add script to output a .csv of all existing guides in the library (#7237)

Author: andystevensname

scripts/url-spreadsheet/generate_urls_recursive.sh

@@ -0,0 +1,93 @@
+#!/bin/bash
+
+# Get the absolute path to where the script is located
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+# Define the path to parse, assuming it's always in "/docs/docs/guides" relative to the repository root
+GUIDES_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)/docs/guides"
+
+# Define the output CSV file in the script's directory
+OUTPUT_FILE="$SCRIPT_DIR/urls.csv"
+
+# Define the base URL
+BASE_URL="https://www.linode.com/docs/guides/"
+
+# Initialize the CSV file with a header
+echo "URL,Title,Description,Keyword(s),Deprecation Status,Published Date,Updated Date" > "$OUTPUT_FILE"
+
+# Function to extract and trim a given field from a line
+extract_field() {
+  echo "$1" | sed "s/^$2:\s*//" | xargs
+}
+
+# Function to sanitize the description field
+sanitize_description() {
+  echo "$1" | sed 's/"/'\''/g; s/'"'"'/\\'"'"'/g; s/,/\\,/g; s/:/\\:/g; s/;/\\;/g' | xargs
+}
+
+# Function to clean and format the keywords field
+format_keywords() {
+  echo "$1" | sed 's/[][]//g' | sed 's/, */, /g' | xargs
+}
+
+# Function to parse fields and build the CSV
+parse_directory_recursively() {
+  local dir="$1"
+
+  # Find all index.md files recursively in the directory, excluding specified folders
+  find "$dir" -type d \( -name "_shortguides" -o -name "concentrations" -o -name "audiences" -o -name "linode-writers-formatting-guide" \) -prune -o -type f -name "index.md" -print | while read -r file; do
+    # Initialize default values
+    slug=""
+    title=""
+    description=""
+    keywords=""
+    deprecated="false"
+    published_date=""
+    updated_date=""
+
+    # Extract fields from each line
+    while read -r line; do
+      case "$line" in
+        slug:*)
+          slug=$(extract_field "$line" "slug")
+          ;;
+        title:*)
+          title=$(extract_field "$line" "title")
+          ;;
+        description:*)
+          description=$(extract_field "$line" "description")
+          description=$(sanitize_description "$description")
+          ;;
+        keywords:*)
+          keywords=$(extract_field "$line" "keywords")
+          keywords=$(format_keywords "$keywords")
+          ;;
+        deprecated:*)
+          deprecated_value=$(extract_field "$line" "deprecated")
+          if [ "$deprecated_value" = "true" ]; then
+            deprecated="true"
+          fi
+          ;;
+        published:*)
+          published_date=$(extract_field "$line" "published")
+          ;;
+        modified:*)
+          updated_date=$(extract_field "$line" "modified")
+          ;;
+      esac
+    done < "$file"
+
+    # Construct the full URL without spaces, if slug exists
+    if [ -n "$slug" ]; then
+      full_url="${BASE_URL}${slug}"
+
+      # Append the data to the CSV file
+      echo "\"$full_url\",\"$title\",\"$description\",\"$keywords\",\"$deprecated\",\"$published_date\",\"$updated_date\"" >> "$OUTPUT_FILE"
+    fi
+  done
+}
+
+# Parse the designated guides directory
+parse_directory_recursively "$GUIDES_DIR"
+
+echo "Data has been written to $OUTPUT_FILE"

scripts/url-spreadsheet/grab-csv.gs

@@ -0,0 +1,41 @@
+function importCSVFromDrive() {
+  // The name of the CSV file in Google Drive
+  var fileName = 'urls.csv'; // Replace with your actual file name if different
+
+  try {
+    // Fetch the file from Google Drive
+    var files = DriveApp.getFilesByName(fileName);
+
+    if (files.hasNext()) {
+      var file = files.next();
+      var csvContent = file.getBlob().getDataAsString();
+
+      // Ensure that the CSV content is not empty
+      if (!csvContent) {
+        throw new Error('The CSV file is empty or could not be read.');
+      }
+
+      // Parse the CSV content
+      var csvData = Utilities.parseCsv(csvContent);
+
+      // Check if parsed data is non-empty
+      if (csvData.length === 0) {
+        throw new Error('Parsed CSV data is empty.');
+      }
+
+      // Get the active sheet
+      var sheet = SpreadsheetApp.getActiveSpreadsheet().getActiveSheet();
+
+      // Clear existing content on the sheet
+      sheet.clear();
+
+      // Set the values to the sheet starting at A1
+      sheet.getRange(1, 1, csvData.length, csvData[0].length).setValues(csvData);
+    } else {
+      throw new Error("File not found with the name: " + fileName);
+    }
+  } catch (e) {
+    Logger.log('Failed to import CSV: ' + e.toString());
+    SpreadsheetApp.getUi().alert('Failed to import the CSV file: ' + e.toString());
+  }
+}

scripts/url-spreadsheet/test.csv

@@ -0,0 +1,2 @@
+URL,Title,Description,Keyword(s),Deprecation Status,Published Date,Updated Date
+https://example.com,"Sample Title","Sample Description","keyword1, keyword2",false,"2022-01-01","2022-02-01"