Pfthb

I have no prior experience with Qt/PyQt.
I'm just trying to use PyQt for the web engine capabilities, to 'convert' a folder of html files to pdf documents.

The code works well if there is only 1 html file, but when there are multiple html files it only generates a pdf for the last file in the loop.

I think the issue must be to do with Qt stuff, looping, events etc - but I have no idea where to begin to sort this out. As you can tell I'm only Qt to produce html->pdf, I'm not interested in building a GUI.

I read about using QApplication.processEvents() at the end of the loop may fix this, but the result was the same.
I tried adding a sleep/pause to the code, also the same.

import sys
import os

from PyQt5.QtWidgets import QApplication
from PyQt5.QtWebEngineWidgets import QWebEngineView
from PyQt5.QtCore import QDir, QUrl

# read somewhere this is needed to load local html, works without for me though
sys.argv.append("--disable-web-security")
app = QApplication(sys.argv)

iter_num = 0

directory = 'my_webfile_directory'
for filename in os.listdir(directory):
 if filename.endswith(".htm") or filename.endswith(".html"):
 with open(os.path.join(directory, filename), 'r') as myfile:

 print(filename)
 raw_html = myfile.read()
 # init qt web view
 view = QWebEngineView()
 view.setHtml(raw_html)

 # set to close web view after pdf is created
 view.page().pdfPrintingFinished.connect(view.close)
 # generate filename
 iter_num += 1
 outputfilename = str(iter_num) + ".pdf"
 outputfullpath = os.path.join(directory, outputfilename)

 def save_pdf(finished):
 view.page().printToPdf(outputfullpath)
 # when web view is ready, save the pdf
 view.loadFinished.connect(save_pdf)
 # QApplication.processEvents()

app.exec()

I think QWebEngineView is not thread-safe because I was able to make it work consistently by creating a queue of files to be processed and executing one after the other using a signal, here is a demo application:

import sys
import os

from PyQt5.QtWidgets import QApplication, QMainWindow, QMessageBox
from PyQt5.QtWebEngineWidgets import QWebEngineView
from PyQt5.QtCore import QObject, QDir, QUrl, pyqtSignal


class HtmlToPdfConverter(QObject):

 queueProcessed = pyqtSignal()

 def __init__(self):
 super().__init__()

 self._queue = 
 self._current = None

 def queue(self, html_file, output_file):
 self._queue.append((html_file, output_file))

 def process_queue(self):
 if self._queue:
 raw_html = ''
 self._current = self._queue.pop(0)
 with open(self._current[0], 'r') as my_file:
 raw_html = my_file.read()

 view = QWebEngineView()
 view.loadFinished.connect(self._get_load_finished_event(view))
 view.page().pdfPrintingFinished.connect(self._get_printing_finished_event(view))
 view.setHtml(raw_html)
 else:
 self.queueProcessed.emit()

 def _get_load_finished_event(self, view):
 def _load_finished(success):
 if success:
 view.page().printToPdf(self._current[1])
 return _load_finished

 def _get_printing_finished_event(self, view):
 def _printing_finished(file, success):
 view.close()
 self.process_queue()
 return _printing_finished


class App(QApplication):
 def __init__(self, sys_argv):
 super().__init__(sys_argv)

 self.dummy_window = QMainWindow()
 self.dummy_window.show()

 def generate_pdfs(self, directory):
 converter = HtmlToPdfConverter()
 converter.queueProcessed.connect(self._queue_processed)

 iter_num = 0

 for filename in os.listdir(directory):
 if filename.endswith(".htm") or filename.endswith(".html"):
 iter_num += 1
 out_filename = os.path.join(directory, str(iter_num) + ".pdf")
 converter.queue(os.path.join(directory, filename), out_filename)

 converter.process_queue()

 def _queue_processed(self):
 QMessageBox.information(self.dummy_window, 'Pdf Generator', 'All PDF files have been generated.')


if __name__ == '__main__':
 app = App(sys.argv)
 app.generate_pdfs('c:/temp/test')

 sys.exit(app.exec_())