Python CsvItemExporter.start_exporting方法代码示例

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class TutorialPipeline(object):
    def __init__(self):
        self.files = {}

    @classmethod
    def from_crawler(cls, crawler):
        pipeline = cls()
        crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
        crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
        return pipeline

    def spider_opened(self, spider):
        file = open('%s_items.csv' % spider.name, 'w+b')
        self.files[spider] = file
        self.exporter = CsvItemExporter(file)
        list = ['id','title', 'time', 'director', 'year', 'star','cost']
        self.exporter.fields_to_export = list
        self.exporter.start_exporting()

    def spider_closed(self, spider):
        self.exporter.finish_exporting()
        file = self.files.pop(spider)
        file.close()

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

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class CSVPipeline(object):
    def __init__(self):
        self.files = {}
        self.exporter = None

    @classmethod
    def from_crawler(cls, crawler):
        pipeline = cls()
        crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
        crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
        return pipeline

    def spider_opened(self, spider):
        try:
            fo = open(spider.output_file, 'w+b')
        except IOError as e:
            spider.crawler.engine.close_spider(spider, "ERROR: Can't create CSV file: " + str(e))
            return

        self.files[spider] = fo
        self.exporter = CsvItemExporter(fo)
        self.exporter.fields_to_export = settings.getlist("EXPORT_FIELDS")
        self.exporter.start_exporting()

    def spider_closed(self, spider):
        if self.exporter is not None:
            self.exporter.finish_exporting()
            f = self.files.pop(spider)
            f.close()

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

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class YangmaodangPipeline(object):
    '''
    保存采集的水木羊毛信息，将其保存到csv文件中，并将其传到邮箱中。
    '''
    def __init__(self):
        self.filename = 'output/newsmth-'+time.strftime('%Y%m%d')+'.csv'
        self.file = open(self.filename, 'wb')
        self.items = []
        # self.file.write('$$'.join(YangmaodangItem.fields))

    def open_spider(self, spider):
        self.exporter = CsvItemExporter(self.file)
        self.exporter.start_exporting()

    def close_spider(self, spider):
        # 利用回复数对文章排序
        sortedlist = sorted(self.items, key=lambda x: int(operator.itemgetter('reply_num')(x)), reverse=True)
        for item in sortedlist:
            self.exporter.export_item(item)

        self.exporter.finish_exporting()
        self.file.close()

        send_email(self.filename)


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

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class GnewsPipeline(object):
    def __init__(self):
        self.files = {}

    @classmethod
    def from_crawler(cls, crawler):
         pipeline = cls()
         crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
         crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
         return pipeline

    def spider_opened(self, spider):
        file = open('%s.csv' % spider.name, 'w+b')
        self.files[spider] = file
        self.exporter = CsvItemExporter(file,True,'\n')
        self.exporter.fields_to_export=['category','topstory','snippet','link','originallink','sublinks','sublinktext','gpost','gpostsnip','extras','extraslink','related']
        self.exporter.start_exporting()

    def spider_closed(self, spider):
        self.exporter.finish_exporting()
        file = self.files.pop(spider)
        file.close()

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

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class OpossumPipeline(object):
    @classmethod
    def from_crawler(cls, crawler):
        pipeline = cls()
        crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
        crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
        return pipeline

    def spider_opened(self, spider):
        self.file = open('/home/moorcock/work/mrs_opossum/items.csv', 'w+b')
        self.exporter = CsvItemExporter(self.file)
        self.exporter.fields_to_export = ['id', 'title', 'image', 'keywords']
        self.exporter.start_exporting()

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

    def process_item(self, item, spider):
        item_exp = ExportImageItem(
            id=item['id'],
            title=item['title'].strip(' \t\n'),
            image=item['images'][0]['path'].split('/')[-1].split('.')[0],
            keywords=item['keywords']
        )
        self.exporter.export_item(item_exp)
        return item_exp

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class BuildingsPipeline(object):
    def __init__(self):
        self.files = {}

    @classmethod
    def from_crawler(cls, crawler):
        pipeline = cls()
        crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
        crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
        return pipeline

    def spider_opened(self, spider):
        file = open("buildings.csv", "w+b")
        self.files[spider] = file
        self.exporter = CsvItemExporter(file)
        self.exporter.fields_to_export = fields_to_export
        self.exporter.start_exporting()

    def spider_closed(self, spider):
        self.exporter.finish_exporting()
        file = self.files.pop(spider)
        file.close()

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

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class GameListingPipeline(object):

    def __init__(self):
        self.files = {}

    @classmethod
    def from_crawler(cls, crawler):
        pipeline = cls()
        crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
        crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
        return pipeline

    def spider_opened(self, spider):
        file = open('%s_products.csv' % spider.name, 'w+b')
        self.files[spider] = file
        self.exporter = CsvItemExporter(file)
        self.exporter.start_exporting()

    def spider_closed(self, spider):
        self.exporter.finish_exporting()
        file = self.files.pop(spider)
        file.close()

    def process_item(self, item, spider):

        keys = ['name','address','zipCode','jobCostMin','jobCostMax',
            'contactName','contactPhone','website','licenseNumber',
            'averageRating','profileUrl','followers','following',
            'badgeCount','projectCount','reviewCount','commentCount']
        dictionary = item_to_dictionary(item,keys)
        # print 'document to insert',dictionary
        client.insert('updatedListings', dictionary, callback=insert_callback)
        # client.insert('listings', dictionary, callback=insert_callback)

        self.exporter.export_item(item)

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class CSVPipeline(object):

  def __init__(self):
    self.files = {}

  @classmethod
  def from_crawler(cls, crawler):
    pipeline = cls()
    crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
    crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
    return pipeline

  def spider_opened(self, spider):
    file = open('%s_items.csv' % spider.name, 'w+b')
    self.files[spider] = file
    self.exporter = CsvItemExporter(file)
    self.exporter.fields_to_export = ['name', 'rank', 'overallScore', 'teachingScore', 'internationalOutlook', 'industryIncome', 'research', 'citations', 'textBelow']
    self.exporter.start_exporting()

  def spider_closed(self, spider):
    self.exporter.finish_exporting()
    file = self.files.pop(spider)
    file.close()

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

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class FinancePipeline(object):
	def __init__(self):
		self.files = {}

	@classmethod
	def from_crawler(cls, crawler):
		pipeline = cls()
		crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
		crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
		return pipeline

	def spider_opened(self, spider):
		file = open('%s_stock.csv' % spider.code, 'w+b')
		self.files[spider] = file
		self.exporter = CsvItemExporter(file, 
				fields_to_export=['date','Open','High', 'Low', 'Close', 'Volume', 'AdjClose'])
		self.exporter.start_exporting()

	def spider_closed(self, spider):
		self.exporter.finish_exporting()
		file = self.files.pop(spider)
		file.close()

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

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class EaCOpenListBotPipeline(object):

    def __init__(self):
        self.files = {}

    @classmethod
    def from_crawler(cls, crawler):
        pipeline = cls()
        crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
        crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
        return pipeline

    def spider_opened(self, spider):
        file = open('%s_%s_items.csv' % (spider.name, spider.category), 'w+b')
        self.files[spider] = file
        self.exporter = CsvItemExporter(file)
        self.exporter.fields_to_export = ['vendor', 'product', 'default']
        #self.exporter.fields_to_export = ['default']
        self.exporter.start_exporting()

    def spider_closed(self, spider):
        self.exporter.finish_exporting()
        file = self.files.pop(spider)
        file.close()

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

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class CSVPipeline(object):

    def __init__(self):
        self.files = {}

    @classmethod
    def from_crawler(cls, crawler):
        pipeline = cls()
        crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
        crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
        return pipeline

    def spider_opened(self, spider):
        file = open('%s_items.csv' % spider.name, 'w+b')
        self.files[spider] = file
        self.exporter = CsvItemExporter(file)
        self.exporter.fields_to_export = ['team_year', 'track', 'region']
        self.exporter.start_exporting()

    def spider_closed(self, spider):
        self.exporter.finish_exporting()
        file = self.files.pop(spider)
        file.close()

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

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class CsvExportPipeline(object):
	def process_item(self, item, spider):

		outputdir = '%s%s/%s' % (settings['ADAPTFM_OUTPUT_PATH'], spider.folder, item['brandCategory'][0])
		name = item['brandFeed'][0].replace('http://','').replace('/','_').replace('.xml','')
		filename = '%s/%s.csv' % (outputdir, name)
		if not os.path.isdir (os.path.dirname(filename)):
			os.mkdir(os.path.dirname(filename))

		file = open(filename, 'a+b')


		self.exporter = CsvItemExporter(file)
		self.exporter.start_exporting()



		self.exporter.export_item(item)


		self.exporter.finish_exporting()
		file.close()


		return item

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class CsvExportPipeline(object):

    def __init__(self):
        dispatcher.connect(self.spider_opened, signals.spider_opened)
        dispatcher.connect(self.spider_closed, signals.spider_closed)
        self.files = {}

    def spider_opened(self, spider):
        file = open('%s_%s.csv' % (spider.name, int(time.time())), 'w+b')
        self.files[spider] = file
        if 'yopt' in spider.name:
            self.exporter = CsvItemExporter(file,fields_to_export = ['date','instrument','option_symbol','symbol','expiration','type','strike','last','change','bid','ask','volume','open_int'],dialect='excel')
        elif 'prices' in spider.name:
            self.exporter = CsvItemExporter(file,fields_to_export = ['date','open','high','low','close','volume','adj_close'],dialect='excel')
        self.exporter.start_exporting()

    def spider_closed(self, spider):
        self.exporter.finish_exporting()
        file = self.files.pop(spider)
        file.close()

    def process_item(self, item, spider):
        if item is None:
            raise DropItem("None")
        self.exporter.export_item(item)
        return item 

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class MultiCSVItemPipeline(object):
    def __init__(self):
        self.files = {}
        self.exporter1 = CsvItemExporter(fields_to_export=ProfRatingItem.fields.keys(),file=open("profRating.csv",'wb'))
        self.exporter2 = CsvItemExporter(fields_to_export=ProfSummaryItem.fields.keys(),file=open("profSummary.csv",'wb'))

	@classmethod
	def from_crawler(cls, crawler):
		pipeline = cls()
		crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
		crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
		return pipeline

    def spider_opened(self, spider):
    	self.exporter1.start_exporting()
    	self.exporter2.start_exporting()

    def spider_closed(self, spider):
        self.exporter1.finish_exporting()
        self.exporter2.finish_exporting()
        file = self.files.pop(spider)
        file.close()

    def process_item(self, item, spider):
        self.exporter1.export_item(item)
        self.exporter2.export_item(item)
        return item

# 需要导入模块: from scrapy.contrib.exporter import CsvItemExporter [as 别名]
# 或者: from scrapy.contrib.exporter.CsvItemExporter import start_exporting [as 别名]
class TutorialPipeline(object):

  def __init__(self):
    self.files = {}

  @classmethod
  def from_crawler(cls, crawler):
    pipeline = cls()
    crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
    crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
    return pipeline

  def spider_opened(self, spider):
    file = open("mediabase.csv", 'w+b')
    self.files[spider] = file
    self.exporter = CsvItemExporter(file)
    #self.exporter.fields_to_export = ["Name","Address","City","Neighborhood","State","Zip","Phone","Website","Image_url","Hours_Mon","Hours_Tue","Hours_Wed","Hours_Thu","Hours_Fri","Hours_Sat","Hours_Sun","Price","TakesReservation","Delivery","TakeOut","AcceptsCreditCards","GoodFor","Parking","WheelChairAccessible","BikeParking","GoodForKids","GoodForGroups","Attire","Ambience","NoiseLevel","Alcohol","OutDoorSeating","Wifi","HasTV","WaiterService","Caters","Url"]
    self.exporter.fields_to_export = ["Type","Area","PlaceName","Web","Tel","Address","Zip","Town","Hours","CompanyName","OrganizationNo","Turnover","Employed","LastName","FirstName","Telephone","AllabolagUrl","EniroUrl"]
    self.exporter.start_exporting()
  def spider_closed(self, spider):
    self.exporter.finish_exporting()
    file = self.files.pop(spider)
    file.close()

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