docs: new vale rule (#1890)

new rule looking for H1's
slight adjustments to accept.txt & .vale.ini

Author: TC-MO

.github/styles/Apify/H1.yml

@@ -0,0 +1,6 @@
+extends: existence
+message: 'Do not use H1 headings (#). The main title is generated automatically. Please use H2 (##) or lower.'
+level: error
+scope: heading.h1
+tokens:
+  - '.+'

.github/styles/config/vocabularies/Docs/accept.txt

@@ -1,5 +1,3 @@
-\bApify\b(?:-\w+)?
-@apify\.com
 SDK(s)
 [Ss]torages
 Crawlee
@@ -84,6 +82,7 @@ preconfigured
 [Tt]rello
 [Pp]refill
 [Gg]umloop
+[Aa]pify
 
 [Mm]ultiselect
 

.github/workflows/vale.yaml

@@ -31,6 +31,7 @@ jobs:
                     files: ${{ steps.changed-files.outputs.all_changed_files }}
                     separator: ','
                     fail_on_error: true
+                    filter_mode: nofilter
                     vale_flags: '--minAlertLevel=error'
                     reporter: github-pr-annotations
 

.vale.ini

@@ -12,13 +12,13 @@ mdx = md
 [*.md]
 BasedOnStyles = Vale, Apify, write-good, Microsoft
 # Ignore URLs, HTML/XML tags, lines with =, emails, curly braces, inline code
-TokenIgnores = (<\/?[A-Z][^>]*>), ([^\n]+=[^\n]*), ([^\n]+@[^\n]+\.[^\n]), ({[^}]*}), `[^`]+`
+TokenIgnores = (<\/?[A-Z][^>]*>), ([^\n]+=[^\n]*), ([^\n]+@[^\n]+\.[^\n]), ({[^}]*})
 # Ignore HTML comments and Markdown code blocks
 BlockIgnores = (?s) (<!--.*?-->)|(```.*?```)
-Vale.Spelling = YES
-
 
 # Disabling rules (NO)
+Vale.Spelling = NO
+write-good.ThereIs = NO
 Microsoft.Dashes = NO
 Microsoft.Avoid = NO
 Microsoft.Contractions = NO
@@ -30,3 +30,9 @@ Microsoft.Auto = NO
 Microsoft.URLFormat = NO
 Microsoft.GeneralURL = NO
 Microsoft.RangeFormat = NO
+Apify.Apify = NO
+Apify.Capitalization = NO
+Apify.Languages = NO
+
+[{README.md,CONTRIBUTING.md}]
+Apify.H1 = NO

CONTRIBUTING.md

@@ -1,4 +1,4 @@
-# Contributing to Apify Documentation
+# Contributing to Apify documentation
 
 ## Before you start
 

sources/academy/webscraping/scraping_basics_javascript/crawling/finding_links.md

@@ -7,8 +7,6 @@ slug: /web-scraping-for-beginners/crawling/finding-links
 
 import Example from '!!raw-loader!roa-loader!./finding_links.js';
 
-# Finding links {#finding-links}
-
 **Learn what a link looks like in HTML and how to find and extract their URLs when web scraping using both DevTools and Node.js.**
 
 ---

sources/academy/webscraping/scraping_basics_javascript/crawling/index.md

@@ -6,8 +6,6 @@ category: courses
 slug: /web-scraping-for-beginners/crawling
 ---
 
-# Basics of crawling {#basics}
-
 **Learn how to crawl the web with your scraper. How to extract links and URLs from web pages and how to manage the collected links to visit new pages.**
 
 ---