还是用xml的模板爬xml 来的直接。
TestItem in items.py:
class TestItem(scrapy.Item): id = scrapy.Field() name = scrapy.Field() description = scrapy.Field()
main:
from scrapy import log
from scrapy.contrib.spiders import XMLFeedSpider
from myproject.items import TestItem
class MySpider(XMLFeedSpider):
name = 'example'
start_urls = ['portfolio xii xml']
iterator = 'xml' # This is actually unnecessary,since it's the default value
itertag = 'PortfolioStatistics' #Name of Parent Node
def parse_node(self,response,node):
item = TestItem()
item['id'] = node.xpath('@_SalePosition').extract() #Get Parent Node Attribute
item['name'] = node.xpath('EquityStyle/EquityStyleCoreValue/StyleBox/text()').extract() #Get son of grandson
item['description'] = node.xpath('BondStatistics/EffectiveDuration/text()').extract() #Get Grandson
return item
Output: [ {“description”: [“0.53”],“name”: [“6”],“id”: [“L”]} ]
