Scrapy数据导出教程：JSON/CSV/XML多格式导出详解

# 命令行导出
scrapy crawl spider_name -o output.json
scrapy crawl spider_name -o output.csv
scrapy crawl spider_name -o output.xml

# 指定格式
scrapy crawl spider_name -o output.json:json
scrapy crawl spider_name -o output.jl:jsonlines

# JSON格式（最常用）
scrapy crawl quotes -o quotes.json

# JSON Lines格式（推荐，适合大数据量）
scrapy crawl quotes -o quotes.jl

# CSV格式（适合Excel打开）
scrapy crawl quotes -o quotes.csv

# XML格式
scrapy crawl quotes -o quotes.xml

# 指定编码（中文导出必须设置）
scrapy crawl quotes -o quotes.json -s FEED_EXPORT_ENCODING=utf-8

# settings.py

# 方式1：通过FEEDS设置多格式导出
FEEDS = {
    'output/%(name)s/%(time)s.json': {
        'format': 'json',
        'encoding': 'utf-8',
        'indent': 4,
        'overwrite': True,
    },
    'output/%(name)s/latest.csv': {
        'format': 'csv',
        'fields': ['title', 'author', 'price'],  # 指定导出字段
    },
}

# 方式2：全局指定导出字段顺序
FEED_EXPORT_FIELDS = ['title', 'author', 'url', 'content']

import csv
import json
from itemadapter import ItemAdapter

class CsvExportPipeline:
    """自定义CSV导出Pipeline"""

    def open_spider(self, spider):
        self.file = open('custom_output.csv', 'w', newline='', encoding='utf-8')
        self.writer = None
        self.headers_written = False

    def close_spider(self, spider):
        self.file.close()

    def process_item(self, item, spider):
        adapter = ItemAdapter(item)
        fields = dict(adapter)

        if not self.headers_written:
            self.writer = csv.DictWriter(self.file, fieldnames=fields.keys())
            self.writer.writeheader()
            self.headers_written = True

        self.writer.writerow(fields)
        return item


class JsonLinesExportPipeline:
    """JSON Lines导出Pipeline"""

    def open_spider(self, spider):
        self.file = open('output.jl', 'w', encoding='utf-8')

    def close_spider(self, spider):
        self.file.close()

    def process_item(self, item, spider):
        adapter = ItemAdapter(item)
        line = json.dumps(dict(adapter), ensure_ascii=False) + '\n'
        self.file.write(line)
        return item

# settings.py
ITEM_PIPELINES = {
    'myproject.pipelines.CsvExportPipeline': 300,
    'myproject.pipelines.JsonLinesExportPipeline': 301,
}