async def makePdf(Item: Item):
pdfBytes = base64.b64decode(Item.pdffile)
reader = PdfReader(fdata=pdfBytes)
annotator = PdfAnnotator(reader)
for i in Item.annotations:
if i.anType == "line":
await addLine(annotator, i)
elif i.anType == 'polyline':
await addLine(annotator, i)
elif i.anType == 'highlighter':
await addHighlight(annotator, i)
elif i.anType == 'highlighterPolyline':
await addHighlight(annotator, i)
elif i.anType == 'text':
await addText(annotator, i)
elif i.anType == 'identity':
await addIdentity(annotator, i)
# Creating file results
fileid = uuid.uuid4()
fileName = str(fileid) + ".pdf"
annotator.write(fileName)
encoded_string = ""
with open(fileName, "rb") as pdf_file:
encoded_string = base64.b64encode(pdf_file.read())
os.remove(fileName)
return {"result": encoded_string}
def test_identity(self):
t = PdfAnnotator._get_transform(
bounding_box=[0, 0, 100, 200],
rotation=0,
_scale=(1, 1),
)
assert t == identity()
def draw_bounding_poly_pdf(
self,
pdf: PdfReader,
vertices: List[Dict],
color: AnyStr,
):
"""Annotate a PDF document by drawing a bounding polygon of a given color
Args:
pdf: PDF document opened with pdfrw.PdfReader
vertices: List of 4 vertices describing the polygon
Each vertex should a dictionary with normalized coordinates e.g. {"x": 0.1, "y": 0.3}
color: Name of the color e.g. "red", "teal", "skyblue"
Full list on https://matplotlib.org/3.3.2/gallery/color/named_colors.html
"""
if len(vertices) == 4:
pdf_annotator = PdfAnnotator(pdf)
pdf_annotator.set_page_dimensions(
dimensions=(1, 1), page_number=0) # normalize page dimensions
pdf_annotator.add_annotation(
annotation_type="polygon",
location=Location(
points=[(vertices[i].get("x", 0.0),
1.0 - vertices[i].get("y", 0.0))
for i in range(4)],
page=0,
),
appearance=Appearance(stroke_color=colors.to_rgba(color)),
)
else:
raise ValueError(
f"Bounding polygon does not contain 4 vertices: {vertices}")
return pdf
def annotate(self, annotations, infile, outfile):
"""
Annotates a file.
Args:
annotations: list of annotations (title, rgb color, page #, x1, y1, x2, y2)
infile: full path to input file
outfile: full path to output file
"""
annotator = PdfAnnotator(infile)
# List of text ranges already defined
ranges = []
for title, rgb, page, x1, y1, x2, y2 in annotations:
# Highlight text
annotator.add_annotation(
"square", Location(x1=x1, y1=y1, x2=x2, y2=y2, page=page),
Appearance(fill=rgb + (0.3, ),
stroke_color=rgb + (0.3, ),
stroke_width=0))
if title:
# Determine if title text should be in left or right margin
if x1 < 250:
x1, x2 = max(5, x1 - 35), x1
else:
x1, x2 = x2, x2 + 35
# Calculate center of highlight annotation and offset
center = y1 + ((y2 - y1) / 2)
offset = min(max(5, len(title)), 20)
# Set position of text annotation. Handle column layout conflicts.
y1, y2 = self.position(ranges, page, x1 >= 250, center, offset)
# Add title annotation next to highlight
annotator.add_annotation(
"text", Location(x1=x1, y1=y1, x2=x2, y2=y2, page=page),
Appearance(fill=rgb + (1, ),
font_size=7,
stroke_width=1,
content=title))
# Register range
ranges.append((page, 0 if x1 < 250 else 1, y1, y2))
annotator.write(outfile)
def _assert_transform(
self,
expected,
rotation=0,
scale=(1, 1),
bounding_box=None,
):
bounding_box = bounding_box or [0, 0, 100, 200]
t = PdfAnnotator._get_transform(
bounding_box=bounding_box,
rotation=rotation,
_scale=scale,
)
assert_matrices_equal(t, expected)
def redactDocument(dirname, filename, boxes):
a = PdfAnnotator(dirname+"/"+filename)
for i in boxes:
a.add_annotation('square', Location(x1=i[0]*72, y1=(790-i[1]*72), x2=i[2]*72, y2=(790-i[3]*72), page=0),
Appearance(stroke_color=(0, 0, 0), stroke_width=13, fill=(0,0,0)),)
resultFilename = 'Redacted'+filename
a.write(resultFilename)
print("[INFO]: Process Completed.")
return resultFilename
def produce_debug_pdf(self):
debug_path = path.join('debug', self.filename.split('/', 1)[1])
makedirs(path.dirname(debug_path), exist_ok=True)
annotator = PdfAnnotator(self.filename)
for shape, loc, appearance in self.annotations:
annotator.add_annotation(shape, loc, appearance)
annotator.write(debug_path)
def pdf_add_Annot_old(path, file, stamp):
from pdf_annotate import PdfAnnotator, Location, Appearance
a = PdfAnnotator(os.path.join(path, file))
a.add_annotation(
'square',
Location(x1=50, y1=50, x2=100, y2=100, page=0),
Appearance(stroke_color=(1, 0, 0), stroke_width=5),
)
a.write(os.path.join(
path, 'new_w_stamp.pdf')) # or use overwrite=True if you feel lucky
def redactDocument(dirname, filename, boxes):
print("Dirname: " + dirname[0:len(dirname) - 14])
print("Filename: " + filename)
dirname = dirname[0:len(dirname) - 14]
a = PdfAnnotator(dirname+filename)
for i in boxes:
a.add_annotation('square', Location(x1=i[0]*72, y1=(790-i[1]*72), x2=i[2]*72, y2=(790-i[3]*72), page=0),
Appearance(stroke_color=(0, 0, 0), stroke_width=13, fill=(0,0,0)),)
a.write(dirname + filename)
print("[INFO]: Process Completed.")
return dirname + filename
def test_get_page_bounding_box(self):
a = PdfAnnotator(files.SIMPLE)
# The simple file has both MediaBox and CropBox set to the same value
assert a.get_page_bounding_box(0) == [0, 0, 612, 792]
page = a._pdf.get_page(0)
# Still works without CropBox
page.CropBox = None
assert a.get_page_bounding_box(0) == [0, 0, 612, 792]
page.MediaBox = [1, 1, 611, 791]
assert a.get_page_bounding_box(0) == [1, 1, 611, 791]
# But CropBox takes precedence
page.CropBox = [12, 16, 600, 792]
assert a.get_page_bounding_box(0) == [12, 16, 600, 792]
def test_add_annotation_page_dimensions(self):
# Ensure that changing a page's dimensions results in annotations being
# placed in the proper locations.
a = PdfAnnotator(files.SIMPLE)
# Act like the PDF was rastered at 144 DPI (2x default user space)
a.set_page_dimensions((1224, 1584), 0)
a.add_annotation(
'square',
Location(x1=10, y1=20, x2=20, y2=30, page=0),
Appearance(),
)
with write_to_temp(a) as t:
annotations = load_annotations_from_pdf(t)
square = annotations.pop()
assert len(annotations) == 0
assert square.Subtype == '/Square'
# The outer bounding box of the square is padded outward by the stroke
# width, and then scaled down by two.
self.assertEqual(square.Rect, ['4.5', '9.5', '10.5', '15.5'])
def generate_timesheet(form):
# Setting default strings
sunday_in = ''
monday_in = ''
tuesday_in = ''
wednesday_in = ''
thursday_in = ''
friday_in = ''
saturday_in = ''
sunday_out = ''
monday_out = ''
tuesday_out = ''
wednesday_out = ''
thursday_out = ''
friday_out = ''
saturday_out = ''
sunday_hours = ''
monday_hours = ''
tuesday_hours = ''
wednesday_hours = ''
thursday_hours = ''
friday_hours = ''
saturday_hours = ''
fund = ''
def calc_hours_worked(time_in, time_out):
hours = datetime.datetime.combine(
datetime.date.today(), time_out.data) - datetime.datetime.combine(
datetime.date.today(), time_in.data)
return round(hours.seconds / 3600, 2)
def next_saturday(d):
if d.weekday() == 5:
return d
else:
days_ahead = 5 - d.weekday()
if days_ahead < 0:
days_ahead += 7
return d + datetime.timedelta(days_ahead)
def previous_sunday(d):
if d.weekday() == 6:
return d
else:
days_behind = -d.weekday() - 1
return d + datetime.timedelta(days_behind)
name = form['name'].data
mcgill_id = form['mcgill_id'].data
hourly_rate = round(float(form['hourly_rate'].data), 2)
if form['fund_number'].data is not None:
fund = form['fund_number'].data
week = datetime.date(int(form['week_of_year'].data),
int(form['week_of_month'].data),
int(form['week_of_day'].data))
# find the closest past sunday
week_start = previous_sunday(week)
# find the closest future saturday
week_end = next_saturday(week)
total_hours = 0
if form['sunday_in'].data is not None and form[
'sunday_out'].data is not None:
sunday_in = form['sunday_in'].data.strftime('%H:%M')
sunday_out = form['sunday_out'].data.strftime('%H:%M')
sunday_hours = calc_hours_worked(form['sunday_in'], form['sunday_out'])
total_hours += sunday_hours
if form['monday_in'].data is not None and form[
'monday_out'].data is not None:
monday_in = form['monday_in'].data.strftime('%H:%M')
monday_out = form['monday_out'].data.strftime('%H:%M')
monday_hours = calc_hours_worked(form['monday_in'], form['monday_out'])
total_hours += monday_hours
if form['tuesday_in'].data is not None and form[
'tuesday_out'].data is not None:
tuesday_in = form['tuesday_in'].data.strftime('%H:%M')
tuesday_out = form['tuesday_out'].data.strftime('%H:%M')
tuesday_hours = calc_hours_worked(form['tuesday_in'],
form['tuesday_out'])
total_hours += tuesday_hours
if form['wednesday_in'].data is not None and form[
'wednesday_out'].data is not None:
wednesday_in = form['wednesday_in'].data.strftime('%H:%M')
wednesday_out = form['wednesday_out'].data.strftime('%H:%M')
wednesday_hours = calc_hours_worked(form['wednesday_in'],
form['wednesday_out'])
total_hours += wednesday_hours
if form['thursday_in'].data is not None and form[
'thursday_out'].data is not None:
thursday_in = form['thursday_in'].data.strftime('%H:%M')
thursday_out = form['thursday_out'].data.strftime('%H:%M')
thursday_hours = calc_hours_worked(form['thursday_in'],
form['thursday_out'])
total_hours += thursday_hours
if form['friday_in'].data is not None and form[
'friday_out'].data is not None:
friday_in = form['friday_in'].data.strftime('%H:%M')
friday_out = form['friday_out'].data.strftime('%H:%M')
friday_hours = calc_hours_worked(form['friday_in'], form['friday_out'])
total_hours += friday_hours
if form['saturday_in'].data is not None and form[
'saturday_out'].data is not None:
saturday_in = form['saturday_in'].data.strftime('%H:%M')
saturday_out = form['saturday_out'].data.strftime('%H:%M')
saturday_hours = calc_hours_worked(form['saturday_in'],
form['saturday_out'])
total_hours += saturday_hours
total_money = round(total_hours * hourly_rate, 2)
if form['timesheet_template'].data == '1':
base_timesheet = 'academic_casual_timesheet_-_2017_0.pdf'
annotations = constants.annotations_academic_casual_timesheet
personal_data = constants.personal_data_academic_casual_timesheet
else:
base_timesheet = 'admin_support_staff_casual_employee_timesheet_-_2017.pdf'
annotations = constants.annotations_admin_support_staff_casual_employee_timesheet
personal_data = constants.personal_data_admin_support_staff_casual_employee_timesheet
pdf_out_dir = 'pdf/'
out_file = form['name'].data + ' ' + week_start.strftime(
'%d %b %Y') + '.pdf'
# out_file = ''.join([random.choice(string.ascii_letters + string.digits) for n in range(32)]) + '.pdf'
out_path = pdf_out_dir + out_file
department = 'Building 21'
signature_date = datetime.date.today()
timesheet = PdfAnnotator(base_timesheet)
for annotation in annotations:
x1 = annotation[1]
y1 = annotation[2]
x2 = x1 + annotation[3]
y2 = y1 + annotation[4]
timesheet.add_annotation(
'text',
Location(x1=x1, y1=y1, x2=x2, y2=y2, page=0),
Appearance(content=str(eval(annotation[0])),
fill=(0, 0, 0),
text_baseline='bottom'),
)
for annotation in personal_data:
x1 = annotation[1]
y1 = annotation[2]
x2 = x1 + annotation[3]
y2 = y1 + annotation[4]
timesheet.add_annotation(
'text',
Location(x1=x1, y1=y1, x2=x2, y2=y2, page=0),
Appearance(content=str(eval(annotation[0])),
fill=(0, 0, 0),
text_baseline='middle',
text_align='center'),
)
timesheet.write('static/' + out_path)
return out_path
def annotatePDF(pathToPDF):
try:
randomNumber1 = str(randint(0, 9))
randomNumber2 = str(randint(1000, 9999))
a = PdfAnnotator(pathToPDF)
#Name and adress
a.add_annotation(
'text',
Location(x1=350, y1=590, x2=560, y2=650, page=0),
Appearance(content=name + "\n" + adress + "\n" + city.upper(),
font_size=11,
fill=(0, 0, 0),
line_spacing=1.8),
)
#Edition date
a.add_annotation(
'text',
Location(x1=393, y1=550, x2=570, y2=573, page=0),
Appearance(content=beautifulDate,
font_size=9,
fill=(0, 0, 0),
line_spacing=1.65),
)
#Request number
a.add_annotation(
'text',
Location(x1=1.37 * 72,
y1=8.23 * 72,
x2=3.58 * 72,
y2=8.40 * 72,
page=0),
Appearance(content=date + '-' + randomNumber1 + '-' +
randomNumber2,
font_size=9,
fill=(0, 0, 0),
line_spacing=1.65),
)
#name and date of birth
a.add_annotation(
'text',
Location(x1=0.73 * 72, y1=8 * 72, x2=2.1 * 72, y2=8.3 * 72,
page=0),
Appearance(content=lastName.upper() + ' le : ' + birthDate,
font_size=9,
fill=(0, 0, 0),
line_spacing=1.5),
)
#PrelevementDateTime
a.add_annotation(
'text',
Location(x1=1.32 * 72,
y1=7.43 * 72,
x2=3 * 72,
y2=7.7 * 72,
page=0),
Appearance(content=date + ' . ' + hour,
font_size=9,
fill=(0, 0, 0),
line_spacing=1.1),
)
#ValidationDate1
a.add_annotation(
'text',
Location(x1=5.34 * 72,
y1=1.75 * 72,
x2=5.85 * 72,
y2=1.93 * 72,
page=0),
Appearance(content=date,
font_size=9,
fill=(0, 0, 0),
line_spacing=1.1),
)
#ValidationDate2
a.add_annotation(
'text',
Location(x1=3.6 * 72,
y1=0.45 * 72,
x2=4.1 * 72,
y2=0.60 * 72,
page=0),
Appearance(content=date,
font_size=9,
fill=(0, 0, 0),
line_spacing=1.1),
)
#Create a new file
a.write(pathToPDF.replace('inputs', 'outputs'))
return 'Done'
except Exception as e:
return e
from pdfscrape import Scraped_PDF
import PyPDF2
import os
from pdf_annotate import PdfAnnotator, Appearance, Location
annotator = PdfAnnotator(os.getcwd()+'/trade_tickets/Company_Q2_p1.pdf')
annotator.add_annotation('square',Location(x1=300, y1=265, x2=500, y2=330, page=0),Appearance(stroke_color=(1, 0, 0), stroke_width=3),)
annotator.write('annotated.pdf')
class Annotate(object):
def __init__(self, pdf_obj):
#!/usr/bin/env vpython3
from pdf_annotate import PdfAnnotator, Location, Appearance
annotationtext = "some text"
a = PdfAnnotator("pdf.pdf")
a.add_annotation(
"text",
Location(x1=50, y1=50, x2=200, y2=100, page=0),
Appearance(
fill=(0, 0, 0),
stroke_width=1,
wrap_text=True,
font_size=12,
content=annotationtext,
),
)
a.write("pdf-a.pdf")
def test_get_scale_from_init(self):
a = PdfAnnotator(files.SIMPLE, scale=0.48)
assert a.get_scale(0) == (0.48, 0.48)
def test_end_to_end(self):
a = PdfAnnotator(self.INPUT_FILENAME)
self._add_annotations(a)
output_file = self._get_output_file()
a.write(output_file)
def draw_rectangles_for_solution(self, f_in, f_out, solution, points):
"""Drawing green filled rectangles near the correct answers for every problem,
in order to indicate the correct solution.
It calculates and writes the total score achieved too.
Parameters:
f_in (str): Path to the input PDF file.
f_out (str): Path to the output PDF file.
solution (dict): The solution (correct answers) corresponding to the input PDF file (f_in).
points (float): Total points achieved.
"""
pr = PdfFileReader(f_in)
dest = pr.getNamedDestinations()
fields = pr.getFields()
# """IT IS NOT WORKING IF THIS COMES FIRST:"""
# a = PdfAnnotator(f_in)
# for p in range(pr.getNumPages()):
# for dk, dv in dest.items():
# if pr.getDestinationPageNumber(dv) == p and dk.startswith('ht_'):
# inds = [int(ind) for ind in dk[3:].split(':')]
# # if inds[2] in solution[inds[1]][1]:
# if inds[4] in solution[inds[1]][1]:
# # using some hard-coded values:
# a.add_annotation('square',
# Location(x1=float(dv['/Left']), y1=float(dv['/Top']), x2=float(dv['/Left'])+5, y2=float(dv['/Top'])+5, page=p),
# Appearance(stroke_color=(0, 1, 0), stroke_width=5),)
# a.write(f_out)
pw = PdfFileWriter()
# pr = PdfFileReader(f_out, strict=False)
pr = PdfFileReader(f_in, strict=False)
pw.appendPagesFromReader(pr)
pw._root_object.update(
{NameObject("/AcroForm"): pr.trailer["/Root"]["/AcroForm"]})
pw._root_object["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
for p in range(pr.getNumPages()):
self._update_page_form_checkbox_values(pw.getPage(p), {
fk: fv['/V']
for fk, fv in fields.items() if '/V' in fv.keys()
}) # sometimes '/V' disappears from the keys
self._update_page_form_checkbox_values(pw.getPage(0),
{'points': str(points)})
f = codecs.open(f_out, 'wb')
pw.write(f)
f.close()
a = PdfAnnotator(f_out)
for p in range(pr.getNumPages()):
for dk, dv in dest.items():
if pr.getDestinationPageNumber(dv) == p and dk.startswith(
'ht_'):
inds = [int(ind) for ind in dk[3:].split(':')]
# if inds[2] in solution[inds[1]][1]:
if inds[4] in solution[inds[1]][1]:
# using some hard-coded values:
a.add_annotation(
'square',
Location(x1=float(dv['/Left']),
y1=float(dv['/Top']),
x2=float(dv['/Left']) + 5,
y2=float(dv['/Top']) + 5,
page=p),
Appearance(stroke_color=(0, 1, 0), stroke_width=5),
)
a.write(f_out)
def test_get_scale_default(self):
a = PdfAnnotator(files.SIMPLE)
assert a.get_scale(0) == (1, 1)
from pdf_annotate import PdfAnnotator, Location, Appearance
a = PdfAnnotator('template.pdf')
def create_annotation(node: PdfAnnotator, is_name: bool, count: int, value):
coordinate_dict_name = {
'1': {
'x1': 95,
'y1': 720,
'x2': 160,
'y2': 740
},
'2': {
'x1': 335,
'y1': 720,
'x2': 405,
'y2': 740
},
'3': {
'x1': 95,
'y1': 690,
'x2': 160,
'y2': 710
},
'4': {
'x1': 335,
'y1': 690,
'x2': 405,
'y2': 710
}
def test_write_with_compress_off_smoke_test(self):
a = PdfAnnotator(PdfReader(files.SIMPLE), compress=False)
with write_to_temp(a) as t:
assert load_annotations_from_pdf(t) is None
def test_get_scale_from_page_dimensions(self):
a = PdfAnnotator(files.SIMPLE)
# Rastered at different X and Y scales. Why would you do that?
a.set_page_dimensions((1275, 3300), 0)
assert a.get_scale(0) == (0.48, 0.24)
def process_drawing_stamps(self):
try:
os.mkdir(f'{self.file_path_drawing_to_stamp}/Stamped')
except Exception as e:
print(e)
self.ui.listWidget_drawing_stamper.clear()
self.ui.listWidget_drawing_stamper.addItem("Unable to create directory - error code below:\n")
self.ui.listWidget_drawing_stamper.addItem(str(e))
today = date.today()
today_date = today.strftime("%d/%m/%y")
drawing_status = ""
if self.ui.radioButton_status_a.isChecked() == True:
drawing_status = "A"
elif self.ui.radioButton_status_b.isChecked() == True:
drawing_status = "B"
elif self.ui.radioButton_status_c.isChecked() == True:
drawing_status = "C"
else:
drawing_status = "Unknown"
self.ui.listWidget_drawing_stamper.clear()
self.ui.listWidget_drawing_stamper.addItem("Adding annotations:\n")
for drawing in self.list_of_drawingstostamp:
try:
full_drawing_path = self.file_path_drawing_to_stamp + '/' + drawing
self.ui.listWidget_drawing_stamper.addItem(drawing)
QtCore.QCoreApplication.processEvents()
full_path_drawing_stamp = self.file_path_drawing_to_stamp + "/Blank_Stamp.png"
a = PdfAnnotator(full_drawing_path)
a.add_annotation(
'image',
Location(x1=50, y1=50, x2=400, y2=400, page=0),
Appearance(image=full_path_drawing_stamp)
)
except Exception as e:
print("Unable to add image")
try:
a.add_annotation(
'text',
Location(x1=120, y1=320, x2=300, y2=332, page=0),
Appearance(stroke_color=(1, 1, 1), stroke_width=5, content=self.ui.lineEdit_drawing_stamper_jobnumber.text(), fill=(0.705, 0.094, 0.125, 1))
) #https://doc.instantreality.org/tools/color_calculator/
a.add_annotation(
'text',
Location(x1=130, y1=305, x2=300, y2=317, page=0),
Appearance(stroke_color=(1, 1, 1), stroke_width=5, content=self.ui.lineEdit_drawing_stamper_date.text(), fill=(0.705, 0.094, 0.125, 1))
)
a.add_annotation(
'text',
Location(x1=75, y1=276, x2=300, y2=288, page=0),
Appearance(stroke_color=(1, 1, 1), stroke_width=5, content=self.ui.lineEdit_drawing_stamper_reviewerinitials.text(), fill=(0.705, 0.094, 0.125, 1))
)
a.add_annotation(
'text',
Location(x1=200, y1=276, x2=320, y2=288, page=0),
Appearance(stroke_color=(1, 1, 1), stroke_width=5, content=f"Status {drawing_status}", fill=(0.705, 0.094, 0.125, 1))
)
a.add_annotation(
'text',
Location(x1=330, y1=276, x2=400, y2=288, page=0),
Appearance(stroke_color=(1, 1, 1), stroke_width=5, content=today_date, fill=(0.705, 0.094, 0.125, 1))
)
# Put an X in the box noting the status
if drawing_status == "A":
a.add_annotation(
'text',
Location(x1=117, y1=203, x2=300, y2=215, page=0),
Appearance(stroke_color=(1, 1, 1), stroke_width=5,
content="X", fill=(0.705, 0.094, 0.125, 1))
)
if drawing_status == "B":
a.add_annotation(
'text',
Location(x1=117, y1=189, x2=300, y2=201, page=0),
Appearance(stroke_color=(1, 1, 1), stroke_width=5,
content="X", fill=(0.705, 0.094, 0.125, 1))
)
if drawing_status == "C":
a.add_annotation(
'text',
Location(x1=117, y1=174, x2=300, y2=186, page=0),
Appearance(stroke_color=(1, 1, 1), stroke_width=5,
content="X", fill=(0.705, 0.094, 0.125, 1))
)
except Exception as e:
print(e)
self.ui.listWidget_drawing_stamper.addItem("Unable to add annotation - error code below:\n")
self.ui.listWidget_drawing_stamper.addItem(str(e))
self.ui.listWidget_drawing_stamper.addItem("Check - is this file a PDF?")
try:
#Write the resultant file
a.write(f'{self.file_path_drawing_to_stamp}/Stamped/{drawing}')
except Exception as e:
print(e)
self.ui.listWidget_drawing_stamper.addItem("Unable to save file - error code below:\n")
self.ui.listWidget_drawing_stamper.addItem(str(e))
self.ui.listWidget_drawing_stamper.addItem("Check - do these files already exist?")
return
#Display success message
self.ui.listWidget_drawing_stamper.clear()
self.ui.listWidget_drawing_stamper.addItem("Stamps added successfully!")
return
import pypdftk
import openpyxl
import time
wb = openpyxl.load_workbook('demos.xlsx')
ws = wb['demos']
ANNOT_KEY = '/Annots'
ANNOT_FIELD_KEY = '/T'
ANNOT_VAL_KEY = '/V'
ANNOT_RECT_KEY = '/Rect'
SUBTYPE_KEY = '/Subtype'
WIDGET_SUBTYPE_KEY = '/Widget'
for row in ws.iter_rows(min_row=31, max_row=59):
a = PdfAnnotator('template.pdf')
annotate_pdf(a, create_data_dict(row))
# def write_fillable_pdf(input_pdf_path, output_pdf_path, data_dict):
# template_pdf = pdfrw.PdfReader(input_pdf_path)
# annotations = template_pdf.pages[0][ANNOT_KEY]
# for annotation in annotations:
# if annotation[SUBTYPE_KEY] == WIDGET_SUBTYPE_KEY:
# if annotation[ANNOT_FIELD_KEY]:
# key = annotation[ANNOT_FIELD_KEY][1:-1]
# if key in data_dict.keys():
# annotation.update(
# pdfrw.PdfDict(AP='', V='{}'.format(data_dict[key]))
# )
# pdfrw.PdfWriter().write(output_pdf_path, template_pdf)
def test_get_size(self):
a = PdfAnnotator(files.SIMPLE)
size = a.get_size(0)
assert size == (612.0, 792.0)
def test_get_rotated_scale_from_dimensions(self):
a = PdfAnnotator(files.ROTATED_90)
a.set_page_dimensions((3300, 1275), 0)
assert a.get_scale(0) == (0.24, 0.48)
def scrape_pdf(self):
pdfFileObject = open(os.getcwd() + "/" + self.path, 'rb')
pdf_info = list(
filter(
lambda x: any(c.isalnum() for c in x),
PyPDF2.PdfFileReader(pdfFileObject).getPage(
0).extractText().split('\n')))
for i, x in enumerate(pdf_info):
pdf_info[i] = x.strip()
annotator = PdfAnnotator(os.getcwd() + self.path)
annotated = False
self.company_name = pdf_info[1]
if pdf_info.index('Trans Type') == pdf_info.index('Quantity') - 2:
self.transaction_type = pdf_info[pdf_info.index('Trans Type') + 1]
else:
self.transaction_type = None
annotator.add_annotation(
'square',
Location(x1=80, y1=435, x2=140, y2=490, page=0),
Appearance(stroke_color=(1, 0, 0), stroke_width=3),
)
annotated = True
if pdf_info.index('Quantity') == pdf_info.index('PPS') - 2:
self.quantity = int(pdf_info[pdf_info.index('Quantity') +
1].replace(',', ''))
else:
self.quantity = None
annotator.add_annotation(
'square',
Location(x1=160, y1=435, x2=220, y2=490, page=0),
Appearance(stroke_color=(1, 0, 0), stroke_width=3),
)
annotated = True
if pdf_info.index('PPS') == pdf_info.index('Security') - 2:
self.price_per_share = int(
pdf_info[pdf_info.index('PPS') +
1][1:len(pdf_info[pdf_info.index('PPS') + 1]) - 3])
else:
self.price_per_share = None
annotator.add_annotation(
'square',
Location(x1=225, y1=435, x2=285, y2=490, page=0),
Appearance(stroke_color=(1, 0, 0), stroke_width=3),
)
annotated = True
if len(pdf_info[3]) > 14:
self.date_of_order = pdf_info[3][15:]
else:
print("date of order missing")
self.date_of_order = None
annotator.add_annotation(
'square',
Location(x1=150, y1=570, x2=280, y2=590, page=0),
Appearance(stroke_color=(1, 0, 0), stroke_width=3),
)
annotated = True
if len(pdf_info[4]) > 10:
self.custodian = pdf_info[4][11:]
else:
self.custodian = None
annotator.add_annotation(
'square',
Location(x1=130, y1=540, x2=280, y2=565, page=0),
Appearance(stroke_color=(1, 0, 0), stroke_width=3),
)
annotated = True
if pdf_info.index('Security') == pdf_info.index('Type of Order') - 2:
self.security = pdf_info[pdf_info.index('Security') + 1]
else:
self.security = None
annotator.add_annotation(
'square',
Location(x1=295, y1=435, x2=360, y2=490, page=0),
Appearance(stroke_color=(1, 0, 0), stroke_width=3),
)
annotated = True
if pdf_info.index(
'Type of Order') == pdf_info.index('Instructions') - 2:
self.type = pdf_info[pdf_info.index('Type of Order') + 1]
else:
self.type = None
annotator.add_annotation(
'square',
Location(x1=360, y1=435, x2=460, y2=490, page=0),
Appearance(stroke_color=(1, 0, 0), stroke_width=3),
)
annotated = True
if pdf_info.index('Broker/Dealer') == pdf_info.index(
'Broker/Dealer Representative') - 2:
self.broker_dealer = pdf_info[pdf_info.index('Broker/Dealer') + 1]
else:
self.broker_dealer = None
annotator.add_annotation(
'square',
Location(x1=70, y1=330, x2=285, y2=400, page=0),
Appearance(stroke_color=(1, 0, 0), stroke_width=3),
)
annotated = True
if pdf_info.index('Broker/Dealer Representative'
) == pdf_info.index('Comments:') - 2:
self.broker_dealer_representative = pdf_info[
pdf_info.index('Broker/Dealer Representative') + 1]
else:
self.broker_dealer_representative = None
annotator.add_annotation(
'square',
Location(x1=300, y1=330, x2=500, y2=400, page=0),
Appearance(stroke_color=(1, 0, 0), stroke_width=3),
)
annotated = True
if pdf_info.index('Phone:') == pdf_info.index('Signature:') - 3:
self.phone = pdf_info[pdf_info.index('Phone:') +
1] + "-" + pdf_info[pdf_info.index('Phone:')
+ 2]
else:
self.phone = None
annotator.add_annotation(
'square',
Location(x1=300, y1=265, x2=500, y2=330, page=0),
Appearance(stroke_color=(1, 0, 0), stroke_width=3),
)
annotated = True
try:
self.amount = self.quantity * self.price_per_share
except:
self.amount = None
if annotated:
# os.mkdir(os.getcwd() + "/ANNOTATED/trade_tickets")
annotator.write(os.getcwd() + "/ANNOTATED" + self.path)
# else maybe move it to the completed folder
self.valid_pdf = self.amount != None and self.transaction_type != None and self.quantity != None
pdfFileObject.close()
import re
import io
import sys
start_time = time.time()
check_version = "developer"
test_times = 1
# Open a PDF file.
if check_version == "developer":
spec_number = r"acrf_CRAD001Y2301-SPEC"
pdf_path = r"F:\Novartis\ReaderSpec\files/" + spec_number + '.pdf'
test_times = test_times + 1
output_path = r"F:\Novartis\ReaderSpec\result/" + spec_number + "_" + str(test_times) + ".xlsx"
offset = 1.5
annotator = PdfAnnotator(pdf_path)
else:
offset = 1.5
# Read the PDF with pdfplumber.
df = pd.DataFrame()
with pdfplumber.open(pdf_path) as pdf:
all_pages = pdf.pages
for curpage in range(len(all_pages)):
page = all_pages[curpage]
axis_info_ = page.tmp_find_tables(table_settings={"keep_blank_chars": True})
counttable = 0
for table in page.extract_tables(table_settings={"keep_blank_chars": True}):
axis_info_1 = axis_info_[counttable]
counttable += 1
header_index = 0
def create_annotation(node: PdfAnnotator, is_name: bool, count: int, value):
coordinate_dict_name = {
'1': {
'x1': 95,
'y1': 720,
'x2': 160,
'y2': 740
},
'2': {
'x1': 335,
'y1': 720,
'x2': 405,
'y2': 740
},
'3': {
'x1': 95,
'y1': 690,
'x2': 160,
'y2': 710
},
'4': {
'x1': 335,
'y1': 690,
'x2': 405,
'y2': 710
}
}
coordinate_dict_id = {
'1': {
'x1': 215,
'y1': 720,
'x2': 295,
'y2': 740
},
'2': {
'x1': 465,
'y1': 720,
'x2': 550,
'y2': 740
},
'3': {
'x1': 215,
'y1': 690,
'x2': 295,
'y2': 710
},
'4': {
'x1': 465,
'y1': 690,
'x2': 550,
'y2': 710
}
}
if is_name:
return node.add_annotation(
'text',
Location(x1=coordinate_dict_name[str(count)]['x1'],
y1=coordinate_dict_name[str(count)]['y1'],
x2=coordinate_dict_name[str(count)]['x2'],
y2=coordinate_dict_name[str(count)]['y2'],
page=0),
Appearance(stroke_color=(0, 0, 0),
stroke_width=5,
content=value,
fill=(0, 0, 0, 1)))
else:
return node.add_annotation(
'text',
Location(x1=coordinate_dict_id[str(count)]['x1'],
y1=coordinate_dict_id[str(count)]['y1'],
x2=coordinate_dict_id[str(count)]['x2'],
y2=coordinate_dict_id[str(count)]['y2'],
page=0),
Appearance(stroke_color=(0, 0, 0),
stroke_width=5,
content=value,
fill=(0, 0, 0, 1)))
def test_get_rotation(self):
assert PdfAnnotator(files.SIMPLE).get_rotation(0) == 0
assert PdfAnnotator(files.ROTATED_90).get_rotation(0) == 90
