def test_generate_pdf_and_url_special_chars(self):
"""
Test outputting a PDF with special characters.
One unicode character is tested.
Also, the Javascript escape character for multi-line strings (due to us using it in document.write(`{}`))
"""
from chromepdf import generate_pdf, generate_pdf_url # top-level, not via chromepdf.shortcuts
html = 'Unicode Char: \u0394 Javascript escape character: ` Some quotes: "\''
# generate_pdf
pdfbytes = generate_pdf(html)
self.assertIsInstance(pdfbytes, bytes)
self.assertEqual(1, extractText(pdfbytes).count(html))
# generate_pdf_url
extracted_text = ''
try:
tempfile = createTempFile(html)
tempfile_uri = pathlib.Path(tempfile.name).as_uri()
pdfbytes = generate_pdf_url(tempfile_uri)
extracted_text = extractText(pdfbytes).strip()
finally:
os.remove(tempfile.name)
self.assertEqual(1, extracted_text.count(html))
def test_generate_pdf_chrome_path_success(self):
from chromepdf import generate_pdf # top-level, not via chromepdf.shortcuts
html = 'One Word'
pdfbytes = generate_pdf(html, chrome_path=findChromePath())
self.assertIsInstance(pdfbytes, bytes)
self.assertEqual(1, extractText(pdfbytes).count(html))
def test_generate_pdf_maker_with_pdf_kwargs(self):
"""Test outputting a PDF using a ChromePdfMaker object, and passing pdf_kwargs."""
html = 'One Word'
pdfmaker = ChromePdfMaker()
pdfbytes = pdfmaker.generate_pdf(html, clean_pdf_kwargs())
self.assertIsInstance(pdfbytes, bytes)
self.assertEqual(1, extractText(pdfbytes).count(html))
def test_generate_pdf(self):
"""Test outputting a PDF using the generate_pdf() shortcut function."""
from chromepdf import generate_pdf # top-level, not via chromepdf.shortcuts
html = 'One Word'
pdfbytes = generate_pdf(html)
self.assertIsInstance(pdfbytes, bytes)
self.assertEqual(1, extractText(pdfbytes).count(html))
def test_generate_pdf_chromedriver_path_success(self):
from chromepdf import generate_pdf # top-level, not via chromepdf.shortcuts
chromedriver_path = download_chromedriver_version(
get_chrome_version(findChromePath()))
html = 'One Word'
pdfbytes = generate_pdf(html, chromedriver_path=chromedriver_path)
self.assertIsInstance(pdfbytes, bytes)
self.assertEqual(1, extractText(pdfbytes).count(html))
def test_generate_pdf_huge_pdfs(self):
"""Test outputting PDFs when the HTML is 1 MB."""
from chromepdf import generate_pdf # top-level, not via chromepdf.shortcuts
html = '123456789 ' * ((1000 * 1000) // 10) # 10 bytes * 1 MB = 1 MB
# generate_pdf
pdfbytes = generate_pdf(html)
self.assertIsInstance(pdfbytes, bytes)
extracted_text = extractText(pdfbytes).strip()
self.assertEqual(1000 * 100, extracted_text.count('123456789'))
def test_generate_pdf_url_huge_pdfs(self):
from chromepdf import generate_pdf_url # top-level, not via chromepdf.shortcuts
html = '123456789 ' * ((1000 * 1000) // 10) # 10 bytes * 1 MB = 1 MB
# generate_pdf_url
try:
with tempfile.NamedTemporaryFile(delete=False) as temp:
temp.write(html.encode('utf8')) # 10* 100*1000 = 1 MB
tempfile_uri = pathlib.Path(temp.name).as_uri()
pdfbytes = generate_pdf_url(tempfile_uri)
extracted_text = extractText(pdfbytes).strip()
self.assertEqual(1000 * 100, extracted_text.count('123456789'))
finally:
os.remove(temp.name)
def test_generate_pdf_url(self):
"""Test outputting a PDF using the generate_pdf_url() shortcut function."""
from chromepdf import generate_pdf_url # top-level, not via chromepdf.shortcuts
html = "This is a test"
extracted_text = ''
try:
tempfile = createTempFile(html)
tempfile_uri = pathlib.Path(tempfile.name).as_uri()
pdfbytes = generate_pdf_url(tempfile_uri)
self.assertIsInstance(pdfbytes, bytes)
extracted_text = extractText(pdfbytes)
finally:
os.remove(tempfile.name)
self.assertEqual(1, extracted_text.count(html))
