<?xml version="1.0" encoding="UTF-8"?>
<movie>
  <title>黑客帝國</title>
  <originaltitle>The Matrix</originaltitle>
  <year>1999</year>
  <plot>一名年輕的網(wǎng)絡(luò)黑客發(fā)現(xiàn)看似正常的現(xiàn)實(shí)世界實(shí)際上是由名為"矩陣"的計(jì)算機(jī)人工智能系統(tǒng)控制的...</plot>
  <director>莉莉·沃卓斯基</director>
  <rating>8.7</rating>
  <genre>科幻</genre>
  <genre>動(dòng)作</genre>
  <actor>
    <name>基努·里維斯</name>
    <role>尼奧</role>
    <thumb>https://example.com/keanu.jpg</thumb>
  </actor>
</movie>

import xml.etree.ElementTree as ET

pip install lxml beautifulsoup4 pynfo

def read_nfo(file_path):
    """讀取并解析 .nfo 文件"""
    try:
        tree = ET.parse(file_path)
        root = tree.getroot()
        return root
    except ET.ParseError as e:
        print(f"解析錯(cuò)誤: {e}")
        return None
    except FileNotFoundError:
        print(f"文件不存在: {file_path}")
        return None

# 使用示例
movie_nfo = read_nfo("The.Matrix.nfo")

def extract_movie_info(root):
    """提取電影基本信息"""
    if root.tag != 'movie':
        return None
    
    info = {
        'title': root.findtext('title'),
        'year': root.findtext('year'),
        'plot': root.findtext('plot'),
        'director': root.findtext('director'),
        'rating': root.findtext('rating'),
        'genres': [genre.text for genre in root.findall('genre')],
        'actors': []
    }
    
    # 提取演員信息
    for actor in root.findall('actor'):
        info['actors'].append({
            'name': actor.findtext('name'),
            'role': actor.findtext('role'),
            'thumb': actor.findtext('thumb')
        })
    
    return info

# 使用示例
movie_info = extract_movie_info(movie_nfo)
print(f"電影標(biāo)題: {movie_info['title']}")

def update_nfo_rating(file_path, new_rating):
    """更新電影評(píng)分"""
    tree = ET.parse(file_path)
    root = tree.getroot()
    
    # 查找或創(chuàng)建 rating 元素
    rating_elem = root.find('rating')
    if rating_elem is None:
        rating_elem = ET.SubElement(root, 'rating')
    
    rating_elem.text = str(new_rating)
    
    # 保存修改
    tree.write(file_path, encoding='utf-8', xml_declaration=True)

# 使用示例
update_nfo_rating("The.Matrix.nfo", 9.2)

def create_nfo_file(file_path, movie_data):
    """創(chuàng)建新的 .nfo 文件"""
    # 創(chuàng)建根元素
    movie = ET.Element('movie')
    
    # 添加子元素
    ET.SubElement(movie, 'title').text = movie_data['title']
    ET.SubElement(movie, 'year').text = str(movie_data['year'])
    ET.SubElement(movie, 'plot').text = movie_data['plot']
    
    # 添加類型
    for genre in movie_data['genres']:
        ET.SubElement(movie, 'genre').text = genre
    
    # 添加演員
    for actor in movie_data['actors']:
        actor_elem = ET.SubElement(movie, 'actor')
        ET.SubElement(actor_elem, 'name').text = actor['name']
        ET.SubElement(actor_elem, 'role').text = actor['role']
    
    # 創(chuàng)建 XML 樹
    tree = ET.ElementTree(movie)
    
    # 寫入文件
    tree.write(file_path, encoding='utf-8', xml_declaration=True)
    print(f"已創(chuàng)建 .nfo 文件: {file_path}")

# 使用示例
new_movie = {
    'title': '盜夢(mèng)空間',
    'year': 2010,
    'plot': '一群能夠潛入他人夢(mèng)境竊取思想的盜賊...',
    'genres': ['科幻', '驚悚'],
    'actors': [
        {'name': '萊昂納多·迪卡普里奧', 'role': '科布'},
        {'name': '約瑟夫·高登-萊維特', 'role': '亞瑟'}
    ]
}
create_nfo_file("Inception.nfo", new_movie)

from lxml import etree

def parse_with_lxml(file_path):
    """使用 lxml 解析 .nfo 文件"""
    parser = etree.XMLParser(remove_blank_text=True)
    tree = etree.parse(file_path, parser)
    root = tree.getroot()
    
    # 使用 XPath 查詢
    actors = root.xpath('//actor[name="萊昂納多·迪卡普里奧"]')
    for actor in actors:
        print(f"角色: {actor.xpath('role/text()')[0]}")
    
    return tree

# 添加命名空間支持
def parse_with_namespace(file_path):
    ns = {'ns': 'http://www.example.com/nfo'}
    tree = etree.parse(file_path)
    title = tree.xpath('//ns:title', namespaces=ns)[0].text
    print(f"帶命名空間的標(biāo)題: {title}")

def handle_non_standard_nfo(file_path):
    """處理非標(biāo)準(zhǔn)格式的 .nfo 文件"""
    from bs4 import BeautifulSoup
    
    with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
        content = f.read()
    
    # 修復(fù)常見格式問題
    content = content.replace('&', '&')  # 修復(fù)未轉(zhuǎn)義的 & 符號(hào)
    
    # 使用 BeautifulSoup 解析
    soup = BeautifulSoup(content, 'lxml-xml')
    
    # 提取信息
    title = soup.find('title').text if soup.find('title') else None
    
    return {
        'title': title,
        'soup': soup  # 返回 BeautifulSoup 對(duì)象供進(jìn)一步處理
    }

import os
from pathlib import Path

def batch_process_nfo(directory):
    """批量處理目錄中的 .nfo 文件"""
    nfo_files = Path(directory).glob('*.nfo')
    results = []
    
    for nfo_file in nfo_files:
        try:
            tree = ET.parse(nfo_file)
            root = tree.getroot()
            info = extract_movie_info(root)
            results.append((nfo_file.name, info))
        except Exception as e:
            print(f"處理 {nfo_file} 失敗: {e}")
    
    return results

# 使用 pandas 導(dǎo)出結(jié)果
import pandas as pd

def export_to_csv(nfo_dir, output_file):
    """導(dǎo)出 .nfo 信息到 CSV"""
    data = batch_process_nfo(nfo_dir)
    df = pd.DataFrame({
        'file': [item[0] for item in data],
        'title': [item[1]['title'] for item in data],
        'year': [item[1]['year'] for item in data],
        'rating': [item[1]['rating'] for item in data]
    })
    df.to_csv(output_file, index=False)

def sync_with_media_library(nfo_dir, media_dir):
    """將 .nfo 信息同步到媒體文件"""
    for nfo_file in Path(nfo_dir).glob('*.nfo'):
        # 解析 .nfo
        tree = ET.parse(nfo_file)
        root = tree.getroot()
        title = root.findtext('title')
        
        # 查找對(duì)應(yīng)的媒體文件
        media_file = find_media_file(media_dir, title)
        
        if media_file:
            # 使用 mutagen 更新媒體文件元數(shù)據(jù)
            from mutagen import File
            audio = File(media_file)
            audio['title'] = title
            audio['artist'] = root.findtext('director')
            audio.save()

def generate_html_report(nfo_files, output_file):
    """從 .nfo 文件生成 HTML 報(bào)告"""
    html = """
    <html>
    <head>
        <title>媒體庫報(bào)告</title>
        <style>
            table { border-collapse: collapse; width: 100%; }
            th, td { border: 1px solid #ddd; padding: 8px; }
            tr:nth-child(even) { background-color: #f2f2f2; }
        </style>
    </head>
    <body>
        <h1>媒體庫報(bào)告</h1>
        <table>
            <tr>
                <th>標(biāo)題</th>
                <th>年份</th>
                <th>導(dǎo)演</th>
                <th>評(píng)分</th>
            </tr>
    """
    
    for nfo_file in nfo_files:
        root = read_nfo(nfo_file)
        if root:
            html += f"""
            <tr>
                <td>{root.findtext('title')}</td>
                <td>{root.findtext('year')}</td>
                <td>{root.findtext('director')}</td>
                <td>{root.findtext('rating')}</td>
            </tr>
            """
    
    html += """
        </table>
    </body>
    </html>
    """
    
    with open(output_file, 'w', encoding='utf-8') as f:
        f.write(html)

import requests
from bs4 import BeautifulSoup

def enrich_nfo_info(file_path):
    """補(bǔ)充缺失的電影信息"""
    tree = ET.parse(file_path)
    root = tree.getroot()
    
    title = root.findtext('title')
    if not title:
        return
    
    # 從豆瓣API獲取信息
    url = f"https://api.douban.com/v2/movie/search?q={title}"
    response = requests.get(url)
    data = response.json()
    
    if data['movies']:
        movie_data = data['movies'][0]
        
        # 更新缺失字段
        if not root.findtext('plot'):
            ET.SubElement(root, 'plot').text = movie_data['summary']
        
        if not root.findtext('rating'):
            ET.SubElement(root, 'rating').text = str(movie_data['rating']['average'])
        
        # 保存更新
        tree.write(file_path, encoding='utf-8', xml_declaration=True)

def read_nfo_with_encoding(file_path):
    """自動(dòng)檢測(cè)編碼讀取 .nfo 文件"""
    encodings = ['utf-8', 'gbk', 'iso-8859-1']
    
    for enc in encodings:
        try:
            with open(file_path, 'r', encoding=enc) as f:
                content = f.read()
            return ET.fromstring(content)
        except UnicodeDecodeError:
            continue
    
    # 嘗試二進(jìn)制解析
    with open(file_path, 'rb') as f:
        return ET.fromstring(f.read())

def sanitize_nfo_content(content):
    """清理 .nfo 內(nèi)容中的特殊字符"""
    replacements = {
        '&': '&',
        '<': '&lt;',
        '>': '&gt;',
        '"': '&quot;',
        "'": '&apos;'
    }
    
    for char, entity in replacements.items():
        content = content.replace(char, entity)
    
    return content

def validate_nfo(file_path, schema_path='nfo_schema.xsd'):
    """使用 XML Schema 驗(yàn)證 .nfo 文件"""
    from lxml import etree
    
    # 解析 XML
    xml_doc = etree.parse(file_path)
    
    # 加載 Schema
    schema_doc = etree.parse(schema_path)
    schema = etree.XMLSchema(schema_doc)
    
    # 驗(yàn)證
    if schema.validate(xml_doc):
        print("文件有效")
        return True
    else:
        print("文件無效:")
        for error in schema.error_log:
            print(f"行 {error.line}: {error.message}")
        return False

class NfoProcessor:
    """處理 .nfo 文件的工具類"""
    
    def __init__(self, file_path=None):
        self.file_path = file_path
        self.tree = None
        self.root = None
        
        if file_path:
            self.load(file_path)
    
    def load(self, file_path):
        """加載 .nfo 文件"""
        self.file_path = file_path
        try:
            self.tree = ET.parse(file_path)
            self.root = self.tree.getroot()
        except ET.ParseError:
            # 嘗試使用 lxml 解析
            try:
                from lxml import etree
                parser = etree.XMLParser(recover=True)
                self.tree = etree.parse(file_path, parser)
                self.root = self.tree.getroot()
            except Exception as e:
                raise ValueError(f"無法解析文件: {e}")
    
    def save(self, file_path=None):
        """保存 .nfo 文件"""
        save_path = file_path or self.file_path
        if not save_path:
            raise ValueError("未指定保存路徑")
        
        if self.tree is not None:
            self.tree.write(save_path, encoding='utf-8', xml_declaration=True)
        else:
            raise ValueError("沒有可保存的數(shù)據(jù)")
    
    def get_value(self, path):
        """獲取指定路徑的值"""
        elem = self.root.find(path)
        return elem.text if elem is not None else None
    
    def set_value(self, path, value):
        """設(shè)置指定路徑的值"""
        parts = path.split('/')
        current = self.root
        
        # 創(chuàng)建或獲取元素
        for part in parts:
            elem = current.find(part)
            if elem is None:
                elem = ET.SubElement(current, part)
            current = elem
        
        # 設(shè)置值
        current.text = str(value)
    
    def get_actors(self):
        """獲取演員列表"""
        return [
            {
                'name': actor.findtext('name'),
                'role': actor.findtext('role'),
                'thumb': actor.findtext('thumb')
            }
            for actor in self.root.findall('actor')
        ]
    
    def add_actor(self, name, role, thumb=None):
        """添加演員"""
        actor = ET.SubElement(self.root, 'actor')
        ET.SubElement(actor, 'name').text = name
        ET.SubElement(actor, 'role').text = role
        if thumb:
            ET.SubElement(actor, 'thumb').text = thumb
    
    def to_dict(self):
        """轉(zhuǎn)換為字典"""
        return {
            'title': self.get_value('title'),
            'year': self.get_value('year'),
            'plot': self.get_value('plot'),
            'director': self.get_value('director'),
            'rating': self.get_value('rating'),
            'genres': [g.text for g in self.root.findall('genre')],
            'actors': self.get_actors()
        }

# 使用示例
processor = NfoProcessor("The.Matrix.nfo")
print(processor.get_value('title'))  # 輸出: 黑客帝國
processor.set_value('rating', 9.0)
processor.add_actor('凱瑞-安·莫斯', '崔妮蒂')
processor.save()