python怎么读取pdf为文本_使用Python向现有PDF添加文本

[Python 2.7]示例：from pyPdf import PdfFileWriter, PdfFileReader

import StringIO

from reportlab.pdfgen import canvas

from reportlab.lib.pagesizes import letter

packet = StringIO.StringIO()

# create a new PDF with Reportlab

can = canvas.Canvas(packet, pagesize=letter)

can.drawString(10, 100, "Hello world")

can.save()

#move to the beginning of the StringIO buffer

packet.seek(0)

new_pdf = PdfFileReader(packet)

# read your existing PDF

existing_pdf = PdfFileReader(file("original.pdf", "rb"))

output = PdfFileWriter()

# add the "watermark" (which is the new pdf) on the existing page

page = existing_pdf.getPage(0)

page.mergePage(new_pdf.getPage(0))

output.addPage(page)

# finally, write "output" to a real file

outputStream = file("destination.pdf", "wb")

output.write(outputStream)

outputStream.close()

Python 3.x示例：from PyPDF2 import PdfFileWriter, PdfFileReader

import io

from reportlab.pdfgen import canvas

from reportlab.lib.pagesizes import letter

packet = io.BytesIO()

# create a new PDF with Reportlab

can = canvas.Canvas(packet, pagesize=letter)

can.drawString(10, 100, "Hello world")

can.save()

#move to the beginning of the StringIO buffer

packet.seek(0)

new_pdf = PdfFileReader(packet)

# read your existing PDF

existing_pdf = PdfFileReader(open("original.pdf", "rb"))

output = PdfFileWriter()

# add the "watermark" (which is the new pdf) on the existing page

page = existing_pdf.getPage(0)

page.mergePage(new_pdf.getPage(0))

output.addPage(page)

# finally, write "output" to a real file

outputStream = open("destination.pdf", "wb")

output.write(outputStream)

outputStream.close()