Python CSV写入格式化问题：使用标准库csv模块避免常见陷阱

# 假设 genres = "Adventure, Fantasy, Shounen, Supernatural"
# 假设 synopsis = "It is the dark century..."
# 手动拼接示例：
# details = ..., genres + ',' + synopsis
# 最终的字符串可能是：
# "Adventure, Fantasy, Shounen, Supernatural,It is the dark century..."

import re

def parse_anime_data(data):
    """
    解析原始动漫数据并返回一个结构化的列表。
    """
    try:
        # Genre parse
        genres_list = data.get('genres', [])
        genres = ', '.join(genre['name'] for genre in genres_list) if genres_list else ""

        # Studio parse
        studio_name = "unknown"
        studio_parse = str(data.get('studios'))
        match = re.search(r"'name':\s*'([^']*)'", studio_parse)
        if match:
            studio_name = match.group(1)

        # Synopsis parse
        synopsis_dirty = data.get('synopsis', '')
        synopsis = re.sub(r"\(Source: [^\)]+\)", "", synopsis_dirty).strip()
        synopsis = re.sub(r'\[Written by MAL Rewrite\]', '', synopsis).strip()

        # 返回一个列表，每个元素都是一个字段
        return [
            str(data.get('id', '')),
            data.get('title', '').encode('utf-8').decode('cp1252', 'replace'),
            data.get('start_date', ''),
            str(data.get('mean', '')),
            str(data.get('rank', '')),
            str(data.get('popularity', '')),
            str(data.get('num_episodes', '')),
            data.get('rating', ''),
            studio_name,
            genres, # 此时genres是一个包含逗号的字符串
            synopsis # 此时synopsis是一个可能包含逗号或换行符的字符串
        ]
    except Exception as e:
        print(f"Error parsing data: {e}")
        return None

# 示例原始数据（简化版）
sample_api_data = {
    'id': 8,
    'title': 'Bouken Ou Beet',
    'start_date': '2004-09-30',
    'mean': 6.93,
    'rank': 4426,
    'popularity': 5274,
    'num_episodes': 52,
    'rating': 'pg',
    'studios': [{'id': 18, 'name': 'Toei Animation'}],
    'genres': [{'id': 2, 'name': 'Adventure'}, {'id': 10, 'name': 'Fantasy'}, {'id': 27, 'name': 'Shounen'}, {'id': 37, 'name': 'Supernatural'}],
    'synopsis': 'It is the dark century and the people are suffering under the rule of the devil Vandel who is able to manipulate monsters. (Source: MAL Rewrite)'
}

parsed_row = parse_anime_data(sample_api_data)
# parsed_row 现在是：
# ['8', 'Bouken Ou Beet', '2004-09-30', '6.93', '4426', '5274', '52', 'pg', 'Toei Animation', 'Adventure, Fantasy, Shounen, Supernatural', 'It is the dark century and the people are suffering under the rule of the devil Vandel who is able to manipulate monsters.']

import csv

def write_data_to_csv_writer(filename, data_rows, header=None):
    """
    使用 csv.writer 将数据写入CSV文件。
    :param filename: CSV文件名。
    :param data_rows: 包含要写入的数据的列表的列表。
    :param header: 可选的列表，作为CSV的标题行。
    """
    with open(filename, 'w', newline='', encoding='utf-8') as csvfile:
        csv_writer = csv.writer(csvfile)

        if header:
            csv_writer.writerow(header) # 写入标题行

        for row in data_rows:
            csv_writer.writerow(row) # 写入数据行
    print(f"Data successfully written to {filename} using csv.writer.")

# 示例使用
header = ["id", "title", "start-date", "mean", "rank", "popularity", "num_episodes", "rating", "studio", "genres", "synopsis"]
all_anime_data = [parsed_row] # 假设这里有多个解析好的行

write_data_to_csv_writer("anime_data_writer.csv", all_anime_data, header)

def parse_anime_data_to_dict(data):
    """
    解析原始动漫数据并返回一个结构化的字典。
    """
    try:
        genres_list = data.get('genres', [])
        genres = ', '.join(genre['name'] for genre in genres_list) if genres_list else ""

        studio_name = "unknown"
        studio_parse = str(data.get('studios'))
        match = re.search(r"'name':\s*'([^']*)'", studio_parse)
        if match:
            studio_name = match.group(1)

        synopsis_dirty = data.get('synopsis', '')
        synopsis = re.sub(r"\(Source: [^\)]+\)", "", synopsis_dirty).strip()
        synopsis = re.sub(r'\[Written by MAL Rewrite\]', '', synopsis).strip()

        return {
            "id": str(data.get('id', '')),
            "title": data.get('title', '').encode('utf-8').decode('cp1252', 'replace'),
            "start-date": data.get('start_date', ''),
            "mean": str(data.get('mean', '')),
            "rank": str(data.get('rank', '')),
            "popularity": str(data.get('popularity', '')),
            "num_episodes": str(data.get('num_episodes', '')),
            "rating": data.get('rating', ''),
            "studio": studio_name,
            "genres": genres,
            "synopsis": synopsis
        }
    except Exception as e:
        print(f"Error parsing data to dict: {e}")
        return None

parsed_dict_row = parse_anime_data_to_dict(sample_api_data)
# parsed_dict_row 现在是：
# {'id': '8', 'title': 'Bouken Ou Beet', ..., 'genres': 'Adventure, Fantasy, Shounen, Supernatural', 'synopsis': 'It is the dark century and the people are suffering under the rule of the devil Vandel who is able to manipulate monsters.'}

def write_data_to_csv_dictwriter(filename, data_dicts, fieldnames):
    """
    使用 csv.DictWriter 将数据写入CSV文件。
    :param filename: CSV文件名。
    :param data_dicts: 包含要写入的数据的字典列表。
    :param fieldnames: 字典的键列表，用于定义CSV的列顺序和标题。
    """
    with open(filename, 'w', newline='', encoding='utf-8') as csvfile:
        csv_writer = csv.DictWriter(csvfile, fieldnames=fieldnames)

        csv_writer.writeheader() # 写入标题行（根据fieldnames）
        csv_writer.writerows(data_dicts) # 写入数据行
    print(f"Data successfully written to {filename} using csv.DictWriter.")

# 示例使用
fieldnames = ["id", "title", "start-date", "mean", "rank", "popularity", "num_episodes", "rating", "studio", "genres", "synopsis"]
all_anime_data_dicts = [parsed_dict_row] # 假设这里有多个解析好的字典行

write_data_to_csv_dictwriter("anime_data_dictwriter.csv", all_anime_data_dicts, fieldnames)