Python处理PDF及生成多层PDF实例代码

双层PDF应用PDF中的Canvas概念，先画文字，最后将图片画上去，这样就是两层的PDF。

import os
# import urllib2
import time
from reportlab import platypus
from reportlab.lib.pagesizes import letter
from reportlab.lib.units import inch
from reportlab.platypus import SimpleDocTemplate,Image
from reportlab.pdfgen import canvas

image_file = "./42.png"

# Use Canvas to generate pdf
c = canvas.Canvas('reportlab_canvas.pdf',pagesize=letter)
width,height = letter

c.setFillColorRGB(0,0.77,0.77)
# say hello (note after rotate the y coord needs to be negative!)
c.drawString( 3*inch,3*inch,"Hello World")
c.drawImage(image_file,0)
c.showPage()
c.save()

from PyPDF2 import PdfFileWriter,PdfFileReader

output = PdfFileWriter()
input1 = PdfFileReader(open("jquery.pdf","rb"))

# print document info
print(input1.getDocumentInfo())

# print how many pages input1 has:
print ("pdf_document.pdf has %d pages." % input1.getNumPages())

# print page content
page_content = input1.getPage(0).extractText()
print( page_content )

# add page 1 from input1 to output document,unchanged
output.addPage(input1.getPage(0))

# add page 2 from input1,but rotated clockwise 90 degrees
output.addPage(input1.getPage(1).rotateClockwise(90))

# finally,write "output" to document-output.pdf
outputStream = open("PyPDF2-output.pdf","wb")
output.write(outputStream)

| extractText(self) | ## | # Locate all text drawing commands,in the order they are provided in the | # content stream,and extract the text. This works well for some PDF | # files,but poorly for others,depending on the generator used. This will | # be refined in the future. Do not rely on the order of text coming out of | # this function,as it will change if this function is made more | # sophisticated. | #
 | # Stability: Added in v1.7,will exist for all future v1.x releases. May | # be overhauled to provide more ordered text in the future. | # @return a unicode string object