def capture(self, url):
"""
Capture all stylesheets at given URL's HTML document.
Any HTTPError is raised to caller.
url
to capture CSS from
Returns ``cssutils.stylesheets.StyleSheetList``.
"""
self._log.info('\nCapturing CSS from URL:\n %s\n', url)
self._nonparsed = {}
self.stylesheetlist = cssutils.stylesheets.StyleSheetList()
# used to save inline styles
scheme, loc, path, query, fragment = urllib.parse.urlsplit(url)
self._filename = os.path.basename(path)
# get url content
url, res = self._doRequest(url)
if not res:
sys.exit(1)
rawdoc = res.read()
self.docencoding = encutils.getEncodingInfo(
res, rawdoc, log=self._log).encoding
self._log.info('\nUsing Encoding: %s\n', self.docencoding)
doctext = rawdoc.decode(self.docencoding)
# fill list of stylesheets and list of raw css
self._findStyleSheets(url, doctext)
return self.stylesheetlist
def capture(self, url):
"""
Capture all stylesheets at given URL's HTML document.
Any HTTPError is raised to caller.
url
to capture CSS from
Returns ``cssutils.stylesheets.StyleSheetList``.
"""
self._log.info('\nCapturing CSS from URL:\n %s\n', url)
self._nonparsed = {}
self.stylesheetlist = cssutils.stylesheets.StyleSheetList()
# used to save inline styles
scheme, loc, path, query, fragment = urllib.parse.urlsplit(url)
self._filename = os.path.basename(path)
# get url content
url, res = self._doRequest(url)
if not res:
sys.exit(1)
rawdoc = res.read()
self.docencoding = encutils.getEncodingInfo(
res, rawdoc, log=self._log).encoding
self._log.info('\nUsing Encoding: %s\n', self.docencoding)
doctext = rawdoc.decode(self.docencoding)
# fill list of stylesheets and list of raw css
self._findStyleSheets(url, doctext)
return self.stylesheetlist
def test_getEncodingInfo(self):
"encutils.getEncodingInfo"
# (expectedencoding, expectedmismatch): (httpheader, filecontent)
tests = [
# --- application/xhtml+xml ---
# header default and XML default
(('utf-8', False), (
'''Content-Type: application/xhtml+xml''',
'''<?xml version="1.0" ?>
<example>
<meta http-equiv="Content-Type"
content="application/xhtml+xml"/>
</example>''')),
# XML default
(('utf-8', False), (
None,
'''<?xml version="1.0" ?>
<example>
<meta http-equiv="Content-Type"
content="application/xhtml+xml"/>
</example>''')),
# meta is ignored!
(('utf-8', False), (
'''Content-Type: application/xhtml+xml''',
'''<?xml version="1.0" ?>
<example>
<meta http-equiv="Content-Type"
content="application/xhtml+xml;charset=iso_M"/>
</example>''')),
# header enc and XML default
(('iso-h', True), (
'''Content-Type: application/xhtml+xml;charset=iso-H''',
'''<?xml version="1.0" ?>
<example>
<meta http-equiv="Content-Type"
content="application/xhtml+xml"/>
</example>''')),
# mismatch header and XML explicit, header wins
(('iso-h', True), (
'''Content-Type: application/xhtml+xml;charset=iso-H''',
'''<?xml version="1.0" encoding="iso-X" ?>
<example/>''')),
# header == XML, meta ignored!
(('iso-h', False), (
'''Content-Type: application/xhtml+xml;charset=iso-H''',
'''<?xml version="1.0" encoding="iso-h" ?>
<example>
<meta http-equiv="Content-Type"
content="application/xhtml+xml;charset=iso_M"/>
</example>''')),
# XML only, meta ignored!
(('iso-x', False), (
'''Content-Type: application/xhtml+xml''',
'''<?xml version="1.0" encoding="iso-X" ?>
<example>
<meta http-equiv="Content-Type"
content="application/xhtml+xml;charset=iso_M"/>
</example>''')),
# no text or not enough text:
(('iso-h', False), ('Content-Type: application/xml;charset=iso-h',
'1')),
(('utf-8', False), ('Content-Type: application/xml',
None)),
((None, False), ('Content-Type: application/xml',
'1')),
# --- text/xml ---
# default enc
(('ascii', False), (
'''Content-Type: text/xml''',
'''<?xml version="1.0" ?>
<example>
<meta http-equiv="Content-Type"
content="text/xml"/>
</example>''')),
# default as XML ignored and meta completely ignored
(('ascii', False), (
'''Content-Type: text/xml''',
'''<?xml version="1.0" encoding="iso-X" ?>
<example>
<meta http-equiv="Content-Type"
content="text/xml;charset=iso_M"/>
</example>''')),
(('ascii', False), ('Content-Type: text/xml',
'1')),
(('ascii', False), ('Content-Type: text/xml',
None)),
# header enc
(('iso-h', False), (
'''Content-Type: text/xml;charset=iso-H''',
'''<?xml version="1.0" ?>
<example>
<meta http-equiv="Content-Type"
content="text/xml"/>
</example>''')),
# header only, XML and meta ignored!
(('iso-h', False), (
'''Content-Type: text/xml;charset=iso-H''',
'''<?xml version="1.0" encoding="iso-X" ?>
<example/>''')),
(('iso-h', False), (
'''Content-Type: text/xml;charset=iso-H''',
'''<?xml version="1.0" encoding="iso-h" ?>
<example>
<meta http-equiv="Content-Type"
content="text/xml;charset=iso_M"/>
</example>''')),
# --- text/html ---
# default enc
(('iso-8859-1', False), ('Content-Type: text/html;',
'''<meta http-equiv="Content-Type"
content="text/html">''')),
(('iso-8859-1', False), ('Content-Type: text/html;',
None)),
# header enc
(('iso-h', False), ('Content-Type: text/html;charset=iso-H',
'''<meta http-equiv="Content-Type"
content="text/html">''')),
# meta enc
(('iso-m', False), ('Content-Type: text/html',
'''<meta http-equiv="Content-Type"
content="text/html;charset=iso-m">''')),
# mismatch header and meta, header wins
(('iso-h', True), ('Content-Type: text/html;charset=iso-H',
'''<meta http-equiv="Content-Type"
content="text/html;charset=iso-m">''')),
# no header:
((None, False), (None,
'''<meta http-equiv="Content-Type"
content="text/html;charset=iso-m">''')),
# no encoding at all
((None, False), (None,
'''<meta http-equiv="Content-Type"
content="text/html">''')),
((None, False), (None,
'''text''')),
# --- no header ---
((None, False), (None, '')),
(('iso-8859-1', False), ('''NoContentType''',
'''OnlyText''')),
(('iso-8859-1', False), ('Content-Type: text/html;',
None)),
(('iso-8859-1', False), ('Content-Type: text/html;',
'1')),
# XML
(('utf-8', False), (None,
'''<?xml version=''')),
(('iso-x', False), (None,
'''<?xml version="1.0" encoding="iso-X"?>''')),
# meta ignored
(('utf-8', False), (None,
'''<?xml version="1.0" ?>
<html><meta http-equiv="Content-Type"
content="text/html;charset=iso-m"></html>''')),
(('utf-8', False), ('Content-Type: text/css;',
'1')),
(('iso-h', False), ('Content-Type: text/css;charset=iso-h',
'1')),
# only header is used by encutils
(('utf-8', False), ('Content-Type: text/css',
'@charset "ascii";')),
]
for exp, test in tests:
header, text = test
if header:
res = encutils.getEncodingInfo(self._fakeRes(header), text)
else:
res = encutils.getEncodingInfo(text=text)
res = (res.encoding, res.mismatch)
self.assertEqual(exp, res)
