@ai-welopc/opc-content-factory 0.1.0

package/skill/scripts/push_wechat_draft.py

@@ -0,0 +1,240 @@
+#!/usr/bin/env python
+import argparse
+import json
+import mimetypes
+import os
+import re
+import sys
+import time
+import urllib.error
+import urllib.parse
+import urllib.request
+import uuid
+from pathlib import Path
+
+
+API_BASE = "https://api.weixin.qq.com/cgi-bin"
+DIRECT_OPENER = urllib.request.build_opener(urllib.request.ProxyHandler({}))
+
+
+class DraftError(RuntimeError):
+    pass
+
+
+def load_env_file(env_file: str) -> str:
+    if not env_file:
+        return ""
+    path = Path(env_file).resolve()
+    if not path.is_file():
+        raise SystemExit(f"env 文件不存在：{path}")
+    for raw_line in path.read_text(encoding="utf-8-sig").splitlines():
+        line = raw_line.strip()
+        if not line or line.startswith("#") or "=" not in line:
+            continue
+        key, value = line.split("=", 1)
+        key = key.strip()
+        value = value.strip().strip('"').strip("'")
+        if key and key not in os.environ:
+            os.environ[key] = value
+    return str(path)
+
+
+def api_json(url: str, data: bytes | None = None, headers: dict[str, str] | None = None) -> dict:
+    request = urllib.request.Request(url, data=data, headers=headers or {})
+    try:
+        with DIRECT_OPENER.open(request, timeout=60) as response:
+            raw = response.read()
+    except urllib.error.HTTPError as exc:
+        raise DraftError(f"HTTP {exc.code}: {exc.read().decode('utf-8', errors='replace')}") from exc
+    except urllib.error.URLError as exc:
+        raise DraftError(f"网络错误：{exc.reason}") from exc
+    try:
+        payload = json.loads(raw.decode("utf-8"))
+    except json.JSONDecodeError as exc:
+        raise DraftError(raw.decode("utf-8", errors="replace")) from exc
+    if payload.get("errcode") not in (None, 0):
+        raise DraftError(json.dumps(payload, ensure_ascii=False))
+    return payload
+
+
+def get_token(appid: str, secret: str) -> str:
+    query = urllib.parse.urlencode({"grant_type": "client_credential", "appid": appid, "secret": secret})
+    payload = api_json(f"{API_BASE}/token?{query}")
+    token = payload.get("access_token")
+    if not token:
+        raise DraftError(json.dumps(payload, ensure_ascii=False))
+    return token
+
+
+def multipart_file(field_name: str, file_path: Path) -> tuple[bytes, str]:
+    boundary = f"----opcContentFactory{uuid.uuid4().hex}"
+    mime_type = mimetypes.guess_type(str(file_path))[0] or "application/octet-stream"
+    body = bytearray()
+    body.extend(f"--{boundary}\r\n".encode())
+    body.extend(
+        f'Content-Disposition: form-data; name="{field_name}"; filename="{file_path.name}"\r\n'.encode()
+    )
+    body.extend(f"Content-Type: {mime_type}\r\n\r\n".encode())
+    body.extend(file_path.read_bytes())
+    body.extend(f"\r\n--{boundary}--\r\n".encode())
+    return bytes(body), boundary
+
+
+def upload_permanent_thumb(token: str, cover_path: Path) -> str:
+    body, boundary = multipart_file("media", cover_path)
+    query = urllib.parse.urlencode({"access_token": token, "type": "thumb"})
+    payload = api_json(
+        f"{API_BASE}/material/add_material?{query}",
+        data=body,
+        headers={"Content-Type": f"multipart/form-data; boundary={boundary}"},
+    )
+    media_id = payload.get("media_id")
+    if not media_id:
+        raise DraftError(json.dumps(payload, ensure_ascii=False))
+    return media_id
+
+
+def upload_article_image(token: str, image_path: Path) -> str:
+    body, boundary = multipart_file("media", image_path)
+    query = urllib.parse.urlencode({"access_token": token})
+    payload = api_json(
+        f"{API_BASE}/media/uploadimg?{query}",
+        data=body,
+        headers={"Content-Type": f"multipart/form-data; boundary={boundary}"},
+    )
+    url = payload.get("url")
+    if not url:
+        raise DraftError(json.dumps(payload, ensure_ascii=False))
+    return url
+
+
+def rewrite_local_images(html: str, html_file: Path, token: str | None, execute: bool) -> tuple[str, list[dict]]:
+    uploaded = []
+
+    def replace(match: re.Match) -> str:
+        quote = match.group(1)
+        src = match.group(2)
+        if re.match(r"^(https?:)?//|^data:", src):
+            return match.group(0)
+        image_path = (html_file.parent / src).resolve()
+        record = {"local": str(image_path), "original_src": src}
+        if not image_path.is_file():
+            record["error"] = "文件不存在"
+            uploaded.append(record)
+            return match.group(0)
+        if execute and token:
+            url = upload_article_image(token, image_path)
+            record["url"] = url
+            uploaded.append(record)
+            return f'src={quote}{url}{quote}'
+        record["url"] = "DRY_RUN_NEEDS_UPLOAD"
+        uploaded.append(record)
+        return match.group(0)
+
+    rewritten = re.sub(r"src=(['\"])([^'\"]+)\1", replace, html)
+    return rewritten, uploaded
+
+
+def create_draft(token: str, payload: dict) -> str:
+    body = json.dumps(payload, ensure_ascii=False).encode("utf-8")
+    query = urllib.parse.urlencode({"access_token": token})
+    result = api_json(
+        f"{API_BASE}/draft/add?{query}",
+        data=body,
+        headers={"Content-Type": "application/json; charset=utf-8"},
+    )
+    media_id = result.get("media_id")
+    if not media_id:
+        raise DraftError(json.dumps(result, ensure_ascii=False))
+    return media_id
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="把完成后的 HTML 文章导入公众号草稿箱。默认 dry-run。")
+    parser.add_argument("--title", required=True, help="文章标题。")
+    parser.add_argument("--digest", required=True, help="分享摘要。")
+    parser.add_argument("--html-file", required=True, help="准备导入的 HTML 文件。")
+    parser.add_argument("--cover-image", required=True, help="封面图，本地 JPG/PNG。")
+    parser.add_argument("--env-file", default="", help="可选 env 文件，包含 WECHAT_APPID、WECHAT_SECRET、WECHAT_AUTHOR。")
+    parser.add_argument("--author", default="", help="作者名；为空时读取 WECHAT_AUTHOR。")
+    parser.add_argument("--content-source-url", default="", help="原文链接。")
+    parser.add_argument("--show-cover-pic", type=int, choices=[0, 1], default=0)
+    parser.add_argument("--need-open-comment", type=int, choices=[0, 1], default=1)
+    parser.add_argument("--only-fans-can-comment", type=int, choices=[0, 1], default=0)
+    parser.add_argument("--out", default="", help="dry-run 或执行结果 JSON 输出路径。")
+    parser.add_argument("--execute", action="store_true", help="真实创建公众号草稿。")
+    return parser.parse_args()
+
+
+def main() -> int:
+    if hasattr(sys.stdout, "reconfigure"):
+        sys.stdout.reconfigure(encoding="utf-8")
+    if hasattr(sys.stderr, "reconfigure"):
+        sys.stderr.reconfigure(encoding="utf-8")
+    args = parse_args()
+    html_file = Path(args.html_file).resolve()
+    cover_image = Path(args.cover_image).resolve()
+    if not html_file.is_file():
+        raise SystemExit(f"HTML 文件不存在：{html_file}")
+    if not cover_image.is_file():
+        raise SystemExit(f"封面图不存在：{cover_image}")
+
+    loaded_env_file = load_env_file(args.env_file)
+    if not loaded_env_file:
+        for candidate in [html_file.parent / "draft" / "wechat_draft.env", html_file.parent / "wechat_draft.env"]:
+            if candidate.is_file():
+                loaded_env_file = load_env_file(str(candidate))
+                break
+
+    appid = os.environ.get("WECHAT_APPID", "")
+    secret = os.environ.get("WECHAT_SECRET", "")
+    author = args.author or os.environ.get("WECHAT_AUTHOR", "")
+    if args.execute and (not appid or not secret):
+        raise SystemExit("执行模式需要配置 WECHAT_APPID 和 WECHAT_SECRET。不要把密钥写进文章。")
+
+    token = get_token(appid, secret) if args.execute else None
+    html_text = html_file.read_text(encoding="utf-8")
+    content, uploaded_images = rewrite_local_images(html_text, html_file, token, args.execute)
+    thumb_media_id = upload_permanent_thumb(token, cover_image) if args.execute and token else "DRY_RUN_THUMB_MEDIA_ID"
+    payload = {
+        "articles": [
+            {
+                "title": args.title,
+                "author": author,
+                "digest": args.digest,
+                "content": content,
+                "content_source_url": args.content_source_url,
+                "thumb_media_id": thumb_media_id,
+                "show_cover_pic": args.show_cover_pic,
+                "need_open_comment": args.need_open_comment,
+                "only_fans_can_comment": args.only_fans_can_comment,
+            }
+        ]
+    }
+    result = {
+        "ok": True,
+        "dry_run": not args.execute,
+        "title": args.title,
+        "env_file": loaded_env_file,
+        "thumb_media_id": thumb_media_id,
+        "uploaded_images": uploaded_images,
+        "payload": payload,
+        "backend_url": "https://mp.weixin.qq.com",
+        "created_at": int(time.time()),
+    }
+    if args.execute and token:
+        result["draft_media_id"] = create_draft(token, payload)
+
+    text = json.dumps(result, ensure_ascii=False, indent=2)
+    if args.out:
+        Path(args.out).write_text(text, encoding="utf-8")
+    print(text)
+    return 0
+
+
+if __name__ == "__main__":
+    try:
+        raise SystemExit(main())
+    except DraftError as exc:
+        print(json.dumps({"ok": False, "error": str(exc)}, ensure_ascii=False), file=sys.stderr)
+        raise SystemExit(1)