parser.py

from dataclasses import dataclass
from datetime import datetime
from typing import List, Optional, Any, Dict

# 修改后的数据类（添加 Optional 和默认值）


@dataclass
class Author:
    _id: Optional[str] = None
    name: Optional[str] = None
    hidden: Optional[bool] = None


@dataclass
class Paper:
    id: Optional[str] = None
    authors: List[Author] = None
    publishedAt: Optional[datetime] = None
    title: Optional[str] = None
    summary: Optional[str] = None
    upvotes: Optional[int] = None
    discussionId: Optional[str] = None


@dataclass
class SubmittedBy:
    _id: Optional[str] = None
    avatarUrl: Optional[str] = None
    fullname: Optional[str] = None
    name: Optional[str] = None
    type: Optional[str] = None
    isPro: Optional[bool] = None
    isHf: Optional[bool] = None
    isMod: Optional[bool] = None
    followerCount: Optional[int] = None


@dataclass
class Article:
    paper: Optional[Paper] = None
    publishedAt: Optional[datetime] = None
    title: Optional[str] = None
    thumbnail: Optional[str] = None
    numComments: Optional[int] = None
    submittedBy: Optional[SubmittedBy] = None
    isAuthorParticipating: Optional[bool] = None


def safe_get(data: Dict, *keys: str) -> Any:
    """安全获取嵌套字典值"""
    for key in keys:
        data = data.get(key, {}) if isinstance(data, dict) else None
    return data if data != {} else None


def parse_article(data: Dict[str, Any]) -> Article:
    """容错式解析函数"""

    def parse_datetime(dt_str: Optional[str]) -> Optional[datetime]:
        """安全解析时间"""
        if not dt_str:
            return None
        try:
            if dt_str.endswith('Z'):
                dt_str = dt_str[:-1] + '+00:00'
            return datetime.fromisoformat(dt_str)
        except ValueError:
            return None

    # 解析作者列表
    authors = []
    for author_data in safe_get(data, "paper", "authors") or []:
        authors.append(Author(
            _id=author_data.get("_id"),
            name=author_data.get("name"),
            hidden=author_data.get("hidden")
        ))

    # 解析论文
    paper = Paper(
        id=safe_get(data, "paper", "id"),
        authors=authors,
        publishedAt=parse_datetime(safe_get(data, "paper", "publishedAt")),
        title=safe_get(data, "paper", "title"),
        summary=safe_get(data, "paper", "summary"),
        upvotes=safe_get(data, "paper", "upvotes"),
        discussionId=safe_get(data, "paper", "discussionId")
    ) if safe_get(data, "paper") else None

    # 解析提交者
    submitted_by_data = safe_get(data, "submittedBy")
    submitted_by = SubmittedBy(
        _id=submitted_by_data.get("_id") if submitted_by_data else None,
        avatarUrl=submitted_by_data.get("avatarUrl") if submitted_by_data else None,
        fullname=submitted_by_data.get("fullname") if submitted_by_data else None,
        name=submitted_by_data.get("name") if submitted_by_data else None,
        type=submitted_by_data.get("type") if submitted_by_data else None,
        isPro=submitted_by_data.get("isPro") if submitted_by_data else None,
        isHf=submitted_by_data.get("isHf") if submitted_by_data else None,
        isMod=submitted_by_data.get("isMod") if submitted_by_data else None,
        followerCount=submitted_by_data.get("followerCount") if submitted_by_data else None
    ) if submitted_by_data else None

    # 构建最终对象
    return Article(
        paper=paper,
        publishedAt=parse_datetime(data.get("publishedAt")),
        title=data.get("title"),
        thumbnail=data.get("thumbnail"),
        numComments=data.get("numComments"),
        submittedBy=submitted_by,
        isAuthorParticipating=data.get("isAuthorParticipating")
    )


# 使用示例
if __name__ == "__main__":
    import json
    from rich import print

    # 假设您的原始数据保存在 article.json 文件中
    with open("article.json") as f:
        raw_data = json.load(f)

    articles = []

    for raw_article in raw_data:
        article = parse_article(raw_article)
        articles.append(article)

    print(articles[0])
    print(len(articles))