本文實例講述了Python自定義scrapy中間模塊避免重復采集的方法。分享給大家供大家參考。具體如下：

from scrapy import logfrom scrapy.http import Requestfrom scrapy.item import BaseItemfrom scrapy.utils.request import request_fingerprintfrom myproject.items import MyItemclass IgnoreVisitedItems(object):  """Middleware to ignore re-visiting item pages if they  were already visited before.   The requests to be filtered by have a meta['filter_visited']  flag enabled and optionally define an id to use   for identifying them, which defaults the request fingerprint,  although you'd want to use the item id,  if you already have it beforehand to make it more robust.  """  FILTER_VISITED = 'filter_visited'  VISITED_ID = 'visited_id'  CONTEXT_KEY = 'visited_ids'  def process_spider_output(self, response, result, spider):    context = getattr(spider, 'context', {})    visited_ids = context.setdefault(self.CONTEXT_KEY, {})    ret = []    for x in result:      visited = False      if isinstance(x, Request):        if self.FILTER_VISITED in x.meta:          visit_id = self._visited_id(x)          if visit_id in visited_ids:            log.msg("Ignoring already visited: %s" % x.url,                level=log.INFO, spider=spider)            visited = True      elif isinstance(x, BaseItem):        visit_id = self._visited_id(response.request)        if visit_id:          visited_ids[visit_id] = True          x['visit_id'] = visit_id          x['visit_status'] = 'new'      if visited:        ret.append(MyItem(visit_id=visit_id, visit_status='old'))      else:        ret.append(x)    return ret  def _visited_id(self, request):    return request.meta.get(self.VISITED_ID) or request_fingerprint(request)

希望本文所述對大家的Python程序設計有所幫助。