def test_parser_exception(resources):
pdf = Pdf.open(resources / 'graph.pdf')
stream = pdf.pages[0]['/Contents']
with pytest.raises(ValueError):
Object._parse_stream(stream, ExceptionParser())
def outlines(resources):
return Pdf.open(resources / 'outlines.pdf')
def test_has_text(resources, test_file, expected):
pdf = Pdf.open(resources / test_file)
for p in pdf.pages:
page = Page(p)
assert page.has_text() == expected
def test_open_pdf_password(resources):
pdf = Pdf.open(resources / 'graph-encrypted.pdf', password='******')
assert pdf.root['/Pages']['/Count'] == 1
def sandwich(resources):
# Has XMP, docinfo, <?adobe-xap-filters esc="CRLF"?>, shorthand attribute XMP
with Pdf.open(resources / 'sandwich.pdf') as pdf:
yield pdf
def test_open_pdf_password_encoding(self, resources):
with pytest.raises(PasswordError):
Pdf.open(resources / 'graph-encrypted.pdf', password=b'\x01\xfe')
def test_stream(self, resources):
with (resources / 'pal-1bit-trivial.pdf').open('rb') as stream:
pdf = Pdf.open(stream)
assert pdf.root.Pages.Count == 1
def test_file_descriptor(resources):
with (resources / 'pal-1bit-trivial.pdf').open('rb') as f:
with pytest.raises(TypeError):
Pdf.open(f.fileno())
def test_some_permissions_missing(self, resources):
pdf = Pdf.open(resources / 'graph-encrypted.pdf', 'owner')
assert pdf.allow.print_highres == pdf.allow.modify_annotation == False
def test_attr_access(resources):
with Pdf.open(resources / 'graph.pdf') as pdf:
assert int(pdf.Root.Pages.Count) == 1
def test_read_not_readable_file(self, outdir):
writable = (Path(outdir) / 'writeme.pdf').open('wb')
with pytest.raises(ValueError, match=r'not readable'):
Pdf.open(writable)
def compile(
exam,
json,
md,
seed,
subtitle,
with_solutions,
exam_type,
semester,
json_out,
merged_md,
draft,
out,
):
"""
Compile one PDF or JSON (from Markdown), unencrypted.
The exam may be deployed or local (in Markdown or JSON).
If a seed is specified, it will scramble the exam.
"""
if not out:
out = ""
pathlib.Path(out).mkdir(parents=True, exist_ok=True)
if json:
print("Loading exam...")
exam_data = load(json)
elif md:
exam_text_data = md.read()
if merged_md:
buff = LineBuffer(exam_text_data)
handle_imports(buff, path=os.path.dirname(md.name))
merged_md.write("\n".join(buff.lines))
return
print("Compiling exam...")
exam_data = convert(exam_text_data, path=os.path.dirname(md.name), draft=draft)
else:
print("Fetching exam...")
exam_data = get_exam(exam=exam)
if seed:
print("Scrambling exam...")
exam_data = scramble(seed, exam_data, keep_data=with_solutions)
def remove_solutions_from_groups(groups):
for group in groups:
# if isinstance(group, dict):
group.pop("solution", None)
if group.get("type") == "group":
remove_solutions_from_groups(group.get("elements", []))
if not seed and not with_solutions:
print("Removing solutions...")
groups = exam_data.get("groups", [])
remove_solutions_from_groups(groups)
if json_out:
print("Dumping json...")
dump(exam_data, json_out, indent=4, sort_keys=True)
return
print("Rendering exam...")
settings = {
"coursecode": prettify(exam.split("-")[0]),
"description": subtitle,
"examtype": exam_type,
"semester": semester,
}
if seed:
settings["emailaddress"] = sanitize_email(seed)
with render_latex(exam_data, settings) as pdf:
pdf = Pdf.open(BytesIO(pdf))
pdf.save(os.path.join(out, exam + ".pdf"))
pdf.close()
def test_pypdf2_issue_361(private):
with gzip.open(str(private / 'pypdf2_issue_361.pdf.gz'), 'rb') as gz:
with pytest.raises(PdfError, match=r'trailer'):
Pdf.open(gz)
import pandas as pd
import numpy as np
import PyPDF2
import textract
import re
from pikepdf import Pdf
filename ='cba_2020_annual_report.pdf'
pdfFileObj = open(filename,'rb') #open allows you to read the file
pdfReader = PyPDF2.PdfFileReader(pdfFileObj) #The pdfReader variable is a readable object that will be parsed
if pdfReader.isEncrypted:
with Pdf.open(filename,password="******") as pdf:
pdf.save("new"+filename)
filename = "new"+filename
pdfFileObj = open(filename,'rb') #open allows you to read the file
pdfReader = PyPDF2.PdfFileReader(pdfFileObj) #The pdfReader variable is a readable object that will be parsed
#pdfReader.decrypt('')
#num_pages = pdfReader.numPages #discerning the number of pages will allow us to parse through all the pages
num_pages = 58
print(pdfReader.numPages)
count = 55
text = ""
while count < num_pages: #The while loop will read each page
pageObj = pdfReader.getPage(count)
count +=1
text += pageObj.extractText()
#Below if statement exists to check if the above library returned #words. It's done because PyPDF2 cannot read scanned files.
def test_empty(outdir):
target = outdir / 'empty.pdf'
target.touch()
with pytest.raises(PdfError):
Pdf.open(target)
def graph(resources):
# Has XMP and docinfo, all standard format XMP
return Pdf.open(resources / 'graph.pdf')
def test_open_pdf_wrong_password(self, resources):
# The correct passwords are "owner" and "user"
with pytest.raises(PasswordError):
Pdf.open(resources / 'graph-encrypted.pdf', password='******')
def trivial(resources):
# Has no XMP or docinfo
return Pdf.open(resources / 'pal-1bit-trivial.pdf')
def test_open_pdf_no_password_but_needed(self, resources):
with pytest.raises(PasswordError):
Pdf.open(resources / 'graph-encrypted.pdf')
def invalid_creationdate(resources):
# Has nuls in docinfo, old PDF
return Pdf.open(resources / 'invalid_creationdate.pdf')
def test_no_text_stream(self, resources):
with pytest.raises(TypeError):
with (resources / 'pal-1bit-trivial.pdf').open('r') as stream:
Pdf.open(stream)
def test_memory(self, resources):
pdf = (resources / 'pal-1bit-trivial.pdf').read_bytes()
with pytest.raises(Exception):
pdf = Pdf.open(pdf)
def test_attr_access(resources):
pdf = Pdf.open(resources / 'graph.pdf')
assert int(pdf.root.Pages.Count) == 1
def trivial(resources):
return Pdf.open(resources / 'pal-1bit-trivial.pdf')
def test_overwrite_input(resources, outdir):
copy(resources / 'sandwich.pdf', outdir / 'sandwich.pdf')
with Pdf.open(outdir / 'sandwich.pdf') as p:
with pytest.raises(ValueError, match=r'overwrite input file'):
p.save(outdir / 'sandwich.pdf')
def test_non_filename():
with pytest.raises(TypeError):
Pdf.open(42)
def vera(resources):
# Has XMP but no docinfo
return Pdf.open(resources / 'veraPDF test suite 6-2-10-t02-pass-a.pdf')
def test_not_existing_file():
with pytest.raises(FileNotFoundError):
Pdf.open('does_not_exist.pdf')
def test_open_pdf(resources):
pdf = Pdf.open(resources / 'graph.pdf')
page = pdf.pages[0]
Object._parse_stream(page, PrintParser())
def enron1(resources):
# Has nuls in docinfo, old PDF
return Pdf.open(resources / 'enron1_gs.pdf')
