数据存储 Json

数据存储 Json

一、JsonLInesEx

from scrapy.exporters import JsonLinesItemExporter
class JsonLinesItemExporterPipeline(object):
    def __init__(self):
        self.file = open('jsonfile.json', 'wb')  # 必须写入二进制
        self.exporter = JsonLinesItemExporter(self.file, ensure_ascii=False, encoding='utf-8')
    def process_item(self, item, spider):
        self.exporter.export_item(item)
        print(item)
    def close_item(self, spider):
        self.file.close()
        pass

二、自定义方法保存json文件

import json
 
# 自定义处理json保存
class QsbkDemoPipeline(object):
    def __init__(self):
        self.file = open('qsbk.json', 'w', encoding='utf-8')
 
    def open_spider(self, spider):
        print('爬虫开始了...')
        pass
 
    def process_item(self, item, spider):
        # 这里需要把item转换字典
        item_json = json.dumps(dict(item), ensure_ascii=False)
        self.file.write(item_json+'\n')
        return item
 
    def close_spider(self, spider):
        self.file.close()
        print('爬虫结束了...')
        pass

三、JsonItemExporter保存json

from scrapy.exporters import JsonItemExporter
 
# 利用scrapy自带json保存
class JsonExporterPipeline(object):
    def __init__(self):
        self.file = open('qsbk_1.json', 'wb')  # 必须二进制写入
        self.exporter = JsonItemExporter(self.file, encoding='utf-8', ensure_ascii=False)
        # 开始写入
        self.exporter.start_exporting()
 
    def open_spider(self, spider):
        print('爬虫开始')
        pass
 
    def process_item(self, item, spider):
        self.exporter.export_item(item)
        return item
 
    def close_spider(self, spider):
        # 完成写入
        self.exporter.finish_exporting()
        self.file.close()
        pass