灯⽚
slide = prs.slides.add_slide(prs.slide_layouts[0])
# 添加标题和正⽂
title = slide.shapes.title
title.text = "这是标题"
content = slide.shapes.placeholders[1]
content.text = "这是正⽂"
# 保存演⽰⽂稿
prs.save("example.pptx")

from pptx import Presentation
# 打开现有的演⽰⽂稿
prs = Presentation("example.pptx")
# 遍历所有幻灯⽚
for slide in prs.slides:
	for shape in slide.shapes:
		if shape.has_text_frame:
		text_frame = shape.text_frame
		for paragraph in text_frame.paragraphs:
			for run in paragraph.runs:
				run.text = run.text.upper() # 将⽂本转换为⼤写
# 保存修改后的演⽰⽂稿
prs.save("modified_example.pptx")

from pptx import Presentation
from pptx.util import Inches
# 打开现有的演⽰⽂稿
prs = Presentation("example.pptx")
# 添加⼀张幻灯⽚
slide = prs.slides.add_slide(prs.slide_layouts[5])
# 添加图⽚
left = Inches(1)
top = Inches(1)
width = Inches(4)
height = Inches(3)
pic = slide.shapes.add_picture("image.jpg", left, top, width, height)
# 添加形状
left = Inches(5)
top = Inches(1)
width = Inches(2)
height = Inches(2)
shape = slide.shapes.add_shape(1, left, top, width, height)
shape.text = "⾃定义形状"
# 保存修改后的演⽰⽂稿
prs.save("modified_example.pptx")