Python CsvItemExporter.export_item方法代码示例

# 需要导入模块: from scrapy.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
class JsonExportPipeline(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_data.xml' % spider.name, 'w+b')
        import os
        filePath = os.path.dirname(__file__)
        outputDir = filePath +'/output/'
        file = open(outputDir + '%s_data.csv' % spider.name, 'w+b')
        self.files[spider] = file
#         self.exporter = JsonItemExporter(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):
        self.exporter.export_item(item)
        return item

# 需要导入模块: from scrapy.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
class CsvExportPipeline(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_societies.csv' % spider.name, 'w+b')
        self.files[spider] = file
        self.exporter = CsvItemExporter(file)
        self.exporter.fields_to_export = ['name', 'president', 'email', 'url', 'facebook', 'membership', 'about',
                                          'date_established']
        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.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
class CSVExportPipeline(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' % spider.nameOfFile, 'w+b')
        self.files[spider] = file
        self.exporter = CsvItemExporter(file)

        self.exporter.fields_to_export = ['originalString', 'translatedString']

        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.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
class WebcrawlerPipeline(object):
    def __init__ (self):
        self.files = {}
        pass
    
    @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_urls.txt" % (spider.name), "w+b")
        self.files[spider] = file
        self.exporter = CsvItemExporter(file, include_headers_line=False)
        self.exporter.start_exporting()
        pass
    
    def spider_closed(self, spider):
        self.exporter.finish_exporting()
        file = self.files.pop(spider)
        file.close()
        pass
    
    def process_item(self, item, spider):
        self.exporter.export_item(item)
        return item
    pass

# 需要导入模块: from scrapy.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
class CsvExportPipeline(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('vagas.csv', 'wb')
        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):

        self.exporter.export_item(item)

        return item

# 需要导入模块: from scrapy.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
class CSVWriterPipeline(object):
    
    def __init__(self,filename):
        self.filename = filename
        
    @classmethod
    def from_crawler(cls, crawler):
        settings = crawler.settings
        filename = settings.get('OUTPUT_FILE')
        pipeline = cls(filename)
        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(self.filename, 'w+b')
        self.exporter = CsvItemExporter(self.file,include_headers_line=True)
        self.exporter.encoding='utf-8'
        self.exporter.start_exporting()

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

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

# 需要导入模块: from scrapy.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [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,delimiter='\t')
        self.exporter.fields_to_export = ['userId','bookId','name','rating','relativeRating','booklistNum']
        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.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
class catalogscraperPipeline(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 = ["title"]
        #'subject', 'description', 'creator', 'source', 'published', 'rights', 'citation', 'url']
        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.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
class CsvExportPipeline(object):
    """
    app.pipelines.exporter_csv.CsvExportPipeline
    """
    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):
        file_csv = open('%s_items.csv' % spider.name, 'w+b')
        self.files[spider] = file_csv
        self.exporter = CsvItemExporter(file_csv)
        self.exporter.start_exporting()

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

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

# 需要导入模块: from scrapy.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
class DumpToFile(object):
    """
    Dump harvested data into flat file, no other logic is implemented here
    (it's "Dump" :-)
    """
    def __init__(self):
        self.files = {}
        self.counter = 0

    @classmethod
    def from_crawler(cls, crawler):
        pipeline = cls()
        # TODO: verify if still needed for registration of spider_closed/opened event?
        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):
        filename = spider.get_dump_filepath()
        f = open(filename, 'w')
        self.files[spider.name] = f
        # by default csv module uses Windows-style line terminators (\r\n)
        self.exporter = CsvItemExporter(f, include_headers_line=True, delimiter='|', lineterminator='\n')
        self.exporter.start_exporting()

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

    def process_item(self, item, spider):
        self.exporter.export_item(item)
        # for counter, could set att in spider at closing
        self.counter += 1
        return item

# 需要导入模块: from scrapy.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [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 = ["filename", "titel", "publicatie", "dossiernummer", "organisatie", "publicatiedatum", "publicatietype", "file_urls"]
    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.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
 def assertExportResult(self, item, expected, **kwargs):
     fp = BytesIO()
     ie = CsvItemExporter(fp, **kwargs)
     ie.start_exporting()
     ie.export_item(item)
     ie.finish_exporting()
     self.assertCsvEqual(fp.getvalue(), expected)

# 需要导入模块: from scrapy.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
class AmazonCsvPipeline(object):
    def open_spider(self, spider):
        # 保存csv数据的文件对象
        self.f = open("Amazon_goods_crawl.csv", "w")
        # 创建csv文件读写对象
        self.csv_exporter = CsvItemExporter(self.f)
        # 开始进行csv文件读写
        self.csv_exporter.start_exporting()
        # 根据商品标题进行去重处理
        self.add_title = set()

    def process_item(self, item, spider):
        if item['title'] in self.add_title:
            print u'[EEROR] 数据已保存，勿重复%s'% item['title']
        else:
            self.add_title.add(item['title'])
            # 每次写入一个item数据
            # print u'[INFO] 正在写入csv文件中%s'% item['title']
            self.csv_exporter.export_item(item)
        return item

    def close_spider(self, spider):
        # 结束csv文件读写
        # print u'[INFO] 写入csv文件已完成'
        self.csv_exporter.finish_exporting()
        # 关闭文件
        self.f.close()

# 需要导入模块: from scrapy.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
 def test_header_export_two_items(self):
     for item in [self.i, dict(self.i)]:
         output = BytesIO()
         ie = CsvItemExporter(output)
         ie.start_exporting()
         ie.export_item(item)
         ie.export_item(item)
         ie.finish_exporting()
         self.assertCsvEqual(output.getvalue(), 'age,name\r\n22,John\xc2\xa3\r\n22,John\xc2\xa3\r\n')

# 需要导入模块: from scrapy.exporters import CsvItemExporter [as 别名]
# 或者: from scrapy.exporters.CsvItemExporter import export_item [as 别名]
class FashionnovaPipeline(object):
    def __init__(self):
        self.filename = 'fashionnova.csv'
    def open_spider(self, spider):
        self.csvfile = open(self.filename, 'wb')
        self.exporter = CsvItemExporter(self.csvfile)
        self.exporter.start_exporting()
    def close_spider(self, spider):
        self.exporter.finish_exporting()
        self.csvfile.close()
    def process_item(self, item, spider):
        self.exporter.export_item(item)
        return item