How to use pdf method in Puppeteer

Best JavaScript code snippet using puppeteer

main.py

Source:main.py Github

copy

Full Screen

...178 r = convert_checkboxes_and_radio_buttons(record, md)179 r = convert_dropdowns_to_strings(r, md)180 r = collapse_radio_groups(r, md)181 return r182def fill_pdf(input_pdf_path: Path, output_pdf_path: Path, data_dict: dict) -> None:183 '''Main function to handle filling in PDF fields.184 Uses data_dict to populate fields from the template in input_pdf_path, writing the filled-in PDF to output_pdf_path.185 '''186 template_pdf = pdfrw.PdfReader(input_pdf_path)187 for page in template_pdf.pages:188 annotations = page[ANNOT_KEY]189 if annotations is None:190 continue191 for annotation in annotations:192 if annotation[SUBTYPE_KEY] == WIDGET_SUBTYPE_KEY:193 if annotation[ANNOT_FIELD_KEY]: ### Isolated fields (has a '/T' key)194 key = annotation[ANNOT_FIELD_KEY][1:-1]195 if key in data_dict.keys():196 if type(data_dict[key]) == bool: # Checkboxes197 if data_dict[key] == True:198 annotation.update(pdfrw.PdfDict(199 AS=pdfrw.PdfName('Yes'), V=pdfrw.PdfName('Yes'))200 )201 else:202 annotation.update(pdfrw.PdfDict(203 AS=pdfrw.PdfName('Off'), V=pdfrw.PdfName('Off'))204 )205 else: # Text field206 annotation.update(pdfrw.PdfDict(207 AP='', V=data_dict[key])208 )209 210 elif annotation[PARENT_KEY][ANNOT_FIELD_KEY]: ### Grouped fields (has a '/Parent' -> '/T' key)211 group = annotation[PARENT_KEY][ANNOT_FIELD_KEY][1:-1]212 if group in data_dict.keys():213 if type(data_dict[group]) == dict and len(data_dict[group]) != 0: # Radio buttons214 selected_radio_button = pdfrw.PdfName(list(data_dict[group].keys())[0])215 if(selected_radio_button in annotation[APPEARANCE_KEY][D_KEY].keys()):216 # Page 441 of:217 # https://www.adobe.com/content/dam/acom/en/devnet/pdf/pdfs/PDF32000_2008.pdf218 annotation[PARENT_KEY].update(pdfrw.PdfDict(219 V=selected_radio_button)220 )221 annotation.update(pdfrw.PdfDict(222 AS=selected_radio_button)223 )224 elif type(data_dict[group]) == bool: # Linked checkboxes (across multiple pages?)225 if data_dict[group] == True:226 annotation.update(pdfrw.PdfDict(227 AS=pdfrw.PdfName('Yes'), V=pdfrw.PdfName('Yes'))228 )229 else:230 annotation.update(pdfrw.PdfDict(231 AS=pdfrw.PdfName('Off'), V=pdfrw.PdfName('Off'))232 )233 else: # Linked text fields (across multiple pages?)234 annotation[PARENT_KEY].update(pdfrw.PdfDict(235 AP='', V=data_dict[group])236 )237 238 if not output_pdf_path.parent.exists():239 print(f" Location of output PDF '{output_pdf_path}' doesn't exist; creating: {output_pdf_path.parent}")240 output_pdf_path.parent.mkdir(parents=True, exist_ok=True)241 242 template_pdf.Root.AcroForm.update(pdfrw.PdfDict(NeedAppearances=pdfrw.PdfObject('true')))243 pdfrw.PdfWriter().write(output_pdf_path, template_pdf)244 return245################################################################246################################################################247if __name__ == '__main__':248 RECORD,REDCAP_UNIQUE_IDENTIFIER,PDF_TEMPLATE,OUTPUT = get_cmd_line_input(parser.parse_args())249 print()250 secrets = load_secrets(SECRETS_FILE)251 print("Loaded secrets file")252 proj_metadata = redcap_helpers.get_metadata(secrets)253 print("Got project metadata")254 # print(redcap_helpers.get_fields_and_types(proj_metadata))255 # proj_multiple_choice_text = redcap_helpers.get_multiple_choice_text(proj_metadata)256 # print(proj_multiple_choice_text)257 record = redcap_helpers.get_record(secrets, REDCAP_UNIQUE_IDENTIFIER, RECORD)258 print(f"Got record {RECORD} (identified by '{REDCAP_UNIQUE_IDENTIFIER}')")259 prepared_data_dict = prepare_for_fill(record, proj_metadata)260 print("Prepared Python dictionary:", prepared_data_dict)261 print("Using PDF template: " + str(PDF_TEMPLATE))262 fill_pdf(PDF_TEMPLATE, OUTPUT, prepared_data_dict)263 print("PDF written to: " + str(OUTPUT))...

Full Screen

Full Screen

pdf_tenant.py

Source:pdf_tenant.py Github

copy

Full Screen

1from tablesdb import Sql_database2from pathlib import Path3import os4# pdf function generator5class Pdf_tenant:6 def __init__(self, pdf, nom, prenom, adresse, ville, loyer, charge, day, month, years, cat,7 sci_nom, sci_adresse, sci_cp_ville, sci_tel, sci_mail, sci_siret):8 self.month_list = {1: "Janvier", 2: "Fevrier", 3: "Mars",9 4: "Avril", 5: "Mai", 6: "Juin",10 7: "Juillet", 8: "Aout", 9: "Septembre",11 10: "Octobre", 11: "Novembre", 12: "Decembre"}12 self.pdf = pdf13 self.nom = nom14 self.prenom = prenom15 self.adresse = adresse16 self.ville = ville17 self.loyer = loyer18 self.charge = charge19 self.day = day20 self.month = month21 self.year = years22 self.cat = cat23 self.sci_nom = sci_nom24 self.sci_adresse = sci_adresse25 self.sci_cp_ville = sci_cp_ville26 self.sci_tel = sci_tel27 self.sci_mail = sci_mail28 self.sci_siret = sci_siret29 self.database = Sql_database()30 def generator(self):31 self.pdf.setFont("Helvetica", 15)32 if self.cat == 0: # habitation case33 self.pdf.drawString(150, 550,34 f"Loyer pour le mois de {self.month_list[int(self.month)]} {self.year}")35 self.pdf.drawString(140, 450, "Loyer")36 self.pdf.drawString(340, 450, f"{float(self.loyer):0.2f} €")37 self.pdf.drawString(140, 420, "Provision pour charges")38 self.pdf.drawString(345, 420, f"{float(self.charge):0.2f} €")39 self.pdf.drawString(140, 400, "Total")40 self.pdf.drawString(340, 400, f"{float(self.loyer) + float(self.charge):0.2f} €")41 else:42 self.pdf.drawString(150, 570, f"FACTURE N° {self.month}/{self.year}")43 self.pdf.drawString(100, 530,44 f"Loyer pour le mois de {self.month_list[int(self.month)]} {self.year}")45 self.pdf.drawString(100, 450, "Loyer hors taxes")46 loyer_ht = (float(self.loyer / 1.20))47 self.pdf.drawString(350, 450, f"{loyer_ht:0.2f} €")48 self.pdf.drawString(100, 430, "TVA 20 %")49 self.pdf.drawString(355, 430, f"{(float(self.loyer) - loyer_ht):0.2f} €")50 self.pdf.drawString(100, 410, "Provision pour charges")51 self.pdf.drawString(355, 410, f"{float(self.charge):0.2f} €")52 self.pdf.drawString(100, 390, "Montant TTC")53 self.pdf.drawString(350, 390, f"{float(self.loyer) + float(self.charge):0.2f} €")54 # Coordonnées de la SCI55 self.pdf.drawString(20, 800, f"{self.sci_nom}") # colon, row ( 0 down / 800 up) ( 0 left / 600 right)56 self.pdf.drawString(20, 785, f"{self.sci_adresse}")57 self.pdf.drawString(20, 770, f"{self.sci_cp_ville}")58 self.pdf.drawString(20, 755, f"{self.sci_tel}")59 self.pdf.drawString(20, 740, f"{self.sci_siret}")60 # Coordonnées du locataire61 self.pdf.drawString(350, 700, f"{self.nom} {self.prenom}")62 self.pdf.drawString(350, 685, f"{self.adresse}")63 self.pdf.drawString(350, 670, f"{self.ville}")64 # Date65 self.pdf.drawString(350, 600, f"A {self.sci_cp_ville.split(' ', 1)[1]} le {self.day}/{self.month}/{self.year}")66 # corps67 self.pdf.drawCentredString(160, 613, "QUITTANCE DE LOYER")68 # graphic elements69 self.pdf.line(10, 630, 590, 630)70 self.pdf.line(10, 595, 590, 595)71 self.pdf.line(10, 630, 10, 595)72 self.pdf.line(590, 630, 590, 595)73 p = Path()74 s = p / 'sign.PNG'75 if s.exists():76 self.pdf.drawImage("sign.PNG", 350, 80, width=120, height=120)77 # ending78 self.pdf.showPage()79 self.pdf.save()80class IndexLetter:81 def __init__(self, pdf, nom, prenom, adresse, ville, loyer, charge, day, month, year,82 sci_nom, sci_adresse, sci_cp_ville, sci_tel, sci_mail, sci_siret, indice_base, indice_new, cat, date_entree):83 self.month_list = {1: ["Janvier", "1er trimestre"], 2: ["Fevrier", "1er trimestre"], 3: ["Mars", "1er trimestre"],84 4: ["Avril", "2eme trimestre"], 5: ["Mai", "2eme trimestre"], 6: ["Juin", "2eme trimestre"],85 7: ["Juillet", "3eme trimestre"], 8: ["Aout", "3eme trimestre"], 9: ["Septembre", "3eme trimestre"],86 10: ["Octobre", "3eme trimestre"], 11: ["Novembre", "3eme trimestre"], 12: ["Decembre", "3eme trimestre"]}87 self.pdf = pdf88 self.nom = nom89 self.prenom = prenom90 self.adresse = adresse91 self.ville = ville92 self.loyer = float(loyer) * float(indice_new) / float(indice_base)93 self.charge = charge94 self.day = day95 self.month = month96 self.year = year97 self.sci_nom = sci_nom98 self.sci_adresse = sci_adresse99 self.sci_cp_ville = sci_cp_ville100 self.sci_tel = sci_tel101 self.sci_mail = sci_mail102 self.sci_siret = sci_siret103 self.indice_base = indice_base104 self.new_indice = indice_new105 self.cat = cat106 self.date_entree = date_entree107 self.database = Sql_database()108 if self.cat == 1:109 self.type ="loyers commerciaux"110 else:111 self.type ="de références des loyers"112 def generator(self):113 self.pdf.setFont("Helvetica", 15)114 if self.cat == 1:115 self.pdf.drawString(60, 300, "Loyer hors charges")116 self.pdf.drawString(250, 300, f"{float(self.loyer) / 1.20:0.2f} €")117 self.pdf.drawString(60, 280, "TVA")118 self.pdf.drawString(250, 280, f"{float(self.loyer) - float(self.loyer) / 1.20:0.2f} €")119 self.pdf.drawString(60, 260, "Provisions pour charges")120 self.pdf.drawString(255, 260, f"{self.charge:0.2f} €")121 self.pdf.drawString(60, 240, "Total")122 self.pdf.drawString(250, 240, f"{float(self.loyer) + float(self.charge):0.2f} €")123 else:124 self.pdf.drawString(60, 300, "Loyer")125 self.pdf.drawString(250, 300, f"{float(self.loyer):0.2f} €")126 self.pdf.drawString(60, 280, "Provisions pour charges")127 self.pdf.drawString(255, 280, f"{self.charge:0.2f} €")128 self.pdf.drawString(60, 260, "Total")129 self.pdf.drawString(250, 260, f"{float(self.loyer) + float(self.charge):0.2f} €")130 # Coordonnées de la SCI131 self.pdf.drawString(20, 800, f"{self.sci_nom}") # colon, row ( 0 down / 800 up) ( 0 left / 600 right)132 self.pdf.drawString(20, 785, f"{self.sci_adresse}")133 self.pdf.drawString(20, 770, f"{self.sci_cp_ville}")134 self.pdf.drawString(20, 755, f"{self.sci_tel}")135 self.pdf.drawString(20, 740, f"{self.sci_siret}")136 # Coordonnées du locataire137 self.pdf.drawString(350, 700, f"{self.nom} {self.prenom}")138 self.pdf.drawString(350, 685, f"{self.adresse}")139 self.pdf.drawString(350, 670, f"{self.ville}")140 # Date141 self.pdf.drawString(350, 613, f"A {self.sci_cp_ville.split(' ', 1)[1]} le {self.day}/{self.month}/{self.year}")142 # Corps143 self.pdf.drawString(20, 560, "OBJET : REVISION DU LOYER")144 self.pdf.drawString(20, 500, "Madame, Monsieur")145 self.pdf.drawString(20, 460, f"Par la présente, je vous informe qu'à compter du {self.day} {self.month_list[int(self.month)][0]} {self.year} , votre loyer principal")146 self.pdf.drawString(20, 440, f"mensuel s'élèvera à la somme de {self.loyer:0.2f} € TTC.Cette variation a été calculée")147 self.pdf.drawString(20, 420, f"selon l'indice de révision (indice national des {self.type} prévu dans ")148 self.pdf.drawString(20, 400, "votre bail conformément à la législation en vigeur. Le loyer hors charges est augmenté")149 self.pdf.drawString(20, 380, f"de {float(self.new_indice) / float(self.indice_base):0.2f} %. Les deux indices considérés sont :")150 self.pdf.drawString(60, 360, f"- {self.month_list[int(self.month)][1]} {self.date_entree.split('/')[2]}: {self.indice_base}")151 self.pdf.drawString(60, 340, f"- {self.month_list[int(self.month)][1]} {self.year} : {self.new_indice}")152 self.pdf.drawString(20, 320, "Les nouvelles données de votre quittance seront dorénavant les suivantes :")153 self.pdf.drawString(20, 220, "Je reste à votre dispositionpour de plus amples renseignements. Dans cette attente")154 self.pdf.drawString(20, 200, "veuillez agréer, Madame, Monsieur, l'expression de mes salutaions distinguées")155 self.pdf.drawString(20, 160, "Le Gérant.")156 p = Path()157 s = p / 'sign.PNG'158 if s.exists():159 self.pdf.drawImage("sign.PNG", 20, 30, width=120, height=120)160 self.pdf.showPage()161 self.pdf.save()162class Pdf_shareholder:163 def __init__(self, pdf, nom, prenom, sci, date, montant):164 self.pdf = pdf165 self.nom = nom166 self.prenom = prenom167 self.sci = sci168 self.date = date169 self.montant = montant170 def generator(self):171 self.pdf.drawString(20, 800, f"SCI {self.sci}")172 self.pdf.drawString(350, 613, f"le {self.date}")173 self.pdf.drawString(350, 700, f"{self.nom} {self.prenom}")174 self.pdf.drawString(20, 460, f" Un virement de {self.montant} à été éffectué sur votre compte")175 self.pdf.drawString(20, 220,176 "Je reste à votre dispositionpour de plus amples renseignements. Dans cette attente")177 self.pdf.drawString(20, 200, "veuillez agréer, Madame, Monsieur, l'expression de mes salutaions distinguées")178 self.pdf.drawString(20, 160, "Le Gérant.")179 p = Path()180 s = p / 'sign.PNG'181 if s.exists():182 self.pdf.drawImage("sign.PNG", 20, 30, width=120, height=120)183 self.pdf.showPage()184 self.pdf.save()185if __name__ == "__main__":186 from reportlab.pdfgen import canvas187 directory = Path(__file__).parent188 directory.mkdir(parents=True, exist_ok=True)189 path = directory.joinpath("test.pdf")190 pdf = canvas.Canvas(str(path))191 pdf_gen = Pdf_tenant(pdf, nom="SEBAN", prenom="Emmanuel", adresse="7 rue ducis", ville="78000 VERSAILLES",192 loyer=1000, charge="200", day="12", month="05", years="2020", cat=1,193 sci_nom="JOMO",194 sci_adresse="19 rue laurent Gaudet", sci_cp_ville="78150 LE CHESNAY",195 sci_tel="01 39 55 16 69", sci_mail="marcelseban@hotmail.fr", sci_siret="155522220")196 #pdf_gen = IndexLetter(pdf, nom="SEBAN", prenom="Emmanuel", adresse="7 rue ducis", ville="78000 VERSAILLES",197 # loyer="1000", charge="200", day="12", month="5", year="2020", sci_nom="JOMO",198 # sci_adresse="19 rue laurent Gaudet", sci_cp_ville="78150 LE CHESNAY", sci_tel="01 39 55 16 69"199 # , sci_mail="marcelseban@hotmail.fr", sci_siret="155522220", indice_base="110", indice_new="115", cat=0)...

Full Screen

Full Screen

views.py

Source:views.py Github

copy

Full Screen

1from __future__ import print_function2from django.shortcuts import render3from django.urls import reverse4from django.http import HttpResponseRedirect, Http404, FileResponse5from django.contrib.auth import authenticate, login, logout6from django.db.models import Value, Count, CharField7from django.core.files.storage import FileSystemStorage8from .models import User_profile9from datetime import datetime 10from tzlocal import get_localzone11from PyPDF2 import PdfFileReader, PdfFileWriter, PdfFileMerger12from .forms import PDFMergeForm, PDFSplitForm, PDFDeleteForm13import os14import io15from zipfile import ZipFile16from apiclient.discovery import build17from google.oauth2 import service_account18from oauth2client import file, client, tools19from httplib2 import Http20from . import auth21from users.facadeGoogleDrive import GoogleDrive22# Create your views here.23def index(request):24 return render(request, "pdf/upload.html")25def upload(request ,name , file_path , mimetype):26 GoogleDrive().upload(request,name, file_path, mimetype)27def download(request , file_id , file_name , mimeType) :28 return GoogleDrive().download(file_id, file_name, mimeType)29def get_user_history(folder_id) :30 return GoogleDrive().get_user_history(folder_id)31def merge(request):32 if request.method == 'POST':33 form = PDFMergeForm(request.POST, request.FILES)34 if form.is_valid():35 # get file input from merge form36 file1 = form.cleaned_data['file1']37 file2 = form.cleaned_data['file2']38 # make sure that both input files is pdf39 if ((os.path.splitext(str(file1))[1] != '.pdf') or (os.path.splitext(str(file2))[1] != '.pdf')):40 return render(request, 'pdf/pdf_split.html', {'form':form})41 # merge two file42 pdfMerge = PdfFileMerger()43 pdfMerge.append(PdfFileReader(file1))44 pdfMerge.append(PdfFileReader(file2))45 # write merged file46 pdfMerge.write('merged_file.pdf')47 # output merged file48 response = FileResponse(open('merged_file.pdf', 'rb'))49 response['content_type'] = "application/pdf"50 response['Content-Disposition'] = 'attachment;filename="merged_file.pdf"'51 52 # check if user is not anonymous (authenticated user)53 # upload processed file to google drive54 if not request.user.is_anonymous:55 date_time = datetime.fromtimestamp(datetime.now().timestamp(),get_localzone()).strftime("%d/%m/%Y %H:%M:%S")56 upload(request,"merged file {}.pdf".format(date_time) , "merged_file.pdf" , "pdf")57 # remove processed file58 os.remove('merged_file.pdf')59 return response60 else:61 form = PDFMergeForm()62 else:63 form = PDFMergeForm()64 return render(request, 'pdf/pdf_merge.html', {'form':form})65def split(request):66 if request.method == 'POST':67 form = PDFSplitForm(request.POST, request.FILES)68 if form.is_valid():69 # get file input from split form70 inputFile = form.cleaned_data['file1']71 pageNum = form.cleaned_data['pageNum']72 # make sure that input file is pdf73 if (os.path.splitext(str(inputFile))[1] != '.pdf'):74 return render(request, 'pdf/pdf_split.html', {'form':form})75 # read input pdf76 inputPDF = PdfFileReader(inputFile)77 outputPDF1 = PdfFileWriter()78 outputPDF2 = PdfFileWriter()79 # make sure that page number is valid80 if ((int(pageNum) <= 0) or (int(pageNum) > inputPDF.getNumPages()) or (inputPDF.getNumPages() == 1)):81 return render(request, 'pdf/pdf_split.html', {82 'message': 'Invalid',83 'form': form,84 })85 # split first half of the pdf from 0 to page number86 for i in range(pageNum):87 outputPDF1.addPage(inputPDF.getPage(i))88 with open('splited_file_1.pdf', 'wb') as outfile:89 outputPDF1.write(outfile)90 # split second half of the pdf from (page number+1) to last page91 for i in range(pageNum, inputPDF.getNumPages()):92 outputPDF2.addPage(inputPDF.getPage(i))93 with open('splited_file_2.pdf', 'wb') as outfile:94 outputPDF2.write(outfile)95 # zip two file for output96 zf = ZipFile('splited_files.zip', "w")97 zf.write('splited_file_1.pdf', 'splited_file_1.pdf')98 zf.write('splited_file_2.pdf', 'splited_file_2.pdf')99 zf.close()100 # output splited file101 response = FileResponse(open('splited_files.zip', 'rb'))102 response['content_type'] = "application/pdf"103 response['Content-Disposition'] = 'attachment;filename="splited_files.zip"'104 # check if user is not anonymous (authenticated user)105 # upload processed file to google drive106 if not request.user.is_anonymous:107 date_time = datetime.fromtimestamp(datetime.now().timestamp(),get_localzone()).strftime("%d/%m/%Y %H:%M:%S")108 upload(request,"splited file {}.zip".format(date_time) , "splited_files.zip" , "zip")109 110 # remove processed file111 os.remove('splited_files.zip')112 os.remove('splited_file_1.pdf')113 os.remove('splited_file_2.pdf')114 return response115 else:116 form = PDFSplitForm()117 else:118 form = PDFSplitForm()119 return render(request, 'pdf/pdf_split.html', {'form':form})120def delete(request):121 if request.method == 'POST':122 form = PDFDeleteForm(request.POST, request.FILES)123 if form.is_valid():124 # get file input from delete form125 inputFile = form.cleaned_data['file1']126 # make sure that input file is pdf127 if (os.path.splitext(str(inputFile))[1] != '.pdf'):128 return render(request, 'pdf/pdf_split.html', {'form':form})129 # read input pdf130 inputPDF = PdfFileReader(inputFile)131 outputPDF = PdfFileWriter()132 133 # get the correct page(s) to delete134 pageNum = form.cleaned_data['pageNum'].replace(" ", "").split(',')135 pageToDeleteDup = []136 for page in pageNum:137 pageInt = [int(i) for i in page.split('-')]138 if (len(pageInt) == 2):139 for i in range(pageInt[0], pageInt[-1] + 1):140 pageToDeleteDup += [i]141 else:142 pageToDeleteDup += pageInt143 pageToDelete = []144 # delete duplication page number in list145 for num in pageToDeleteDup:146 if num not in pageToDelete:147 pageToDelete.append(num)148 # make sure that page number is valid149 if ((max(pageToDelete) > inputPDF.getNumPages()) or (min(pageToDelete) <= 0) or (inputPDF.getNumPages() == 1)):150 return render(request, 'pdf/pdf_delete.html', {151 'message': 'Invalid',152 'form': form,153 })154 # delete page(s)155 for i in range(inputPDF.getNumPages()):156 if (i + 1) not in pageToDelete:157 outputPDF.addPage(inputPDF.getPage(i))158 with open('deleted_file.pdf', 'wb') as outfile:159 outputPDF.write(outfile)160 # output deleted file161 response = FileResponse(open('deleted_file.pdf', 'rb'))162 response['content_type'] = "application/pdf"163 response['Content-Disposition'] = 'attachment;filename="deleted_file.pdf"'164 # check if user is not anonymous (authenticated user)165 # upload processed file to google drive166 if not request.user.is_anonymous:167 date_time = datetime.fromtimestamp(datetime.now().timestamp(),get_localzone()).strftime("%d/%m/%Y %H:%M:%S")168 upload(request,"deleted file {}.pdf".format(date_time) , "deleted_file.pdf" , "pdf")169 170 # remove processed file171 os.remove('deleted_file.pdf')172 return response173 else:174 form = PDFDeleteForm()175 else:176 form = PDFDeleteForm()...

Full Screen

Full Screen

PdfImagePlugin.py

Source:PdfImagePlugin.py Github

copy

Full Screen

1#2# The Python Imaging Library.3# $Id$4#5# PDF (Acrobat) file handling6#7# History:8# 1996-07-16 fl Created9# 1997-01-18 fl Fixed header10# 2004-02-21 fl Fixes for 1/L/CMYK images, etc.11# 2004-02-24 fl Fixes for 1 and P images.12#13# Copyright (c) 1997-2004 by Secret Labs AB. All rights reserved.14# Copyright (c) 1996-1997 by Fredrik Lundh.15#16# See the README file for information on usage and redistribution.17#18##19# Image plugin for PDF images (output only).20##21from . import Image, ImageFile, ImageSequence, PdfParser22import io23__version__ = "0.5"24#25# --------------------------------------------------------------------26# object ids:27# 1. catalogue28# 2. pages29# 3. image30# 4. page31# 5. page contents32def _save_all(im, fp, filename):33 _save(im, fp, filename, save_all=True)34##35# (Internal) Image save plugin for the PDF format.36def _save(im, fp, filename, save_all=False):37 resolution = im.encoderinfo.get("resolution", 72.0)38 is_appending = im.encoderinfo.get("append", False)39 title = im.encoderinfo.get("title", None)40 author = im.encoderinfo.get("author", None)41 subject = im.encoderinfo.get("subject", None)42 keywords = im.encoderinfo.get("keywords", None)43 creator = im.encoderinfo.get("creator", None)44 producer = im.encoderinfo.get("producer", None)45 if is_appending:46 existing_pdf = PdfParser.PdfParser(f=fp, filename=filename, mode="r+b")47 else:48 existing_pdf = PdfParser.PdfParser(f=fp, filename=filename, mode="w+b")49 if title:50 existing_pdf.info.Title = title51 if author:52 existing_pdf.info.Author = author53 if subject:54 existing_pdf.info.Subject = subject55 if keywords:56 existing_pdf.info.Keywords = keywords57 if creator:58 existing_pdf.info.Creator = creator59 if producer:60 existing_pdf.info.Producer = producer61 #62 # make sure image data is available63 im.load()64 existing_pdf.start_writing()65 existing_pdf.write_header()66 existing_pdf.write_comment("created by PIL PDF driver " + __version__)67 #68 # pages69 ims = [im]70 if save_all:71 append_images = im.encoderinfo.get("append_images", [])72 for append_im in append_images:73 append_im.encoderinfo = im.encoderinfo.copy()74 ims.append(append_im)75 numberOfPages = 076 image_refs = []77 page_refs = []78 contents_refs = []79 for im in ims:80 im_numberOfPages = 181 if save_all:82 try:83 im_numberOfPages = im.n_frames84 except AttributeError:85 # Image format does not have n_frames. It is a single frame image86 pass87 numberOfPages += im_numberOfPages88 for i in range(im_numberOfPages):89 image_refs.append(existing_pdf.next_object_id(0))90 page_refs.append(existing_pdf.next_object_id(0))91 contents_refs.append(existing_pdf.next_object_id(0))92 existing_pdf.pages.append(page_refs[-1])93 #94 # catalog and list of pages95 existing_pdf.write_catalog()96 pageNumber = 097 for imSequence in ims:98 for im in ImageSequence.Iterator(imSequence):99 # FIXME: Should replace ASCIIHexDecode with RunLengthDecode (packbits)100 # or LZWDecode (tiff/lzw compression). Note that PDF 1.2 also supports101 # Flatedecode (zip compression).102 bits = 8103 params = None104 if im.mode == "1":105 filter = "ASCIIHexDecode"106 colorspace = PdfParser.PdfName("DeviceGray")107 procset = "ImageB" # grayscale108 bits = 1109 elif im.mode == "L":110 filter = "DCTDecode"111 # params = "<< /Predictor 15 /Columns %d >>" % (width-2)112 colorspace = PdfParser.PdfName("DeviceGray")113 procset = "ImageB" # grayscale114 elif im.mode == "P":115 filter = "ASCIIHexDecode"116 palette = im.im.getpalette("RGB")117 colorspace = [PdfParser.PdfName("Indexed"), PdfParser.PdfName("DeviceRGB"), 255, PdfParser.PdfBinary(palette)]118 procset = "ImageI" # indexed color119 elif im.mode == "RGB":120 filter = "DCTDecode"121 colorspace = PdfParser.PdfName("DeviceRGB")122 procset = "ImageC" # color images123 elif im.mode == "CMYK":124 filter = "DCTDecode"125 colorspace = PdfParser.PdfName("DeviceCMYK")126 procset = "ImageC" # color images127 else:128 raise ValueError("cannot save mode %s" % im.mode)129 #130 # image131 op = io.BytesIO()132 if filter == "ASCIIHexDecode":133 if bits == 1:134 # FIXME: the hex encoder doesn't support packed 1-bit135 # images; do things the hard way...136 data = im.tobytes("raw", "1")137 im = Image.new("L", (len(data), 1), None)138 im.putdata(data)139 ImageFile._save(im, op, [("hex", (0, 0)+im.size, 0, im.mode)])140 elif filter == "DCTDecode":141 Image.SAVE["JPEG"](im, op, filename)142 elif filter == "FlateDecode":143 ImageFile._save(im, op, [("zip", (0, 0)+im.size, 0, im.mode)])144 elif filter == "RunLengthDecode":145 ImageFile._save(im, op, [("packbits", (0, 0)+im.size, 0, im.mode)])146 else:147 raise ValueError("unsupported PDF filter (%s)" % filter)148 #149 # Get image characteristics150 width, height = im.size151 existing_pdf.write_obj(image_refs[pageNumber], stream=op.getvalue(),152 Type=PdfParser.PdfName("XObject"),153 Subtype=PdfParser.PdfName("Image"),154 Width=width, # * 72.0 / resolution,155 Height=height, # * 72.0 / resolution,156 Filter=PdfParser.PdfName(filter),157 BitsPerComponent=bits,158 DecodeParams=params,159 ColorSpace=colorspace)160 #161 # page162 existing_pdf.write_page(page_refs[pageNumber],163 Resources=PdfParser.PdfDict(164 ProcSet=[PdfParser.PdfName("PDF"), PdfParser.PdfName(procset)],165 XObject=PdfParser.PdfDict(image=image_refs[pageNumber])),166 MediaBox=[0, 0, int(width * 72.0 / resolution), int(height * 72.0 / resolution)],167 Contents=contents_refs[pageNumber]168 )169 #170 # page contents171 page_contents = PdfParser.make_bytes(172 "q %d 0 0 %d 0 0 cm /image Do Q\n" % (173 int(width * 72.0 / resolution),174 int(height * 72.0 / resolution)))175 existing_pdf.write_obj(contents_refs[pageNumber], stream=page_contents)176 pageNumber += 1177 #178 # trailer179 existing_pdf.write_xref_and_trailer()180 if hasattr(fp, "flush"):181 fp.flush()182 existing_pdf.close()183#184# --------------------------------------------------------------------185Image.register_save("PDF", _save)186Image.register_save_all("PDF", _save_all)187Image.register_extension("PDF", ".pdf")...

Full Screen

Full Screen

pdf_manager.js

Source:pdf_manager.js Github

copy

Full Screen

1/* -*- Mode: Java; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */2/* vim: set shiftwidth=2 tabstop=2 autoindent cindent expandtab: */3/* Copyright 2012 Mozilla Foundation4 *5 * Licensed under the Apache License, Version 2.0 (the "License");6 * you may not use this file except in compliance with the License.7 * You may obtain a copy of the License at8 *9 * http://www.apache.org/licenses/LICENSE-2.010 *11 * Unless required by applicable law or agreed to in writing, software12 * distributed under the License is distributed on an "AS IS" BASIS,13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.14 * See the License for the specific language governing permissions and15 * limitations under the License.16 */17/* globals NotImplementedException, MissingDataException, Promise, Stream,18 PDFDocument, ChunkedStreamManager, createPromiseCapability */19'use strict';20// The maximum number of bytes fetched per range request21var RANGE_CHUNK_SIZE = 65536;22// TODO(mack): Make use of PDFJS.Util.inherit() when it becomes available23var BasePdfManager = (function BasePdfManagerClosure() {24 function BasePdfManager() {25 throw new Error('Cannot initialize BaseManagerManager');26 }27 BasePdfManager.prototype = {28 onLoadedStream: function BasePdfManager_onLoadedStream() {29 throw new NotImplementedException();30 },31 ensureDoc: function BasePdfManager_ensureDoc(prop, args) {32 return this.ensure(this.pdfDocument, prop, args);33 },34 ensureXRef: function BasePdfManager_ensureXRef(prop, args) {35 return this.ensure(this.pdfDocument.xref, prop, args);36 },37 ensureCatalog: function BasePdfManager_ensureCatalog(prop, args) {38 return this.ensure(this.pdfDocument.catalog, prop, args);39 },40 getPage: function BasePdfManager_pagePage(pageIndex) {41 return this.pdfDocument.getPage(pageIndex);42 },43 cleanup: function BasePdfManager_cleanup() {44 return this.pdfDocument.cleanup();45 },46 ensure: function BasePdfManager_ensure(obj, prop, args) {47 return new NotImplementedException();48 },49 requestRange: function BasePdfManager_ensure(begin, end) {50 return new NotImplementedException();51 },52 requestLoadedStream: function BasePdfManager_requestLoadedStream() {53 return new NotImplementedException();54 },55 sendProgressiveData: function BasePdfManager_sendProgressiveData(chunk) {56 return new NotImplementedException();57 },58 updatePassword: function BasePdfManager_updatePassword(password) {59 this.pdfDocument.xref.password = this.password = password;60 if (this._passwordChangedCapability) {61 this._passwordChangedCapability.resolve();62 }63 },64 passwordChanged: function BasePdfManager_passwordChanged() {65 this._passwordChangedCapability = createPromiseCapability();66 return this._passwordChangedCapability.promise;67 },68 terminate: function BasePdfManager_terminate() {69 return new NotImplementedException();70 }71 };72 return BasePdfManager;73})();74var LocalPdfManager = (function LocalPdfManagerClosure() {75 function LocalPdfManager(data, password) {76 var stream = new Stream(data);77 this.pdfDocument = new PDFDocument(this, stream, password);78 this._loadedStreamCapability = createPromiseCapability();79 this._loadedStreamCapability.resolve(stream);80 }81 LocalPdfManager.prototype = Object.create(BasePdfManager.prototype);82 LocalPdfManager.prototype.constructor = LocalPdfManager;83 LocalPdfManager.prototype.ensure =84 function LocalPdfManager_ensure(obj, prop, args) {85 return new Promise(function (resolve, reject) {86 try {87 var value = obj[prop];88 var result;89 if (typeof value === 'function') {90 result = value.apply(obj, args);91 } else {92 result = value;93 }94 resolve(result);95 } catch (e) {96 reject(e);97 }98 });99 };100 LocalPdfManager.prototype.requestRange =101 function LocalPdfManager_requestRange(begin, end) {102 return Promise.resolve();103 };104 LocalPdfManager.prototype.requestLoadedStream =105 function LocalPdfManager_requestLoadedStream() {106 };107 LocalPdfManager.prototype.onLoadedStream =108 function LocalPdfManager_getLoadedStream() {109 return this._loadedStreamCapability.promise;110 };111 LocalPdfManager.prototype.terminate =112 function LocalPdfManager_terminate() {113 return;114 };115 return LocalPdfManager;116})();117var NetworkPdfManager = (function NetworkPdfManagerClosure() {118 function NetworkPdfManager(args, msgHandler) {119 this.msgHandler = msgHandler;120 var params = {121 msgHandler: msgHandler,122 httpHeaders: args.httpHeaders,123 withCredentials: args.withCredentials,124 chunkedViewerLoading: args.chunkedViewerLoading,125 disableAutoFetch: args.disableAutoFetch,126 initialData: args.initialData127 };128 this.streamManager = new ChunkedStreamManager(args.length, RANGE_CHUNK_SIZE,129 args.url, params);130 this.pdfDocument = new PDFDocument(this, this.streamManager.getStream(),131 args.password);132 }133 NetworkPdfManager.prototype = Object.create(BasePdfManager.prototype);134 NetworkPdfManager.prototype.constructor = NetworkPdfManager;135 NetworkPdfManager.prototype.ensure =136 function NetworkPdfManager_ensure(obj, prop, args) {137 var pdfManager = this;138 return new Promise(function (resolve, reject) {139 function ensureHelper() {140 try {141 var result;142 var value = obj[prop];143 if (typeof value === 'function') {144 result = value.apply(obj, args);145 } else {146 result = value;147 }148 resolve(result);149 } catch(e) {150 if (!(e instanceof MissingDataException)) {151 reject(e);152 return;153 }154 pdfManager.streamManager.requestRange(e.begin, e.end, ensureHelper);155 }156 }157 ensureHelper();158 });159 };160 NetworkPdfManager.prototype.requestRange =161 function NetworkPdfManager_requestRange(begin, end) {162 return new Promise(function (resolve) {163 this.streamManager.requestRange(begin, end, function() {164 resolve();165 });166 }.bind(this));167 };168 NetworkPdfManager.prototype.requestLoadedStream =169 function NetworkPdfManager_requestLoadedStream() {170 this.streamManager.requestAllChunks();171 };172 NetworkPdfManager.prototype.sendProgressiveData =173 function NetworkPdfManager_sendProgressiveData(chunk) {174 this.streamManager.onReceiveData({ chunk: chunk });175 };176 NetworkPdfManager.prototype.onLoadedStream =177 function NetworkPdfManager_getLoadedStream() {178 return this.streamManager.onLoadedStream();179 };180 NetworkPdfManager.prototype.terminate =181 function NetworkPdfManager_terminate() {182 this.streamManager.networkManager.abortAllRequests();183 };184 return NetworkPdfManager;...

Full Screen

Full Screen

video_reader.py

Source:video_reader.py Github

copy

Full Screen

1import os2import cv23import time4from moviepy.editor import AudioFileClip5import tqdm6import glob7from PyPDF2 import PdfFileMerger, PdfFileReader8from modules.tape import TapeFrame, Tapes, PDF9class VideoReader:10 def __init__(self, dt: float = 1.0, take_speech: bool = True, verbose: bool = True, **kwargs):11 self.dt = dt12 self.take_speech = take_speech13 self.verbose = verbose14 self.saving_folder = kwargs.get("saving_folder", 'resultsdata')15 self.kwargs = kwargs16 self.pdf_paths = []17 os.makedirs("tempdata", exist_ok=True)18 os.makedirs("resultsdata", exist_ok=True)19 def make_pdf_from_mp4(self, mp4_filename: str) -> str:20 vidcap = cv2.VideoCapture(mp4_filename)21 audioclip = AudioFileClip(mp4_filename) if self.take_speech else None22 pdf = PDF(os.path.basename(mp4_filename).replace(".mp4", ''),23 take_text=self.take_speech,24 saving_folder=self.saving_folder,)25 tapes = Tapes()26 cv2.startWindowThread()27 t_i = time.time()28 frame_start_time = 029 frame_end_time = 030 time_s = 031 print(f"Reading of the video ...") if self.verbose else None32 while True:33 vidcap.set(cv2.CAP_PROP_POS_MSEC, time_s * 1_000)34 success, image = vidcap.read()35 if not success:36 break37 image = cv2.resize(image, (min(980, image.shape[0]), min(750, image.shape[1])))38 if not tapes.has_image_at(image, -1):39 frame_end_time = time_s40 if self.take_speech and len(tapes) > 0:41 subaudio = audioclip.subclip(frame_start_time, frame_end_time)42 # print("duration audio cut: ", time.strftime('%H:%M:%S', time.gmtime(subaudio.duration)),43 # " [h:m:s] ", (frame_start_time, frame_end_time))44 tapes[-1].audioclip = subaudio45 if len(tapes) > 0:46 frame_start_time = frame_end_time47 tapes[-1].times = (frame_start_time, frame_end_time)48 tapes.add_tape(TapeFrame(image, **self.kwargs))49 time_s += self.dt50 cv2.destroyAllWindows()51 t_f = time.time()52 vidcap.release()53 print(f"Reading of the video done") if self.verbose else None54 print(f"Making the pdf...") if self.verbose else None55 pdf.add_diapos(tapes)56 pdf.save()57 print(f"Making pdf done") if self.verbose else None58 print(f"elapse time: {t_f - t_i:.2f} [s]") if self.verbose else None59 self.pdf_paths.append(pdf.path)60 return pdf.path61 def get_sort_pdf_paths(self) -> list:62 sorted_paths = self.pdf_paths.copy()63 sorted_paths.sort()64 return sorted_paths65 def make_pdf_from_folder(self, dir_path: str) -> str:66 self.saving_folder = dir_path67 for mp4_file_path in tqdm.tqdm(glob.glob(os.path.join(self.saving_folder, '*.mp4')), unit="mp4_file"):68 self.make_pdf_from_mp4(mp4_file_path)69 # Call the PdfFileMerger70 merged_pdf = PdfFileMerger()71 # Loop through all of pdf and append their pages72 for pdf_path in tqdm.tqdm(self.get_sort_pdf_paths(), unit="pdf_file"):73 merged_pdf.append(PdfFileReader(pdf_path, 'rb'))74 # Write all the files into a file which is named as shown below75 merged_pdf_path = f"{self.saving_folder}/{os.path.basename(dir_path)}.pdf"76 merged_pdf.write(merged_pdf_path)...

Full Screen

Full Screen

Mine_Tool.py

Source:Mine_Tool.py Github

copy

Full Screen

...5import urllib.request6# Tools designed to work with ArXiv_Miner.Miner_base and ArXiv_Miner.Arxiv7# Mostly for converting file types and querying files8# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -9def get_arxiv_pdf(pdf_id, target='Target.pdf'):10 # Attempts to locate an ArXiv pdf with a specific id11 # Does a 2nd pass if none is found at ID with a /hep-ex/ prefix12 # An outer loop checks again if nothing is found (fixes most server end issues)13 # for a maximum of 4 checks14 flag = 015 while flag < 2:16 try:17 urllib.request.urlretrieve('https://export.arxiv.org/pdf/' + pdf_id + '.pdf', target)18 flag += 119 return None20 except:21 print('ArXiv PDF not present at address')22 try:23 pdf_id.replace("hep-ex/", "")...

Full Screen

Full Screen

pdfviewer_lib.gyp

Source:pdfviewer_lib.gyp Github

copy

Full Screen

1# Copyright 2015 Google Inc.2#3# Use of this source code is governed by a BSD-style license that can be4# found in the LICENSE file.5# GYP file to build pdfviewer.6#7# To build on Linux:8# ./gyp_skia pdfviewer.gyp && make pdfviewer9#10{11 'targets': [12 {13 'target_name': 'pdfviewer_lib',14 'type': 'static_library',15 'sources': [16 # FIXME: Include directory is named "inc" (instead of "include") in17 # order to not be considered the public API.18 '../experimental/PdfViewer/inc/SkPdfContext.h',19 '../experimental/PdfViewer/inc/SkPdfDiffEncoder.h',20 '../experimental/PdfViewer/inc/SkPdfRenderer.h',21 '../experimental/PdfViewer/inc/SkPdfTokenLooper.h',22 '../experimental/PdfViewer/src/SkPdfContext.cpp',23 '../experimental/PdfViewer/src/SkPdfRenderer.cpp',24 '../experimental/PdfViewer/src/SkTDStackNester.h',25 '../experimental/PdfViewer/src/SkPdfDiffEncoder.cpp',26 '../experimental/PdfViewer/SkPdfGraphicsState.cpp',27 '../experimental/PdfViewer/SkPdfFont.cpp',28 '../experimental/PdfViewer/SkPdfReporter.cpp',29 '../experimental/PdfViewer/SkPdfUtils.cpp',30 #'../experimental/PdfViewer/SkPdfNYI.cpp',31 '../experimental/PdfViewer/SkTrackDevice.cpp',32 '../experimental/PdfViewer/SkTracker.cpp',33 '../experimental/PdfViewer/pdfparser/native/SkPdfNativeObject.cpp',34 '../experimental/PdfViewer/pdfparser/native/SkPdfNativeTokenizer.cpp',35 '../experimental/PdfViewer/pdfparser/native/SkPdfNativeDoc.cpp',36 '../experimental/PdfViewer/pdfparser/native/pdfapi/SkPdfMapper_autogen.cpp',37 '../experimental/PdfViewer/pdfparser/native/pdfapi/SkPdfHeaders_autogen.cpp',38 ],39 'include_dirs': [40 '../experimental/PdfViewer',41 '../experimental/PdfViewer/inc',42 '../experimental/PdfViewer/src',43 '../experimental/PdfViewer/pdfparser',44 '../experimental/PdfViewer/pdfparser/native',45 '../experimental/PdfViewer/pdfparser/native/pdfapi',46 '../src/core',47 ],48 'dependencies': [49 'skia_lib.gyp:skia_lib',50 'skflate.gyp:skflate',51 ],52 },53 ],...

Full Screen

Full Screen

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.

LambdaTest Learning Hubs:

YouTube

You could also refer to video tutorials over LambdaTest YouTube channel to get step by step demonstration from industry experts.

Run Puppeteer automation tests on LambdaTest cloud grid

Perform automation testing on 3000+ real desktop and mobile devices online.

... View sample repo... View DocumentationSign up Free
›
_

Try LambdaTest Now !!

Get 100 minutes of automation test minutes FREE!!

...
Sign up with GoogleSign up with Email
Next-Gen App & Browser Testing Cloud

Was this article helpful?

Helpful

NotHelpful