Method migrate

scripts/migrate_wordpress.py:310–377

Main migration entry point.

(self, url_filter: Optional[str] = None)

        print(f"\n  Total: {len(docs)} docs across {len(path_counts)} directories")

    def migrate(self, url_filter: Optional[str] = None) -> None:
        """Main migration entry point."""
        mode = "[DRY RUN] " if self.dry_run else ""
        print(f"\n{mode}Starting migration from {self.site_url}")
        print(f"Output directory: {self.output_dir}")
        if url_filter:
            print(f"URL filter: {url_filter}")
        print()

        docs = self.get_all_docs()

        if url_filter:
            docs = [d for d in docs if url_filter.lower() in d.get("link", "").lower()]
            print(f"After filter: {len(docs)} docs match '{url_filter}'")

        print(f"\nTotal docs to process: {len(docs)}")

        path_entries: Dict[str, List[dict]] = {}

        for i, doc in enumerate(docs, 1):
            self.stats["total"] += 1
            title = self.clean_title(doc.get("title", {}).get("rendered", ""))
            link = doc.get("link", "")
            output_path, _ = self.detect_output_path(link)
            print(f"[{i:3d}/{len(docs)}] {title[:65]}")

            try:
                zh_file, fm = self.save_document(doc)
                if fm is None:
                    self.stats["skipped"] += 1
                    print(f"        SKIP (empty content)")
                    continue

                if output_path not in path_entries:
                    path_entries[output_path] = []
                path_entries[output_path].append({
                    "id": fm["id"],
                    "title": fm["title"],
                    "status": fm["status"],
                    "source_url": fm["source_url"],
                    "source_url_verified": fm["source_url_verified"],
                    "effective_date": fm.get("effective_date", ""),
                })

                self.stats["success"] += 1
                if self.dry_run:
                    print(f"        -> [DRY] {output_path}/{doc.get('slug', '')}.zh.md")
                else:
                    print(f"        -> {zh_file.relative_to(self.output_dir)}")
            except Exception as e:
                self.stats["error"] += 1
                print(f"        ERROR: {e}")

            time.sleep(self.delay)

        if not self.dry_run:
            print("\nUpdating _index.json files...")
            for path, entries in path_entries.items():