def create(id, userid):
if id == 1:
pdf_path = os.path.dirname(__file__) + '/files/VTB_anketa.pdf'
elif id == 2:
return send_from_directory(directory=os.path.abspath(os.path.dirname(__file__) + '/files'),
filename='VTB_accept.pdf')
elif id == 3:
pdf_path = os.path.dirname(__file__) + '/files/VTB_spravka.pdf'
else:
return 'BAD ID'
with open(pdf_path, 'rb') as f:
pdf = PdfFileReader(f)
fields = pdf.getFormTextFields()
checkboxes = {}
for i in pdf.getFields().keys():
if 'Check Box' in i:
checkboxes[i] = pdf.getFields()[i]
docChecker(id=id, userid=userid, fields=checkboxes)
docWriter(id=id, userid=userid, fields=fields)
pdf_writer = PdfFileWriter()
for page in range(pdf.getNumPages()):
pdf_writer.addPage(pdf.getPage(page))
pdf_writer.updatePageFormFieldValues(page=pdf_writer.getPage(page), fields=fields)
updateCheckboxValues(page=pdf_writer.getPage(page), fields=checkboxes)
with open(os.path.dirname(__file__) + '/files/downloaded.pdf', 'wb') as out:
pdf_writer.write(out)
return send_from_directory(directory=os.path.abspath(os.path.dirname(__file__) + '/files'),
filename='downloaded.pdf')
def test_get_form(src, expected, expected_get_fields):
"""Check if we can read out form data."""
src = os.path.join(RESOURCE_ROOT, src)
reader = PdfFileReader(src)
fields = reader.getFormTextFields()
assert fields == expected
fields = reader.getFields()
assert fields == expected_get_fields
def main(args: List[str]) -> int:
filename = args[1]
reader = PdfFileReader(filename)
fields = reader.getFields()
for f in fields.keys():
print(f"Name: '{f}', "
f"Type: '{readable_type(fields[f])}', "
f"Value: {get_value(fields[f])}")
return 0
def addInTemplate(filepath):
with app.tabbedFrame('form_templates'):
template_name = filepath.split('/')[-1].replace('.pdf', '')
with open(filepath, 'rb') as intemp:
template_form = PdfFileReader(intemp)
with app.tab(template_name):
app.setStretch('both')
app.addListBox(template_name,
sorted(template_form.getFields()), 0, 0, 10, 10)
app.setListBoxGroup(template_name)
app.setListBoxChangeFunction(template_name,
updateFormTemplateEdit)
def main():
# --- Parse argv ---------------------------------------------------
arg_parser = argparse.ArgumentParser(description='PDF field parser')
arg_parser.add_argument('filenames', metavar='file', nargs='+',
help='Path to one or more PDF to parse')
arg_parser.add_argument('-o',
metavar='output_file', dest='output', default = "output.csv",
help='Output filename (default: output.csv)')
args = arg_parser.parse_args()
# --- Read in data from all the files ------------------------------
parsed_data = []
for file in args.filenames:
with open(file, "rb") as con:
pdf = PdfFileReader(con)
fields = pdf.getFields()
for column, objects in fields.items():
fields[column] = str(objects["/V"]) if "/V" in objects else ""
parsed_data.append(fields)
# If our dictionary is empty, assume that we have no data and exit
# TODO: This only checks the first file. This could be more robust.
if parsed_data[0] is None:
sys.exit(0)
# --- Write out data to the CSV file ------------------------------
with open(args.output, "w") as outfile:
csvwriter = DictWriter(
outfile,
delimiter=",",
quotechar="\"",
lineterminator="\n",
quoting=QUOTE_NONNUMERIC,
fieldnames = parsed_data[0].keys()
)
csvwriter.writeheader()
for row in parsed_data:
csvwriter.writerow(row)
def displaySourceData(window, fsource):
'''Post the metadata for a pdf file'''
'''NOTE: setting strict to False prevents PdfReadWarning. See https://github.com/mstamy2/PyPDF2/issues/36 '''
PDFSource = PdfFileReader(fsource, strict=False)
info = PDFSource.getDocumentInfo()
window['-NUMPAGES-'].update(PDFSource.getNumPages())
window['-FIELDS-'].update(PDFSource.getFields(fsource))
window['-ENCRYPTED-'].update(PDFSource.isEncrypted)
window['-AUTHOR-'].update(info.author)
window['-CREATIONDATE-'].update(str(convertDate(info)))
window['-CREATOR-'].update(info.creator)
window['-PRODUCER-'].update(info.producer)
window['-SUBJECT-'].update(info.subject)
window['-TITLE-'].update(info.title)
return PDFSource
def parse_pdf_impl(filenames):
# --- Read in data from all the files ------------------------------
parsed_data = []
for file in filenames:
with open(file, "rb") as con:
pdf = PdfFileReader(con)
fields = pdf.getFields()
for column, objects in fields.items():
fields[column] = str(objects["/V"]) if "/V" in objects else ""
parsed_data.append(fields)
# --- return as Pandas DataFrame ------------------------------
parsed_data = pd.DataFrame(parsed_data)
return parsed_data
def _get_fields_from_pdf(pdf_data_path, radio_btn_group1, radio_btn_group2):
pdf_data_source =\
PdfFileReader(pdf_data_path.open(mode="rb"), strict=False)
field_values = pair_fields_name_and_val(pdf_data_source.getFields(), True)
try:
group1_index = radio_btn_group1.index(field_values.get(_NAME_GROUP1))
field_values[_NAME_GROUP1] = group1_index
except ValueError:
pass
try:
group2_index = radio_btn_group2.index(field_values.get(_NAME_GROUP2))
field_values[_NAME_GROUP2] = group2_index
except ValueError:
pass
group4_index = _index_from_btn_group4(field_values.get(_NAME_GROUP4))
if group4_index >= 0:
field_values[_NAME_GROUP4] = group4_index
return field_values
def read_pdf(filedir, stForms, i):
form_fields = {}
clean = CleanUtil()
try:
pdf_reader = PdfFileReader(
open(filedir, "rb")
) #this creates a pdf reader so we can gather information from the pdf form
fields = pdf_reader.getFields(
) #this is a dictionary with field key values and their associative input data
except:
fields = None
if fields is None:
fields = {}
for key in fields: #key is the forms field name i.e 'email' is the key for '*****@*****.**'
if key != 'sig_univ_employee' and key != 'sig_dept_chair' and key != 'dean_students':
fl = fields[key]
form_fields[fl.name] = clean.sanitize(fl.value, fl.fieldType)
if 'employee_responsible_name' in form_fields:
stForms['1'] = form_fields
elif 'colleges-st10' not in form_fields:
stForms['2' + str(i)] = form_fields
return
return writer
if __name__ == '__main__':
csv_filename = "EISAutoFill.csv"
pdf_filename = "EIS 3 Certificate - Autofilled.pdf"
csvin = os.path.normpath(os.path.join(os.getcwd(), 'in', csv_filename))
pdfin = os.path.normpath(os.path.join(os.getcwd(), 'in', pdf_filename))
pdfout = os.path.normpath(os.path.join(os.getcwd(), 'out'))
data = pd.read_csv(csvin)
pdf = PdfFileReader(open(pdfin, "rb"), strict=False)
if "/AcroForm" in pdf.trailer["/Root"]:
pdf.trailer["/Root"]["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
pdf_fields = [str(x) for x in pdf.getFields().keys()
] # List of all pdf field names
csv_fields = data.columns.tolist()
i = 0 #Filename numerical prefix
for j, rows in data.iterrows():
i += 1
pdf2 = PdfFileWriter()
set_need_appearances_writer(pdf2)
if "/AcroForm" in pdf2._root_object:
pdf2._root_object["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
# Key = pdf_field_name : Value = csv_field_value
field_dictionary_1 = {
"Full Name":
from collections import OrderedDict
from PyPDF2 import PdfFileWriter, PdfFileReader, pdf
from PyPDF2.generic import BooleanObject, NameObject, IndirectObject
from pprint import pprint
import pandas as pd
import numpy as np
import os
data = pd.read_csv('WestulDatabaseOrd.csv')
pdfpath = os.getcwd()
pdf_new_name = 'Form_Final.pdf'
pdfread = PdfFileReader(open(pdf_new_name, 'rb'))
page = pdfread.getFields()
fields = pdf.trailer
def pdf(self, fp, csv_row):
password = ''
extracted_text = ''
self.parser = PDFParser(fp)
self.document_t = PDFDocument
pf = PdfFileReader
# isEncrypted
try:
i = 0
try:
thread = Thread(target=self.load_pdf,
args=(PDFDocument, password))
thread.start()
thread.join(timeout=90)
except Exception as e:
print('PDF I/O error: ' + e.__str__())
row = [
self.line_count,
'PDF DOCUMENT OBJECT FAILED TO LOAD - ' + e.__str__() +
': ' + self.url,
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
'',
]
# self.line_count += 1
report_path = self.report_folder + self.report_name
# 90 SECONDS or LOAD FAIL
with open(report_path, 'a', encoding='utf8',
newline='') as csv_file:
writer = csv.writer(csv_file, quoting=csv.QUOTE_ALL)
writer.dialect.lineterminator.replace('\n', '')
writer.writerow(row)
stop_event.set()
document = PDFDocument
document = self.document_t
pf = PdfFileReader(BytesIO(open(self.pdf_path, 'rb').read()))
# ENCRYPTION
if self.parser.doc.encryption is not None:
csv_row.insert(4, [self.csv_header[4], 'ENCRYPTED'])
csv_row.insert(5, [self.csv_header[5], 'ENCRYPTED'])
else:
csv_row.insert(4, [self.csv_header[4], 'FALSE'])
csv_row.insert(5, [self.csv_header[5], 'NA'])
except Exception as e:
csv_row.insert(4, [self.csv_header[4], 'FAILED: ' + e.__str__()])
csv_row.insert(5, [self.csv_header[5], 'NA'])
exit_call = e.__str__() + ' document failed!!'
print(exit_call)
pass
page_count = 0
# istagged
try:
pages = PDFPage.get_pages(document)
if not document.is_extractable:
raise PDFTextExtractionNotAllowed
rsrcmgr = PDFResourceManager()
laparams = LAParams()
page_no = 0
istagged = 'FALSE'
try:
# document.catalog
if document.catalog['MarkInfo']:
istagged = 'TRUE'
except Exception as e:
exit_call = e.__str__() + ' tagged info failed!!'
print(exit_call)
page_count = resolve1(document.catalog['Pages'])['Count']
csv_row.insert(6, [self.csv_header[6], istagged])
csv_row.insert(7, [self.csv_header[7], page_count])
except Exception as e:
csv_row.insert(6, [self.csv_header[6], 'IsTagged: ' + e.__str__()])
csv_row.insert(7,
[self.csv_header[7], 'Page Count: ' + e.__str__()])
exit_call = e.__str__() + ' tagged info failed!!'
print(exit_call)
# TOC
try:
if pf.outlines:
csv_row.insert(8, [self.csv_header[8], 'TRUE'])
'''pdf_path_toc = self.document_folder + pdf_name + '_toc.txt'
places_list = pf.outlines
with open(pdf_path_toc, 'w') as filehandle:
filehandle.writelines("%s\n" % place for place in places_list)
filehandle.close()'''
else:
csv_row.insert(8, [self.csv_header[8], 'FALSE'])
except Exception as e:
csv_row.insert(8,
[self.csv_header[8], 'TOC FAILED: ' + e.__str__()])
exit_call = e.__str__() + ' toc info failed!!'
print(exit_call)
# isForm, fields,
try:
if pf.getFields():
csv_row.insert(9, [self.csv_header[9], 'TRUE'])
csv_row.insert(10,
[self.csv_header[10],
pf.getFields().__len__()])
else:
csv_row.insert(9, [self.csv_header[9], 'FALSE'])
csv_row.insert(10, [self.csv_header[10], 0])
except Exception as e:
csv_row.insert(9, [self.csv_header[9], 'FORMS: ' + e.__str__()])
csv_row.insert(10, [self.csv_header[10], 'FIELDS: ' + e.__str__()])
exit_call = e.__str__() + ' forms failed!!'
print(exit_call)
# tables
csv_row.insert(11, [self.csv_header[11], 'NOT RUN'])
write_clip = ''
word_count = 0
words_per_page = 0
char_count = 0
chars_per_word = 0
image_count = 0
# TODO: write 3 page sample and word count
try:
if pf.getNumPages() < 50:
for page in range(pf.getNumPages()):
p = pf.getPage(page)
text_clip = p.extractText().encode('UTF-8')
text_clip = BytesIO(text_clip).read().__str__()[2:]
count_clip = re.findall(r"[^\W_]+", text_clip,
re.MULTILINE)
word_count += len(count_clip)
char_count += len(text_clip)
if page <= 3:
write_clip += '[ PAGE ' + (page +
1).__str__() + ' START ] '
write_clip += text_clip.replace('\n', '').replace(
',', ' ').replace('"', '')
write_clip += '[ PAGE ' + (page +
1).__str__() + ' END ]'
else:
write_clip = 'OVER 50 PAGES - SAMPLE SKIPPED'
except Exception as e:
exit_call = e.__str__() + ' :: TEXT sample failed!!'
write_clip = exit_call
word_count = exit_call
char_count = exit_call
print(exit_call)
# TODO: Words/chars per page
try:
if not word_count == 0:
chars_per_word = char_count / word_count
else:
chars_per_word = 0
if not page_count == 0:
words_per_page = word_count / page_count
else:
words_per_page = 0
except Exception as e:
exit_call = e.__str__() + ' :: WORD METRICS failed!!'
chars_per_word = exit_call
words_per_page = exit_call
print(exit_call)
# TODO: Add to row
i = 12
try:
csv_row.insert(i, [self.csv_header[i], word_count.__str__()])
except Exception as e:
csv_row.insert(i,
[self.csv_header[i], 'WORD_COUNT: ' + e.__str__()])
i = 13
try:
csv_row.insert(i, [self.csv_header[i], char_count.__str__()])
except Exception as e:
csv_row.insert(i,
[self.csv_header[i], 'CHAR_COUNT: ' + e.__str__()])
i = 14
try:
csv_row.insert(i, [self.csv_header[i], words_per_page.__str__()])
except Exception as e:
csv_row.insert(i, [self.csv_header[i], 'WPP: ' + e.__str__()])
i = 15
try:
csv_row.insert(i, [self.csv_header[i], chars_per_word.__str__()])
except Exception as e:
csv_row.insert(i, [self.csv_header[i], 'CPP: ' + e.__str__()])
# TODO: IMAGES
i = 16
'''try:
pdfImages = Globals.base_folder + 'cli-tools\\pdfimages.exe'
img_folder = self.document_folder + 'images\\' # + pdf_name[:-4] + '\\'
if not os.path.exists(img_folder):
os.makedirs(img_folder)
# cmd = pdfImages + ' -list ' + '\"' + pdf_path + '\"'
# output = subprocess.Popen(cmd, stdout=subprocess.PIPE).communicate()[0].split(b'\n')
# save images to disk
cmd = pdfImages + ' -list \"' + self.pdf_path + '\" \"' + ' ' + '\"'
# subprocess.Popen(cmd, stdout=subprocess.PIPE)
os.chdir(img_folder)
image_list = subprocess.Popen(cmd, stdout=subprocess.PIPE).communicate()[0].split(b'\r\n')
# os.remove(img_folder)
# image_count = output.count('\n')
image_count = image_list.__len__()
if image_count > 2:
# target = open(pdf_path_image, 'w')
# target.write(image_list)
# target.close()
csv_row.insert(i, [self.csv_header[i], (image_count - 2).__str__()])
elif image_count == 0:
csv_row.insert(i, [self.csv_header[i], 0])
else:
csv_row.insert(i, [self.csv_header[i], 0])
except Exception as e:
csv_row.insert(i, [self.csv_header[i], e.__str__() + ' image info failed!!'])
exit_call = e.__str__() + ' image info failed!!'
print(exit_call)'''
# TODO: IMAGES per page
i = 17
percent_img_per_page = float
try:
if not image_count == 0 or page_count == 0:
percent_img_per_page = (float(image_count) /
float(page_count)) * 100
else:
percent_img_per_page = 0
csv_row.insert(i, [self.csv_header[i], percent_img_per_page])
except Exception as e:
csv_row.insert(i, [self.csv_header[i], 'IMG: ' + e.__str__()])
# TODO: OCR risk
i = 18
try:
if words_per_page == 0 or percent_img_per_page > 3000:
ocr_risk = 5
elif words_per_page < 15 or percent_img_per_page > 2000:
ocr_risk = 4
elif words_per_page < 40 or percent_img_per_page > 1000:
ocr_risk = 3
elif words_per_page < 70 or percent_img_per_page > 425:
ocr_risk = 2
elif words_per_page < 80 or percent_img_per_page > 200:
ocr_risk = 1
else:
ocr_risk = 0
csv_row.insert(i, [self.csv_header[i], ocr_risk])
except Exception as e:
csv_row.insert(i, [self.csv_header[i], 'OCR: ' + e.__str__()])
# author, creator, producer, subject, title,
di = pf
try:
di = pf.documentInfo
except Exception as e:
exit_call = e.__str__() + ' :: DOCUMENT INFO LOAD failed!!'
print(exit_call)
# Document info
if di:
# Author
try:
i = 19
if di.author:
csv_row.insert(
i, [self.csv_header[i],
di.author.encode('UTF-8')])
else:
csv_row.insert(i, [self.csv_header[i], 'NULL'])
except Exception as e:
csv_row.insert(i,
[self.csv_header[i], 'AUTHOR: ' + e.__str__()])
exit_call = e.__str__() + ' doc info failed!!'
print(exit_call)
# Creator
try:
i = 20
if di.creator:
csv_row.insert(
i, [self.csv_header[i],
di.creator.encode('UTF-8')])
else:
csv_row.insert(i, [self.csv_header[i], 'NULL'])
except Exception as e:
csv_row.insert(i,
[self.csv_header[i], 'CREATOR: ' + e.__str__()])
print(exit_call)
print('#5.1')
# Producer
try:
i = 21
if di.producer:
csv_row.insert(
i, [self.csv_header[i],
di.producer.encode('UTF-8')])
else:
csv_row.insert(i, [self.csv_header[i], 'NULL'])
except Exception as e:
csv_row.insert(
i, [self.csv_header[i], 'PRODUCER: ' + e.__str__()])
print(exit_call)
# Subject
try:
i = 22
if di.subject:
csv_row.insert(
i, [self.csv_header[i],
di.subject.encode('UTF-8')])
else:
csv_row.insert(i, [self.csv_header[i], 'NULL'])
except Exception as e:
csv_row.insert(i,
[self.csv_header[i], 'SUBJECT: ' + e.__str__()])
print(exit_call)
# Title
try:
i = 23
if di.title:
csv_row.insert(
i, [self.csv_header[i],
di.title.encode('UTF-8')])
else:
csv_row.insert(i, [self.csv_header[i], 'NULL'])
except Exception as e:
csv_row.insert(i,
[self.csv_header[i], 'TITLE: ' + e.__str__()])
print(exit_call)
# Document clip
i = 24
try:
csv_row.insert(i, [self.csv_header[i], write_clip])
except Exception as e:
csv_row.insert(i, [self.csv_header[i], e.__str__()])
# Write results
row = []
for i in range(csv_row.__len__()):
row.append(csv_row[i][1])
report_path = self.report_folder + self.report_name
# COPLETE WRITE
with open(report_path, 'a', encoding='utf8', newline='') as csv_file:
writer = csv.writer(csv_file, quoting=csv.QUOTE_ALL)
writer.dialect.lineterminator.replace('\n', '')
writer.writerow(row)
# csv_file.close()
fp.close()
os.remove(self.pdf_path)
# Log close
msg = (' >>>> PDF complete:[' + self.url + '] ' +
self.line_count.__str__() + ' ' +
(datetime.datetime.now().__str__()[:-7]))
print(msg)
utils.logline(self.log, msg)
def process_file(self):
infile = PdfFileReader(open(self.fp, 'rb'))
fields = infile.getFields()
self.content = self.parse_fields(fields)
#!/usr/bin/python
from PyPDF2 import PdfFileReader
pdf_document = "file.pdf"
with open(pdf_document, "rb") as filehandle:
pdf = PdfFileReader(filehandle)
info = pdf.getDocumentInfo()
pages = pdf.getNumPages()
print('file information: ', info)
print("number of pages: %i" % pages)
page1 = pdf.getPage(0)
print(pdf.getIsEncrypted())
print(pdf.pageMode)
print(pdf.getFields())
print(pdf.stream)
print(pdf.flattenedPages)
print(page1)
print(page1.extractText())
True)
return writer
except Exception as e:
print('set_need_appearances_writer() catch : ', repr(e))
return writer
csvin = "H:\\gitprojects\\\PyPDF2-Pandas-PDFFieldUpdater\\in\\data.csv"
infile = "H:\\gitprojects\\\PyPDF2-Pandas-PDFFieldUpdater\\in\\PatientIntakeForm.pdf"
data = pd.read_csv(csvin)
pdf = PdfFileReader(open(infile, "rb"), strict=False)
if "/AcroForm" in pdf.trailer["/Root"]:
pdf.trailer["/Root"]["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
fields = pdf.getFields() # Run in console to see Key names for field entry
i = 0 #Filename numerical prefix
for j, rows in data.iterrows():
outfile = "H:\\gitprojects\\\PyPDF2-Pandas-PDFFieldUpdater\\out\\"
i += 1
pdf2 = PdfFileWriter()
set_need_appearances_writer(pdf2)
if "/AcroForm" in pdf2._root_object:
pdf2._root_object["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
if "/AcroForm" in pdf2._root_object:
pdf2._root_object["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
def get_headers(infile):
inputStream = open(infile, "rb")
pdf_reader = PdfFileReader(inputStream, strict=False)
fields = pdf_reader.getFields().keys()
print('Headers needed for data file: {}'.format(list(fields)))
def PDFForm2Excel(mypath, outfile):
errcount = 0
mypath = abspath(mypath)
pdffiles = []
#Put PDF Files into Array pdffiles
if parser.parse_args(
).boolean_recursive == False: #non recursive: Only input Folder is analyzed
pdffiles = sorted([
join(mypath, f) for f in listdir(mypath)
if f[-4:] == '.pdf' and isfile(join(mypath, f))
])
if parser.parse_args(
).boolean_recursive == True: #recursive: input Folder and Subfolders are analyzed
for r, d, f in walk(mypath):
for file in f:
if file[-4:] == '.pdf' in file:
pdffiles.append(join(abspath(r), file))
#Start with Initial PDF to create Dataframe schema
#It needs to be assured that the first PDF and its Form Fields are always readable
#They create the master schema for all following PDFs
#It also has to be assured that the follwing PDF Forms have the same fields in the same order
#print(pdffiles)
pdf = pdffiles[0]
# pdf
#Define Objects f (file) and fields
f = PdfFileReader(pdf)
fields = f.getFields()
#Define Dataframe Object for Results
results = pd.DataFrame()
#Define dataframe for Field Name List
try:
df = pd.DataFrame([(k, k1, v1) for k, v in fields.items()
for k1, v1 in v.items()],
columns=['Field', 'Type', pdf])
df2 = df.loc[df['Type'] == '/V'] # Filter for Values := '/V' only
df2 = df2.filter(items=['Field', pdf])
df2 = df2.reset_index(drop=True) # Reset Row Index
results = df2.set_index('Field')
results = results.drop(pdf, axis='columns')
except:
exit("##initial pdf read error## " + pdf)
#Loop through all PDF Files in Input Folder
for pdf in pdffiles:
f = PdfFileReader(pdf) # PDF Fileobject
producer = f.getDocumentInfo().producer
try:
fields = f.getFields()
df = pd.DataFrame([(k, k1, v1) for k, v in fields.items()
for k1, v1 in v.items()],
columns=['Field', 'Type', pdf])
df2 = df.loc[df['Type'] == '/V'] # Filter for Values := '/V' only
df2 = df2.filter(items=['Field',
pdf]) # Add Filename as ColumnHeader
df2 = df2.set_index('Field') # Set 'Field' as Row Index
df2[pdf] = df2[pdf].map(lambda x: x.lstrip(
'=')) #remove heading '=' from future excel Cells
results = results.merge(
df2, on='Field', how='left') # Write Values to Array 'results'
print("read success " + str(producer) + " " + pdf)
except:
results[pdf] = '' #Create empty Column in results for failed PDF
print("##read error## " + str(producer) + " " + pdf)
errcount = errcount + 1
continue
print('--------------')
print("Summary: " + str(len(pdffiles)) + " files read with " +
str(errcount) + " file read Errors")
#write results to Excel
try:
if parser.parse_args().boolean_col == False:
results.T.to_excel(
mypath + outfile, header=True, index=True
) # Write Result dataframe in one line per PDF to Excel File
else:
results.to_excel(
mypath + outfile, header=True, index=True
) # Write Result dataframe in one Coumn per PDF to Excel File
print("File " + mypath + outfile + " successfully written")
except:
print("Error writing File " + mypath + outfile)
def cargoDoc():
fp = open(r"C:\Users\ssleep\Documents\Programming\Cargo Docker\Thursday\LCBO\601331975 PARS MANIFESTS.pdf", 'rb')
parser = PDFParser(fp)
doc = PDFDocument()
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize('')
visited = set()
pars = []
for xref in doc.xrefs:
for objid in xref.get_objids():
if objid in visited: continue
visited.add(objid)
obj = doc.getobj(objid)
if obj is None: continue
pars = extract(objid,obj)
pdfFileObj = open(specificPath, 'rb')
pdfReader = PdfFileReader(pdfFileObj)
fields = pdfReader.getFields()
# print(len(fields)-15)
for i in range(len(fields)-15):
containerNumber = ""
weight = ""
consignee = ""
shipper = ""
eta = ""
portOfLoading = ""
portOfDischarge = ""
description = ""
if i == 0:
# prefix = str(i) + "."
containerNumber = fields["Container Row1"].value
weight = float(fields["Weight KGRow1"].value)
consignee = fields["Consignee"].value
shipper = fields["Shipper"].value
eta = fields["ETA DATE"].value
portOfLoading = fields["undefined"].value
portOfDischarge = fields["Port of Discharge"].value
description = fields["Description of goods"].value
else:
for j in list(fields.keys()):
if j==str(i):
for k in list(fields[j]["/Kids"]):
try:
if(k.getObject()['/T']=="WO"):
wo=k.getObject()['/V']
elif(k.getObject()['/T']=="Container Row1"):
containerNumber=k.getObject()['/V']
elif(k.getObject()['/T']=="SizeRow1"):
size=k.getObject()['/V']
elif(k.getObject()['/T']=="Weight KGRow1"):
weight=float(k.getObject()['/V'])
elif(k.getObject()['/T']=="Consignee"):
consignee=k.getObject()['/V']
elif(k.getObject()['/T']=="Shipper"):
shipper=k.getObject()['/V']
elif(k.getObject()['/T']=="ETA DATE"):
eta=k.getObject()['/V']
elif(k.getObject()['/T']=="undefined"):
portOfLoading=k.getObject()['/V']
elif(k.getObject()['/T']=="Port of Discharge"):
portOfDischarge=k.getObject()['/V']
elif(k.getObject()['/T']=="Description of goods"):
description=k.getObject()['/V']
except KeyError:
True
now = datetime.datetime.now()
print str(now)
year = now.year
month = now.month
day = now.day
month_six_later = month + 6
date = '{}/{}/{}'.format(day, month, year)
date_six_later = '{}/{}/{}'.format(day, month_six_later, year)
print(date)
#infile = "Test-Sheet-3.pdf"
infile = askopenfilename()
pdf_reader = PdfFileReader(open(infile, "rb"))
dictionary = pdf_reader.getFormTextFields() # returns a python dictionary
dictionary_2 = pdf_reader.getFields(tree=None, retval=None)
patient_last_name = str(dictionary['Pat_LastName'])
patient_first_name = str(dictionary['Pat_FirstName'])
patient_name = '{} {}'.format(patient_first_name, patient_last_name)
#patient_gender = str(dictionary['Pat_Gender'])
patient_DOB = str(dictionary['Pat_DOB'])
patient_gender = str(dictionary_2['Pat_Gender'])
if patient_gender[102] == 'F':
patient_gender = 'Female'
elif patient_gender[102] == 'M':
patient_gender = 'Male'
knee_for_analysis = str(dictionary_2['Pat_Side'])
def write(client, doc): path_in_file = os.path.join(PDF_TEMPLATE_DIR, doc.file_name) inpt = open(path_in_file, 'rb') clients_file_name = str(client.first_name) + ' ' + str(client.last_name) + \ '_' + str(doc.file_name) # date or time p_file_path = os.path.join(PDF_GENERATED_RESULT_DIR, clients_file_name) reads = PdfFileReader(inpt) read = reads.getFormTextFields() checkboxes = reads.getFields() ## дефолтные значения ne menyat read['Text Field 490'] = ' ' # fio esli menyalos read['Text Field 473'] = ' ' # reklama read['Text Field 475'] = ' ' # inoe read['Text Field 493'] = ' ' read['Text Field 494'] = ' ' read['Text Field 492'] = ' ' read['Text Field 496'] = ' ' read['Text Field 497'] = ' ' read['Text Field 498'] = ' ' read['Text Field 50910'] = ' ' read['Text Field 50610'] = ' ' read['Text Field 505'] = ' ' read['Text Field 504'] = ' ' read['Text Field 506'] = ' ' for i in range(11, 21, 1): read['Text Field 50' + str(i)] = ' ' ##Заемщик\созаемщик checkboxes['Check Box 136'] = '/Yes' # zaemschik checkboxes['Check Box 137'] = '/Yes' # sozaemschik checkboxes['Check Box 97'] = '/Yes' # не убирать ########## Адрес checkboxes['Check Box 138'] = '/Yes' # fakt adres sovpadaet s registr ############Основания для проживания checkboxes['Check Box 101'] = '/Yes' # соц наем checkboxes['Check Box 102'] = '/Yes' # коммерческий наем checkboxes['Check Box 103'] = '/Yes' # собственность checkboxes['Check Box 104'] = '/Yes' # у родственников checkboxes['Check Box 105'] = '/Yes' # иное, отразить в Листе дополнений ###### Семейное положение checkboxes['Check Box 106'] = '/Yes' # женат\замужем checkboxes['Check Box 107'] = '/Yes' # в разводе checkboxes['Check Box 108'] = '/Yes' # вдовец\вдова checkboxes['Check Box 109'] = '/Yes' # гражданский брак checkboxes['Check Box 110'] = '/Yes' # холост\не замужем ## Брачный договор checkboxes['Check Box 111'] = '/Yes' # есть checkboxes['Check Box 112'] = '/Yes' # нет ## Изменялась фамилия checkboxes['Check Box 113'] = '/Yes' # да checkboxes['Check Box 114'] = '/Yes' # нет # Дети совместно проживают # первый ребенок checkboxes['Check Box 115'] = '/Yes' # да checkboxes['Check Box 116'] = '/Yes' # net ## второй ребенок checkboxes['Check Box 117'] = '/Yes' # da checkboxes['Check Box 118'] = '/Yes' # net ## третий ребенок checkboxes['Check Box 119'] = '/Yes' # da checkboxes['Check Box 120'] = '/Yes' # net ############Образование checkboxes['Check Box 121'] = '/Yes' # nizhe srednego checkboxes['Check Box 122'] = '/Yes' # srednee checkboxes['Check Box 123'] = '/Yes' # srednee spec checkboxes['Check Box 124'] = '/Yes' # neokon vishee checkboxes['Check Box 125'] = '/Yes' # highest checkboxes['Check Box 126'] = '/Yes' # neskolko high checkboxes['Check Box 127'] = '/Yes' # dop vish checkboxes['Check Box 128'] = '/Yes' # uchenaya stepen checkboxes['Check Box 129'] = '/Yes' # MBA checkboxes['Check Box 130'] = '/Yes' # inoe ################занятонсть checkboxes['Check Box 131'] = '/Yes' # yavlyatsya zarplatnym proektom checkboxes['Check Box 132'] = '/Yes' # ne yavlyaetsa ############Место работы checkboxes['Check Box 133'] = '/Yes' # ispytatelny srok checkboxes['Check Box 134'] = '/Yes' # ne ispytatelny srok checkboxes['Check Box 139'] = '/Yes' # по найму бессрочно checkboxes['Check Box 140'] = '/Yes' # по найму срочно checkboxes['Check Box 141'] = '/Yes' # ИП checkboxes['Check Box 142'] = '/Yes' # собственность бизнеса ###### Сфера деятельности организации checkboxes['Check Box 144'] = '/Yes' # армия checkboxes['Check Box 145'] = '/Yes' # ИТ checkboxes['Check Box 146'] = '/Yes' # Консалтинг checkboxes['Check Box 147'] = '/Yes' # Медицина checkboxes['Check Box 148'] = '/Yes' # наука checkboxes['Check Box 149'] = '/Yes' # образование checkboxes['Check Box 150'] = '/Yes' # строительство checkboxes['Check Box 151'] = '/Yes' # отповая розничная культура checkboxes['Check Box 152'] = '/Yes' # органы власти и управления checkboxes['Check Box 153'] = '/Yes' # охранная деятельность checkboxes['Check Box 154'] = '/Yes' # предприятия ТЭК checkboxes['Check Box 155'] = '/Yes' # промышленность и машиностроение checkboxes['Check Box 156'] = '/Yes' # социальная сфера checkboxes['Check Box 157'] = '/Yes' # транспорт checkboxes['Check Box 158'] = '/Yes' # туризм checkboxes['Check Box 159'] = '/Yes' # услуги checkboxes['Check Box 160'] = '/Yes' # финансы, банки, стразование checkboxes['Check Box 161'] = '/Yes' # другие отрасли ######################Численность персонала checkboxes['Check Box 162'] = '/Yes' # do 10 checkboxes['Check Box 163'] = '/Yes' # 11-50 checkboxes['Check Box 164'] = '/Yes' # 51-100 checkboxes['Check Box 165'] = '/Yes' # 101-500 checkboxes['Check Box 166'] = '/Yes' # 501-1000 checkboxes['Check Box 167'] = '/Yes' # >1000 ################Срок существования организации checkboxes['Check Box 168'] = '/Yes' # до 2 лет checkboxes['Check Box 169'] = '/Yes' # от 2 до 5 лет checkboxes['Check Box 170'] = '/Yes' # свыше 5 лет ################Дополнительное место работы checkboxes['Check Box 171'] = '/Yes' # имею checkboxes['Check Box 172'] = '/Yes' # не имею ##########Денежные средства (с учетом первоначального взноса) checkboxes['Check Box 17310'] = '/Yes' # имею checkboxes['Check Box 174'] = '/Yes' # не имею# ####################Автомобиль checkboxes['Check Box 175'] = '/Yes' # есть checkboxes['Check Box 176'] = '/Yes' # нет ##########Недвижисое имущество checkboxes['Check Box 1731011'] = '/Yes' # есть checkboxes['Check Box 173'] = '/Yes' # нет ############Основания возниконовения права на имущество checkboxes['Check Box 177'] = '/Yes' # покупка checkboxes['Check Box 178'] = '/Yes' # приватизация checkboxes['Check Box 179'] = '/Yes' # наследство checkboxes['Check Box 180'] = '/Yes' # дарение checkboxes['Check Box 181'] = '/Yes' # иное ##############процедура бонкротства checkboxes['Check Box 182'] = '/Yes' # применялось checkboxes['Check Box 183'] = '/Yes' # не применялось ################Алиментные обязательства checkboxes['Check Box 184'] = '/Yes' # yest checkboxes['Check Box 185'] = '/Yes' # net ################Не редаткировать. Принять условия соглашения checkboxes['Check Box 186'] = '/Yes' # иное checkboxes['Check Box 187'] = '/Yes' # иное checkboxes['Check Box 189'] = '/Yes' # согласие на обработку ПДн ######################Представитель checkboxes['Check Box 188'] = '/Yes' # есть представитель ################Клиент read['Text Field 470'] = 'stepen rodstva s zaemschikom' read['Text Field 471'] = client.last_name + ' ' + client.first_name + \ ' ' + client.part_name read['Text Field 472'] = client.passport.gender # male/female read['Text Field 474'] = client.snils # 'snils' read['Text Field 476'] = client.inn # 'INN' read['Text Field 477'] = 'index' read['Text Field 478'] = 'РФ' read['Text Field 479'] = 'oblast' read['Text Field 480'] = 'rayon' read['Text Field 481'] = client.address.city # 'naselenny punkt' read['Text Field 482'] = client.address.street # 'street' read['Text Field 483'] = client.address.buildingNumber # 'number of home' read['Text Field 484'] = 'korpus' read['Text Field 485'] = client.address.flat # 'flat' read['Text Field 486'] = 'phone' read['Text Field 487'] = 'home phone reg' read['Text Field 488'] = 'home phone prozhivanie' read['Text Field 489'] = 'work phone' read['Text Field 490'] = 'e-mail' if checkboxes['Check Box 113'] == '/Yes': # изменялась ли фамилмя read['Text Field 491'] = 'FIO' read['Text Field 492'] = 'god izmeneniya' ##################Дети read['Text Field 493'] = 'data rozhdeniya 1go rebenka' read['Text Field 494'] = 'data rozhdeniya 2go rebenka' ################Зарплатный проект if checkboxes['Check Box 131'] == '/Yes': read['Text Field 496'] = 'nomer karty' ####################Работа if checkboxes['Check Box 136'] == '/Yes': read['Text Field 497'] = 's' read['Text Field 498'] = 'do' if checkboxes['Check Box 138'] == '/Yes': read['Text Field 499'] = '% buisness' read['Text Field 500'] = 'должность' read['Text Field 501'] = 'среднемесячный доход' read['Text Field 502'] = "стаж работы на текущем месте, лет" read['Text Field 50311'] = 'Стаж по профилю, лет' read['Text Field 50411'] = 'Общий стаж работы общий, лет' read['Text Field 50510'] = 'Название организации' read['Text Field 50610'] = 'инн организации' read['Text Field 50710'] = 'фактический адрес' read['Text Field 50810'] = 'телефон организации' read['Text Field 50910'] = 'добавочный номер' read['Text Field 5010'] = 'сайт организации' if checkboxes['Check Box 151'] == '/Yes': read['Text Field 505'] = 'сфера розничной торговли' if checkboxes['Check Box 159'] == '/Yes': read['Text Field 504'] = 'уточните сферу' if checkboxes['Check Box 161'] == '/Yes': read['Text Field 503'] = 'Уточните' ######################Активы if checkboxes['Check Box 173'] == '/Yes': read['Text Field 5011'] = 'Наличные средства, сумма, руб' read['Text Field 5012'] = 'Банк №1' read['Text Field 5013'] = 'Банк №2' read['Text Field 5014'] = 'Сумма' read['Text Field 5015'] = 'Сумма' if checkboxes['Check Box 175'] == '/Yes': read['Text Field 5016'] = 'марка' read['Text Field 5017'] = 'год приобретения' read['Text Field 5018'] = 'стоимость по вашей оценке' if checkboxes['Check Box 1731011'] == '/Yes': read['Text Field 5019'] = 'Тип объекта недвижимости' read['Text Field 5020'] = 'Текущая рыночная стоимость(по вашей оценке)' if checkboxes['Check Box 181'] == '/Yes': read['Text Field 506'] = 'иное' ######################Представитель if checkboxes['Check Box 188'] == '/Yes': read['Text Field 5021'] = 'Фио представителя' ########################Согласие на Пдн read['Text Field 5026'] = client.last_name + ' ' + client.first_name + \ ' ' + client.part_name # Пдн outpt = open(p_file_path, 'wb') write = PdfFileWriter() set_need_appearances_writer(write) for i in range(reads.getNumPages()): write.addPage(reads.getPage(i)) updateCheckboxValues(reads.getPage(i), checkboxes) write.updatePageFormFieldValues(reads.getPage(i), read) write.write(outpt) inpt.close() outpt.close()
# this is the smallest example of a pdf I could find from the examples at
# https://stackoverflow.com/questions/17279712/what-is-the-smallest-possible-valid-pdf.
# it does _not_ successfully parse with pypdf2, but it might be enough to exercise the
# code enough to get internal imports or caches initialized before the fork. IRL you
# might like to use a real pdf for this.
r = PdfFileReader(
BytesIO(
codecs.decode(
b"255044462D312E0D747261696C65723C"
b"3C2F526F6F743C3C2F50616765733C3C"
b"2F4B6964735B3C3C2F4D65646961426F"
b"785B302030203320335D3E3E5D3E3E3E"
b"3E3E3E",
"hex",
)))
except PyPdfError:
pass
import sys
from cpytraceafl import fuzz_from_here, crashing_excepthook
fuzz_from_here(excepthook=crashing_excepthook)
with open(sys.argv[1], "rb") as f:
try:
r = PdfFileReader(f)
r.getFields()
r.getXmpMetadata()
except PyPdfError:
pass
def get_form_fields(infile):
infile = PdfFileReader(open(infile, 'rb'))
fields = infile.getFields()
return OrderedDict((k, v.get('/V', '')) for k, v in fields.items())
def write(client, doc): path_in_file = os.path.join(PDF_TEMPLATE_DIR, doc.file_name) inpt = open(path_in_file, 'rb') clients_file_name = str(client.first_name) + ' ' + str(client.last_name) + \ '_' + str(doc.file_name) # date or time p_file_path = os.path.join(PDF_GENERATED_RESULT_DIR, clients_file_name) reads = PdfFileReader(inpt) read = reads.getFormTextFields() checkboxes = reads.getFields() checkboxes['chk0'] = '/Yes' ## checkboxes['chk1'] = '/Yes' #Созаемщик ## checkboxes['chk2'] = '/Yes' #Поручитель checkboxes['untitled9'] = '/Yes' # Квартира checkboxes['untitled10'] = '/Yes' # Дом с участком checkboxes['untitled11'] = '/Yes' # Апартаменты checkboxes['untitled12'] = '/Yes' # Таунхаус checkboxes['untitled13'] = '/Yes' # страховка checkboxes['untitled14'] = '/Yes' # мужчина checkboxes['untitled15'] = '/Yes' # женщина ## if str(checkboxes['chk1']) == '/Yes' or str(checkboxes['chk2']) == '/Yes': ## read['str0'] = 'фамилия заемщика' ## if checkboxes['chk'] read['str1'] = 'Сумма кредита' read['str2'] = 'срок кредита' read['str3'] = 'сумма первоначального взноса' read['str4'] = 'стоимость объекта' read['str5'] = 'запрашиваемая сумма top up' read['str6'] = 'регион приобретения недвижимости' read['str7'] = client.last_name read['str8'] = client.first_name read['str9'] = client.part_name read['str10'] = 'дата рождения' read['str11'] = 'гражданство' read['str12'] = 'место рождения' read['str13'] = client.snils # 'снилс' read['str14'] = client.inn # inn read['str15'] = 'фио при изменении' read['str16'] = client.passport.serial + ' ' + client.passport.number # 'серия номер паспорта' read['str17'] = 'дата выдачи' read['str18'] = 'код подразделения' read['str19'] = client.passport._from # 'кем выдан' read['str20'] = 'адрес регистрации' read['str21'] = 'адрес проживания' # lj,bnm read['str22'] = 'мобильный' read['str23'] = 'регистрац' read['str24'] = 'тел жит' read['str25'] = 'email' read['str62'] = 'кол-во детей' read['str26'] = 'регистрац' outpt = open(p_file_path, 'wb') write = PdfFileWriter() set_need_appearances_writer(write) for i in range(reads.getNumPages() - 1): # пока хз почему write.addPage(reads.getPage(i)) updateCheckboxValues(reads.getPage(i), checkboxes) write.updatePageFormFieldValues(reads.getPage(0), read) write.write(outpt) inpt.close() outpt.close()
def return_infile():
from PyPDF2 import PdfFileReader
infile = "C:\\Users\\\mark.nations\\Desktop\\H-15\\h15.pdf"
pdf = PdfFileReader(open(infile, "rb"), strict=False)
fields = pdf.getFields()
return PdfFileReader, fields, infile, pdf
def arrive(specificPath):
pdfFileObj = open(specificPath, 'rb')
pdfReader = PdfFileReader(pdfFileObj)
fields = pdfReader.getFields()
# print(len(fields)-15)
for i in range(len(fields) - 15):
driver.switch_to_default_content()
driver.switch_to_frame(
driver.find_element_by_css_selector(
"frame[src='portals/portal.asp']"))
containerNumber = ""
size = ""
weight = ""
otherInfo = ""
consignee = ""
if i == 0:
# prefix = str(i) + "."
wo = fields["WO"].value
containerNumber = fields["Container Row1"].value
size = fields["SizeRow1"].value
weight = float(fields["Weight KGRow1"].value)
otherInfo = fields["Other info"].value
consignee = fields["Consignee"].value
else:
for j in list(fields.keys()):
if j == str(i):
for k in list(fields[j]["/Kids"]):
try:
if (k.getObject()['/T'] == "WO"):
wo = k.getObject()['/V']
elif (k.getObject()['/T'] == "Container Row1"):
containerNumber = k.getObject()['/V']
elif (k.getObject()['/T'] == "SizeRow1"):
size = k.getObject()['/V']
elif (k.getObject()['/T'] == "Weight KGRow1"):
weight = float(k.getObject()['/V'])
elif (k.getObject()['/T'] == "Other info"):
otherInfo = k.getObject()['/V']
elif (k.getObject()['/T'] == "Consignee"):
consignee = k.getObject()['/V']
except KeyError:
True
elem = driver.find_element_by_name("container_prefix_dof")
elem.send_keys(containerNumber[:4])
elem = driver.find_element_by_name("container_number_dof")
elem.send_keys(containerNumber[4:11])
select = Select(driver.find_element_by_name("ddlLoadStatus_dof"))
select.select_by_visible_text("Load")
select = Select(driver.find_element_by_name("lineid"))
select.select_by_visible_text("Hapag-Lloyd Container Line")
elem = driver.find_element_by_name("ddlSzTyCnt")
elem.send_keys(size)
elem = driver.find_element_by_name("cargo_weight")
elem.send_keys(str(weight))
select = Select(driver.find_element_by_name("ddWeightUnits"))
select.select_by_visible_text("Kgs")
elem = driver.find_element_by_id("CkbCR")
elem.click()
try:
if not ("LCBO" in consignee or "LIQUOR CONTROL" in consignee):
elem = driver.find_element_by_id("CkbFR")
elem.click()
except:
elem = driver.find_element_by_id("CkbFR")
elem.click()
reservation = "import"
if size == "20R86" or size == "40R96":
m = re.search("Temperature: ", otherInfo)
n = re.search(r"\.\d+ C", otherInfo[m.end():])
# print(str(m.end()) + " " + str(n.start()))
reservation += otherInfo[m.end():n.start() + m.end()] + "c"
elem = driver.find_element_by_name("bkg_nbr_dof")
elem.send_keys(reservation)
select = Select(driver.find_element_by_name("Line"))
select.select_by_visible_text("Hapag-Lloyd Container Line")
elem = driver.find_element_by_name("Submit")
elem.click()
wait = WebDriverWait(driver, 10)
wait.until(lambda driver: "Equipment is already on Terminal" in driver.
page_source or EC.element_to_be_clickable(
driver.find_element_by_name("Close")))
if "Equipment is already on Terminal" in driver.page_source:
f = open(testfile, "a+")
f.write("WO: " + wo + " " + "Container: " +
containerNumber + "\n")
f.close()
driver.switch_to_default_content()
driver.switch_to_frame(
driver.find_element_by_css_selector(
"frame[src='MenuNavFrame.asp?MenuID=10']"))
elem = driver.find_element_by_css_selector(
'a[href*="Gate/VirtualArrive/VirtualArrive.asp"')
elem.click()
else:
elem = driver.find_element_by_name("Close")
elem.click()
def make_pdf(self):
#Import dependencies
from PyPDF2 import PdfFileReader
from datetime import datetime
import os
import pypdftk
import pytz
pdf_pages = []
#Cycle through pages
for j, page in enumerate(self.pages):
template_name = os.path.join(THIS_FOLDER,
"./pdf_templates/form.pdf")
#Read pdf templates using PyPDF2
form = PdfFileReader(open(template_name, "rb"))
#Get main form field names from pdf reader
fields = form.getFields(tree=None, retval=None, fileobj=None)
field_names = list(fields.keys())
#Make a copy of field_values
field_values = self.details[:]
#Add values from each page
for product in page:
field_values += [
product.reference, product.lot, product.quantity,
product.description
]
#Pad out unused fields, zip into dict for writing
field_values += [""] * (len(field_names) - len(field_values))
field_dict = dict(
zip(field_names, map(lambda x: x.upper(), field_values)))
#Add page to writer, update fields from input data
pdf_pages.append(pypdftk.fill_form(template_name, field_dict))
if self.checklist:
end_form_template_name = os.path.join(
THIS_FOLDER, "./pdf_templates/end_page.pdf")
#Get pdf templates using PyPDF2
end_form = PdfFileReader(open(end_form_template_name, "rb"))
#Get end form fields from reader
end_fields = end_form.getFields(tree=None,
retval=None,
fileobj=None)
end_field_names = list(end_fields.keys())
#Populate end field values with name and date, position depending on options
end_field_values = [""] * 4
index = 2 if self.new else 0
tz = pytz.timezone("Australia/Brisbane")
current_date = datetime.now(tz)
end_field_values[index:index + 1] = [
self.client.first_name + " " + self.client.last_name,
current_date.strftime("%d/%m/%Y")
]
#Zip end field values and names into dict
end_field_dict = dict(zip(end_field_names, end_field_values))
pdf_pages.append(
pypdftk.fill_form(end_form_template_name, end_field_dict))
pypdftk.concat(pdf_pages,
os.path.join(THIS_FOLDER, "../dynamic/print.pdf"))
def printMeta(directorio):
try:
print('Analizando el directorio: ' + directorio, '\n')
for dirpath, dirnames, files in os.walk(directorio):
for name in files:
ext = name.lower().rsplit('.', 1)[-1]
#Documentos
if ext in ['pdf']:
print("[*] Metadatos del archivo: %s " %
(dirpath + os.path.sep + name))
print(
'----------------------------------------------------------'
)
try:
pdfFile = PdfFileReader(
open(dirpath + os.path.sep + name,
'rb')) #abrimos el fichero
docInfo = pdfFile.getDocumentInfo(
) #creamos un diccionario con la info recolectada
for metaItem in docInfo:
print('[+]' + metaItem + ':' +
str(docInfo[metaItem]))
docInfoextra = {
pdfFile.getNumPages(): 'Numero de paginas: ',
pdfFile.getPageMode(): 'Modo de la pagina: ',
pdfFile.isEncrypted: 'Encriptacion: ',
pdfFile.getFields(): 'Campos de texto: '
}
for element in docInfoextra:
if element != None:
print('[+]/' + docInfoextra[element] +
str(element))
xmpinfo = pdfFile.getXmpMetadata()
except:
pass
if xmpinfo != None:
if hasattr(xmpinfo, 'dc_contributor'):
print('[+]/' + 'dc_contributor',
xmpinfo.dc_contributor)
elif hasattr(xmpinfo, 'dc_identifier'):
print('[+]/' + 'dc_identifier',
xmpinfo.dc_identifier)
elif hasattr(xmpinfo, 'dc_date'):
print('[+]/' + 'dc_date', xmpinfo.dc_date)
elif hasattr(xmpinfo, 'dc_source'):
print('[+]/' + 'dc_source', xmpinfo.dc_source)
elif hasattr(xmpinfo, 'dc_subject'):
print('[+]/' + 'dc_subject', xmpinfo.dc_subject)
elif hasattr(xmpinfo, 'xmp_modifyDate'):
print('[+]/' + 'xmp_modifyDate',
xmpinfo.xmp_modifyDate)
elif hasattr(xmpinfo, 'xmp_metadataDate'):
print('[+]/' +
'xmp_metadataDate'), xmpinfo.xmp_metadataDate
elif hasattr(xmpinfo, 'xmpmm_documentId'):
print('[+]/' + 'xmpmm_documentId',
xmpinfo.xmpmm_documentId)
elif hasattr(xmpinfo, 'xmpmm_instanceId'):
print('[+]/' + 'xmpmm_instanceId',
xmpinfo.xmpmm_instanceId)
elif hasattr(xmpinfo, 'pdf_keywords'):
print('[+]/' + 'pdf_keywords',
xmpinfo.pdf_keywords)
elif hasattr(xmpinfo, 'pdf_pdfversion'):
print('[+]/' + 'pdf_pdfversion',
xmpinfo.pdf_pdfversion)
print("\n")
#Imagenes
elif ext in ['jpg', 'tiff']:
print("[*] Metadatos del archivo: %s " %
(dirpath + os.path.sep + name))
print(
'----------------------------------------------------------'
)
f = open(dirpath + os.path.sep + name, 'rb')
tags = exifread.process_file(f)
if len(tags) == 0:
print('[!]No hay metadatos')
for tag in tags.keys():
if tag not in ('JPEGThumbnail', 'TIFFThumbnail',
'Filename', 'EXIF MakerNote'):
print("[+]: %s, valor %s" % (tag, tags[tag]))
print("\n")
#Musica
elif ext in ['mp3']:
print("[*] Metadatos del archivo: %s " %
(dirpath + os.path.sep + name))
print(
'----------------------------------------------------------'
)
tag = eyed3.id3.Tag()
tag.parse(dirpath + os.path.sep + name)
if tag.artist is not None:
print('Artista: ', tag.artist)
if tag.album is not None:
print('Album: ', tag.album)
if tag.title is not None:
print('Titulo: ', tag.title)
if tag.track_num[0] is not None:
print('Track: ', tag.track_num[0])
else:
print('[!]No hay metadatos')
#Docs
elif ext in ['docs']:
print("[*] Metadatos del archivo: %s " %
(dirpath + os.path.sep + name))
print(
'----------------------------------------------------------'
)
document = docx.Document(docx=dirpath + os.path.sep + name)
core_properties = document.core_properties
print(core_properties.author)
print(core_properties.created)
print(core_properties.last_modified_by)
print(core_properties.last_printed)
print(core_properties.modified)
print(core_properties.revision)
print(core_properties.title)
print(core_properties.category)
print(core_properties.comments)
print(core_properties.identifier)
print(core_properties.keywords)
print(core_properties.language)
print(core_properties.subject)
print(core_properties.version)
print(core_properties.keywords)
print(core_properties.content_status)
print('[+]Ejecucion finalizada')
except (KeyboardInterrupt, SystemExit):
print('[!]Se ha interrumpido la ejecucion')
except:
print("Unexpected error:", sys.exc_info()[0])
def main():
pdf = PdfFileReader(file('tt.pdf', 'rb'), strict=False)
print pdf.getFields({''})
def write(client, doc): path_in_file = os.path.join(PDF_TEMPLATE_DIR, doc.file_name) inpt = open(path_in_file, 'rb') clients_file_name = str(client.first_name) + ' ' + str(client.last_name) + \ '_' + str(doc.file_name) # date or time p_file_path = os.path.join(PDF_GENERATED_RESULT_DIR, clients_file_name) reads = PdfFileReader(inpt) read = reads.getFormTextFields() checkboxes = reads.getFields() ## checkboxes['chk0'] = '/Yes' read['gText1'] = 'Наименование компании-партнёра' read['gText2'] = 'ФИО сотрудника компании-партнёра' read['gText3'] = '*****@*****.**' read['Text1'] = read['Text28'] = 'Фамилия' # client.last_name read['Text2'] = 'Имя' # client.first_name read['Text3'] = 'Отчество' # client.part_name ## read['Text28'] = client.first_name + client.part_name read['gNum1'] = 9379373737 # телефон партнера read['Num1'] = 99999 # запрашиваемая сумма кредита read['Num2'] = 122 # количество месяцев срок кредита read['Num3'] = 99999 # Предваритаельная стоимость жилья read['Text32'] = 'РФ' read['Text7'] = 'РФ' read['Text8'] = 'oblast' read['Text9'] = 'rayon' read['Num33'] = 'номер квартиры' # client.address.flat read['Text33'] = 'ulitsa' # client.address.street read['Num32'] = 123 # client.address.buildingNumber read['Text44'] = 44 # client.address korpus ?? read['Text35'] = 'gorod' # client.address.city read['Num6'] = 433 # client.address.flat read['Num4'] = 443531 # client.address.index ?? read['Num7'] = 9061264537 # stacion telefon read['email'] = '*****@*****.**' # client.email read['Num14'] = 9061264536 # client.phone_number read['Text20'] = 'nameOfOrganiz' # client.OrganizationInfo.full_name read['Text21'] = 'address_of_jobs' # client.OrganizationInfo.address read['Num17'] = 'inn' # client.OrganizationInfo.inn_number read['Num18'] = 45523455549 # client.OrganizationInfo.hr_number read['Num19'] = 45523455548 # client.OrganizationInfo.phoneJob ?? # рабочий телефон read['Num20'] = 99 # stazh v godah in organization read['Num21'] = 11 # stazh v month in organization read['Num22'] = 24 # full stazh in years read['Num23'] = 11 # full stazh in months read['Num24'] = 555555 # client.AdditionalClientInfo.average_income read['Num25'] = 12222 # client.AdditionalClinetInfo.aliment read['Num26'] = 222222 # client.AdditionalClinetInfo.monetary_obligations read['Num27'] = 3608 # client.passport.serial read['Num28'] = 128333 # client.passport.number read['Num29'] = 640 # str(clent.passport.code_of)[:3] read['Num30'] = 128 # str(client.passport.code_of)[4:] read['Text31'] = '' # пока так дальше видно будет outpt = open(out, 'wb') write = PdfFileWriter() set_need_appearances_writer(write) for i in range(reads.getNumPages() - 1): # пока хз почему write.addPage(reads.getPage(i)) updateCheckboxValues(reads.getPage(i), checkboxes) write.updatePageFormFieldValues(reads.getPage(i), read) write.write(outpt) inpt.close() outpt.close()
