def get_violation_definitions(cls):
return {
'empty.anchors': {
'title':
_('Empty anchor(s) found'),
'description':
_('Empty anchors are not good for Search Engines. '
'Empty anchors were found for links to: %s.'),
'value_parser':
cls.get_empty_anchors_parsed_value,
'category':
_('SEO'),
'generic_description':
_('By using empty anchor text won\'t prevent search '
'engines from indexing your pages but you will lose a '
'good opportunity to add relevance to your pages. '
'Google uses anchor text in order to qualify the '
'resources you create a reference to. '
'In consequences if a page got links with "example" '
'as anchor text pointing to itself, this page '
'relevance on "example" request will increase. '
'So better do not let empty anchor text and choose '
'wisely the words (or keywords) you use in it.')
}
}
def get_fact_definitions(cls):
return {
'page.title': {
'title': _('Page Title'),
'description': lambda value: value,
'category': _('SEO'),
}
}
def get_fact_definitions(cls):
return {
'page.last_modified': {
'title': _('Last-Modified'),
'description': lambda value: value,
'category': _('HTTP'),
'unit': 'datetime'
}
}
def get_violation_definitions(cls):
return {
'invalid.url_word_separator': {
'title': _('URLs should use hyphens to separate words'),
'description': cls.get_url_with_underscore_message(),
'category': _('SEO'),
'generic_description': cls.get_url_with_underscore_message()
}
}
def get_fact_definitions(cls):
return {
'robots.url': {
'title': _('Robots file URL'),
'description': lambda value: value,
'category': _('SEO'),
'unit': 'link',
}
}
def get_fact_definitions(cls):
return {
'robots.url': {
'title': _('Robots file URL'),
'description': lambda value: value,
'category': _('SEO'),
'unit': 'link',
}
}
def get_fact_definitions(cls):
return {
'page.google_analytics': {
'title': _('Google Analytics'),
'description': lambda value: list(value),
'unit': 'google-analytics',
'category': _('SEO'),
}
}
def get_violation_definitions(cls):
return {
'invalid.url_word_separator': {
'title': _('URLs should use hyphens to separate words'),
'description': cls.get_url_with_underscore_message(),
'category': _('SEO'),
'generic_description': cls.get_url_with_underscore_message()
}
}
def get_fact_definitions(cls):
return {
'page.google_analytics': {
'title': _('Google Analytics'),
'description': lambda value: list(value),
'unit': 'google-analytics',
'category': _('SEO'),
}
}
def get_fact_definitions(cls):
return {
'page.last_modified': {
'title': _('Last-Modified'),
'description': lambda value: value,
'category': _('HTTP'),
'unit': 'datetime'
}
}
def get_fact_definitions(cls):
return {
'meta.tags': {
'title': _('Meta Tags'),
'description': lambda value: value,
'unit': 'values',
'category': _('Meta'),
}
}
def get_fact_definitions(cls):
return {
'meta.tags': {
'title': _('Meta Tags'),
'description': lambda value: value,
'unit': 'values',
'category': _('Meta'),
}
}
def get_fact_definitions(cls):
return {
"page.heading_hierarchy": {
"title": _("Heading Hierarchy"),
"description": lambda value: list(value),
"unit": "heading-hierarchy",
"category": _("SEO"),
}
}
def get_fact_definitions(cls):
return {
'page.heading_hierarchy': {
'title': _('Heading Hierarchy'),
'description': lambda value: list(value),
'unit': 'heading-hierarchy',
'category': _('SEO'),
},
}
def get_violation_definitions(cls):
return {
'page.body.not_found': {
'title': _('Page body not found'),
'description': _('Body was not found on %s.'),
'category': _('Semantics'),
'generic_description': _(
'The <body> tag defines the documents body\'s, it\'s contains '
'all the content of an HTML document. The ausence of a this tag '
'represents a no content and sematically invalid webpage.'
),
}
}
def get_violation_definitions(cls):
return {
'absent.metatags.open_graph': {
'title': _('Open Graph tags not found'),
'description': _('Some tags are missing: %(tags)s'),
'value_parser': cls.get_open_graph_parsed_value,
'category': _('SEO'),
'generic_description': _(
'Validates the absent of Open Graph metatags. '
'They allow the Facebook Crawler to generate '
'previews when your content is shared on Facebook.'
)
},
}
def get_violation_definitions(cls):
return {
'absent.meta.tags': {
'title': _('Required Meta Tags were not found'),
'description': _("Meta tags for %s were not found."),
'value_parser': lambda value: ', '.join(value),
'category': _('HTTP'),
'generic_description': _(
'Validates the absent of user defined MetaTags. '
'This values are configurable by Holmes Configuration.'
),
'unit': 'list'
}
}
def get_violation_definitions(cls):
return {
'link.redirect.302': {
'title': _('Link with 302 redirect'),
'description': _(
'Link with 302 redirect, in most cases, should '
'not be used. Redirects were found for '
'link: %s.'),
'category': _('HTTP'),
'generic_description': _(
'Validates temporary redirections (302). '
'They should not be used in the most cases, instead '
'is best to use a 301 permanent redirect.'
)
},
'link.redirect.307': {
'title': _('Link with 307 redirect'),
'description': _(
'Link with 307 redirect, in most cases, should '
'not be used. Redirects were found for '
'link: %s.'),
'category': _('HTTP'),
'generic_description': _(
'Validates temporary redirections (307). '
'They should not be used in the most cases, instead '
'is best to use a 301 permanent redirect.'
)
},
}
def get_fact_definitions(cls):
return {
'page.css': {
'title': _('CSS'),
'description': lambda value: list(value),
'unit': 'css',
'category': _('Static'),
},
'total.requests.css': {
'title': _('Total CSS requests'),
'description': lambda value: '%d' % value,
'category': _('HTTP'),
'unit': 'number'
},
'total.size.css': {
'title': _('Total CSS size'),
'description': lambda value: '%d' % value,
'unit': 'kb',
'category': _('SEO'),
},
'total.size.css.gzipped': {
'title': _('Total CSS size gzipped'),
'description': lambda value: '%d' % value,
'unit': 'kb',
'category': _('SEO'),
}
}
def get_violation_definitions(cls):
return {
'invalid.images.alt': {
'title': _('Image(s) without alt attribute'),
'description': _(
'Images without alt text are not good for '
'Search Engines. Images without alt were '
'found for: %(images)s.'),
'value_parser': cls.get_without_alt_parsed_value,
'category': _('SEO'),
'generic_description': _(
'Images without alt attribute are not good for '
'search engines. They are searchable by the content '
'of this attribute, so if it\'s empty, it cause bad '
'indexing optimization.'
)
},
'invalid.images.alt_too_big': {
'title': _('Image(s) with alt attribute too big'),
'description': _(
'Images with alt text bigger than %(max_size)d chars are '
'not good for search engines. Images with a too big alt '
'were found for: %(images)s.'),
'value_parser': cls.get_alt_too_big_parsed_value,
'category': _('SEO'),
'generic_description': _(
'Images with alt text too long are not good to SEO. '
'This maximum value are configurable '
'by Holmes configuration.'
),
'unit': 'number'
}
}
def get_fact_definitions(cls):
return {
'page.links': {
'title': _('Links to'),
'description': lambda value: list(value),
'unit': 'links',
'category': _('SEO'),
},
'total.number.links': {
'title': _('Link count'),
'description': lambda value: value,
'category': _('HTTP'),
'unit': 'number'
},
'total.number.invalid_links': {
'title': _('Total invalid links'),
'description': lambda value: value,
'category': _('Semantics'),
'unit': 'number'
},
'page.invalid_links': {
'title': _('Invalid Links'),
'description': lambda value: list(value),
'unit': 'invalid-links',
'category': _('Semantics'),
}
}
def get_violation_definitions(cls):
return {
'link.broken': {
'title': _('Broken link(s) found'),
'description': _(
'This page contains broken links to %(links)s '
'(the urls failed to load or timed-out after 10 seconds). '
'This can lead your site to lose rating with '
'search engines and is misleading to users.'),
'value_parser': cls.get_links_parsed_value,
'category': _('HTTP'),
'generic_description': _(
'Validates hyperlinks with a invalid resource. '
'The pointed resource can be a Client or a '
'Server Error, they can be timeout load or, '
'in most cases, means a not founded page.'
)
},
'link.moved.temporarily': {
'title': _('Moved Temporarily'),
'description': _(
'A link from your page to "%(links)s" is using a 302 or '
'307 redirect. It passes 0%% of link juice (ranking '
'power) and, in most cases, should not be used. Use '
'301 instead.'),
'value_parser': cls.get_links_parsed_value,
'category': _('HTTP'),
'generic_description': _(
'Validates links that uses a 302 or 307 redirect. '
'In this cases, it passes 0% of link juice (ranking '
'power) and, in most cases, should not be used. Use of '
'301 is recommended.'
)
}
}
def get_violation_definitions(cls):
return {
'absent.metatags': {
'title': _('Meta tags not present'),
'description': _(
'No meta tags found on this page. This is damaging for '
'Search Engines.'
),
'category': _('HTTP'),
'generic_description': _(
'Validates the presence of metatags. They are important '
'to inform metadata about the HTML document. '
'The absent of metatags are damaging for search '
'engines. Meta elements are typically used to specify '
'page description, keywords, author of the document, last '
'modified, and other metadata.'
)
},
'page.metatags.description_too_big': {
'title': _('Maximum size of description meta tag'),
'description': _(
'The meta description tag is longer than %(max_size)s '
'characters. It is best to keep meta descriptions '
'shorter for better indexing on search engines.'
),
'category': _('SEO'),
'generic_description': _(
'Validates the size of a description metatag. It is best '
'to keep meta descriptions shorter for better indexing on '
'search engines. This limit is configurable by Holmes '
'Configuration.'
),
'unit': 'number'
}
}
def get_violation_definitions(cls):
return {
'total.requests.css': {
'title': _('Too many CSS requests'),
'description': _(
'This page has %(total_css_files)d CSS request '
'(%(over_limit)d over limit). Having too many '
'requests impose a tax in the browser due to handshakes.'),
'category': _('Performance'),
'generic_description': _(
'Pages with too many CSS requests aren\'t good to '
'performance. Overflowing this limit of requests can '
'impose a tax in the browser due to handshakes. This '
'limit of requests per page is configurable.'
),
'unit': 'number'
},
'total.size.css': {
'title': _('CSS size in kb is too big'),
'description': _(
'There\'s %.2fkb of CSS in this page and that '
'adds up to more download time slowing down the '
'page rendering to the user.'),
'category': _('Performance'),
'generic_description': _(
'Pages with too big CSS files aren\'t good to performance. '
'Having this limit of file sizes overflow adds up to more '
'download time slowing down the page rendering to the user. '
'This limit of requests per page is configurable.'
),
'unit': 'number'
},
}
def get_violation_definitions(cls):
return {
'total.requests.js': {
'title': _('Too many JavaScript requests'),
'description': _(
'This page has %(total_js_files)d JavaScript request '
'(%(over_limit)d over limit). Having too many requests '
'impose a tax in the browser due to handshakes.'),
'category': _('Performance'),
'generic_description': _(
'A site with too many JavaScript requests per page can '
'deacrease the page load speed and performance. This '
'limits are configurable in Holmes configuration.'
),
'unit': 'number'
},
'total.size.js': {
'title': _('JavaScript size in kb is too big'),
'description': _(
'There\'s %.2fkb of JavaScript in this page and '
'that adds up to more download time slowing down '
'the page rendering to the user.'),
'category': _('Performance'),
'generic_description': _(
'A site with a too big total JavaScript size per page can '
'decrease the page load speed and performance. This '
'limits are configurable in Holmes configuration.'
),
'unit': 'number'
}
}
def get_violation_definitions(cls):
return {
'total.requests.js': {
'title':
_('Too many JavaScript requests'),
'description':
_('This page has %(total_js_files)d JavaScript request '
'(%(over_limit)d over limit). Having too many requests '
'impose a tax in the browser due to handshakes.'),
'category':
_('Performance'),
'generic_description':
_('A site with too many JavaScript requests per page can '
'deacrease the page load speed and performance. This '
'limits are configurable in Holmes configuration.'),
'unit':
'number'
},
'total.size.js': {
'title':
_('JavaScript size in kb is too big'),
'description':
_('There\'s %.2fkb of JavaScript in this page and '
'that adds up to more download time slowing down '
'the page rendering to the user.'),
'category':
_('Performance'),
'generic_description':
_('A site with a too big total JavaScript size per page can '
'decrease the page load speed and performance. This '
'limits are configurable in Holmes configuration.'),
'unit':
'number'
}
}
def get_fact_definitions(cls):
return {
'page.css': {
'title': _('CSS'),
'description': lambda value: list(value),
'unit': 'css',
'category': _('Static'),
},
'total.requests.css': {
'title': _('Total CSS requests'),
'description': lambda value: '%d' % value,
'category': _('HTTP'),
'unit': 'number'
},
'total.size.css': {
'title': _('Total CSS size'),
'description': lambda value: '%d' % value,
'unit': 'kb',
'category': _('SEO'),
},
'total.size.css.gzipped': {
'title': _('Total CSS size gzipped'),
'description': lambda value: '%d' % value,
'unit': 'kb',
'category': _('SEO'),
}
}
def get_violation_definitions(cls):
return {
'link.redirect.302': {
'title':
_('Link with 302 redirect'),
'description':
_('Link with 302 redirect, in most cases, should '
'not be used. Redirects were found for '
'link: %s.'),
'category':
_('HTTP'),
'generic_description':
_('Validates temporary redirections (302). '
'They should not be used in the most cases, instead '
'is best to use a 301 permanent redirect.')
},
'link.redirect.307': {
'title':
_('Link with 307 redirect'),
'description':
_('Link with 307 redirect, in most cases, should '
'not be used. Redirects were found for '
'link: %s.'),
'category':
_('HTTP'),
'generic_description':
_('Validates temporary redirections (307). '
'They should not be used in the most cases, instead '
'is best to use a 301 permanent redirect.')
},
}
def get_fact_definitions(cls):
return {
"page.js": {
"title": _("JS"),
"description": lambda value: list(value),
"unit": "js",
"category": _("Static"),
},
"total.requests.js": {
"title": _("Total JS requests"),
"description": lambda value: value,
"category": _("HTTP"),
"unit": "number",
},
"total.size.js": {
"title": _("Total JS size"),
"description": lambda value: "%d" % value,
"unit": "kb",
"category": _("SEO"),
},
"total.size.js.gzipped": {
"title": _("Total JS size gzipped"),
"description": lambda value: "%d" % value,
"unit": "kb",
"category": _("SEO"),
},
}
def get_fact_definitions(cls):
return {
'page.links': {
'title': _('Links to'),
'description': lambda value: list(value),
'unit': 'links',
'category': _('SEO'),
},
'total.number.links': {
'title': _('Link count'),
'description': lambda value: value,
'category': _('HTTP'),
'unit': 'number'
},
'total.number.invalid_links': {
'title': _('Total invalid links'),
'description': lambda value: value,
'category': _('Semantics'),
'unit': 'number'
},
'page.invalid_links': {
'title': _('Invalid Links'),
'description': lambda value: list(value),
'unit': 'invalid-links',
'category': _('Semantics'),
}
}
def get_violation_definitions(cls):
return {
'blacklist.domains': {
'title': _('Domain Blacklist'),
'description': _('Some links are blacklisted: %s'),
'value_parser': cls.get_blacklist_parsed_value,
'category': _('SEO'),
'generic_description': _(
'Detected domain blacklisted hyperlinks. '
'Links with this violation are those that have anchors '
'to websites added in Holmes\'s Black List configuration.'
),
'unit': 'list'
}
}
def get_violation_definitions(cls):
return {
'presence.meta.robots.noindex': {
'title': _('Meta Robots with value of noindex'),
'description': cls.META_ROBOTS_NO_INDEX,
'category': _('SEO'),
'generic_description': cls.META_ROBOTS_NO_INDEX
},
'presence.meta.robots.nofollow': {
'title': _('Meta Robots with value of nofollow'),
'description': cls.META_ROBOTS_NO_FOLLOW,
'category': _('SEO'),
'generic_description': cls.META_ROBOTS_NO_FOLLOW
}
}
def get_violation_definitions(cls):
return {
'presence.meta.robots.noindex': {
'title': _('Meta Robots with value of noindex'),
'description': cls.META_ROBOTS_NO_INDEX,
'category': _('SEO'),
'generic_description': cls.META_ROBOTS_NO_INDEX
},
'presence.meta.robots.nofollow': {
'title': _('Meta Robots with value of nofollow'),
'description': cls.META_ROBOTS_NO_FOLLOW,
'category': _('SEO'),
'generic_description': cls.META_ROBOTS_NO_FOLLOW
}
}
def get_violation_definitions(cls):
return {
'page.body.not_found': {
'title':
_('Page body not found'),
'description':
_('Body was not found on %s.'),
'category':
_('Semantics'),
'generic_description':
_('The <body> tag defines the documents body\'s, it\'s contains '
'all the content of an HTML document. The ausence of a this tag '
'represents a no content and sematically invalid webpage.'),
}
}
def get_violation_definitions(cls):
return {
'page.last_modified.not_found': {
'title': _('Last-Modified not found'),
'description': _('Last-Modified was not found on %s.'),
'category': _('HTTP'),
'generic_description': _(
'The Last-Modified Header information allows Web Crawlers '
'(like Holmes) and search engines to know if the page is '
'modified since the last content retrival. If '
'Last-Modified wasn\'t present, all requests made by '
'this engines on the page will proccess all the content '
'and can be performatically bad to the server.'
)
}
}
def get_url_with_underscore_message(cls):
return _('Google treats a hyphen as a word separator, but does '
'not treat an underscore that way. Google treats and '
'underscore as a word joiner, so red_sneakers is the '
'same as redsneakers to Google. This has been confirmed '
'directly by Google themselves, including the fact that '
'using dashes over underscores will have a (minor) '
'ranking benefit.')
def get_url_with_underscore_message(cls):
return _('Google treats a hyphen as a word separator, but does '
'not treat an underscore that way. Google treats and '
'underscore as a word joiner, so red_sneakers is the '
'same as redsneakers to Google. This has been confirmed '
'directly by Google themselves, including the fact that '
'using dashes over underscores will have a (minor) '
'ranking benefit.')
def validate(self):
css_files = self.get_css_requests()
js_files = self.get_js_requests()
img_files = self.get_img_requests()
self.add_fact(key='total.requests',
value=len(css_files) + len(js_files) + len(img_files),
title=_('Total requests'))
def get_violation_definitions(cls):
return {
'invalid.links.nofollow': {
'title': _('Links with rel="nofollow"'),
'description': _(
'Links with rel="nofollow" to the same '
'domain as the page make it harder for search '
'engines to crawl the website. Links with '
'rel="nofollow" were found for hrefs (%(links)s).'),
'value_parser': cls.get_links_nofollow_parsed_value,
'category': _('SEO'),
'generic_description': _(
'Validates links with rel="nofollow", this whos links to '
'the same domain as the page make it harder for search '
'engines to crawl the website.'
)
}
}
def get_violation_definitions(cls):
return {
'absent.meta.tags': {
'title':
_('Required Meta Tags were not found'),
'description':
_("Meta tags for %s were not found."),
'value_parser':
lambda value: ', '.join(value),
'category':
_('HTTP'),
'generic_description':
_('Validates the absent of user defined MetaTags. '
'This values are configurable by Holmes Configuration.'),
'unit':
'list'
}
}
def get_violation_definitions(cls):
return {
'page.last_modified.not_found': {
'title':
_('Last-Modified not found'),
'description':
_('Last-Modified was not found on %s.'),
'category':
_('HTTP'),
'generic_description':
_('The Last-Modified Header information allows Web Crawlers '
'(like Holmes) and search engines to know if the page is '
'modified since the last content retrival. If '
'Last-Modified wasn\'t present, all requests made by '
'this engines on the page will proccess all the content '
'and can be performatically bad to the server.')
}
}
def get_violation_definitions(cls):
return {
'blacklist.domains': {
'title':
_('Domain Blacklist'),
'description':
_('Some links are blacklisted: %s'),
'value_parser':
cls.get_blacklist_parsed_value,
'category':
_('SEO'),
'generic_description':
_('Detected domain blacklisted hyperlinks. '
'Links with this violation are those that have anchors '
'to websites added in Holmes\'s Black List configuration.'),
'unit':
'list'
}
}
def validate(self):
css_files = self.get_css_requests()
js_files = self.get_js_requests()
img_files = self.get_img_requests()
self.add_fact(
key='total.requests',
value=len(css_files) + len(js_files) + len(img_files),
title=_('Total requests')
)
def get_violation_definitions(cls):
return {
'page.heading_hierarchy.size': {
'title': _('Maximum size of a heading hierarchy'),
'description': _(
'Heading hierarchy values bigger than %(max_size)s '
'characters aren\'t good for Search Engines. This '
'elements were found: '
'<ul class="violation-hh-list">%(hh_list)s</ul>'),
'value_parser': cls.get_violation_parsed_value,
'category': _('SEO'),
'generic_description': _(
'Heading hierarchy tags with values too big aren\'t good '
'for search engines. The definition of this maximum size '
'can be configurable on Holmes.'
),
'unit': 'number'
}
}
class MetaRobotsValidator(Validator):
META_ROBOTS_NO_INDEX = _('A meta tag with the robots="noindex" '
'attribute tells the search engines that '
'they should not index this page.')
META_ROBOTS_NO_FOLLOW = _('A meta tag with the robots="nofollow" '
'attribute tells the search engines that they '
'should not follow any links in this page.')
@classmethod
def get_violation_definitions(cls):
return {
'presence.meta.robots.noindex': {
'title': _('Meta Robots with value of noindex'),
'description': cls.META_ROBOTS_NO_INDEX,
'category': _('SEO'),
'generic_description': cls.META_ROBOTS_NO_INDEX
},
'presence.meta.robots.nofollow': {
'title': _('Meta Robots with value of nofollow'),
'description': cls.META_ROBOTS_NO_FOLLOW,
'category': _('SEO'),
'generic_description': cls.META_ROBOTS_NO_FOLLOW
}
}
def validate(self):
tags = self.get_meta_tags()
for tag in tags:
if tag['key'] == 'robots' and tag['content'] == 'noindex':
self.add_violation(key='presence.meta.robots.noindex',
value=None,
points=80)
if tag['key'] == 'robots' and tag['content'] == 'nofollow':
self.add_violation(key='presence.meta.robots.nofollow',
value=None,
points=50)
def get_meta_tags(self):
return self.review.data.get('meta.tags', None)
def get_violation_definitions(cls):
return {
'page.heading_hierarchy.h1_not_found': {
'title':
_('H1 Headings not found'),
'description':
_('Your page does not contain any H1 headings. H1 headings '
'help indicate the important topics of your page to '
'search engines. While less important than good '
'meta-titles and descriptions, H1 headings may still '
'help define the topic of your page to search engines.'),
'category':
'SEO',
'generic_description':
('H1 headings help indicate the important topics of your '
'page to search engines. While less important than good '
'meta-titles and descriptions, H1 headings may still '
'help define the topic of your page to search engines.')
}
}
def get_violation_definitions(cls):
return {
'invalid.links.nofollow': {
'title':
_('Links with rel="nofollow"'),
'description':
_('Links with rel="nofollow" to the same '
'domain as the page make it harder for search '
'engines to crawl the website. Links with '
'rel="nofollow" were found for hrefs (%(links)s).'),
'value_parser':
cls.get_links_nofollow_parsed_value,
'category':
_('SEO'),
'generic_description':
_('Validates links with rel="nofollow", this whos links to '
'the same domain as the page make it harder for search '
'engines to crawl the website.')
}
}
def get_violation_definitions(cls):
return {
'page.heading_hierarchy.h1_not_found': {
'title': _('H1 Headings not found'),
'description': _(
'Your page does not contain any H1 headings. H1 headings '
'help indicate the important topics of your page to '
'search engines. While less important than good '
'meta-titles and descriptions, H1 headings may still '
'help define the topic of your page to search engines.'
),
'category': 'SEO',
'generic_description': (
'H1 headings help indicate the important topics of your '
'page to search engines. While less important than good '
'meta-titles and descriptions, H1 headings may still '
'help define the topic of your page to search engines.'
)
}
}
def get_violation_definitions(cls):
return {
'absent.meta.canonical': {
'title': _('Link with rel="canonical" not found'),
'description': _(
'As can be seen in this page '
'<a href="https://support.google.com/webmasters/answer/'
'139394?hl=en">About rel="canonical"</a>, it\'s a good '
'practice to include rel="canonical" urls in the pages '
'for your website.'
),
'category': _('SEO'),
'generic_description': _(
'Validates the absent of link with rel="canonical" on '
'the head of a page. This indicates the preferred URL '
'to use to access the green dress post, so that the '
'search results will be more likely to show users '
'that URL structure.'
),
'unit': 'boolean'
}
}
def get_violation_definitions(cls):
return {
'empty.anchors': {
'title': _('Empty anchor(s) found'),
'description': _(
'Empty anchors are not good for Search Engines. '
'Empty anchors were found for links to: %s.'),
'value_parser': cls.get_empty_anchors_parsed_value,
'category': _('SEO'),
'generic_description': _(
'By using empty anchor text won\'t prevent search '
'engines from indexing your pages but you will lose a '
'good opportunity to add relevance to your pages. '
'Google uses anchor text in order to qualify the '
'resources you create a reference to. '
'In consequences if a page got links with "example" '
'as anchor text pointing to itself, this page '
'relevance on "example" request will increase. '
'So better do not let empty anchor text and choose '
'wisely the words (or keywords) you use in it.')
}
}
def get_violation_definitions(cls):
return {
'page.heading_hierarchy.size': {
'title':
_('Maximum size of a heading hierarchy'),
'description':
_('Heading hierarchy values bigger than %(max_size)s '
'characters aren\'t good for Search Engines. This '
'elements were found: '
'<ul class="violation-hh-list">%(hh_list)s</ul>'),
'value_parser':
cls.get_violation_parsed_value,
'category':
_('SEO'),
'generic_description':
_('Heading hierarchy tags with values too big aren\'t good '
'for search engines. The definition of this maximum size '
'can be configurable on Holmes.'),
'unit':
'number'
}
}
def get_violation_definitions(cls):
return {
'absent.meta.canonical': {
'title':
_('Link with rel="canonical" not found'),
'description':
_('As can be seen in this page '
'<a href="https://support.google.com/webmasters/answer/'
'139394?hl=en">About rel="canonical"</a>, it\'s a good '
'practice to include rel="canonical" urls in the pages '
'for your website.'),
'category':
_('SEO'),
'generic_description':
_('Validates the absent of link with rel="canonical" on '
'the head of a page. This indicates the preferred URL '
'to use to access the green dress post, so that the '
'search results will be more likely to show users '
'that URL structure.'),
'unit':
'boolean'
}
}
def get_violation_definitions(cls):
return {
'page.canonicalization.different_endpoints': {
'title': _('Canonical URLs have different endpoints'),
'description': _(
'This page have the canonical url`s "%(no_www_url)s" and '
'"%(www_url)s" with different endpoints. This both url`s '
'should point to the same location. '
'Not fixing this may cause search engines to be unsure as '
'to which URL is the correct one to index.'
),
'category': _('SEO'),
'generic_description': _(
'Canonical URLs is a couple of URLs with and without '
'the \'www\' prefix. For example: site.com and www.site.com '
'are canonical URLs. This violation is about a root page with '
'your canonical URLs pointing to different endpoints. This '
'behavior is down ranked in Search Engines indexing.'
)
},
'page.canonicalization.no_301_redirect': {
'title': _('Canonical URLs have a non 301 redirect'),
'description': _(
'This Canonical url "%(effective_url)s" is redirecting to '
'"%(location)s" with a different than 301 status code: '
'%(status_code)s. This may cause search engines to be '
'unsure to where the URL is being redirected.'),
'value_parser': cls.get_no_301_parsed_value,
'category': _('SEO'),
'generic_description': _(
'Canonical URLs is a couple of URLs with and without '
'the \'www\' prefix. For example: site.com and www.site.com '
'are canonical URLs. Canonical URLs should point to the '
'same points. This violation is about a redirection of one '
'of this URLs maked by a non 301 redirection. Redirections '
'different than a 301 type may cause search engines to be '
'unsure to where the URL is being redirected.'
)
}
}
def get_violation_definitions(cls):
return {
'invalid.images.alt': {
'title':
_('Image(s) without alt attribute'),
'description':
_('Images without alt text are not good for '
'Search Engines. Images without alt were '
'found for: %(images)s.'),
'value_parser':
cls.get_without_alt_parsed_value,
'category':
_('SEO'),
'generic_description':
_('Images without alt attribute are not good for '
'search engines. They are searchable by the content '
'of this attribute, so if it\'s empty, it cause bad '
'indexing optimization.')
},
'invalid.images.alt_too_big': {
'title':
_('Image(s) with alt attribute too big'),
'description':
_('Images with alt text bigger than %(max_size)d chars are '
'not good for search engines. Images with a too big alt '
'were found for: %(images)s.'),
'value_parser':
cls.get_alt_too_big_parsed_value,
'category':
_('SEO'),
'generic_description':
_('Images with alt text too long are not good to SEO. '
'This maximum value are configurable '
'by Holmes configuration.'),
'unit':
'number'
}
}
def get_fact_definitions(cls):
return {
'total.sitemap.indexes': {
'title': _('Total SiteMap indexes'),
'category': _('SEO'),
'unit': 'number'
},
'total.sitemap.urls': {
'title': _('Total SiteMap urls'),
'category': _('SEO'),
'unit': 'number'
},
'total.size.sitemap': {
'title': _('Total SiteMap size'),
'unit': 'kb',
'category': _('SEO'),
},
'total.size.sitemap.gzipped': {
'title': _('Total SiteMap gzipped size'),
'unit': 'kb',
'category': _('SEO'),
}
}