重庆分公司,新征程启航
为企业提供网站建设、域名注册、服务器等服务
这篇文章给大家分享的是有关python分布式爬虫中scrapy.spider的使用示例的内容。小编觉得挺实用的,因此分享给大家做个参考。一起跟随小编过来看看吧。
创新互联主要从事成都网站制作、做网站、网页设计、企业做网站、公司建网站等业务。立足成都服务宜阳,10年网站建设经验,价格优惠、服务专业,欢迎来电咨询建站服务:18982081108源码:
""" Base class for Scrapy spiders See documentation in docs/topics/spiders.rst """ import logging import warnings from scrapy import signals from scrapy.http import Request from scrapy.utils.trackref import object_ref from scrapy.utils.url import url_is_from_spider from scrapy.utils.deprecate import create_deprecated_class from scrapy.exceptions import ScrapyDeprecationWarning from scrapy.utils.deprecate import method_is_overridden class Spider(object_ref): """Base class for scrapy spiders. All spiders must inherit from this class. """ name = None custom_settings = None def __init__(self, name=None, **kwargs): if name is not None: self.name = name elif not getattr(self, 'name', None): raise ValueError("%s must have a name" % type(self).__name__) self.__dict__.update(kwargs) if not hasattr(self, 'start_urls'): self.start_urls = [] @property def logger(self): logger = logging.getLogger(self.name) return logging.LoggerAdapter(logger, {'spider': self}) def log(self, message, level=logging.DEBUG, **kw): """Log the given message at the given log level This helper wraps a log call to the logger within the spider, but you can use it directly (e.g. Spider.logger.info('msg')) or use any other Python logger too. """ self.logger.log(level, message, **kw) @classmethod def from_crawler(cls, crawler, *args, **kwargs): spider = cls(*args, **kwargs) spider._set_crawler(crawler) return spider def set_crawler(self, crawler): warnings.warn("set_crawler is deprecated, instantiate and bound the " "spider to this crawler with from_crawler method " "instead.", category=ScrapyDeprecationWarning, stacklevel=2) assert not hasattr(self, 'crawler'), "Spider already bounded to a " \ "crawler" self._set_crawler(crawler) def _set_crawler(self, crawler): self.crawler = crawler self.settings = crawler.settings crawler.signals.connect(self.close, signals.spider_closed) def start_requests(self): cls = self.__class__ if method_is_overridden(cls, Spider, 'make_requests_from_url'): warnings.warn( "Spider.make_requests_from_url method is deprecated; it " "won't be called in future Scrapy releases. Please " "override Spider.start_requests method instead (see %s.%s)." % ( cls.__module__, cls.__name__ ), ) for url in self.start_urls: yield self.make_requests_from_url(url) else: for url in self.start_urls: yield Request(url, dont_filter=True) def make_requests_from_url(self, url): """ This method is deprecated. """ return Request(url, dont_filter=True) def parse(self, response): raise NotImplementedError('{}.parse callback is not defined'.format(self.__class__.__name__)) @classmethod def update_settings(cls, settings): settings.setdict(cls.custom_settings or {}, priority='spider') @classmethod def handles_request(cls, request): return url_is_from_spider(request.url, cls) @staticmethod def close(spider, reason): closed = getattr(spider, 'closed', None) if callable(closed): return closed(reason) def __str__(self): return "<%s %r at 0x%0x>" % (type(self).__name__, self.name, id(self)) __repr__ = __str__ BaseSpider = create_deprecated_class('BaseSpider', Spider) class ObsoleteClass(object): def __init__(self, message): self.message = message def __getattr__(self, name): raise AttributeError(self.message) spiders = ObsoleteClass( '"from scrapy.spider import spiders" no longer works - use ' '"from scrapy.spiderloader import SpiderLoader" and instantiate ' 'it with your project settings"' ) # Top-level imports from scrapy.spiders.crawl import CrawlSpider, Rule from scrapy.spiders.feed import XMLFeedSpider, CSVFeedSpider from scrapy.spiders.sitemap import SitemapSpider
其中需要关注的是name(爬虫名字)、start_urls(抓取的起始url列表)、allowed_domains(限定抓取的url所在域名)、start_requests(开始抓取的方法)
name、start_urls、allowed_domains是属性,在创建创建项目的时候已经建好了,稍作修改即可。start_requests是起始的抓取方法,一般是默认的遍历start_urls列表生成Request对象,在scrapy中需要登录的时候可以复写该方法,这个比较简单不在赘述。
感谢各位的阅读!关于python分布式爬虫中scrapy.spider的使用示例就分享到这里了,希望以上内容可以对大家有一定的帮助,让大家可以学到更多知识。如果觉得文章不错,可以把它分享出去让更多的人看到吧!