时间：2022-10-08 12:54:11 | 栏目：Python代码 | 点击：次
python3.7
Pycharm
PyPDF2
reportlab
PyPDF2没有办法从PDF文档中提取图像、图表或其他媒体，但它可以提取文本，并将其返回为Python字符串。
import PyPDF2
reader = PyPDF2.PdfFileReader('test.pdf')
page = reader.getPage(0)
print(page.extractText())
上面的代码中通过创建PdfFileReader对象的方式来读取PDF文档，该对象的getPage方法可以获得PDF文档的指定页并得到一个PageObject对象，通过PageObject对象的rotateClockwise和rotateCounterClockwise方法可以实现页面的顺时针和逆时针方向旋转，通过PageObject对象的addBlankPage方法可以添加一个新的空白页，代码如下所示。
import PyPDF2
from PyPDF2.pdf import PageObject
# 创建一个读PDF文件的Reader对象
reader = PyPDF2.PdfFileReader('resources/xxx.pdf')
# 创建一个写PDF文件的Writer对象
writer = PyPDF2.PdfFileWriter()
# 对PDF文件所有页进行循环遍历
for page_num in range(reader.numPages):
# 获取指定页码的Page对象
current_page = reader.getPage(page_num) # type: PageObject
if page_num % 2 == 0:
# 奇数页顺时针旋转90度
current_page.rotateClockwise(90)
else:
# 偶数页反时针旋转90度
current_page.rotateCounterClockwise(90)
writer.addPage(current_page)
# 最后添加一个空白页并旋转90度
page = writer.addBlankPage() # type: PageObject
page.rotateClockwise(90)
# 通过Writer对象的write方法将PDF写入文件
with open('resources/xxx.pdf', 'wb') as file:
writer.write(file)
使用PyPDF2中的PdfFileWrite对象可以为PDF文档加密，如果需要给一系列的PDF文档设置统一的访问口令，使用Python程序来处理就会非常的方便。
import PyPDF2
reader = PyPDF2.PdfFileReader('resources/XGBoost.pdf')
writer = PyPDF2.PdfFileWriter()
for page_num in range(reader.numPages):
writer.addPage(reader.getPage(page_num))
# 通过encrypt方法加密PDF文件，方法的参数就是设置的密码
writer.encrypt('foobared')
with open('resources/XGBoost-encrypted.pdf', 'wb') as file:
writer.write(file)
创建PDF文档需要三方库reportlab的支持,使用 pip install reportlab 命令安装
from reportlab.lib.pagesizes import A4
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
from reportlab.pdfgen import canvas
pdf_canvas = canvas.Canvas('resources/python创建.pdf', pagesize=A4)
width, height = A4
# 绘图
image = canvas.ImageReader('resources/xxx.jpg')
pdf_canvas.drawImage(image, 20, height - 395, 250, 375)
# 显示当前页
pdf_canvas.showPage()
# 注册字体文件
pdfmetrics.registerFont(TTFont('Font1', 'resources/fonts/Vera.ttf'))
pdfmetrics.registerFont(TTFont('Font2', 'resources/fonts/青呱石头体.ttf'))
# 写字
pdf_canvas.setFont('Font2', 40)
pdf_canvas.setFillColorRGB(0.9, 0.5, 0.3, 1)
pdf_canvas.drawString(width // 2 - 120, height // 2, '你好，世界！')
pdf_canvas.setFont('Font1', 40)
pdf_canvas.setFillColorRGB(0, 1, 0, 0.5)
pdf_canvas.rotate(18)
pdf_canvas.drawString(250, 250, 'hello, world!')
# 保存
pdf_canvas.save()
合并PDF
from PyPDF2 import PdfFileReader, PdfFileWriter def merge_pdfs(paths, output): pdf_writer = PdfFileWriter() for path in paths: pdf_reader = PdfFileReader(path) for page in range(pdf_reader.getNumPages()): # 将每页添加到writer对象 pdf_writer.addPage(pdf_reader.getPage(page)) # 写入合并的pdf with open(output, 'wb') as out: pdf_writer.write(out) if __name__ == '__main__': paths = ['document1.pdf', 'document2.pdf'] merge_pdfs(paths, output='merged.pdf')
添加水印
from PyPDF2 import PdfFileWriter, PdfFileReader def create_watermark(input_pdf, output, watermark): watermark_obj = PdfFileReader(watermark) watermark_page = watermark_obj.getPage(0) pdf_reader = PdfFileReader(input_pdf) pdf_writer = PdfFileWriter() # 给所有页面添加水印 for page in range(pdf_reader.getNumPages()): page = pdf_reader.getPage(page) page.mergePage(watermark_page) pdf_writer.addPage(page) with open(output, 'wb') as out: pdf_writer.write(out) if __name__ == '__main__': create_watermark( input_pdf='Jupyter_Notebook_An_Introduction.pdf', output='watermarked_notebook.pdf', watermark='watermark.pdf')