scrapy pipeline导出csv乱码处理,关键点是要把编码格式改为utf-8-sig

from scrapy import signals
from scrapy.exporters import CsvItemExporter

class JsgovcspiderPipeline(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, encoding='utf-8-sig')
self.exporter.fields_to_export = ['project_name']
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

猜你喜欢

转载自www.cnblogs.com/jwr810/p/10415671.html