Transition words in content (#37)

* Transitionword check * Fix styling * Transition word check including Dutch translations * Fix styling * Update README * Use filterXpath so filtering with CSS select is not needed * wip * Fix styling * Remove unnecessary url param * Use readability to get the amount of phrases * Update README * wip * Fix styling * Improving splitting text in phrases * Fix styling * wip --------- Co-authored-by: Baspa <[email protected]>
vormkracht10 · Aug 17, 2023 · 57abf96 · 57abf96
1 parent f334e0f
commit 57abf96
Show file tree

Hide file tree

Showing 9 changed files with 501 additions and 56 deletions.
diff --git a/README.md b/README.md
@@ -13,7 +13,7 @@
 
 ## Introduction
 
-This package is your guidance to get a better SEO score on search engines. Laravel SEO Scanner scans your code and crawls the routes from your app. The package has 22 checks that will check on performance, configurations, use of meta tags and content quality.
+This package is your guidance to get a better SEO score on search engines. Laravel SEO Scanner scans your code and crawls the routes from your app. The package has 23 checks that will check on performance, configurations, use of meta tags and content quality.
 
 Easily configure which routes to scan, exclude or include specific checks or even add your own checks! Completing checks will further improve the SEO score and thus increase the chance of ranking higher at the search engines.
 
@@ -255,6 +255,9 @@ These checks are available in the package. You can add or remove checks in the c
 ✅ The page contains no broken links. <br>
 ✅ The page contains no broken images. <br>
 ✅ Length of the content is at least 2100 characters. <br>
+✅ A minimum of 30% of the sentences contain a transition word or phrase. <br>
+
+> Note: To change the locale of the transition words, you can publish the config file and change the locale in the config file. The default locale is `null` which uses the language of your `app` config. If set to `nl` or `en`, the transition words will be in Dutch or English. If you want to add more locales, you can create a pull request.
 
 ### Meta
 

diff --git a/config/seo.php b/config/seo.php
@@ -1,6 +1,18 @@
 <?php
 
 return [
+
+ /*
+ |--------------------------------------------------------------------------
+ | Default options
+ |--------------------------------------------------------------------------
+ |
+ | The following array lists the default options for the application.
+ |
+ */
+ // en, nl or null (which will use the app locale)
+ 'language' => null,
+
  /*
  |--------------------------------------------------------------------------
  | Cache

diff --git a/resources/lang/en.json b/resources/lang/en.json
@@ -30,5 +30,88 @@
  "failed.performance.javascript_size": "The page contains Javascript files that are too large (max :expectedValue). These files were found: :actualValue.",
  "failed.performance.response": "The page returned a response code other than :expectedValue. The actual response code was :actualValue.",
  "failed.performance.ttfb": "The page took too long to load (max :expectedValuems). The actual time was :actualValuems.",
- "failed.performance.ttfb.missing_url": "We could not get the TTFB for this page."
-}
+ "failed.performance.ttfb.missing_url": "We could not get the TTFB for this page.",
+ "failed.content.transition_words_ratio_check.too_few_transition_words": "The page contains too few transition words. The recommended minimum is 30%, while the actual number is :actualValue%.",
+ "failed.content.transition_words_ratio_check.no_phrases_found": "The page does not contain any transition words.",
+ "additionally": "additionally",
+ "moreover": "moreover",
+ "furthermore": "furthermore",
+ "in addition": "in addition",
+ "not only": "not only",
+ "but also": "but also",
+ "as well as": "as well as",
+ "besides": "besides",
+ "what's more": "what's more",
+ "however": "however",
+ "nevertheless": "nevertheless",
+ "on the other hand": "on the other hand",
+ "in contrast": "in contrast",
+ "conversely": "conversely",
+ "although": "although",
+ "while": "while",
+ "yet": "yet",
+ "even though": "even though",
+ "nonetheless": "nonetheless",
+ "similarly": "similarly",
+ "likewise": "likewise",
+ "in comparison": "in comparison",
+ "just as": "just as",
+ "compared to": "compared to",
+ "similarly to": "similarly to",
+ "therefore": "therefore",
+ "thus": "thus",
+ "consequently": "consequently",
+ "as a result": "as a result",
+ "because": "because",
+ "since": "since",
+ "so": "so",
+ "due to": "due to",
+ "owing to": "owing to",
+ "accordingly": "accordingly",
+ "indeed": "indeed",
+ "certainly": "certainly",
+ "of course": "of course",
+ "undoubtedly": "undoubtedly",
+ "without a doubt": "without a doubt",
+ "naturally": "naturally",
+ "for example": "for example",
+ "for instance": "for instance",
+ "such as": "such as",
+ "to illustrate": "to illustrate",
+ "in particular": "in particular",
+ "first": "first",
+ "second": "second",
+ "third": "third",
+ "next": "next",
+ "then": "then",
+ "afterward": "afterward",
+ "finally": "finally",
+ "in the meantime": "in the meantime",
+ "subsequently": "subsequently",
+ "in conclusion": "in conclusion",
+ "to sum up": "to sum up",
+ "ultimately": "ultimately",
+ "in summary": "in summary",
+ "all in all": "all in all",
+ "overall": "overall",
+ "meanwhile": "meanwhile",
+ "before": "before",
+ "after": "after",
+ "during": "during",
+ "until": "until",
+ "eventually": "eventually",
+ "soon": "soon",
+ "in the past": "in the past",
+ "in the future": "in the future",
+ "in other words": "in other words",
+ "that is to say": "that is to say",
+ "specifically": "specifically",
+ "to clarify": "to clarify",
+ "in this case": "in this case",
+ "an example of this is": "an example of this is",
+ "to demonstrate": "to demonstrate",
+ "admittedly": "admittedly",
+ "granted": "granted",
+ "while it is true": "while it is true"
+}
+
diff --git a/resources/lang/nl.json b/resources/lang/nl.json
@@ -1,31 +1,114 @@
 {
- "failed.configuration.nofollow.meta": "The page contains a nofollow meta tag, while it should not.",
- "failed.configuration.nofollow.tag": "The page contains a nofollow tag, while it should not.",
- "failed.configuration.noindex.meta": "The page contains a noindex meta tag, while it should not.",
- "failed.configuration.noindex.tag": "The page contains a noindex tag, while it should not.",
- "failed.configuration.robots.disallowed": "The robots.txt file for this page contains a disallow rule for this page.",
- "failed.configuration.robots.missing_url": "We could not get the robots.txt file for this page.",
- "failed.content.alt_tag": "The page contains images without or empty alt tags. These images were found: :actualValue.",
- "failed.content.broken_images": "The page contains broken images. These images were found: :actualValue.",
- "failed.content.broken_links": "The page contains broken links. These links were found: :actualValue.",
- "failed.content.length": "The content is :actualValue characters long. It should be at least :expectedValue characters long.",
- "failed.content.mixed_content": "The page contains links to insecure addresses, while it should not. These links were found :actualValue.",
- "failed.content.multiple_h1": "The page contains multiple h1 tags, while it should not. These tags were found :actualValue.",
- "failed.content.no_heading": "The page does not contain any h1 tag, while it should.",
- "failed.content.no_title": "The page does not contain a title tag, while it should.",
- "failed.content.title_length": "The page title is :actualValue characters long. It should be max :expectedValue characters long.",
- "failed.meta.description": "The page does not contain a description meta tag, while it should.",
- "failed.meta.no_lang": "The page does not contain a lang attribute, while it should.",
- "failed.meta.open_graph_image": "The page does not contain an open graph image, while it should.",
- "failed.meta.open_graph_image.broken": "The page contains a broken open graph image. This image was found: :actualValue.",
- "failed.meta.title": "The page title contains :actualValue in the title, while it should not.",
- "failed.meta.title.no_content": "The page title is empty, while it should not be.",
- "failed.performance.compression": "The page is not compressed (using either gzip or deflate), while it should be.",
- "failed.performance.css_size": "The page contains CSS files that are too large (max :expectedValue). These files were found: :actualValue.",
- "failed.performance.html_size": "The page contains HTML that is too large (max :expectedValue), the actual size is :actualValue.",
- "failed.performance.image_size": "The page contains images that are too large (max :expectedValue). These images were found: :actualValue.",
- "failed.performance.javascript_size": "The page contains Javascript files that are too large (max :expectedValue). These files were found: :actualValue.",
- "failed.performance.response": "The page returned a response code other than :expectedValue. The actual response code was :actualValue.",
- "failed.performance.ttfb": "The page took too long to load (max :expectedValuems). The actual time was :actualValuems.",
- "failed.performance.ttfb.missing_url": "We could not get the TTFB for this page."
+ "failed.configuration.nofollow.meta": "De pagina bevat een nofollow meta-tag, terwijl dat niet zou moeten.",
+ "failed.configuration.nofollow.tag": "De pagina bevat een nofollow-tag, terwijl dat niet zou moeten.",
+ "failed.configuration.noindex.meta": "De pagina bevat een noindex meta-tag, terwijl dat niet zou moeten.",
+ "failed.configuration.noindex.tag": "De pagina bevat een noindex-tag, terwijl dat niet zou moeten.",
+ "failed.configuration.robots.disallowed": "Het robots.txt-bestand voor deze pagina bevat een regel die deze pagina uitsluit.",
+ "failed.configuration.robots.missing_url": "We konden het robots.txt-bestand voor deze pagina niet ophalen.",
+ "failed.content.alt_tag": "De pagina bevat afbeeldingen zonder alt-tags of met lege alt-tags. Deze afbeeldingen zijn gevonden: :actualValue.",
+ "failed.content.broken_images": "De pagina bevat kapotte afbeeldingen. Deze afbeeldingen zijn gevonden: :actualValue.",
+ "failed.content.broken_links": "De pagina bevat kapotte links. Deze links zijn gevonden: :actualValue.",
+ "failed.content.length": "De inhoud is :actualValue tekens lang. Het zou minstens :expectedValue tekens lang moeten zijn.",
+ "failed.content.length.parse": "We konden de inhoud van deze pagina niet analyseren, probeer het opnieuw.",
+ "failed.content.mixed_content": "De pagina bevat links naar onveilige adressen, terwijl dat niet zou moeten. Deze links zijn gevonden: :actualValue.",
+ "failed.content.multiple_h1": "De pagina bevat meerdere h1-tags, terwijl dat niet zou moeten. Deze tags zijn gevonden: :actualValue.",
+ "failed.content.no_heading": "De pagina bevat geen enkele h1-tag, terwijl dat zou moeten.",
+ "failed.content.no_title": "De pagina bevat geen titel-tag, terwijl dat zou moeten.",
+ "failed.content.title_length": "De paginatitel is :actualValue tekens lang. Het zou maximaal :expectedValue tekens lang moeten zijn.",
+ "failed.meta.description": "De pagina bevat geen beschrijvende meta-tag, terwijl dat zou moeten.",
+ "failed.meta.no_lang": "De pagina bevat geen taalattribuut, terwijl dat zou moeten.",
+ "failed.meta.open_graph_image": "De pagina bevat geen Open Graph-afbeelding, terwijl dat zou moeten.",
+ "failed.meta.open_graph_image.broken": "De pagina bevat een kapotte Open Graph-afbeelding. Deze afbeelding is gevonden: :actualValue.",
+ "failed.meta.title": "De paginatitel bevat :actualValue in de titel, terwijl dat niet zou moeten.",
+ "failed.meta.title.no_content": "De paginatitel is leeg, terwijl dat niet zou moeten.",
+ "failed.performance.compression": "De pagina is niet gecomprimeerd (met gzip of deflate), terwijl dat zou moeten.",
+ "failed.performance.css_size": "De pagina bevat CSS-bestanden die te groot zijn (maximaal :expectedValue). Deze bestanden zijn gevonden: :actualValue.",
+ "failed.performance.html_size": "De pagina bevat HTML die te groot is (maximaal :expectedValue), de werkelijke grootte is :actualValue.",
+ "failed.performance.image_size": "De pagina bevat afbeeldingen die te groot zijn (maximaal :expectedValue). Deze afbeeldingen zijn gevonden: :actualValue.",
+ "failed.performance.javascript_size": "De pagina bevat Javascript-bestanden die te groot zijn (maximaal :expectedValue). Deze bestanden zijn gevonden: :actualValue.",
+ "failed.performance.response": "De pagina heeft een andere responscodes dan :expectedValue geretourneerd. De werkelijke responstijd was :actualValue.",
+ "failed.performance.ttfb": "De pagina heeft te lang geladen (maximaal :expectedValuems). De werkelijke tijd was :actualValuems.",
+ "failed.performance.ttfb.missing_url": "We konden de TTFB voor deze pagina niet ophalen.",
+ "failed.content.transition_words_ratio_check.too_few_transition_words": "De pagina bevat te weinig transitiewoorden. Het zou minstens 30% moeten zijn, maar het is :actualValue%.",
+ "failed.content.transition_words_ratio_check.no_phrases_found": "De pagina bevat geen zinnen.",
+ "additionally": "daarnaast",
+ "moreover": "bovendien",
+ "furthermore": "verder",
+ "in addition": "daarnaast",
+ "not only": "niet alleen",
+ "but also": "maar ook",
+ "as well as": "evenals",
+ "besides": "bovendien",
+ "what's more": "wat meer is",
+ "however": "echter",
+ "nevertheless": "desalniettemin",
+ "on the other hand": "aan de andere kant",
+ "in contrast": "in tegenstelling",
+ "conversely": "omgekeerd",
+ "although": "hoewel",
+ "while": "terwijl",
+ "yet": "toch",
+ "even though": "zelfs als",
+ "nonetheless": "desondanks",
+ "similarly": "op dezelfde wijze",
+ "likewise": "evenzo",
+ "in comparison": "in vergelijking",
+ "just as": "net zoals",
+ "compared to": "vergeleken met",
+ "similarly to": "net als",
+ "therefore": "daarom",
+ "thus": "zo",
+ "consequently": "als gevolg",
+ "as a result": "als resultaat",
+ "because": "omdat",
+ "since": "aangezien",
+ "so": "dus",
+ "due to": "vanwege",
+ "owing to": "te danken aan",
+ "accordingly": "overeenkomstig",
+ "indeed": "inderdaad",
+ "certainly": "zeker",
+ "of course": "natuurlijk",
+ "undoubtedly": "ongetwijfeld",
+ "without a doubt": "zonder twijfel",
+ "naturally": "natuurlijkerwijs",
+ "for example": "bijvoorbeeld",
+ "for instance": "bijvoorbeeld",
+ "such as": "zoals",
+ "to illustrate": "ter illustratie",
+ "in particular": "in het bijzonder",
+ "first": "eerst",
+ "second": "tweede",
+ "third": "derde",
+ "next": "volgende",
+ "then": "dan",
+ "afterward": "daarna",
+ "finally": "uiteindelijk",
+ "in the meantime": "ondertussen",
+ "subsequently": "vervolgens",
+ "in conclusion": "ter conclusie",
+ "to sum up": "om samen te vatten",
+ "ultimately": "uiteindelijk",
+ "in summary": "samengevat",
+ "all in all": "alles bij elkaar genomen",
+ "overall": "over het geheel genomen",
+ "meanwhile": "ondertussen",
+ "before": "voordat",
+ "after": "na",
+ "during": "tijdens",
+ "until": "totdat",
+ "eventually": "uiteindelijk",
+ "soon": "binnenkort",
+ "in the past": "in het verleden",
+ "in the future": "in de toekomst",
+ "in other words": "met andere woorden",
+ "that is to say": "dat wil zeggen",
+ "specifically": "specifiek",
+ "to clarify": "om te verduidelijken",
+ "in this case": "in dit geval",
+ "an example of this is": "een voorbeeld hiervan is",
+ "to demonstrate": "om te demonstreren",
+ "admittedly": "toegegeven",
+ "granted": "toegegeven",
+ "while it is true": "terwijl het waar is"
 }
diff --git a/src/Checks/Content/AltTagCheck.php b/src/Checks/Content/AltTagCheck.php
@@ -39,27 +39,10 @@ public function check(Response $response, Crawler $crawler): bool
  public function validateContent(Crawler $crawler): bool
  {
  $imagesWithoutAlt = $crawler->filterXPath('//img[not(@alt)]')->each(function (Crawler $node, $i) {
- $src = $node->attr('src');
-
- $dimensions = $this->getImageDimensions($src, $node);
-
- if ($dimensions['width'] < 5 || $dimensions['height'] < 5) {
- return null;
- }
-
- return $src;
+ return $this->filterImage($node);
  });
-
  $imagesWithEmptyAlt = $crawler->filterXPath('//img[@alt=""]')->each(function (Crawler $node, $i) {
- $src = $node->attr('src');
-
- $dimensions = $this->getImageDimensions($src, $node);
-
- if ($dimensions['width'] < 5 || $dimensions['height'] < 5) {
- return null;
- }
-
- return $src;
+ return $this->filterImage($node);
  });
 
  // Remove null values from the arrays
@@ -81,7 +64,24 @@ public function validateContent(Crawler $crawler): bool
  return true;
  }
 
- public function getImageDimensions(string $src, Crawler $node): array
+ private function filterImage($node): ?string
+ {
+ $src = $node->attr('src');
+
+ if (str_contains($src, '.svg')) {
+ return $src;
+ }
+
+ $dimensions = $this->getImageDimensions($src, $node);
+
+ if ($dimensions['width'] < 5 || $dimensions['height'] < 5) {
+ return null;
+ }
+
+ return $src;
+ }
+
+ private function getImageDimensions(string $src, Crawler $node): array
  {
  if (app()->runningUnitTests()) {
  return [

diff --git a/src/Checks/Content/ContentLengthCheck.php b/src/Checks/Content/ContentLengthCheck.php
@@ -41,23 +41,21 @@ public function check(Response $response, Crawler $crawler): bool
  $content = $this->getContentToValidate($response, $crawler);
 
  if (! $content) {
- return true;
+ return false;
  }
 
  return $this->validateContent($content);
  }
 
  public function getContentToValidate(Response $response, Crawler $crawler): ?string
  {
- $url = $response->transferStats->getHandlerStats()['url'];
-
  $body = $response->body();
 
  if ($this->useJavascript) {
  $body = $crawler->filter('body')->html();
  }
 
- $readability = new Readability($body, $url);
+ $readability = new Readability($body);
 
  $readability->init();