Scrapy指定順序輸出 -《狗嗨默示錄》-

items.py

import scrapy class CollectipsItem(scrapy.Item): IP = scrapy.Field() PORT = scrapy.Field() POSITION = scrapy.Field() TYPE = scrapy.Field() SPEED = scrapy.Field() CONNECT_TIME = scrapy.Field() SURVIVE_TIME = scrapy.Field() LAST_CHECK_TIME = scrapy.Field()

（1）在spiders中增長文件csv_item_exporter.py

from scrapy.conf import settings from scrapy.contrib.exporter import CsvItemExporter class MyProjectCsvItemExporter(CsvItemExporter): def __init__(self, *args, **kwargs): delimiter = settings.get('CSV_DELIMITER', ',') kwargs['delimiter'] = delimiter fields_to_export = settings.get('FIELDS_TO_EXPORT', []) if fields_to_export : kwargs['fields_to_export'] = fields_to_export super(MyProjectCsvItemExporter, self).__init__(*args, **kwargs)

（2）在settings.py中配置

FEED_EXPORTERS = { 'csv': 'CollectIPs.spiders.csv_item_exporter.MyProjectCsvItemExporter', } #CollectIPs爲工程名
 FIELDS_TO_EXPORT = [ 'IP', 'PORT', 'POSITION', 'TYPE', 'SPEED', 'CONNECT_TIME', 'SURVIVE_TIME', 'LAST_CHECK_TIME' ]

在settings.py中也能夠指定csv文件中的分隔符

CSV_DELIMITER = "\t"