I'm using PdfPages from matplotlib and I can loop through each figure object and save each one as a separate page in the same PDF:
from matplotlib.backends.backend_pdf import PdfPages
pp = PdfPages('output.pdf')
for fig in figs:
pp.savefig(fig)
pp.close()
This works great. But is there a way for me to add a page number for each page in the PDF?
Thanks.
A nice solution using reportlib and PyPDF (base on this):
import os
from PyPDF4.pdf import PdfFileReader, PdfFileWriter
from reportlab.lib.units import mm
from reportlab.pdfgen import canvas
def create_page_pdf(num, tmp):
c = canvas.Canvas(tmp)
for i in range(1, num + 1):
c.drawString((210 // 2) * mm, (4) * mm, str(i))
c.showPage()
c.save()
def add_page_numgers(pdf_path):
"""
Add page numbers to a pdf, save the result as a new pdf
@param pdf_path: path to pdf
"""
tmp = "__tmp.pdf"
writer = PdfFileWriter()
with open(pdf_path, "rb") as f:
reader = PdfFileReader(f, strict=False)
n = reader.getNumPages()
# create new PDF with page numbers
create_page_pdf(n, tmp)
with open(tmp, "rb") as ftmp:
number_pdf = PdfFileReader(ftmp)
# iterarte pages
for p in range(n):
page = reader.getPage(p)
numberLayer = number_pdf.getPage(p)
# merge number page with actual page
page.mergePage(numberLayer)
writer.addPage(page)
# write result
if writer.getNumPages():
newpath = pdf_path[:-4] + "_numbered.pdf"
with open(newpath, "wb") as f:
writer.write(f)
os.remove(tmp)
Something like this:
from matplotlib.backends.backend_pdf import PdfPages
pp = PdfPages('output.pdf')
for n, fig in enumerate(figs):
fig.text(4.25/8.5, 0.5/11., str(n+1), ha='center', fontsize=8)
pp.savefig(fig)
pp.close()
Use numbering2pdf library.
from numbering2pdf import add_numbering_to_pdf
add_numbering_to_pdf("old_file.pdf", "new_file.pdf")
Either PyPDF2 or pdfrw will let you overlay two PDFs (so, for example, you can generate a PDF which is only page numbers, and use it to watermark your images). pdfrw has a watermark example that uses a single watermark page, but this could easily be modified to use a set of watermark pages, one for each page number.
If you want to get fancier, you can use reportlab to generate these pages on the fly.
pdfrw also has a facility that allows you to import a PDF page into reportlab as if it were an image. There are a couple of examples around that do this dynamically -- here is a good starting point.
Finally, rst2pdf (which is not all that well maintained but works well for simple cases) also lets you import PDFs as images -- it uses pdfrw and reportlab under the hood -- so you can easily use restructuredText to create documents with your images embedded. AFAIK, the best reportlab to use with the released version of rst2pdf is 2.7.
(Disclaimer: I am the pdfrw author and have made contributions to rst2pdf.)
Requirements:
# generate a page with a page number:
pip install reportlab --upgrade
# merge that numbered (otherwise empty) page with the original:
pip install PyPDF2 --upgrade
Using a slightly modified version of the code of ofir dubi:
import os
from PyPDF2 import PdfReader, PdfWriter
from reportlab.lib.units import mm
from reportlab.pdfgen import canvas
def create_page_pdf(num, tmp):
c = canvas.Canvas(tmp)
for i in range(1, num + 1):
c.drawString((210 // 2) * mm, (4) * mm, str(i))
c.showPage()
c.save()
def add_page_numgers(pdf_path, newpath):
"""
Add page numbers to a pdf, save the result as a new pdf
@param pdf_path: path to pdf
"""
tmp = "__tmp.pdf"
writer = PdfWriter()
with open(pdf_path, "rb") as f:
reader = PdfReader(f)
n = len(reader.pages)
# create new PDF with page numbers
create_page_pdf(n, tmp)
with open(tmp, "rb") as ftmp:
number_pdf = PdfReader(ftmp)
# iterarte pages
for p in range(n):
page = reader.pages[p]
number_layer = number_pdf.pages[p]
# merge number page with actual page
page.merge_page(number_layer)
writer.add_page(page)
# write result
if len(writer.pages) > 0:
with open(newpath, "wb") as f:
writer.write(f)
os.remove(tmp)
if __name__ == "__main__"
add_page_numgers("input.pdf", "output.pdf")
Here is my answer which uses Matplotlib PDF backend to generate a PDF w/ just page numbers and PyPDF2 to merge the "footer" PDF w/ the desired PDF:
def add_header_footer(source_path, save_path, footer_pdf_path=None, start_page=0, header_text=None):
''' Adds header & footer info to existing PDFs '''
footer_pdf_path = os.path.join(os.path.dirname(source_path), 'footer.pdf')
reader = PdfReader(source_path)
writer = PdfWriter()
n_pages = len(reader.pages)
# Step 1: generate header/footer PDF to be merged into source PDF
pp = PdfPages(footer_pdf_path)
for p in range(n_pages):
fig = plt.figure(num=613, figsize=(8.5, 11), constrained_layout=1, facecolor='white')
fig.patch.set_alpha(0)
fig.text(0.48, 0.04, f'{p + 1} | <FOOTER TEXT>',
horizontalalignment='center', weight='bold',
verticalalignment='bottom', fontsize=6, color='grey')
if header_text is not None:
fig.text(0.1, 0.95, header_text,
horizontalalignment='left', weight='bold',
verticalalignment='center', fontsize=6, color='grey')
pp.savefig(fig)
plt.close()
pp.close()
footer_reader = PdfReader(footer_pdf_path)
# Step 2: merge source PDF & header/footer PDF
for index in list(range(start_page, n_pages)):
content_page = reader.pages[index]
footer_page = footer_reader.pages[index]
mediabox = content_page.mediabox
content_page.merge_page(footer_page)
content_page.mediabox = mediabox
writer.add_page(content_page)
# Step 3: save merged PDF
with open(save_path, "wb") as fp:
writer.write(fp)
return None
You can also use fpdf2 (pip install fpdf2). If you have the images saved then you can do something like this:
from fpdf import FPDF
import glob
class MyPDF(FPDF):
def footer(self):
# position footer from bottom of page
self.set_y(-0.6)
# set the font, I=italic
self.set_font("helvetica", style="I", size=8)
# set page number and center it
pageNum = f'- {self.page_no()} -'
self.cell(0, 0.5, pageNum, align="C")
filenames = glob.iglob('*.jpg')
pdf = MyPDF()
pdf = MyPDF(orientation='P', unit='in', format='Letter')
for fname in filenames:
pdf.add_page(orientation='P')
pdf.image(fname, x=1.0, h=4.8)
pdf.output('Images.pdf')
