How To Convert Webpage Into PDF By Using Python

I was finding solution to print webpage into local file PDF, using Python. one of the good solution is to use Qt, found here, https://bharatikunal.wordpress.com/2010/01/. It didn't

Solution 1:

You also can use pdfkit:

Usage

import pdfkit
pdfkit.from_url('http://google.com', 'out.pdf')

Install

MacOS: brew install Caskroom/cask/wkhtmltopdf

Debian/Ubuntu: apt-get install wkhtmltopdf

Windows: choco install wkhtmltopdf

See official documentation for MacOS/Ubuntu/other OS: https://github.com/JazzCore/python-pdfkit/wiki/Installing-wkhtmltopdf

Solution 2:

WeasyPrint

pip install weasyprint  # No longer supports Python 2.x.

python
>>> import weasyprint
>>> pdf = weasyprint.HTML('http://www.google.com').write_pdf()
>>> len(pdf)
92059
>>> open('google.pdf', 'wb').write(pdf)

Solution 3:

thanks to below posts, and I am able to add on the webpage link address to be printed and present time on the PDF generated, no matter how many pages it has.

Add text to Existing PDF using Python

https://github.com/disflux/django-mtr/blob/master/pdfgen/doc_overlay.py

To share the script as below:

import time
from pyPdf import PdfFileWriter, PdfFileReader
import StringIO
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
from xhtml2pdf import pisa
import sys 
from PyQt4.QtCore import *
from PyQt4.QtGui import * 
from PyQt4.QtWebKit import * 

url = 'http://www.yahoo.com'
tem_pdf = "c:\\tem_pdf.pdf"
final_file = "c:\\younameit.pdf"

app = QApplication(sys.argv)
web = QWebView()
#Read the URL given
web.load(QUrl(url))
printer = QPrinter()
#setting format
printer.setPageSize(QPrinter.A4)
printer.setOrientation(QPrinter.Landscape)
printer.setOutputFormat(QPrinter.PdfFormat)
#export file as c:\tem_pdf.pdf
printer.setOutputFileName(tem_pdf)

def convertIt():
    web.print_(printer)
    QApplication.exit()

QObject.connect(web, SIGNAL("loadFinished(bool)"), convertIt)

app.exec_()
sys.exit

# Below is to add on the weblink as text and present date&time on PDF generated

outputPDF = PdfFileWriter()
packet = StringIO.StringIO()
# create a new PDF with Reportlab
can = canvas.Canvas(packet, pagesize=letter)
can.setFont("Helvetica", 9)
# Writting the new line
oknow = time.strftime("%a, %d %b %Y %H:%M")
can.drawString(5, 2, url)
can.drawString(605, 2, oknow)
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(tem_pdf, "rb"))
pages = existing_pdf.getNumPages()
output = PdfFileWriter()
# add the "watermark" (which is the new pdf) on the existing page
for x in range(0,pages):
    page = existing_pdf.getPage(x)
    page.mergePage(new_pdf.getPage(0))
    output.addPage(page)
# finally, write "output" to a real file
outputStream = file(final_file, "wb")
output.write(outputStream)
outputStream.close()

print final_file, 'is ready.'

Solution 4:

here is the one working fine:

import sys 
from PyQt4.QtCore import *
from PyQt4.QtGui import * 
from PyQt4.QtWebKit import * 

app = QApplication(sys.argv)
web = QWebView()
web.load(QUrl("http://www.yahoo.com"))
printer = QPrinter()
printer.setPageSize(QPrinter.A4)
printer.setOutputFormat(QPrinter.PdfFormat)
printer.setOutputFileName("fileOK.pdf")

def convertIt():
    web.print_(printer)
    print("Pdf generated")
    QApplication.exit()

QObject.connect(web, SIGNAL("loadFinished(bool)"), convertIt)
sys.exit(app.exec_())

Solution 5:

Here is a simple solution using QT. I found this as part of an answer to a different question on StackOverFlow. I tested it on Windows.

from PyQt4.QtGui import QTextDocument, QPrinter, QApplication

import sys
app = QApplication(sys.argv)

doc = QTextDocument()
location = "c://apython//Jim//html//notes.html"
html = open(location).read()
doc.setHtml(html)

printer = QPrinter()
printer.setOutputFileName("foo.pdf")
printer.setOutputFormat(QPrinter.PdfFormat)
printer.setPageSize(QPrinter.A4);
printer.setPageMargins (15,15,15,15,QPrinter.Millimeter);

doc.print_(printer)
print "done!"