def test_xhtml_converter(self):
url_table = URLTable()
image_filename = os.path.join(self.temp_dir.name, 'image.png')
tubes_filename = os.path.join(self.temp_dir.name, 'tubes.html')
ferret_filename = os.path.join(self.temp_dir.name, 'ferret.jpg')
url_table.add_many([
AddURLInfo('http://example.com/styles.css', None, None),
AddURLInfo('http://example.com/image.png', None, None),
AddURLInfo('http://example.com/cat.jpg', None, None),
AddURLInfo('http://example.com/fox.jpg', None, None),
AddURLInfo('http://example.com/ferret.jpg', None, None),
AddURLInfo('http://example.com/tubes.html', None, None),
])
url_table.update_one('http://example.com/styles.css',
status=Status.done.value,
link_type='css')
url_table.update_one('http://example.com/image.png',
status=Status.done.value,
filename=os.path.relpath(image_filename,
self.temp_dir.name))
url_table.update_one('http://example.com/tubes.html',
status=Status.done.value,
filename=os.path.relpath(tubes_filename,
self.temp_dir.name))
url_table.update_one('http://example.com/ferret.jpg',
status=Status.done.value,
filename=os.path.relpath(ferret_filename,
self.temp_dir.name))
html_filename = os.path.join(self.temp_dir.name, 'index.html')
new_html_filename = os.path.join(self.temp_dir.name, 'index.html-new')
with open(html_filename, 'w') as out_file:
out_file.write(XHTML_TEXT)
for filename in [image_filename, tubes_filename, ferret_filename]:
with open(filename, 'wb'):
pass
element_walker = ElementWalker(css_scraper=CSSScraper())
converter = HTMLConverter(self.get_html_parser(), element_walker,
url_table)
converter.convert(html_filename,
new_html_filename,
base_url='http://example.com/index.html')
with open(new_html_filename, 'r') as in_file:
converted_text = in_file.read()
self.assertIn("url('image.png')", converted_text)
self.assertIn("url('http://example.com/cat.jpg')", converted_text)
self.assertIn('"tubes.html"', converted_text)
self.assertIn('"http://example.com/lol.html"', converted_text)
self.assertIn("url('http://example.com/fox.jpg')", converted_text)
self.assertIn("url('ferret.jpg')", converted_text)
self.assertIn("hello world!!", converted_text)
self.assertIn("<hr/>", converted_text)
def test_html_converter(self):
with TemporaryDirectory() as temp_dir:
path_namer = PathNamer(temp_dir)
url_table = URLTable()
url_table.add([
'http://example.com/styles.css',
'http://example.com/image.png',
'http://example.com/cat.jpg',
'http://example.com/fox.jpg',
'http://example.com/ferret.jpg',
'http://example.com/tubes.html',
])
url_table.update('http://example.com/styles.css',
status=Status.done,
link_type='css')
url_table.update(
'http://example.com/image.png',
status=Status.done,
)
url_table.update(
'http://example.com/tubes.html',
status=Status.done,
)
url_table.update(
'http://example.com/ferret.jpg',
status=Status.done,
)
html_filename = os.path.join(temp_dir, 'index.html')
new_html_filename = os.path.join(temp_dir, 'index.html-new')
with open(html_filename, 'w') as out_file:
out_file.write(HTML_TEXT)
converter = HTMLConverter(path_namer, url_table)
converter.convert(html_filename,
new_html_filename,
base_url='http://example.com/index.html')
with open(new_html_filename, 'r') as in_file:
converted_text = in_file.read()
self.assertIn("url('image.png')", converted_text)
self.assertIn("url('http://example.com/cat.jpg')", converted_text)
self.assertIn('"tubes.html"', converted_text)
self.assertIn('"http://example.com/lol.html"', converted_text)
self.assertIn("url('http://example.com/fox.jpg')", converted_text)
self.assertIn("url('ferret.jpg')", converted_text)
