scrapy保存数据为xlsx和csv

最新推荐文章于 2024-07-23 17:03:32 发布

划船的使者

最新推荐文章于 2024-07-23 17:03:32 发布

阅读量1k

点赞数

文章标签： scrapy

本文链接：https://blog.csdn.net/weixin_42185136/article/details/102611851

版权

保存为csv文件

from scrapy.exporters import CsvItemExporter


class FtimesPipeline(object):
    def open_spider(self, spider):
        self.file = open('ftoutput.csv', 'wb')
        self.exporter = CsvItemExporter(self.file, delimiter='~')
        self.exporter.start_exporting()

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

    def process_item(self, item, spider):
        self.exporter.export_item(item)
        return item

保存为xlsx文件

from openpyxl import Workbook

class MapdataPipeline(object):
    wb = Workbook()
    ws = wb.active
    # 设置表头
    ws.append(['area', 'total'])

    def process_item(self, item, spider):
        # 添加数据
        line = [item['area'], item['total']]
        self.ws.append(line) # 按行添加
        self.wb.save('printingshop.xlsx')
        return item