def _format_css_rules(content: list, indent_level: int) -> str:
"""
Helper function for CSS formatting that formats a list of CSS selectors.
INPUTS
content: A list of component values generated by the tinycss2 library
OUTPUTS
A string of formatted CSS
"""
output = ""
for token in tinycss2.parse_rule_list(content):
if token.type == "error":
raise se.InvalidCssException("Couldn’t parse CSS. Exception: {token.message}")
if token.type == "qualified-rule":
output += ("\t" * indent_level) + _format_css_component_list(token.prelude, True).replace("\n", "\n" + ("\t" * indent_level)) + "{\n" + _format_css_declarations(token.content, indent_level + 1) + "\n" + ("\t" * indent_level) + "}\n\n"
if token.type == "at-rule":
output += ("\t" * indent_level) + "@" + token.lower_at_keyword + " " + _format_css_component_list(token.prelude, True).replace("\n", " ") + "{\n" + _format_css_rules(token.content, indent_level + 1) + "\n" + ("\t" * indent_level) + "}\n\n"
if token.type == "comment":
# House style: If the comment starts with /* End, then attach it to the previous block
if token.value.strip().lower().startswith("end"):
output = output.rstrip() + "\n"
output += ("\t" * indent_level) + "/* " + token.value.strip() + " */\n"
if token.value.strip().lower().startswith("end"):
output += "\n"
return output.rstrip()
def _find_rules_selectors(self, rule):
"""
Find all selectors for a given CSS rule
:param rule: rule to find selectors
:return: list of selectors found
"""
selectors = []
# types: QualifiedRule, AtRule, Comment
if rule.type == 'at-rule' and rule.content:
ruleList = tinycss2.parse_rule_list(rule.content)
for r in ruleList:
selectors += self._find_rules_selectors(r)
return selectors
if rule.type == 'qualified-rule':
rule_selectors = rule.serialize().split('{')[0]
selectors += rule_selectors.split(',')
# ignore comments
if rule.type == 'comment':
pass
if rule.type == 'error':
pass
# rules not covered (@todo Cover this rules if they showup in any new css library used)
if rule.type not in ('comment', 'at-rule', 'qualified-rule', 'error',
'whitespace'):
pass
return selectors
def _remove_unused_selectors_from_rule(self, rule, unused):
new_css = ''
# ignore @media queries
if rule.type == 'at-rule' and rule.lower_at_keyword == 'media':
rule_list = tinycss2.parse_rule_list(rule.content)
new_css = ''
for r in rule_list:
# recursion to deal with @media elements
css = self._remove_unused_selectors_from_rule(r, unused)
new_css += css
# reconstruct media CSS if any rule is left inside @media
if new_css:
media_css = '@media'
for node in rule.prelude:
media_css += node.serialize()
# log.debug(node.serialize())
media_css = media_css + '{' + new_css + '}'
return media_css
else:
return ''
# check if there are any used selectors
rule_css = rule.serialize()
selectors = self._get_all_selectors(rule_css)
selectors_left = selectors[:]
for sel in selectors:
if sel in unused:
selectors_left.remove(sel)
# .nav,.sidebar li,.thumbnails{list-style:none}
# remove class: .thumbnails
rule_css = rule_css.replace(',' + sel + '{', '{')
# remove class: .sidebar li or .nav
rule_css = rule_css.replace(sel + ',', '')
# remove class: .nav{
rule_css = rule_css.replace(sel + '{', '{')
# if any selector left... uses the remaining css
if selectors_left:
if self._is_css_valid(rule_css):
new_css += rule_css
else:
logger.error(
'Invalid CSS rule detected after removing unused classes!')
logger.error(rule_css)
exit()
return new_css
def gen_js_style_nodes(self, node_type, styles):
res = []
# Parsing the node
for style in styles:
parsed = tinycss2.parse_rule_list(style.text)
for node in parsed:
if isinstance(node, tinycss2.ast.AtRule
) and node.lower_at_keyword == node_type:
res.append(node)
return res
def validate_at_rule(self, rule):
prelude_errors = self.validate_component_values(rule.prelude)
keyword = strip_vendor_prefix(rule.lower_at_keyword)
if keyword in ("media", "keyframes"):
rules = tinycss2.parse_rule_list(rule.content)
rule_errors = self.validate_rule_list(rules)
elif keyword == "page":
rule_errors = self.validate_qualified_rule(rule)
else:
return ValidationError(rule.source_line, "UNKNOWN_AT_RULE", {"keyword": rule.at_keyword})
return itertools.chain(prelude_errors, rule_errors)
def validate_at_rule(self, rule):
prelude_errors = self.validate_component_values(rule.prelude)
keyword = strip_vendor_prefix(rule.lower_at_keyword)
if keyword in ("media", "keyframes"):
rules = tinycss2.parse_rule_list(rule.content)
rule_errors = self.validate_rule_list(rules)
elif keyword == "page":
rule_errors = self.validate_qualified_rule(rule)
else:
return ValidationError(rule.source_line, "UNKNOWN_AT_RULE",
{"keyword": rule.at_keyword})
return itertools.chain(prelude_errors, rule_errors)
def find_urls_in_css_rules(name, css_rules):
"""
Find the url of the given image name in the given style.
>>> stylesheet = get_embedded_styles(get_html_tree('https://www.apple.com/retail/fifthavenue/'), 'image-hero')[0]
>>> css_rules = tinycss2.parse_stylesheet(stylesheet, skip_comments=True, skip_whitespace=True)
>>> find_urls_in_css_rules('image-hero', css_rules)[1]
'https://www.apple.com/retail/fifthavenue/images/hero_large_2x.jpg'
"""
urls = []
for rule in css_rules:
if rule.type == 'qualified-rule':
url = _get_url_if_contains_token_name(name, rule)
urls.append(_format_url(url)) if url else None
elif rule.type == 'at-rule' and rule.at_keyword == 'media':
nested_rules = tinycss2.parse_rule_list(rule.content,
skip_whitespace=True)
urls.extend(find_urls_in_css_rules(name, nested_rules))
return urls
def extract_inline_style_source(self, style):
"""
Extracts sources for an inline style tag
Parses inline style tags in order to extract sources that are relevant
to the style-src directive.
:param style: style tag to extract the source from
:return: None
"""
parsed = tinycss2.parse_rule_list(style.text)
for node in parsed:
if isinstance(node, tinycss2.ast.AtRule):
print(node, type(node))
if node.lower_at_keyword == 'import':
print('import')
self.find_import_source(node)
if node.lower_at_keyword == 'font-face':
print('font-face')
self.find_fontface_source(node)
def __init__(self, rule, parent_style_sheet=None, parent_rule=None):
"""Constructs a CSSMediaRule object.
Arguments:
rule: A parsed CSS at-rule object.
parent_style_sheet (CSSStyleSheet, optional): The parent CSS style
sheet.
parent_rule (CSSRule, optional): The parent CSS rule.
"""
super().__init__(rule,
CSSRule.MEDIA_RULE,
parent_style_sheet=parent_style_sheet,
parent_rule=parent_rule)
self._media = MediaList()
self._media.media_text = tinycss2.serialize(rule.prelude)
rules = tinycss2.parse_rule_list(rule.content,
skip_comments=True,
skip_whitespace=True)
css_rules = CSSParser.parse_rules(
rules, parent_style_sheet=parent_style_sheet, parent_rule=self)
self.css_rules.extend(css_rules)
def _parse_content(self, content):
nodes = tinycss2.parse_rule_list(content,
skip_comments=True,
skip_whitespace=True)
for node in nodes:
if node.type == 'at-rule':
# tinycss2.parse_one_component_value() returns ParseError
feature_type = node.lower_at_keyword
name = None
feature_values = None
for token in node.content:
if token.type == 'ident':
name = token.value
elif token.type == 'literal' and token.value == ':':
if name is not None:
feature_values = list()
elif token.type == 'number' and token.is_integer:
if feature_values is not None and token.int_value >= 0:
feature_values.append(token.int_value)
elif token.type == 'literal' and token.value == ';':
if (name is not None and feature_values is not None
and len(feature_values) > 0):
if feature_type == 'annotation':
self._annotation[name] = feature_values
elif feature_type == 'character-variant':
self._character_variant[name] = feature_values
elif feature_type == 'ornaments':
self._ornaments[name] = feature_values
elif feature_type == 'styleset':
self._styleset[name] = feature_values
elif feature_type == 'stylistic':
self._stylistic[name] = feature_values
elif feature_type == 'swash':
self._swash[name] = feature_values
name = None
feature_values = None
def preprocess_stylesheet(device_media_type, base_url, stylesheet_rules,
url_fetcher, matcher, page_rules, fonts,
font_config, ignore_imports=False):
"""Do the work that can be done early on stylesheet, before they are
in a document.
"""
for rule in stylesheet_rules:
if getattr(rule, 'content', None) is None and (
rule.type != 'at-rule' or rule.lower_at_keyword != 'import'):
continue
if rule.type == 'qualified-rule':
declarations = list(preprocess_declarations(
base_url, tinycss2.parse_declaration_list(rule.content)))
if declarations:
logger_level = WARNING
try:
selectors = cssselect2.compile_selector_list(rule.prelude)
for selector in selectors:
matcher.add_selector(selector, declarations)
if selector.pseudo_element not in PSEUDO_ELEMENTS:
if selector.pseudo_element.startswith('-'):
logger_level = DEBUG
raise cssselect2.SelectorError(
'ignored prefixed pseudo-element: %s'
% selector.pseudo_element)
else:
raise cssselect2.SelectorError(
'unknown pseudo-element: %s'
% selector.pseudo_element)
ignore_imports = True
except cssselect2.SelectorError as exc:
LOGGER.log(
logger_level,
"Invalid or unsupported selector '%s', %s",
tinycss2.serialize(rule.prelude), exc)
continue
else:
ignore_imports = True
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'import':
if ignore_imports:
LOGGER.warning('@import rule "%s" not at the beginning of the '
'the whole rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude),
rule.source_line, rule.source_column)
continue
tokens = remove_whitespace(rule.prelude)
if tokens and tokens[0].type in ('url', 'string'):
url = tokens[0].value
else:
continue
media = media_queries.parse_media_query(tokens[1:])
if media is None:
LOGGER.warning('Invalid media type "%s" '
'the whole @import rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude),
rule.source_line, rule.source_column)
continue
if not media_queries.evaluate_media_query(
media, device_media_type):
continue
url = url_join(
base_url, url, allow_relative=False,
context='@import at %s:%s',
context_args=(rule.source_line, rule.source_column))
if url is not None:
try:
CSS(
url=url, url_fetcher=url_fetcher,
media_type=device_media_type, font_config=font_config,
matcher=matcher, page_rules=page_rules)
except URLFetchingError as exc:
LOGGER.error(
'Failed to load stylesheet at %s : %s', url, exc)
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'media':
media = media_queries.parse_media_query(rule.prelude)
if media is None:
LOGGER.warning('Invalid media type "%s" '
'the whole @media rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude),
rule.source_line, rule.source_column)
continue
ignore_imports = True
if not media_queries.evaluate_media_query(
media, device_media_type):
continue
content_rules = tinycss2.parse_rule_list(rule.content)
preprocess_stylesheet(
device_media_type, base_url, content_rules, url_fetcher,
matcher, page_rules, fonts, font_config, ignore_imports=True)
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'page':
data = parse_page_selectors(rule)
if data is None:
LOGGER.warning(
'Unsupported @page selector "%s", '
'the whole @page rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude),
rule.source_line, rule.source_column)
continue
ignore_imports = True
for page_type in data:
specificity = page_type.pop('specificity')
page_type = PageType(**page_type)
content = tinycss2.parse_declaration_list(rule.content)
declarations = list(preprocess_declarations(base_url, content))
if declarations:
selector_list = [(specificity, None, page_type)]
page_rules.append((rule, selector_list, declarations))
for margin_rule in content:
if margin_rule.type != 'at-rule' or (
margin_rule.content is None):
continue
declarations = list(preprocess_declarations(
base_url,
tinycss2.parse_declaration_list(margin_rule.content)))
if declarations:
selector_list = [(
specificity, '@' + margin_rule.lower_at_keyword,
page_type)]
page_rules.append(
(margin_rule, selector_list, declarations))
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'font-face':
ignore_imports = True
content = tinycss2.parse_declaration_list(rule.content)
rule_descriptors = dict(preprocess_descriptors(base_url, content))
for key in ('src', 'font_family'):
if key not in rule_descriptors:
LOGGER.warning(
"Missing %s descriptor in '@font-face' rule at %s:%s",
key.replace('_', '-'),
rule.source_line, rule.source_column)
break
else:
if font_config is not None:
font_filename = font_config.add_font_face(
rule_descriptors, url_fetcher)
if font_filename:
fonts.append(font_filename)
def preprocess_stylesheet(device_media_type,
base_url,
stylesheet_rules,
url_fetcher,
matcher,
page_rules,
fonts,
font_config,
counter_style,
ignore_imports=False):
"""Do the work that can be done early on stylesheet, before they are
in a document.
"""
for rule in stylesheet_rules:
if getattr(rule, 'content', None) is None and (
rule.type != 'at-rule' or rule.lower_at_keyword != 'import'):
continue
if rule.type == 'qualified-rule':
declarations = list(
preprocess_declarations(
base_url, tinycss2.parse_declaration_list(rule.content)))
if declarations:
logger_level = WARNING
try:
selectors = cssselect2.compile_selector_list(rule.prelude)
for selector in selectors:
matcher.add_selector(selector, declarations)
if selector.pseudo_element not in PSEUDO_ELEMENTS:
if selector.pseudo_element.startswith('-'):
logger_level = DEBUG
raise cssselect2.SelectorError(
'ignored prefixed pseudo-element: '
f'{selector.pseudo_element}')
else:
raise cssselect2.SelectorError(
'unknown pseudo-element: '
f'{selector.pseudo_element}')
ignore_imports = True
except cssselect2.SelectorError as exc:
LOGGER.log(logger_level,
"Invalid or unsupported selector '%s', %s",
tinycss2.serialize(rule.prelude), exc)
continue
else:
ignore_imports = True
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'import':
if ignore_imports:
LOGGER.warning(
'@import rule %r not at the beginning of the '
'the whole rule was ignored at %d:%d.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
tokens = remove_whitespace(rule.prelude)
url = None
if tokens:
if tokens[0].type == 'string':
url = url_join(base_url,
tokens[0].value,
allow_relative=False,
context='@import at %s:%s',
context_args=(rule.source_line,
rule.source_column))
else:
url_tuple = get_url(tokens[0], base_url)
if url_tuple and url_tuple[1][0] == 'external':
url = url_tuple[1][1]
if url is None:
continue
media = media_queries.parse_media_query(tokens[1:])
if media is None:
LOGGER.warning(
'Invalid media type %r '
'the whole @import rule was ignored at %d:%d.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
if not media_queries.evaluate_media_query(media,
device_media_type):
continue
if url is not None:
try:
CSS(url=url,
url_fetcher=url_fetcher,
media_type=device_media_type,
font_config=font_config,
counter_style=counter_style,
matcher=matcher,
page_rules=page_rules)
except URLFetchingError as exc:
LOGGER.error('Failed to load stylesheet at %s : %s', url,
exc)
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'media':
media = media_queries.parse_media_query(rule.prelude)
if media is None:
LOGGER.warning(
'Invalid media type %r '
'the whole @media rule was ignored at %d:%d.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
ignore_imports = True
if not media_queries.evaluate_media_query(media,
device_media_type):
continue
content_rules = tinycss2.parse_rule_list(rule.content)
preprocess_stylesheet(device_media_type,
base_url,
content_rules,
url_fetcher,
matcher,
page_rules,
fonts,
font_config,
counter_style,
ignore_imports=True)
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'page':
data = parse_page_selectors(rule)
if data is None:
LOGGER.warning(
'Unsupported @page selector %r, '
'the whole @page rule was ignored at %d:%d.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
ignore_imports = True
for page_type in data:
specificity = page_type.pop('specificity')
page_type = PageType(**page_type)
content = tinycss2.parse_declaration_list(rule.content)
declarations = list(preprocess_declarations(base_url, content))
if declarations:
selector_list = [(specificity, None, page_type)]
page_rules.append((rule, selector_list, declarations))
for margin_rule in content:
if margin_rule.type != 'at-rule' or (margin_rule.content is
None):
continue
declarations = list(
preprocess_declarations(
base_url,
tinycss2.parse_declaration_list(
margin_rule.content)))
if declarations:
selector_list = [
(specificity, f'@{margin_rule.lower_at_keyword}',
page_type)
]
page_rules.append(
(margin_rule, selector_list, declarations))
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'font-face':
ignore_imports = True
content = tinycss2.parse_declaration_list(rule.content)
rule_descriptors = dict(
preprocess_descriptors('font-face', base_url, content))
for key in ('src', 'font_family'):
if key not in rule_descriptors:
LOGGER.warning(
"Missing %s descriptor in '@font-face' rule at %d:%d",
key.replace('_', '-'), rule.source_line,
rule.source_column)
break
else:
if font_config is not None:
font_filename = font_config.add_font_face(
rule_descriptors, url_fetcher)
if font_filename:
fonts.append(font_filename)
elif (rule.type == 'at-rule'
and rule.lower_at_keyword == 'counter-style'):
name = counters.parse_counter_style_name(rule.prelude,
counter_style)
if name is None:
LOGGER.warning(
'Invalid counter style name %r, the whole '
'@counter-style rule was ignored at %d:%d.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
ignore_imports = True
content = tinycss2.parse_declaration_list(rule.content)
counter = {
'system': None,
'negative': None,
'prefix': None,
'suffix': None,
'range': None,
'pad': None,
'fallback': None,
'symbols': None,
'additive_symbols': None,
}
rule_descriptors = dict(
preprocess_descriptors('counter-style', base_url, content))
for descriptor_name, descriptor_value in rule_descriptors.items():
counter[descriptor_name] = descriptor_value
if counter['system'] is None:
system = (None, 'symbolic', None)
else:
system = counter['system']
if system[0] is None:
if system[1] in ('cyclic', 'fixed', 'symbolic'):
if len(counter['symbols'] or []) < 1:
LOGGER.warning(
'In counter style %r at %d:%d, '
'counter style %r needs at least one symbol', name,
rule.source_line, rule.source_column, system[1])
continue
elif system[1] in ('alphabetic', 'numeric'):
if len(counter['symbols'] or []) < 2:
LOGGER.warning(
'In counter style %r at %d:%d, '
'counter style %r needs at least two symbols',
name, rule.source_line, rule.source_column,
system[1])
continue
elif system[1] == 'additive':
if len(counter['additive_symbols'] or []) < 2:
LOGGER.warning(
'In counter style %r at %d:%d, '
'counter style "additive" '
'needs at least two additive symbols', name,
rule.source_line, rule.source_column)
continue
counter_style[name] = counter
def test_bad_unicode():
parse_one_declaration('background:\udca9')
parse_rule_list('@\udca9')
def test_serialize_rules():
source = '@import "a.css"; foo#bar.baz { color: red } /**/ @media print{}'
rules = parse_rule_list(source)
assert serialize(rules) == source
def test_rule_list(input):
return parse_rule_list(input, **SKIP)
def preprocess_stylesheet(device_media_type,
base_url,
stylesheet_rules,
url_fetcher,
matcher,
page_rules,
fonts,
font_config,
ignore_imports=False):
"""Do the work that can be done early on stylesheet, before they are
in a document.
"""
for rule in stylesheet_rules:
if getattr(rule, 'content', None) is None and (
rule.type != 'at-rule' or rule.lower_at_keyword != 'import'):
continue
if rule.type == 'qualified-rule':
declarations = list(
preprocess_declarations(
base_url, tinycss2.parse_declaration_list(rule.content)))
if declarations:
logger_level = WARNING
try:
selectors = cssselect2.compile_selector_list(rule.prelude)
for selector in selectors:
matcher.add_selector(selector, declarations)
if selector.pseudo_element not in PSEUDO_ELEMENTS:
if selector.pseudo_element.startswith('-'):
logger_level = DEBUG
raise cssselect2.SelectorError(
'ignored prefixed pseudo-element: %s' %
selector.pseudo_element)
else:
raise cssselect2.SelectorError(
'unknown pseudo-element: %s' %
selector.pseudo_element)
ignore_imports = True
except cssselect2.SelectorError as exc:
LOGGER.log(logger_level,
"Invalid or unsupported selector '%s', %s",
tinycss2.serialize(rule.prelude), exc)
continue
else:
ignore_imports = True
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'import':
if ignore_imports:
LOGGER.warning(
'@import rule "%s" not at the beginning of the '
'the whole rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
tokens = remove_whitespace(rule.prelude)
if tokens and tokens[0].type in ('url', 'string'):
url = tokens[0].value
else:
continue
media = parse_media_query(tokens[1:])
if media is None:
LOGGER.warning(
'Invalid media type "%s" '
'the whole @import rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
if not evaluate_media_query(media, device_media_type):
continue
url = url_join(base_url,
url,
allow_relative=False,
context='@import at %s:%s',
context_args=(rule.source_line, rule.source_column))
if url is not None:
try:
CSS(url=url,
url_fetcher=url_fetcher,
media_type=device_media_type,
font_config=font_config,
matcher=matcher,
page_rules=page_rules)
except URLFetchingError as exc:
LOGGER.error('Failed to load stylesheet at %s : %s', url,
exc)
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'media':
media = parse_media_query(rule.prelude)
if media is None:
LOGGER.warning(
'Invalid media type "%s" '
'the whole @media rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
ignore_imports = True
if not evaluate_media_query(media, device_media_type):
continue
content_rules = tinycss2.parse_rule_list(rule.content)
preprocess_stylesheet(device_media_type,
base_url,
content_rules,
url_fetcher,
matcher,
page_rules,
fonts,
font_config,
ignore_imports=True)
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'page':
data = parse_page_selectors(rule)
if data is None:
LOGGER.warning(
'Unsupported @page selector "%s", '
'the whole @page rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
ignore_imports = True
for page_type in data:
specificity = page_type.pop('specificity')
page_type = PageType(**page_type)
# Use a double lambda to have a closure that holds page_types
match = (lambda page_type: lambda page_names: list(
matching_page_types(page_type, names=page_names))
)(page_type)
content = tinycss2.parse_declaration_list(rule.content)
declarations = list(preprocess_declarations(base_url, content))
if declarations:
selector_list = [(specificity, None, match)]
page_rules.append((rule, selector_list, declarations))
for margin_rule in content:
if margin_rule.type != 'at-rule' or (margin_rule.content is
None):
continue
declarations = list(
preprocess_declarations(
base_url,
tinycss2.parse_declaration_list(
margin_rule.content)))
if declarations:
selector_list = [
(specificity, '@' + margin_rule.lower_at_keyword,
match)
]
page_rules.append(
(margin_rule, selector_list, declarations))
elif rule.type == 'at-rule' and rule.lower_at_keyword == 'font-face':
ignore_imports = True
content = tinycss2.parse_declaration_list(rule.content)
rule_descriptors = dict(preprocess_descriptors(base_url, content))
for key in ('src', 'font_family'):
if key not in rule_descriptors:
LOGGER.warning(
"Missing %s descriptor in '@font-face' rule at %s:%s",
key.replace('_', '-'), rule.source_line,
rule.source_column)
break
else:
if font_config is not None:
font_filename = font_config.add_font_face(
rule_descriptors, url_fetcher)
if font_filename:
fonts.append(font_filename)
def preprocess_stylesheet(device_media_type, base_url, stylesheet_rules,
url_fetcher, rules, fonts, font_config):
"""Do the work that can be done early on stylesheet, before they are
in a document.
"""
selector_to_xpath = cssselect.HTMLTranslator().selector_to_xpath
for rule in stylesheet_rules:
if rule.type == 'qualified-rule':
declarations = list(
preprocess_declarations(
base_url, tinycss2.parse_declaration_list(rule.content)))
if declarations:
selector_string = tinycss2.serialize(rule.prelude)
try:
selector_list = []
for selector in cssselect.parse(selector_string):
xpath = selector_to_xpath(selector)
try:
lxml_xpath = lxml.etree.XPath(xpath)
except ValueError as exc:
# TODO: Some characters are not supported by lxml's
# XPath implementation (including control
# characters), but these characters are valid in
# the CSS2.1 specification.
raise cssselect.SelectorError(str(exc))
selector_list.append(
Selector((0, ) + selector.specificity(),
selector.pseudo_element, lxml_xpath))
for selector in selector_list:
if selector.pseudo_element not in PSEUDO_ELEMENTS:
raise cssselect.ExpressionError(
'Unknown pseudo-element: %s' %
selector.pseudo_element)
except cssselect.SelectorError as exc:
LOGGER.warning("Invalid or unsupported selector '%s', %s",
selector_string, exc)
continue
rules.append((rule, selector_list, declarations))
elif rule.type == 'at-rule' and rule.at_keyword == 'import':
tokens = remove_whitespace(rule.prelude)
if tokens and tokens[0].type in ('url', 'string'):
url = tokens[0].value
else:
continue
media = parse_media_query(tokens[1:])
if media is None:
LOGGER.warning(
'Invalid media type "%s" '
'the whole @import rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
if not evaluate_media_query(media, device_media_type):
continue
url = url_join(base_url,
url,
allow_relative=False,
context='@import at %s:%s',
context_args=(rule.source_line, rule.source_column))
if url is not None:
try:
stylesheet = CSS(url=url,
url_fetcher=url_fetcher,
media_type=device_media_type,
font_config=font_config)
except URLFetchingError as exc:
LOGGER.warning('Failed to load stylesheet at %s : %s', url,
exc)
else:
for result in stylesheet.rules:
rules.append(result)
elif rule.type == 'at-rule' and rule.at_keyword == 'media':
media = parse_media_query(rule.prelude)
if media is None:
LOGGER.warning(
'Invalid media type "%s" '
'the whole @media rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
if not evaluate_media_query(media, device_media_type):
continue
content_rules = tinycss2.parse_rule_list(rule.content)
preprocess_stylesheet(device_media_type, base_url, content_rules,
url_fetcher, rules, fonts, font_config)
elif rule.type == 'at-rule' and rule.at_keyword == 'page':
tokens = remove_whitespace(rule.prelude)
# TODO: support named pages (see CSS3 Paged Media)
if not tokens:
pseudo_class = None
specificity = (0, 0)
elif (len(tokens) == 2 and tokens[0].type == 'literal'
and tokens[0].value == ':' and tokens[1].type == 'ident'):
pseudo_class = tokens[1].lower_value
specificity = {
'first': (1, 0),
'blank': (1, 0),
'left': (0, 1),
'right': (0, 1),
}.get(pseudo_class)
if not specificity:
LOGGER.warning(
'Unknown @page pseudo-class "%s", '
'the whole @page rule was ignored '
'at %s:%s.', pseudo_class, rule.source_line,
rule.source_column)
continue
else:
LOGGER.warning(
'Unsupported @page selector "%s", '
'the whole @page rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
content = tinycss2.parse_declaration_list(rule.content)
declarations = list(preprocess_declarations(base_url, content))
# Use a double lambda to have a closure that holds page_types
match = (lambda page_types: lambda _document: page_types)(
PAGE_PSEUDOCLASS_TARGETS[pseudo_class])
if declarations:
selector_list = [Selector(specificity, None, match)]
rules.append((rule, selector_list, declarations))
for margin_rule in content:
if margin_rule.type != 'at-rule':
continue
declarations = list(
preprocess_declarations(
base_url,
tinycss2.parse_declaration_list(margin_rule.content)))
if declarations:
selector_list = [
Selector(specificity, '@' + margin_rule.at_keyword,
match)
]
rules.append((margin_rule, selector_list, declarations))
elif rule.type == 'at-rule' and rule.at_keyword == 'font-face':
content = tinycss2.parse_declaration_list(rule.content)
rule_descriptors = dict(preprocess_descriptors(base_url, content))
for key in ('src', 'font_family'):
if key not in rule_descriptors:
LOGGER.warning(
"Missing %s descriptor in '@font-face' rule at %s:%s",
key.replace('_', '-'), rule.source_line,
rule.source_column)
break
else:
if font_config is not None:
font_filename = font_config.add_font_face(
rule_descriptors, url_fetcher)
if font_filename:
fonts.append(font_filename)
def preprocess_stylesheet(device_media_type, base_url, stylesheet_rules,
url_fetcher, matcher, page_rules, fonts,
font_config):
"""Do the work that can be done early on stylesheet, before they are
in a document.
"""
for rule in stylesheet_rules:
if rule.type == 'qualified-rule':
declarations = list(
preprocess_declarations(
base_url, tinycss2.parse_declaration_list(rule.content)))
if declarations:
try:
selectors = cssselect2.compile_selector_list(rule.prelude)
for selector in selectors:
matcher.add_selector(selector, declarations)
if selector.pseudo_element not in PSEUDO_ELEMENTS:
raise cssselect2.SelectorError(
'Unknown pseudo-element: %s' %
selector.pseudo_element)
except cssselect2.SelectorError as exc:
LOGGER.warning("Invalid or unsupported selector '%s', %s",
tinycss2.serialize(rule.prelude), exc)
continue
elif rule.type == 'at-rule' and rule.at_keyword == 'import':
tokens = remove_whitespace(rule.prelude)
if tokens and tokens[0].type in ('url', 'string'):
url = tokens[0].value
else:
continue
media = parse_media_query(tokens[1:])
if media is None:
LOGGER.warning(
'Invalid media type "%s" '
'the whole @import rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
if not evaluate_media_query(media, device_media_type):
continue
url = url_join(base_url,
url,
allow_relative=False,
context='@import at %s:%s',
context_args=(rule.source_line, rule.source_column))
if url is not None:
try:
CSS(url=url,
url_fetcher=url_fetcher,
media_type=device_media_type,
font_config=font_config,
matcher=matcher,
page_rules=page_rules)
except URLFetchingError as exc:
LOGGER.error('Failed to load stylesheet at %s : %s', url,
exc)
elif rule.type == 'at-rule' and rule.at_keyword == 'media':
media = parse_media_query(rule.prelude)
if media is None:
LOGGER.warning(
'Invalid media type "%s" '
'the whole @media rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
if not evaluate_media_query(media, device_media_type):
continue
content_rules = tinycss2.parse_rule_list(rule.content)
preprocess_stylesheet(device_media_type, base_url, content_rules,
url_fetcher, matcher, page_rules, fonts,
font_config)
elif rule.type == 'at-rule' and rule.at_keyword == 'page':
tokens = remove_whitespace(rule.prelude)
types = {
'side': None,
'blank': False,
'first': False,
'name': None
}
# TODO: Specificity is probably wrong, should clean and test that.
if not tokens:
specificity = (0, 0, 0)
elif (len(tokens) == 2 and tokens[0].type == 'literal'
and tokens[0].value == ':' and tokens[1].type == 'ident'):
pseudo_class = tokens[1].lower_value
if pseudo_class in ('left', 'right'):
types['side'] = pseudo_class
specificity = (0, 0, 1)
elif pseudo_class in ('blank', 'first'):
types[pseudo_class] = True
specificity = (0, 1, 0)
else:
LOGGER.warning(
'Unknown @page pseudo-class "%s", '
'the whole @page rule was ignored '
'at %s:%s.', pseudo_class, rule.source_line,
rule.source_column)
continue
elif len(tokens) == 1 and tokens[0].type == 'ident':
types['name'] = tokens[0].value
specificity = (1, 0, 0)
else:
LOGGER.warning(
'Unsupported @page selector "%s", '
'the whole @page rule was ignored at %s:%s.',
tinycss2.serialize(rule.prelude), rule.source_line,
rule.source_column)
continue
page_type = PageType(**types)
# Use a double lambda to have a closure that holds page_types
match = (lambda page_type: lambda page_names: list(
matching_page_types(page_type, names=page_names)))(page_type)
content = tinycss2.parse_declaration_list(rule.content)
declarations = list(preprocess_declarations(base_url, content))
if declarations:
selector_list = [(specificity, None, match)]
page_rules.append((rule, selector_list, declarations))
for margin_rule in content:
if margin_rule.type != 'at-rule':
continue
declarations = list(
preprocess_declarations(
base_url,
tinycss2.parse_declaration_list(margin_rule.content)))
if declarations:
selector_list = [(specificity,
'@' + margin_rule.at_keyword, match)]
page_rules.append(
(margin_rule, selector_list, declarations))
elif rule.type == 'at-rule' and rule.at_keyword == 'font-face':
content = tinycss2.parse_declaration_list(rule.content)
rule_descriptors = dict(preprocess_descriptors(base_url, content))
for key in ('src', 'font_family'):
if key not in rule_descriptors:
LOGGER.warning(
"Missing %s descriptor in '@font-face' rule at %s:%s",
key.replace('_', '-'), rule.source_line,
rule.source_column)
break
else:
if font_config is not None:
font_filename = font_config.add_font_face(
rule_descriptors, url_fetcher)
if font_filename:
fonts.append(font_filename)