upload_to_google_docs.py

"""
上传 Markdown 章节到 Google Docs

使用前准备：
1. 访问 https://console.cloud.google.com/
2. 创建新项目或选择现有项目
3. 启用 Google Docs API
4. 创建 OAuth 2.0 凭据（桌面应用）
5. 下载 credentials.json 放到脚本同目录
"""

import os
import re
from pathlib import Path
from google.auth.transport.requests import Request
from google.oauth2.credentials import Credentials
from google_auth_oauthlib.flow import InstalledAppFlow
from googleapiclient.discovery import build
from googleapiclient.errors import HttpError

# Google API 权限范围
SCOPES = ['https://www.googleapis.com/auth/documents']

# 配置
CHAPTERS_DIR = Path(r"/Users/am/Downloads/1lllllll1lll1llll1l-main/PIL_Chapters")
DOCUMENT_ID = "15zlTTawHQXO-5EoYfFxJbJifKMj9jGTUL9Db8wcM7YA"

def get_credentials():
    """获取 Google API 认证"""
    creds = None
    
    # token.json 存储用户的访问和刷新令牌
    if os.path.exists('token.json'):
        creds = Credentials.from_authorized_user_file('token.json', SCOPES)
    
    # 如果没有有效凭据，让用户登录
    if not creds or not creds.valid:
        if creds and creds.expired and creds.refresh_token:
            creds.refresh(Request())
        else:
            flow = InstalledAppFlow.from_client_secrets_file(
                'credentials.json', SCOPES)
            creds = flow.run_local_server(port=0)
        
        # 保存凭据供下次使用
        with open('token.json', 'w') as token:
            token.write(creds.to_json())
    
    return creds

def parse_markdown(md_file):
    """
    解析 Markdown 文件
    返回格式：[
        {'type': 'heading1', 'text': '1.1 Introduction'},
        {'type': 'paragraph', 'text': 'Public international law is...'},
        {'type': 'heading2', 'text': '1.2.1 Historical context'},
    ]
    """
    with open(md_file, 'r', encoding='utf-8') as f:
        content = f.read()
    
    elements = []
    
    for block in content.split('\n\n'):
        block = block.strip()
        if not block:
            continue
        
        # 识别 Markdown 标题
        heading_match = re.match(r'^(#{1,6})\s+(.+)$', block)
        
        if heading_match:
            level = len(heading_match.group(1))  # # 的数量
            text = heading_match.group(2)
            
            elements.append({
                'type': f'heading{level}',
                'text': text
            })
        else:
            # 普通段落
            elements.append({
                'type': 'paragraph',
                'text': block
            })
    
    return elements

def create_google_docs_requests(elements, start_index=1):
    """
    生成 Google Docs API 请求
    """
    requests = []
    current_index = start_index
    
    for element in elements:
        text = element['text'] + '\n'
        
        # 插入文本
        requests.append({
            'insertText': {
                'location': {'index': current_index},
                'text': text
            }
        })
        
        # 应用样式
        style = element['type']
        if style.startswith('heading'):
            # Heading 1, Heading 2, etc.
            level = int(style.replace('heading', ''))
            named_style = f'HEADING_{level}'
        else:
            named_style = 'NORMAL_TEXT'
        
        requests.append({
            'updateParagraphStyle': {
                'range': {
                    'startIndex': current_index,
                    'endIndex': current_index + len(text)
                },
                'paragraphStyle': {
                    'namedStyleType': named_style
                },
                'fields': 'namedStyleType'
            }
        })
        
        current_index += len(text)
    
    return requests

def create_new_tab(service, document_id, tab_title):
    """创建新的标签页（Tab）"""
    
    # 注意：Google Docs API 不直接支持 "tabs"
    # 我们需要用其他方法：在文档末尾添加分页符和标题
    
    # 获取文档当前长度
    doc = service.documents().get(documentId=document_id).execute()
    content = doc.get('body').get('content')
    end_index = content[-1].get('endIndex') - 1
    
    # 添加分页符
    requests = [
        {
            'insertPageBreak': {
                'location': {'index': end_index}
            }
        },
        {
            'insertText': {
                'location': {'index': end_index + 1},
                'text': f'\n{tab_title}\n\n'
            }
        },
        {
            'updateParagraphStyle': {
                'range': {
                    'startIndex': end_index + 1,
                    'endIndex': end_index + len(tab_title) + 3
                },
                'paragraphStyle': {
                    'namedStyleType': 'TITLE'
                },
                'fields': 'namedStyleType'
            }
        }
    ]
    
    result = service.documents().batchUpdate(
        documentId=document_id,
        body={'requests': requests}
    ).execute()
    
    return end_index + len(tab_title) + 3

def upload_chapter(service, document_id, md_file, chapter_name):
    """上传单个章节"""
    
    print(f"\n📄 处理：{md_file.name}")
    
    # 解析 Markdown
    elements = parse_markdown(md_file)
    print(f"   • 解析出 {len(elements)} 个元素")
    
    # 创建新标签页
    print(f"   • 创建标签页：{chapter_name}")
    start_index = create_new_tab(service, document_id, chapter_name)
    
    # 生成插入请求
    requests = create_google_docs_requests(elements, start_index)
    
    # 批量更新（Google API 限制每次最多500个请求）
    batch_size = 500
    for i in range(0, len(requests), batch_size):
        batch = requests[i:i + batch_size]
        
        try:
            service.documents().batchUpdate(
                documentId=document_id,
                body={'requests': batch}
            ).execute()
            print(f"   • 上传批次 {i//batch_size + 1}/{(len(requests)-1)//batch_size + 1}")
        except HttpError as error:
            print(f"   ❌ 错误：{error}")
            return False
    
    print(f"   ✓ 完成！")
    return True

def main():
    print(f"\n{'='*70}")
    print("📚 上传 PIL 章节到 Google Docs")
    print(f"{'='*70}\n")
    
    # 检查目录
    if not CHAPTERS_DIR.exists():
        print(f"❌ 错误：找不到目录 {CHAPTERS_DIR}")
        return
    
    # 获取所有 Markdown 文件
    md_files = sorted(CHAPTERS_DIR.glob("Chapter_*.md"))
    print(f"📁 找到 {len(md_files)} 个章节文件\n")
    
    if not md_files:
        print("❌ 没有找到任何 Markdown 文件")
        return
    
    # 认证
    print("🔐 Google API 认证中...")
    try:
        creds = get_credentials()
        service = build('docs', 'v1', credentials=creds)
        print("✓ 认证成功\n")
    except Exception as e:
        print(f"❌ 认证失败：{e}")
        print("\n请确保：")
        print("1. credentials.json 文件在当前目录")
        print("2. 已启用 Google Docs API")
        return
    
    # 确认操作
    print(f"📄 目标文档：https://docs.google.com/document/d/{DOCUMENT_ID}/edit")
    print(f"\n⚠️  将上传 {len(md_files)} 个章节到该文档")
    confirm = input("\n继续？(y/n): ")
    
    if confirm.lower() != 'y':
        print("❌ 已取消")
        return
    
    # 上传每个章节
    print(f"\n{'='*70}")
    print("开始上传...")
    print(f"{'='*70}")
    
    success_count = 0
    
    for md_file in md_files:
        # 提取章节名称
        match = re.match(r'Chapter_(\d+)_(.+)\.md', md_file.name)
        if match:
            chapter_num = match.group(1)
            chapter_name = f"Chapter {chapter_num}"
        else:
            chapter_name = md_file.stem
        
        if upload_chapter(service, DOCUMENT_ID, md_file, chapter_name):
            success_count += 1
    
    # 总结
    print(f"\n{'='*70}")
    print(f"✅ 完成！")
    print(f"{'='*70}")
    print(f"成功上传：{success_count}/{len(md_files)} 章节")
    print(f"\n查看文档：https://docs.google.com/document/d/{DOCUMENT_ID}/edit")
    print(f"{'='*70}\n")

if __name__ == '__main__':
    main()