def test_add_named_destination():
reader = PdfReader(os.path.join(RESOURCE_ROOT, "pdflatex-outline.pdf"))
writer = PdfWriter()
for page in reader.pages:
writer.add_page(page)
from PyPDF2.generic import NameObject
writer.add_named_destination(NameObject("A named dest"), 2)
writer.add_named_destination(NameObject("A named dest2"), 2)
from PyPDF2.generic import IndirectObject
assert writer.get_named_dest_root() == [
"A named dest",
IndirectObject(7, 0, writer),
"A named dest2",
IndirectObject(10, 0, writer),
]
# write "output" to PyPDF2-output.pdf
tmp_filename = "dont_commit_named_destination.pdf"
with open(tmp_filename, "wb") as output_stream:
writer.write(output_stream)
# Cleanup
os.remove(tmp_filename)
def test_encrypt(use_128bit):
reader = PdfReader(os.path.join(RESOURCE_ROOT, "form.pdf"))
writer = PdfWriter()
page = reader.pages[0]
orig_text = page.extract_text()
writer.add_page(page)
writer.encrypt(user_pwd="userpwd",
owner_pwd="ownerpwd",
use_128bit=use_128bit)
# write "output" to PyPDF2-output.pdf
tmp_filename = "dont_commit_encrypted.pdf"
with open(tmp_filename, "wb") as output_stream:
writer.write(output_stream)
with open(tmp_filename, "rb") as input_stream:
data = input_stream.read()
assert b"foo" not in data
reader = PdfReader(tmp_filename, password="******")
new_text = reader.pages[0].extract_text()
assert reader.metadata.get("/Producer") == "PyPDF2"
assert new_text == orig_text
# Cleanup
os.remove(tmp_filename)
def test_write_metadata():
pdf_path = os.path.join(RESOURCE_ROOT, "crazyones.pdf")
reader = PdfReader(pdf_path)
writer = PdfWriter()
for page in reader.pages:
writer.add_page(page)
metadata = reader.metadata
writer.add_metadata(metadata)
writer.add_metadata({"/Title": "The Crazy Ones"})
# finally, write data to PyPDF2-output.pdf
tmp_filename = "dont_commit_writer_added_metadata.pdf"
with open(tmp_filename, "wb") as output_stream:
writer.write(output_stream)
# Check if the title was set
reader = PdfReader(tmp_filename)
metadata = reader.metadata
assert metadata.get("/Title") == "The Crazy Ones"
# Cleanup
os.remove(tmp_filename)
def test_regression_issue670():
filepath = os.path.join(RESOURCE_ROOT, "crazyones.pdf")
reader = PdfReader(filepath, strict=False)
for _ in range(2):
writer = PdfWriter()
writer.add_page(reader.pages[0])
with open("dont_commit_issue670.pdf", "wb") as f_pdf:
writer.write(f_pdf)
def test_pdf_header():
writer = PdfWriter()
assert writer.pdf_header == b"%PDF-1.3"
reader = PdfReader(os.path.join(RESOURCE_ROOT, "crazyones.pdf"))
writer.add_page(reader.pages[0])
assert writer.pdf_header == b"%PDF-1.5"
writer.pdf_header = b"%PDF-1.6"
assert writer.pdf_header == b"%PDF-1.6"
def test_remove_child_in_tree():
pdf = os.path.join(RESOURCE_ROOT, "form.pdf")
tree = TreeObject()
reader = PdfReader(pdf)
writer = PdfWriter()
writer.add_page(reader.pages[0])
writer.add_bookmark("foo", pagenum=0)
obj = writer._objects[-1]
tree.add_child(obj, writer)
tree.remove_child(obj)
tree.add_child(obj, writer)
tree.empty_tree()
def test_fill_form():
reader = PdfReader(os.path.join(RESOURCE_ROOT, "form.pdf"))
writer = PdfWriter()
page = reader.pages[0]
writer.add_page(page)
writer.update_page_form_field_values(writer.pages[0],
{"foo": "some filled in text"},
flags=1)
# write "output" to PyPDF2-output.pdf
tmp_filename = "dont_commit_filled_pdf.pdf"
with open(tmp_filename, "wb") as output_stream:
writer.write(output_stream)
def test_add_bookmark():
reader = PdfReader(os.path.join(RESOURCE_ROOT, "pdflatex-outline.pdf"))
writer = PdfWriter()
for page in reader.pages:
writer.add_page(page)
bookmark = writer.add_bookmark("A bookmark", 1, None, (255, 0, 15), True,
True, "/Fit", 200, 0, None)
writer.add_bookmark("Another", 2, bookmark, None, False, False, "/Fit", 0,
0, None)
# write "output" to PyPDF2-output.pdf
tmp_filename = "dont_commit_bookmark.pdf"
with open(tmp_filename, "wb") as output_stream:
writer.write(output_stream)
# Cleanup
os.remove(tmp_filename)
def test_add_link():
reader = PdfReader(os.path.join(RESOURCE_ROOT, "pdflatex-outline.pdf"))
writer = PdfWriter()
for page in reader.pages:
writer.add_page(page)
from PyPDF2.generic import RectangleObject
writer.add_link(
1,
2,
RectangleObject([0, 0, 100, 100]),
border=[1, 2, 3, [4]],
fit="/Fit",
)
writer.add_link(2, 3, RectangleObject([20, 30, 50, 80]), [1, 2, 3],
"/FitH", None)
writer.add_link(
3,
0,
"[ 200 300 250 350 ]",
[0, 0, 0],
"/XYZ",
0,
0,
2,
)
writer.add_link(
3,
0,
[100, 200, 150, 250],
border=[0, 0, 0],
)
# write "output" to PyPDF2-output.pdf
tmp_filename = "dont_commit_link.pdf"
with open(tmp_filename, "wb") as output_stream:
writer.write(output_stream)
# Cleanup
os.remove(tmp_filename)
def test_overlay(base_path, overlay_path):
if base_path.startswith("http"):
base_path = BytesIO(get_pdf_from_url(base_path,
name="tika-935981.pdf"))
else:
base_path = os.path.join(PROJECT_ROOT, base_path)
reader = PdfReader(base_path)
writer = PdfWriter()
reader_overlay = PdfReader(os.path.join(PROJECT_ROOT, overlay_path))
overlay = reader_overlay.pages[0]
for page in reader.pages:
page.merge_page(overlay)
writer.add_page(page)
with open("dont_commit_overlay.pdf", "wb") as fp:
writer.write(fp)
# Cleanup
os.remove("dont_commit_overlay.pdf")
def test_add_uri():
reader = PdfReader(os.path.join(RESOURCE_ROOT, "pdflatex-outline.pdf"))
writer = PdfWriter()
for page in reader.pages:
writer.add_page(page)
from PyPDF2.generic import RectangleObject
writer.add_uri(
1,
"http://www.example.com",
RectangleObject([0, 0, 100, 100]),
border=[1, 2, 3, [4]],
)
writer.add_uri(
2,
"https://pypdf2.readthedocs.io/en/latest/",
RectangleObject([20, 30, 50, 80]),
border=[1, 2, 3],
)
writer.add_uri(
3,
"https://pypdf2.readthedocs.io/en/latest/user/adding-pdf-annotations.html",
"[ 200 300 250 350 ]",
border=[0, 0, 0],
)
writer.add_uri(
3,
"https://pypdf2.readthedocs.io/en/latest/user/adding-pdf-annotations.html",
[100, 200, 150, 250],
border=[0, 0, 0],
)
# write "output" to PyPDF2-output.pdf
tmp_filename = "dont_commit_uri.pdf"
with open(tmp_filename, "wb") as output_stream:
writer.write(output_stream)
# Cleanup
os.remove(tmp_filename)
def test_basic_features():
pdf_path = os.path.join(RESOURCE_ROOT, "crazyones.pdf")
reader = PdfReader(pdf_path)
writer = PdfWriter()
assert len(reader.pages) == 1
# add page 1 from input1 to output document, unchanged
writer.add_page(reader.pages[0])
# add page 2 from input1, but rotated clockwise 90 degrees
writer.add_page(reader.pages[0].rotate(90))
# add page 3 from input1, but first add a watermark from another PDF:
page3 = reader.pages[0]
watermark_pdf = pdf_path
watermark = PdfReader(watermark_pdf)
page3.merge_page(watermark.pages[0])
writer.add_page(page3)
# add page 4 from input1, but crop it to half size:
page4 = reader.pages[0]
page4.mediabox.upper_right = (
page4.mediabox.right / 2,
page4.mediabox.top / 2,
)
writer.add_page(page4)
# add some Javascript to launch the print window on opening this PDF.
# the password dialog may prevent the print dialog from being shown,
# comment the the encription lines, if that's the case, to try this out
writer.add_js("this.print({bUI:true,bSilent:false,bShrinkToFit:true});")
# encrypt your new PDF and add a password
password = "******"
writer.encrypt(password)
# finally, write "output" to PyPDF2-output.pdf
tmp_path = "PyPDF2-output.pdf"
with open(tmp_path, "wb") as output_stream:
writer.write(output_stream)
# cleanup
os.remove(tmp_path)