def fill_form(targetfile, outputfile, row_data, mapping):
'''
Fill up form based on map data
:param targetfile: Path to pdf file that needs to be filled
:param outputfile: Path to output
:param row_data: Row data from excel file
:param mapping: Dictionary that maps excel row with form field in pdf
'''
logger = logging.getLogger(__name__ + '.fill_form')
template = pdfrw.PdfFileReader(targetfile)
for page in range(len(template.pages)):
annotations = template.pages[page]['/Annots']
for item in annotations:
if item['/Subtype'] == '/Widget':
if item['/T']:
key = item['/T'][1:-1]
if key in mapping.keys():
if 'Check Box' in key:
if row_data[mapping[key]] == 'yes':
item.update(
pdfrw.PdfDict(AS=pdfrw.PdfName('Yes')))
elif row_data[mapping[key]] == 'no':
item.update(
pdfrw.PdfDict(AS=pdfrw.PdfName('No')))
else:
logger.debug('Textbox= {0} Value= {1}'.format(
str(key), str(row_data[mapping[key]])))
item.update(
pdfrw.PdfDict(V=str(row_data[mapping[key]])))
logger.info('Writing to {}'.format(path.join(OUTPUT_FOLDER, outputfile)))
pdfrw.PdfWriter().write(path.join(OUTPUT_FOLDER, outputfile), template)
def simplify_pdf(pdf: str, select: str, outfile: typing.TextIO):
"""
Given a PDF and a metric by which to select the first or last page in a range of pages with the same name,
remove the unnecessary pages
"""
in_pdf = pdfrw.PdfFileReader(pdf)
out_pdf = pdfrw.PdfFileWriter(trailer=in_pdf)
for index in calculate_pages(in_pdf, select):
out_pdf.addPage(in_pdf.getPage(index))
out_pdf.write(outfile)
def list_pdf_fields():
template = pdfrw.PdfFileReader(PDF_TEMPLATE_PATH)
pages = template.pages
for page in range(1, len(pages) + 1):
annotations = pages[page - 1][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]
print(f' Page {page}: {key}, '
f'type {annotation[ANNOT_FORM_type]}, '
f'current value: {annotation[ANNOT_VAL_KEY]}')
def create_watermark(cls, doc_pdf: bytes) -> bytes:
if cls._watermark is None:
return doc_pdf
trailer = pdfrw.PdfFileReader(fdata=doc_pdf)
for page in trailer.pages:
pdfrw.PageMerge(page).add(
cls._watermark,
prepend=cls._underneath,
).render()
stream = io.BytesIO()
pdfrw.PdfWriter(stream, trailer=trailer).write()
result_pdf = stream.getvalue()
stream.close()
return result_pdf
def fill_pdf():
data_dict = transform_data()
template = pdfrw.PdfFileReader(PDF_TEMPLATE_PATH)
pages = template.pages
for key in data_dict.keys():
data_row = transform_data_dict(data_dict[key])
for page in range(1, len(pages) + 1):
if data_row.get(str(page)) is None:
print(f'Skipping page {page} in file {key}...')
continue
page_data = data_row[str(page)]
page_data = {k.split('.')[1]: v for k, v in page_data.items()}
annotations = pages[page - 1][ANNOT_KEY]
for annotation in annotations:
if annotation[SUBTYPE_KEY] == WIDGET_SUBTYPE_KEY:
if annotation[ANNOT_FIELD_KEY]:
pdf_key = annotation[ANNOT_FIELD_KEY][1:-1]
if pdf_key in page_data.keys():
# if annotation[ANNOT_FORM_type] == ANNOT_FORM_button:
# print(f'Updating page {page}: {key},'
# f'field {pdf_key},'
# f' new value: {page_data[pdf_key]}')
# annotation.update(pdfrw.PdfDict(V=pdfrw.PdfDict(page_data[pdf_key]),
# AS=pdfrw.PdfName(page_data[pdf_key]) ))
if annotation[ANNOT_FORM_type] == ANNOT_FORM_text:
print(f'Updating file {key}:'
f' page {page}:'
f'field {pdf_key},'
f' new value: {page_data[pdf_key]}')
annotation.update(
pdfrw.PdfDict(V=page_data[pdf_key],
AP=page_data[pdf_key]))
template.Root.AcroForm.update(
pdfrw.PdfDict(NeedAppearances=pdfrw.PdfObject('true')))
output_pdf_path = f'{OUTPUT_FOLDER}{PATH_SEPARATOR}{key}.pdf'
pdfrw.PdfWriter().write(output_pdf_path, template)
def __init__(self, fname, password):
self.fname = fname
self.password = password if password != "" else None
self.compress = False
self.objects = []
with open(fname, "rb") as fi:
self.datau = fi.read()
self.startdata = len(self.datau)
self.annotbutton = False
s = b"startxref"
i = self.datau.rfind(s)
assert i != -1
i += len(s)
while self.datau[i] not in b"0123456789":
i += 1
j = i
while self.datau[j] in b"0123456789":
j += 1
s = self.datau[i:j].decode()
startprev = int(s, 10)
self.startprev = startprev
self.prev = pdf.PdfFileReader(fdata=self.datau,
decrypt=(password is not None),
password=password)
def get_page_dimensions(self):
pdf = pdfrw.PdfFileReader(self.filename)
self.num_pages = len(pdf.pages)
self.page_width = float(pdf.pages[0].MediaBox[2])
self.page_height = float(pdf.pages[0].MediaBox[3])
def main(filename):
try:
pdf = pdfrw.PdfFileReader(filename)
except Exception as e:
print('Error: couldn\'t open statement.')
print(
'Are you sure the file "{}" exists? Is it a PDF?'.format(filename))
print()
print('Technical information:')
traceback.print_exc()
return
try:
xfa = pdf.Root.AcroForm.XFA.stream
# if you want to explore the format yourself, I suggest printing
# the contents of the xfa variable --- it's just a string containing
# XML, some of which contains statement information and some of which
# contains JavaScript describing how the data is to be displayed
tree = ET.fromstring(xfa)
datasets = tree.find(
'{http://www.xfa.org/schema/xfa-data/1.0/}datasets')
statement = datasets.find('*/TouchNet/BillingStmt')
except Exception as e:
print('Error: couldn\'t find statement data in PDF.')
print('Are you sure this PDF is a statement from the new MITPAY?')
print()
print('Technical information:')
traceback.print_exc()
return
student_id = statement.find('Student/StuID').text
student_name = statement.find('Student/FullName').text
statement_term = format_term(statement.find('TermCode').text)
statement_date = statement.find('StmtDt').text
statement_due = statement.find('DueDt').text
amount_due = statement.find('AmtDue').text
print_line()
print_center('MIT BILLING STATEMENT')
print_center('UNOFFICIAL. Contact SFS in case of discrepancies.')
print_center(
'This report should hopefully include all personalized information')
print_center('from the PDF except the student\'s address. No guarantees.')
print_center(
'When paying by mailing a check, you MUST use the original PDF.')
print_center('If amount due is negative, you are due a refund.')
print_line()
print_center('{} (ID: {})'.format(student_name, format_id(student_id)))
print_pair('Statement generated on {}'.format(format_date(statement_date)),
'Due on {}'.format(format_date(statement_due)))
print_pair('Term: {}'.format(statement_term),
'Amount due: {}'.format(format_amount(amount_due, False)))
print_line()
for line in statement.findall('LineItem'):
kind = line.find('Type').text
description = line.find('Desc').text
amount = line.find('Amt').text # might be None
date = None
if line.find('TransDt') is not None:
date = line.find('TransDt').text
term = None
if line.find('TermCode') is not None:
term = line.find('TermCode').text
formatted_date = ''
if (date is not None) and (term is not None):
formatted_date = ' ({}, {})'.format(format_term(term),
format_date(date))
elif date is not None:
formatted_date = ' ({})'.format(format_date(date))
elif term is not None:
formatted_date = ' ({})'.format(format_term(term))
complete_description = '{desc}{date}'.format(desc=description,
date=formatted_date)
if amount is None:
print_center(complete_description)
else:
# NB: sometimes Charges have negative amounts
# e.g. "Initial Housing Average Fee Cr" (freshmen getting their
# estimated housing fee back) is a charge for some reason.
invert_sign = (kind == 'Charge') or (kind == 'FutureChgs') \
or kind.endswith('Chg')
print_pair(complete_description,
format_amount(amount, True, invert_sign))
print_line()
print_pair('Amount due', format_amount(amount_due, False))