1.在pipelines.py中自定義自己的pipeline

from openpyxl import Workbook
class ExcelPipeline(object):
    def __init__(self):
        self.wb = Workbook()
        self.ws = self.wb.active
        self.ws.append(['工作名稱', '工作地點', '薪資', '公司名稱', '工作經驗', '學歷', '招收人數', '釋出時間', '工作資訊'])

    def process_item(self, item, spider):
        line = [item['job_name'], item['job_place'], item['salary'], item['company'], item['experience'], item['education_level'], item['person_num'], item['release_time'], item['info']]
        self.ws.append(line)
        self.wb.save('job.xlsx')
        return item
 

2.在settings.py中開啟自己的pipeline

ITEM_PIPELINES = {
   'Job.pipelines.ExcelPipeline': 1,
}