python之通过 reportlab库给PDF文件添加水印

添加页码和水印

水印是纸质或者电子文档上的图像或图案，是一种个人和组织的象征。一些水印只能在特殊照明条件下才能看到。下面是向PDF添加水印方法：

添加文字水印

>>> from reportlab.pdfgen import canvas
>>> from reportlab.lib.units import cm
>>> from reportlab.pdfbase import pdfmetrics
>>> from reportlab.pdfbase.ttfonts import TTFont
>>>
>>> from PyPDF4 import PdfFileWriter,PdfFileReader

>>> content = "Hello"

默认大小为21cm*29.7cm

>>> c = canvas.Canvas('./pdf_file/mark.pdf', pagesize = (30*cm, 30*cm))

移动坐标原点(坐标系左下为(0,0)))

>>> c.translate(10*cm, 10*cm)

灰色

>>> c.setFillColorRGB(0.5,0.5,0.5)

旋转45度，坐标系被旋转

>>> c.rotate(45)
>>> c.drawString(-7*cm, 0*cm, content)
>>> c.drawString(7*cm, 0*cm, content)
>>> c.drawString(0*cm, 7*cm, content)
>>> c.drawString(0*cm, -7*cm, content)

关闭并保存pdf文件

>>> c.save()

使用文件添加水印

>>> input_pdf = './pdf_file/demo1.pdf'
>>> output_pdf = './pdf_file/abc.pdf'
>>> watermark_pdf = './pdf_file/mark.pdf'
>>> watermark = PdfFileReader(watermark_pdf)
>>> watermark_page = watermark.getPage(0)
>>> pdf = PdfFileReader(input_pdf,strict=False)
>>> pdf_writer = PdfFileWriter()
>>> for page in range(pdf.getNumPages()):
>>>     pdf_page = pdf.getPage(page)
>>>     pdf_page.mergePage(watermark_page)
>>>     pdf_writer.addPage(pdf_page)
>>> pdfOutputFile = open(output_pdf,'wb')
>>> pdf_writer.encrypt('hello')
>>> pdf_writer.write(pdfOutputFile)
>>> pdfOutputFile.close()

添加页码

也添加水印相同，使用文件添加页码。

>>> from reportlab.lib.units import mm
>>> import os,sys
>>>
>>> path = './pdf_file/demo1.pdf'
>>>
>>> base = os.path.basename(path)
>>> tmp = "__tmp.pdf"
>>>
>>> batch = 10
>>> batch = 0
>>> output = PdfFileWriter()
>>> with open(path, 'rb') as f:
>>>     pdf = PdfFileReader(f,strict=False)
>>>     n = pdf.getNumPages()
>>>     if batch == 0:
>>>         batch = -n
>>>     c = canvas.Canvas(tmp)
>>>     for i in range(1,n+1):
>>>         c.drawString((210//2)*mm, (4)*mm, str(i))
>>>         c.showPage()
>>>     c.save()
>>>     with open(tmp, 'rb') as ftmp:
>>>         numberPdf = PdfFileReader(ftmp)
>>>         for p in range(n):
>>>             print('page: %d of %d'%(p, n))
>>>             page = pdf.getPage(p)
>>>             numberLayer = numberPdf.getPage(p)
>>>
>>>             page.mergePage(numberLayer)
>>>             output.addPage(page)
>>>         if output.getNumPages():
>>>             newpath = path.replace(base,  base[:-4] + '_page_%d'%(p//batch + 1)  + path[-4:])
>>>             with open(newpath, 'wb') as f:
>>>                 output.write(f)
>>>     os.remove(tmp)
page: 0 of 2
page: 1 of 2