def _extract_pdf_forms(self, fname):
"""Extracts interactive form fields data from a PDF file.
Parameters:
fname (str): Path to PDF file.
Returns:
dict: Form fields data extracted.
"""
f = PdfFileReader(fname)
return f.getFields()
def getFormFields(filepath):
"""
Get field information of pdf file
:param filepath: filepath to pdf file
:return: list with tuples of (field name, field type) as counter to find multi fields
"""
fields = []
with open(filepath, 'rb') as f:
reader = PdfFileReader(f)
for k, v in reader.getFields().iteritems():
if re.search('^\s*[0-9]', v['/T']):
fields.append(("_".join(v['/T'].split('_')[1:]), FIELDTYPES[v['/FT']]))
else:
fields.append((v['/T'], FIELDTYPES[v['/FT']]))
ret = OrderedDict()
for k, v in iter(sorted(Counter(fields).iteritems())):
ret[k[0].encode('utf-8')] = (k[1].encode('utf-8'), v)
return ret
def getFormFields(filepath):
"""
Get field information of pdf file
:param filepath: filepath to pdf file
:return: list with tuples of (field name, field type) as counter to find multi fields
"""
fields = []
with open(filepath, 'rb') as f:
reader = PdfFileReader(f)
for k, v in reader.getFields().iteritems():
if re.search('^\s*[0-9]', v['/T']):
fields.append(
("_".join(v['/T'].split('_')[1:]), FIELDTYPES[v['/FT']]))
else:
fields.append((v['/T'], FIELDTYPES[v['/FT']]))
ret = OrderedDict()
for k, v in iter(sorted(Counter(fields).iteritems())):
ret[k[0].encode('utf-8')] = (k[1].encode('utf-8'), v)
return ret
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)
