大橙子网站建设,新征程启航
为企业提供网站建设、域名注册、服务器等服务
这篇文章主要介绍了python爬虫中Base Spider指的是什么,具有一定借鉴价值,需要的朋友可以参考下。希望大家阅读完这篇文章后大有收获。下面让小编带着大家一起了解一下。
创新互联是一家专注于成都做网站、网站设计与策划设计,府谷网站建设哪家好?创新互联做网站,专注于网站建设十载,网设计领域的专业建站公司;建站业务涵盖:府谷等地区。府谷做网站价格咨询:18980820575
当一个事物的个数很多的时候,我们会把它们归为一个群,比如人群之类的称呼。那对于python中的爬虫来说,我们想要获取数据,就需要大量的爬虫去支撑,不过这里我们肯定不能也给它们起一个群的称呼。同样我们会用类来表示,这就是我们今天要讲Base Spider,感兴趣的小伙伴也来看看这个爬虫中的类究竟是什么吧。
Base Spider
不在使用scrapy原有的Spider类,重写的redisSpider继承了Spider和RedisMixin这两个类,RedisMixin是用来从redis读取url的类。
当我们生成一个Spider继承RedisSpider时,调用setup_redis函数,这个函数会去连接redis数据库,然后会设置signals(信号):
一个是当spider空闲时候的signal,会调用spider_idle函数,这个函数调用schedule_next_request函数,保证spider是一直活着的状态,并且抛出DontCloseSpider异常。
一个是当抓到一个item时的signal,会调用item_scraped函数,这个函数会调用schedule_next_request函数,获取下一个request。
from scrapy import signals from scrapy.exceptions import DontCloseSpider from scrapy.spiders import Spider, CrawlSpider from . import connection, defaults from .utils import bytes_to_str class RedisMixin(object): """Mixin class to implement reading urls from a redis queue.""" redis_key = None redis_batch_size = None redis_encoding = None # Redis client placeholder. server = None def start_requests(self): """Returns a batch of start requests from redis.""" return self.next_requests() def setup_redis(self, crawler=None): """Setup redis connection and idle signal. This should be called after the spider has set its crawler object. """ if self.server is not None: return if crawler is None: # We allow optional crawler argument to keep backwards # compatibility. # XXX: Raise a deprecation warning. crawler = getattr(self, 'crawler', None) if crawler is None: raise ValueError("crawler is required") settings = crawler.settings if self.redis_key is None: self.redis_key = settings.get( 'REDIS_START_URLS_KEY', defaults.START_URLS_KEY, ) self.redis_key = self.redis_key % {'name': self.name} if not self.redis_key.strip(): raise ValueError("redis_key must not be empty") if self.redis_batch_size is None: # TODO: Deprecate this setting (REDIS_START_URLS_BATCH_SIZE). self.redis_batch_size = settings.getint( 'REDIS_START_URLS_BATCH_SIZE', settings.getint('CONCURRENT_REQUESTS'), ) try: self.redis_batch_size = int(self.redis_batch_size) except (TypeError, ValueError): raise ValueError("redis_batch_size must be an integer") if self.redis_encoding is None: self.redis_encoding = settings.get('REDIS_ENCODING', defaults.REDIS_ENCODING) self.logger.info("Reading start URLs from redis key '%(redis_key)s' " "(batch size: %(redis_batch_size)s, encoding: %(redis_encoding)s", self.__dict__) self.server = connection.from_settings(crawler.settings) # The idle signal is called when the spider has no requests left, # that's when we will schedule new requests from redis queue crawler.signals.connect(self.spider_idle, signal=signals.spider_idle) def next_requests(self): """Returns a request to be scheduled or none.""" use_set = self.settings.getbool('REDIS_START_URLS_AS_SET', defaults.START_URLS_AS_SET) fetch_one = self.server.spop if use_set else self.server.lpop # XXX: Do we need to use a timeout here? found = 0 # TODO: Use redis pipeline execution. while found < self.redis_batch_size: data = fetch_one(self.redis_key) if not data: # Queue empty. break req = self.make_request_from_data(data) if req: yield req found += 1 else: self.logger.debug("Request not made from data: %r", data) if found: self.logger.debug("Read %s requests from '%s'", found, self.redis_key) def make_request_from_data(self, data): """Returns a Request instance from data coming from Redis. By default, ``data`` is an encoded URL. You can override this method to provide your own message decoding. Parameters ---------- data : bytes Message from redis. """ url = bytes_to_str(data, self.redis_encoding) return self.make_requests_from_url(url) def schedule_next_requests(self): """Schedules a request if available""" # TODO: While there is capacity, schedule a batch of redis requests. for req in self.next_requests(): self.crawler.engine.crawl(req, spider=self) def spider_idle(self): """Schedules a request if available, otherwise waits.""" # XXX: Handle a sentinel to close the spider. self.schedule_next_requests() raise DontCloseSpider class RedisSpider(RedisMixin, Spider): """Spider that reads urls from redis queue when idle. Attributes ---------- redis_key : str (default: REDIS_START_URLS_KEY) Redis key where to fetch start URLs from.. redis_batch_size : int (default: CONCURRENT_REQUESTS) Number of messages to fetch from redis on each attempt. redis_encoding : str (default: REDIS_ENCODING) Encoding to use when decoding messages from redis queue. Settings -------- REDIS_START_URLS_KEY : str (default: ":start_urls") Default Redis key where to fetch start URLs from.. REDIS_START_URLS_BATCH_SIZE : int (deprecated by CONCURRENT_REQUESTS) Default number of messages to fetch from redis on each attempt. REDIS_START_URLS_AS_SET : bool (default: False) Use SET operations to retrieve messages from the redis queue. If False, the messages are retrieve using the LPOP command. REDIS_ENCODING : str (default: "utf-8") Default encoding to use when decoding messages from redis queue. """ @classmethod def from_crawler(self, crawler, *args, **kwargs): obj = super(RedisSpider, self).from_crawler(crawler, *args, **kwargs) obj.setup_redis(crawler) return obj class RedisCrawlSpider(RedisMixin, CrawlSpider): """Spider that reads urls from redis queue when idle. Attributes ---------- redis_key : str (default: REDIS_START_URLS_KEY) Redis key where to fetch start URLs from.. redis_batch_size : int (default: CONCURRENT_REQUESTS) Number of messages to fetch from redis on each attempt. redis_encoding : str (default: REDIS_ENCODING) Encoding to use when decoding messages from redis queue. Settings -------- REDIS_START_URLS_KEY : str (default: " :start_urls") Default Redis key where to fetch start URLs from.. REDIS_START_URLS_BATCH_SIZE : int (deprecated by CONCURRENT_REQUESTS) Default number of messages to fetch from redis on each attempt. REDIS_START_URLS_AS_SET : bool (default: True) Use SET operations to retrieve messages from the redis queue. REDIS_ENCODING : str (default: "utf-8") Default encoding to use when decoding messages from redis queue. """ @classmethod def from_crawler(self, crawler, *args, **kwargs): obj = super(RedisCrawlSpider, self).from_crawler(crawler, *args, **kwargs) obj.setup_redis(crawler) return obj
感谢你能够认真阅读完这篇文章,希望小编分享python爬虫中Base Spider指的是什么内容对大家有帮助,同时也希望大家多多支持创新互联,关注创新互联行业资讯频道,遇到问题就找创新互联,详细的解决方法等着你来学习!