Converting Multiple html file into pdf using pdfkit in Python

user_8836278 0
Viewed 2780

I try converting multiple html file into pdf using pdfkik. This is my code:

from bs4 import BeautifulSoup
from selenium import webdriver
import pdfkit

driver=webdriver.Chrome()
driver.get('https://www.linkedin.com/in/jaypratappandey/')
time.sleep(40)
soup= BeautifulSoup(driver.page_source, 'lxml')
data=[]
f=open('htmlfile.html', 'w')
top=open('tophtmlfile.html', 'w')

for name in soup.select('.pv-top-card-section__body'):
    top.write("%s" % name)

for item in soup.select('.pv-oc.ember-view'):
    f.write("%s" % item)


pdfkit.from_file(['tophtmlfile.html', 'htmlfile.html'], 'jayprofile.pdf')

driver.quit()

This code give the following error:

Traceback (most recent call last):
  File "lkdndata.py", line 23, in <module>
    pdfkit.from_file(['tophtmlfile.html', 'htmlfile.html'], 'ankurprofile.pdf')
  File "/usr/local/lib/python3.5/dist-packages/pdfkit/api.py", line 49, in from_file
    return r.to_pdf(output_path)
  File "/usr/local/lib/python3.5/dist-packages/pdfkit/pdfkit.py", line 156, in to_pdf
    raise IOError('wkhtmltopdf reported an error:\n' + stderr)
OSError: wkhtmltopdf reported an error:
Error: This version of wkhtmltopdf is build against an unpatched version of QT, and does not support more then one input document.
Exit with code 1, due to unknown error.
web-scraping python-3.x pdf python
2 Answers

The solution i found was to first merge the html files into one and then go on to convert it using pdfkit. so in your case would be to save the tophtml and html files together in same dir and replace the path to that dir.

import pdfkit
import os

# path to folder containing html files
path = "/home/ec2-user/data-science-processes/src/results/"

def multiple_html_to_pdf(path):
    """ converts multiple html files to a single pdf
    args: path to directory containing html files
    """
    empty_html = '<html><head></head><body></body></html>'
    for file in os.listdir(path):
        if file.endswith(".html"):
            print(file)
            # append html files
            with open(path + file, 'r') as f:
                html = f.read()
                empty_html = empty_html.replace('</body></html>', html + '</body></html>')
    # save merged html
    with open('merged.html', 'w') as f:
        f.write(empty_html)
    pdfkit.from_file('/home/ec2-user/data-science-processes/report/merged.html','Report.pdf')

multiple_html_to_pdf(path)
user_130117990
Related