<\/i>bash<\/span>$ sudo apt install python3-pymysql python3-bs4\n<\/code><\/pre><\/div>\n\n\n\n<\/div>\n\n\n\n
<\/span><\/i>MySQL \u63a5\u7d9a\u60c5\u5831\u306e\u78ba\u8a8d<\/span><\/span><\/span><\/h3>\n\n\n\nMySQL \u306e\u63a5\u7d9a\u306b\u5fc5\u8981\u306a\u60c5\u5831\u3092\u6e96\u5099\u3057\u307e\u3059\u3002\u3000\u4e8b\u524d\u306b\u8a2d\u8a08\u66f8\u3084\u8a2d\u5b9a\u66f8\u306b\u8a18\u9332\u3057\u3066\u3044\u308c\u3070\u305d\u308c\u3092\u78ba\u8a8d\u3059\u308b\u3060\u3051\u3067\u3059\u304c\u3001\u500b\u4eba\u74b0\u5883\u306a\u306e\u3067wp-config.php \u306e\u30d5\u30a1\u30a4\u30eb\u3092\u78ba\u8a8d\u3057\u307e\u3059\u3002\u3000<\/p>\n\n\n\n
\u305d\u3057\u3066\u3001\u4eca\u56de\u306fwp-config.php\u30d5\u30a1\u30a4\u30eb\u306e\u4e2d\u306b\u3042\u308b MySQL \u63a5\u7d9a\u60c5\u5831\u3092\u8aad\u307f\u306b\u3044\u304f\u3088\u3046\u306b Python \u30b9\u30af\u30ea\u30d7\u30c8\u3092\u4f5c\u6210\u3059\u308b\u3053\u3068\u306b\u3057\u307e\u3059\u3002\u3000\u3000MySQL\u306e\u63a5\u7d9a\u60c5\u5831\u3092\u4f55\u304b\u6240\u306b\u3082\u8a18\u9332\u3059\u308b\u3088\u308a\u30821\u3064\u306b\u3057\u305f\u65b9\u304c\u826f\u3044\u305f\u3081\u3002<\/p>\n\n\n\n
<\/div>\n\n\n\n
<\/span><\/i>Phtyon\u30b9\u30af\u30ea\u30d7\u30c8\u306e\u4f5c\u6210<\/span><\/span><\/span><\/h3>\n\n\n\n\u30b9\u30af\u30ea\u30d7\u30c8\u306f\u4ee5\u4e0b\u3002\u3000 \u4eca\u306f\u751f\u6210AI\u304c\u3042\u308b\u306e\u3067\u4e00\u77ac\u3067\u30d9\u30fc\u30b9\u306f\u4f5c\u6210\u3067\u304d\u307e\u3059\u3002\u3000\u5185\u5bb9\u3092\u4e00\u901a\u308a\u78ba\u8a8d\u3057\u3066\u3001\u51e6\u7406\u306b\u554f\u984c\u304c\u7121\u3044\u3053\u3068\u3001\u30bb\u30ad\u30e5\u30ea\u30c6\u30a3\u7684\u306b\u554f\u984c\u304c\u7121\u3044\u3053\u3068\u306f\u5b9a\u6027\u7684\u3067\u3059\u304c\u78ba\u8a8d\u306f\u3057\u3066\u304a\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
\u51e6\u7406\u3068\u3057\u3066\u306f\u3001\u3068\u308a\u3042\u3048\u305a\u753b\u50cf\u30c7\u30fc\u30bf\u306fqwen\u306b\u306f\u8aad\u307e\u305b\u306a\u3044\u306e\u3067\u3059\u304c\u3001\u753b\u50cf\u304c\u3042\u3063\u305f\u3053\u3068\u306f\u308f\u304b\u308b\u3088\u3046\u306b <img>\u30bf\u30b0\u306e alt \u5c5e\u6027\u3068\u30d5\u30a1\u30a4\u30eb\u540d\u3092\u6b8b\u3057\u3064\u3064 HTML \u30bf\u30b0\u3092\u9664\u53bb\u3057\u3066\u201dall_posts.txt\u201d\u306b\u30a8\u30af\u30b9\u30dd\u30fc\u30c8\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
<\/i>export_wppost.py<\/span>import re\nimport pymysql\nfrom bs4 import BeautifulSoup\n\n# \u25bc \u74b0\u5883\u306b\u5408\u308f\u305b\u3066 wp-config.php \u306e\u30d1\u30b9\u3092\u6307\u5b9a\nWP_CONFIG_PATH = \"\/var\/www\/html\/wordpress\/wp-config.php\"\nOUTPUT_FILE = \"all_posts.txt\"\n\ndef parse_wp_config(path):\n with open(path, \"r\", encoding=\"utf-8\") as f:\n content = f.read()\n \n def get_define(name):\n m = re.search(rf\"define\\(\\s*['\\\"]{name}['\\\"]\\s*,\\s*['\\\"]([^'\\\"]+)['\\\"]\\s*\\)\", content)\n return m.group(1) if m else None\n\n prefix_m = re.search(r\"\\$table_prefix\\s*=\\s*['\\\"]([^'\\\"]+)['\\\"]\", content)\n \n return {\n \"db\": get_define(\"DB_NAME\"),\n \"user\": get_define(\"DB_USER\"),\n \"password\": get_define(\"DB_PASSWORD\"),\n \"host\": get_define(\"DB_HOST\"),\n \"prefix\": prefix_m.group(1) if prefix_m else \"wp_\"\n }\n\ndef clean_html(html_text):\n if not html_text:\n return \"\"\n soup = BeautifulSoup(html_text, \"html.parser\")\n \n # <img> \u30bf\u30b0\u3092 [\u753b\u50cf: alt\u5c5e\u6027 (\u30d5\u30a1\u30a4\u30eb\u540d)] \u306e\u30c6\u30ad\u30b9\u30c8\u306b\u7f6e\u63db\u3057\u3066\u6587\u8108\u3092\u4fdd\u6301\n for img in soup.find_all(\"img\"):\n alt = img.get(\"alt\", \"\").strip()\n src = img.get(\"src\", \"\").split(\"\/\")[-1]\n label = f\"[\u753b\u50cf: {alt} ({src})]\" if alt else f\"[\u753b\u50cf: {src}]\"\n img.replace_with(f\"\\n{label}\\n\")\n \n # \u4e0d\u8981\u306a script \/ style \u30bf\u30b0\u3092\u524a\u9664\n for tag in soup([\"script\", \"style\"]):\n tag.decompose()\n \n text = soup.get_text(separator=\"\\n\")\n # \u9023\u7d9a\u3059\u308b\u7a7a\u884c\u3092\u6574\u7406\n lines = [line.strip() for line in text.splitlines() if line.strip()]\n return \"\\n\".join(lines)\n\ndef main():\n cfg = parse_wp_config(WP_CONFIG_PATH)\n host_parts = cfg[\"host\"].split(\":\")\n host = host_parts[0]\n port = int(host_parts[1]) if len(host_parts) > 1 else 3306\n\n conn = pymysql.connect(\n host=host,\n port=port,\n user=cfg[\"user\"],\n password=cfg[\"password\"],\n database=cfg[\"db\"],\n charset=\"utf8mb4\",\n cursorclass=pymysql.cursors.DictCursor\n )\n\n table_posts = f\"{cfg['prefix']}posts\"\n sql = f\"\"\"\n SELECT ID, post_date, post_title, post_name, post_content\n FROM {table_posts}\n WHERE post_status = 'publish' AND post_type = 'post'\n ORDER BY post_date ASC\n \"\"\"\n\n with conn.cursor() as cursor:\n cursor.execute(sql)\n rows = cursor.fetchall()\n\n conn.close()\n\n total_chars = 0\n with open(OUTPUT_FILE, \"w\", encoding=\"utf-8\") as out:\n for row in rows:\n cleaned_body = clean_html(row[\"post_content\"])\n block = (\n f\"===\\n\"\n f\"ID: {row['ID']} | Date: {row['post_date']} | Slug: {row['post_name']}\\n\"\n f\"Title: {row['post_title']}\\n\"\n f\"---\\n\"\n f\"{cleaned_body}\\n\"\n f\"===\\n\\n\"\n )\n out.write(block)\n total_chars += len(block)\n\n print(f\"\u62bd\u51fa\u5b8c\u4e86: {len(rows)} \u8a18\u4e8b\")\n print(f\"\u7dcf\u6587\u5b57\u6570: {total_chars:,} \u6587\u5b57\")\n print(f\"\u51fa\u529b\u30d5\u30a1\u30a4\u30eb: {OUTPUT_FILE}\")\n\nif __name__ == \"__main__\":\n main()<\/code><\/pre><\/div>\n\n\n\n<\/div>\n\n\n\n
<\/span>\u30a8\u30af\u30b9\u30dd\u30fc\u30c8\u306e\u5b9f\u884c<\/span><\/span><\/span><\/h2>\n\n\n\npython \u30b9\u30af\u30ea\u30d7\u30c8\u3092\u5b9f\u884c\u3057\u3001MySQL\u4e0a\u306e WordPress \u8a18\u4e8b\u30c7\u30fc\u30bf\u3092\u30a8\u30af\u30b9\u30dd\u30fc\u30c8\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
<\/i>bash<\/span>$ python3 .\/export_wppost.py<\/strong>\n\u62bd\u51fa\u5b8c\u4e86: 486 \u8a18\u4e8b\n\u7dcf\u6587\u5b57\u6570: 2,133,016 \u6587\u5b57\n\u51fa\u529b\u30d5\u30a1\u30a4\u30eb: all_posts.txt<\/code><\/pre><\/div>\n\n\n\n<\/div>\n\n\n\n
486\u8a18\u4e8b\u3001213\u4e07\u6587\u5b57\u304c\u62bd\u51fa\u3067\u304d\u307e\u3057\u305f\u3002\u3000\u30001\u8a18\u4e8b\u5f53\u305f\u308a4,382\u6587\u5b57\u3002\u30002019\u5e74\u306b\u59cb\u3081\u305f\u30d6\u30ed\u30b0\u3067\u3059\u304c\u307e\u3055\u306b\u30c1\u30ea\u3082\u7a4d\u3082\u308c\u3070\u3068\u3044\u3046\u3084\u3064\u3067\u3059\u306d\u3002\u3000<\/p>\n\n\n\n
<\/div>\n\n\n\n
\u4ee5\u4e0a<\/p>\n","protected":false},"excerpt":{"rendered":"
WordPress \u306e\u30c7\u30fc\u30bf\u3092\u683c\u7d0d\u3057\u3066\u3044\u308b RDS \u306e MySQL \u304b\u3089\u30c7\u30fc\u30bf\u3092\u30a8\u30af\u30b9\u30dd\u30fc\u30c8\u3059\u308b\u8a71\u3067\u3059\u3002\u3000\u3000\u30a8\u30af\u30b9\u30dd\u30fc\u30c8\u3059\u308b\u76ee\u7684\u306f\u30d0\u30c3\u30af\u30a2\u30c3\u30d7\u3068\u3044\u3046\u308f\u3051\u3067\u306f\u306a\u304f\uff08\u30d0\u30c3\u30af\u30a2\u30c3\u30d7\u306f RDS \u306e\u6a19\u6e96\u6a5f\u80fd\u3067\u307e\u304b\u306a\u3048\u3066\u3044\u308b\uff09\u3001\u30a8\u30af … <\/p>\n","protected":false},"author":1,"featured_media":20126,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3,5,15],"tags":[],"class_list":["post-20125","post","type-post","status-publish","format-standard","has-post-thumbnail","category-alibaba-cloud","category-ecs","category-alibaba-cloud-rds","entry"],"views":22,"_links":{"self":[{"href":"https:\/\/www.bigriver.jp\/index.php?rest_route=\/wp\/v2\/posts\/20125","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.bigriver.jp\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bigriver.jp\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bigriver.jp\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bigriver.jp\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=20125"}],"version-history":[{"count":1,"href":"https:\/\/www.bigriver.jp\/index.php?rest_route=\/wp\/v2\/posts\/20125\/revisions"}],"predecessor-version":[{"id":20127,"href":"https:\/\/www.bigriver.jp\/index.php?rest_route=\/wp\/v2\/posts\/20125\/revisions\/20127"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.bigriver.jp\/index.php?rest_route=\/wp\/v2\/media\/20126"}],"wp:attachment":[{"href":"https:\/\/www.bigriver.jp\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=20125"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bigriver.jp\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=20125"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bigriver.jp\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=20125"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}