发布于 2015-11-30 01:25:34 | 151 次阅读 | 评论: 0 | 来源: 网友投递
这里有新鲜出炉的Python3 官方中文指南,程序狗速度看过来!
Python编程语言
Python 是一种面向对象、解释型计算机程序设计语言,由Guido van Rossum于1989年底发明,第一个公开发行版发行于1991年。Python语法简洁而清晰,具有丰富和强大的类库。它常被昵称为胶水语言,它能够把用其他语言制作的各种模块(尤其是C/C++)很轻松地联结在一起。
本文实例讲述了Python自定义scrapy中间模块避免重复采集的方法。分享给大家供大家参考。具体如下:
from scrapy import log from scrapy.http import Request from scrapy.item import BaseItem from scrapy.utils.request import request_fingerprint from myproject.items import MyItem class 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)