def test_read_empty():
with pytest.raises(PdfReadError) as exc:
PdfReader(io.BytesIO())
assert exc.value.args[0] == "Cannot read an empty file"
def test_get_page_number(src, page_nb):
src = os.path.join(RESOURCE_ROOT, src)
reader = PdfReader(src)
page = reader.pages[page_nb]
assert reader.get_page_number(page) == page_nb
def test_get_page_mode(src, expected):
src = os.path.join(RESOURCE_ROOT, src)
reader = PdfReader(src)
assert reader.page_mode == expected
def test_get_outlines(src, outline_elements):
reader = PdfReader(src)
outlines = reader._get_outlines()
assert len(outlines) == outline_elements
def test_get_num_pages(src, num_pages):
src = os.path.join(RESOURCE_ROOT, src)
reader = PdfReader(src)
assert len(reader.pages) == num_pages
def test_extract_text(url, name):
data = BytesIO(get_pdf_from_url(url, name=name))
reader = PdfReader(data)
reader.metadata
def test_rotate(degree):
with open(os.path.join(RESOURCE_ROOT, "crazyones.pdf"), "rb") as inputfile:
reader = PdfReader(inputfile)
page = reader.pages[0]
page.rotate(degree)
def test_get_metadata(url, name):
data = BytesIO(get_pdf_from_url(url, name=name))
reader = PdfReader(data)
reader.metadata
def render_to_pdf(html, filename, xml_filename, env={}):
"Render html file to pdf using the given filename and environment. Embed xml data if available"
debug = settings.DEBUG
debug = False
if debug:
return HttpResponse(html)
fd_html, filename_html = tempfile.mkstemp()
fd_pdf, filename_pdf = tempfile.mkstemp(suffix=".pdf")
_, filename_pdf2 = tempfile.mkstemp(suffix=".pdf")
os.close(fd_pdf)
try:
with open(fd_html, 'wb') as f:
f.write(html.encode('utf8'))
path = os.path.join(os.path.dirname(__file__), '..', 'webkit',
'webkit2pdf')
try:
if not debug:
env['DISPLAY'] = ':1'
# Fake empty SSL Confif file to be able to run phantomjs in Buster
env['OPENSSL_CONF'] = os.path.abspath(
os.path.join(os.path.dirname(__file__), '..', 'webkit',
'openssl.cnf'))
except KeyError:
pass
env.update(dict(os.environ)) # keep OS env vars, such as PATH
cmd = [
path, "-f", filename_html, "-o", filename_pdf, "--mediaroot",
settings.MEDIA_ROOT, "--staticroot", settings.STATIC_ROOT,
"--scriptname", settings.FORCE_SCRIPT_NAME or ''
]
proc = subprocess.Popen(cmd, env=env)
while True:
proc.poll()
if proc.returncode is not None:
break
except Exception as error:
print(error)
finally:
os.remove(filename_html)
if xml_filename:
with open(filename_pdf, 'rb') as pdf:
reader = PdfReader(pdf, strict=False)
writer = PdfWriter()
writer.appendPagesFromReader(reader)
with open(xml_filename, "rb") as xml:
writer.addAttachment("certificado.xml", xml.read())
with open(filename_pdf2, "wb") as out:
writer.write(out)
out.close()
pdf.close()
with open(filename_pdf2, 'rb') as pdf:
response = HttpResponse(pdf.read(), content_type='application/pdf')
response[
'Content-Disposition'] = 'attachment;filename=%s' % filename
pdf.close()
os.remove(filename_pdf)
os.remove(filename_pdf2)
return response
else:
with open(filename_pdf, 'rb') as pdf:
response = HttpResponse(pdf.read(), content_type='application/pdf')
response[
'Content-Disposition'] = 'attachment;filename=%s' % filename
pdf.close()
os.remove(filename_pdf)
os.remove(filename_pdf2)
return response
def text_extraction(pdf_path):
reader = PdfReader(pdf_path)
text = ""
for page in reader.pages:
text += page.extract_text()
return text
from PyPDF2 import PdfFileReader as PdfReader, PdfFileWriter as PdfWriter
pdf_obj = open('Ch13/meetingminutes.pdf', 'rb')
pdf_reader = PdfReader(pdf_obj)
print(pdf_reader.numPages) # Output: 19
page_obj = pdf_reader.getPage(0)
print(page_obj.extractText())
def convert_pdf_to_jpeg(path: str,
max_pages: str,
password: str,
horizontal: bool = False):
"""
Converts a PDF file into a jpeg image
:param path: file's path
:param max_pages: max pages to render,
:param password: PDF password
:param horizontal: if True, will combine the pages horizontally
:return: A list of stream of combined images
"""
demisto.debug(f'Loading file at Path: {path}')
input_pdf = PdfReader(open(path, "rb"), strict=False)
pages = len(input_pdf.pages) if max_pages == "*" else min(
int(max_pages), len(input_pdf.pages))
with tempfile.TemporaryDirectory() as output_folder:
demisto.debug('Converting PDF')
convert_from_path(pdf_path=path,
fmt='jpeg',
first_page=1,
last_page=pages,
output_folder=output_folder,
userpw=password,
output_file='converted_pdf_')
demisto.debug('Converting PDF - COMPLETED')
demisto.debug('Combining all pages')
images = []
for page in sorted(os.listdir(output_folder)):
if os.path.isfile(os.path.join(output_folder,
page)) and 'converted_pdf_' in page:
images.append(Image.open(os.path.join(output_folder, page)))
min_shape = min([(np.sum(page_.size), page_.size)
for page_ in images])[1] # get the minimal width
# Divide the list of images into separate lists with constant length (20),
# due to the limitation of images in jpeg format (max size ~65,000 pixels).
# Create a list of lists (length == 20) of images to combine each list (20 images) to one image
images_matrix = [
images[i:i + PAGES_LIMITATION]
for i in range(0, len(images), PAGES_LIMITATION)
]
outputs = []
for images_list in images_matrix:
if horizontal:
imgs_comb = np.hstack([
np.asarray(image.resize(min_shape))
for image in images_list
])
else:
imgs_comb = np.vstack([
np.asarray(image.resize(min_shape))
for image in images_list
])
imgs_comb = Image.fromarray(imgs_comb)
output = BytesIO()
imgs_comb.save(output, 'JPEG') # type: ignore
demisto.debug('Combining all pages - COMPLETED')
outputs.append(output.getvalue())
return outputs
