Add WordPress content importer

benchmarks/WordPressImporterBench.php

@@ -0,0 +1,98 @@
+<?php
+
+declare(strict_types=1);
+
+namespace YiiPress\Benchmarks;
+
+use PhpBench\Attributes\AfterMethods;
+use PhpBench\Attributes\BeforeMethods;
+use PhpBench\Attributes\Iterations;
+use PhpBench\Attributes\Revs;
+use PhpBench\Attributes\Warmup;
+use YiiPress\Import\WordPress\WordPressContentImporter;
+
+#[BeforeMethods('setUp')]
+#[AfterMethods('tearDown')]
+final class WordPressImporterBench
+{
+    private string $sourceDir;
+    private string $sourceFile;
+    private string $targetDir;
+    private WordPressContentImporter $importer;
+
+    public function setUp(): void
+    {
+        $this->sourceDir = sys_get_temp_dir() . '/yiipress-wordpress-bench-source-' . uniqid();
+        $this->targetDir = sys_get_temp_dir() . '/yiipress-wordpress-bench-target-' . uniqid();
+        mkdir($this->sourceDir, 0o755, true);
+        mkdir($this->targetDir, 0o755, true);
+        $this->sourceFile = $this->sourceDir . '/wordpress.xml';
+
+        $items = [];
+        for ($i = 1; $i <= 100; $i++) {
+            $items[] = '<item>'
+                . '<title><![CDATA[Post ' . $i . ']]></title>'
+                . '<link>https://example.com/2024/03/post-' . $i . '/</link>'
+                . '<content:encoded><![CDATA[<p>Body ' . $i . '.</p>]]></content:encoded>'
+                . '<excerpt:encoded><![CDATA[Summary ' . $i . '.]]></excerpt:encoded>'
+                . '<wp:post_id>' . $i . '</wp:post_id>'
+                . '<wp:post_date>2024-03-15 10:30:00</wp:post_date>'
+                . '<wp:post_name>post-' . $i . '</wp:post_name>'
+                . '<wp:status>publish</wp:status>'
+                . '<wp:post_type>post</wp:post_type>'
+                . '<category domain="post_tag" nicename="php"><![CDATA[PHP]]></category>'
+                . '<category domain="category" nicename="docs"><![CDATA[Docs]]></category>'
+                . '</item>';
+        }
+
+        file_put_contents(
+            $this->sourceFile,
+            '<?xml version="1.0" encoding="UTF-8" ?>'
+            . '<rss version="2.0"'
+            . ' xmlns:content="http://purl.org/rss/1.0/modules/content/"'
+            . ' xmlns:excerpt="http://wordpress.org/export/1.2/excerpt/"'
+            . ' xmlns:wp="http://wordpress.org/export/1.2/">'
+            . '<channel>' . implode('', $items) . '</channel></rss>',
+        );
+
+        $this->importer = new WordPressContentImporter();
+    }
+
+    public function tearDown(): void
+    {
+        $this->removeDir($this->sourceDir);
+        $this->removeDir($this->targetDir);
+    }
+
+    #[Revs(10)]
+    #[Iterations(3)]
+    #[Warmup(1)]
+    public function benchImportPosts(): void
+    {
+        $this->removeDir($this->targetDir);
+        mkdir($this->targetDir, 0o755, true);
+
+        $this->importer->import(['file' => $this->sourceFile], $this->targetDir, 'blog');
+    }
+
+    private function removeDir(string $path): void
+    {
+        if (!is_dir($path)) {
+            return;
+        }
+
+        $iterator = new \RecursiveIteratorIterator(
+            new \RecursiveDirectoryIterator($path, \FilesystemIterator::SKIP_DOTS),
+            \RecursiveIteratorIterator::CHILD_FIRST,
+        );
+        foreach ($iterator as $item) {
+            if ($item->isDir()) {
+                rmdir($item->getPathname());
+            } else {
+                unlink($item->getPathname());
+            }
+        }
+
+        rmdir($path);
+    }
+}

config/common/di/importer.php

@@ -4,6 +4,7 @@
 
 use YiiPress\Console\ImportCommand;
 use YiiPress\Import\Telegram\TelegramContentImporter;
+use YiiPress\Import\WordPress\WordPressContentImporter;
 
 $workingDirectory = getcwd() ?: dirname(__DIR__, 3);
 
@@ -13,6 +14,7 @@
             'rootPath' => $workingDirectory,
             'importers' => [
                 'telegram' => new TelegramContentImporter(),
+                'wordpress' => new WordPressContentImporter(),
             ],
         ],
     ],

docs/commands.md

@@ -144,7 +144,7 @@ Imports content from external sources into a YiiPress collection.
 
 **Arguments:**
 
-- `source` — source type to import from (required). Currently supported: `telegram`.
+- `source` — source type to import from (required). Currently supported: `telegram`, `wordpress`.
 
 **Common options:**
 
@@ -191,6 +191,29 @@ Supports both single-chat exports (`result.json` with `messages` array) and full
 ./yiipress import telegram --directory=./telegram-data --content-dir=content
 ```
 
+### WordPress import
+
+Imports posts and pages from a WordPress WXR XML export file. Export your site from WordPress via Tools > Export > All content.
+
+**Importer options:**
+
+- `--file` — path to the WordPress WXR `.xml` export file (required). Absolute or relative to project root.
+
+The importer reads `<item>` records from the export and converts:
+
+- WordPress posts (`wp:post_type = post`) into markdown files in the target collection.
+- WordPress pages (`wp:post_type = page`) into standalone markdown files in the content root.
+- `title`, `wp:post_date`, `link`, `excerpt:encoded`, `content:encoded`, `wp:status`, categories, and tags into YiiPress front matter and body content.
+
+Published posts are imported normally. Non-published posts and pages are imported with `draft: true`. Attachments, revisions, menu items, trashed posts, and auto-drafts are skipped. Duplicate output filenames get numeric suffixes so earlier files are not overwritten.
+
+**Examples:**
+
+```bash
+./yiipress import wordpress --file=/path/to/wordpress-export.xml
+./yiipress import wordpress --file=./export.xml --collection=blog
+```
+
 ### Adding custom importers
 
 Importers implement `YiiPress\Import\ContentImporterInterface` and are registered via [Yii3 DI](https://yiisoft.github.io/docs/guide/concept/di-container.html) in `config/common/di/importer.php`. Each importer declares its own options via the `options()` method. See [Importing content](importing-content.md) for details.

docs/importing-content.md

@@ -60,6 +60,18 @@ Imports messages from a Telegram Desktop channel export (JSON format).
 
 See [commands.md](commands.md#yii-import) for usage details.
 
+### WordPressContentImporter
+
+Imports posts and pages from a WordPress WXR XML export.
+
+**Options:**
+
+- `--file` — Path to the WordPress WXR `.xml` export file (required)
+
+The importer converts WordPress posts into the selected YiiPress collection and WordPress pages into standalone content root markdown files. It preserves common metadata (`title`, date, permalink path, draft status, excerpt summary, tags, and categories), keeps `content:encoded` as the markdown body, skips unsupported WordPress item types, and avoids overwriting duplicate output filenames.
+
+See [commands.md](commands.md#wordpress-import) for usage details.
+
 ## Writing a custom importer
 
 Create a class implementing `ContentImporterInterface`. Each importer declares its own options — a file-based importer might need a `directory`, while an API-based importer might need `url` and `api-key`.

roadmap.md

@@ -106,7 +106,7 @@
 
 ## Priority 9: Data importers
 
-- [ ] WordPress
+- [x] WordPress
 - [ ] Jekyll
 - [ ] Hugo
 - [ ] Medium exported Markdown