安装
pip3 install scrapy-redis
目标：帮助开发者实现分布式爬虫程序
class RFPDupeFilter(BaseDupeFilter): """Request Fingerprint duplicates filter""" def __init__(self, path=None, debug=False): self.fingerprints = set() @classmethod def from_settings(cls, settings): debug = settings.getbool('DUPEFILTER_DEBUG') return cls(job_dir(settings), debug) def request_seen(self, request): # 将request对象转换成唯一标识。 fp = self.request_fingerprint(request) # 判断在集合中是否存在，如果存在则返回True，表示已经访问过。 if fp in self.fingerprints: return True # 之前未访问过，将url添加到访问记录中。 self.fingerprints.add(fp) def request_fingerprint(self, request): return request_fingerprint(request)
class RFPDupeFilter(BaseDupeFilter): """Redis-based request duplicates filter. This class can also be used with default Scrapy's scheduler. """ logger = logger def __init__(self, server, key, debug=False): # self.server = redis连接 self.server = server # self.key = dupefilter:123912873234 self.key = key @classmethod def from_settings(cls, settings): # 读取配置，连接redis server = get_redis_from_settings(settings) # key = dupefilter:123912873234 key = defaults.DUPEFILTER_KEY % {'timestamp': int(time.time())} debug = settings.getbool('DUPEFILTER_DEBUG') return cls(server, key=key, debug=debug) @classmethod def from_crawler(cls, crawler): return cls.from_settings(crawler.settings) def request_seen(self, request): fp = self.request_fingerprint(request) # This returns the number of values added, zero if already exists. # self.server=redis连接 # 添加到redis集合中：1，添加工程；0，已经存在 added = self.server.sadd(self.key, fp) return added == 0 def request_fingerprint(self, request): return request_fingerprint(request) def close(self, reason=''): self.clear() def clear(self): """Clears fingerprints data.""" self.server.delete(self.key)
# 将request对象全部放到内存维护的队列：self.q = deque() # 将request对象全部放到硬盘维护的队列：文件操作 SCHEDULER_DISK_QUEUE = 'scrapy.squeues.PickleLifoDiskQueue' SCHEDULER_MEMORY_QUEUE = 'scrapy.squeues.LifoMemoryQueue' SCHEDULER_PRIORITY_QUEUE = 'queuelib.PriorityQueue' class Scheduler(object): def __init__(self, dupefilter, jobdir=None, dqclass=None, mqclass=None, logunser=False, stats=None, pqclass=None): self.df = dupefilter self.dqdir = self._dqdir(jobdir) self.pqclass = pqclass self.dqclass = dqclass self.mqclass = mqclass self.logunser = logunser self.stats = stats @classmethod def from_crawler(cls, crawler): settings = crawler.settings dupefilter_cls = load_object(settings['DUPEFILTER_CLASS']) dupefilter = dupefilter_cls.from_settings(settings) pqclass = load_object(settings['SCHEDULER_PRIORITY_QUEUE']) dqclass = load_object(settings['SCHEDULER_DISK_QUEUE']) mqclass = load_object(settings['SCHEDULER_MEMORY_QUEUE']) logunser = settings.getbool('LOG_UNSERIALIZABLE_REQUESTS', settings.getbool('SCHEDULER_DEBUG')) return cls(dupefilter, jobdir=job_dir(settings), logunser=logunser, stats=crawler.stats, pqclass=pqclass, dqclass=dqclass, mqclass=mqclass) def has_pending_requests(self): return len(self) > 0 def open(self, spider): self.spider = spider self.mqs = self.pqclass(self._newmq) self.dqs = self._dq() if self.dqdir else None return self.df.open() def close(self, reason): if self.dqs: prios = self.dqs.close() with open(join(self.dqdir, 'active.json'), 'w') as f: json.dump(prios, f) return self.df.close(reason) def enqueue_request(self, request): # request.dont_filter=False # self.df.request_seen(request): # - True,已经访问 # - False，未访问 # request.dont_filter=True，全部加入到调度器 if not request.dont_filter and self.df.request_seen(request): self.df.log(request, self.spider) return False # 如果往下走，把请求加入调度器 dqok = self._dqpush(request) if dqok: self.stats.inc_value('scheduler/enqueued/disk', spider=self.spider) else: self._mqpush(request) self.stats.inc_value('scheduler/enqueued/memory', spider=self.spider) self.stats.inc_value('scheduler/enqueued', spider=self.spider) return True def next_request(self): request = self.mqs.pop() if request: self.stats.inc_value('scheduler/dequeued/memory', spider=self.spider) else: request = self._dqpop() if request: self.stats.inc_value('scheduler/dequeued/disk', spider=self.spider) if request: self.stats.inc_value('scheduler/dequeued', spider=self.spider) return request def __len__(self): return len(self.dqs) + len(self.mqs) if self.dqs else len(self.mqs) def _dqpush(self, request): if self.dqs is None: return try: reqd = request_to_dict(request, self.spider) self.dqs.push(reqd, -request.priority) except ValueError as e: # non serializable request if self.logunser: msg = ("Unable to serialize request: %(request)s - reason:" " %(reason)s - no more unserializable requests will be" " logged (stats being collected)") logger.warning(msg, {'request': request, 'reason': e}, exc_info=True, extra={'spider': self.spider}) self.logunser = False self.stats.inc_value('scheduler/unserializable', spider=self.spider) return else: return True def _mqpush(self, request): self.mqs.push(request, -request.priority) def _dqpop(self): if self.dqs: d = self.dqs.pop() if d: return request_from_dict(d, self.spider) def _newmq(self, priority): return self.mqclass() def _newdq(self, priority): return self.dqclass(join(self.dqdir, 'p%s' % priority)) def _dq(self): activef = join(self.dqdir, 'active.json') if exists(activef): with open(activef) as f: prios = json.load(f) else: prios = () q = self.pqclass(self._newdq, startprios=prios) if q: logger.info("Resuming crawl (%(queuesize)d requests scheduled)", {'queuesize': len(q)}, extra={'spider': self.spider}) return q def _dqdir(self, jobdir): if jobdir: dqdir = join(jobdir, 'requests.queue') if not exists(dqdir): os.makedirs(dqdir) return dqdir
# 将请求通过pickle进行序列化，然后添加到redis： 列表或有序结合中。 SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.LifoQueue' class Scheduler(object): def __init__(self, server, persist=False, flush_on_start=False, queue_key=defaults.SCHEDULER_QUEUE_KEY, queue_cls=defaults.SCHEDULER_QUEUE_CLASS, dupefilter_key=defaults.SCHEDULER_DUPEFILTER_KEY, dupefilter_cls=defaults.SCHEDULER_DUPEFILTER_CLASS, idle_before_close=0, serializer=None): if idle_before_close < 0: raise TypeError("idle_before_close cannot be negative") self.server = server self.persist = persist self.flush_on_start = flush_on_start self.queue_key = queue_key self.queue_cls = queue_cls self.dupefilter_cls = dupefilter_cls self.dupefilter_key = dupefilter_key self.idle_before_close = idle_before_close self.serializer = serializer self.stats = None def __len__(self): return len(self.queue) @classmethod def from_settings(cls, settings): kwargs = { 'persist': settings.getbool('SCHEDULER_PERSIST'), 'flush_on_start': settings.getbool('SCHEDULER_FLUSH_ON_START'), 'idle_before_close': settings.getint('SCHEDULER_IDLE_BEFORE_CLOSE'), } # If these values are missing, it means we want to use the defaults. optional = { # TODO: Use custom prefixes for this settings to note that are # specific to scrapy-redis. 'queue_key': 'SCHEDULER_QUEUE_KEY', 'queue_cls': 'SCHEDULER_QUEUE_CLASS', 'dupefilter_key': 'SCHEDULER_DUPEFILTER_KEY', # We use the default setting name to keep compatibility. 'dupefilter_cls': 'DUPEFILTER_CLASS', 'serializer': 'SCHEDULER_SERIALIZER', } for name, setting_name in optional.items(): val = settings.get(setting_name) if val: kwargs[name] = val # Support serializer as a path to a module. if isinstance(kwargs.get('serializer'), six.string_types): kwargs['serializer'] = importlib.import_module(kwargs['serializer']) server = connection.from_settings(settings) # Ensure the connection is working. server.ping() return cls(server=server, **kwargs) @classmethod def from_crawler(cls, crawler): instance = cls.from_settings(crawler.settings) # FIXME: for now, stats are only supported from this constructor instance.stats = crawler.stats return instance def open(self, spider): self.spider = spider try: self.queue = load_object(self.queue_cls)( server=self.server, spider=spider, key=self.queue_key % {'spider': spider.name}, serializer=self.serializer, ) except TypeError as e: raise ValueError("Failed to instantiate queue class '%s': %s", self.queue_cls, e) try: self.df = load_object(self.dupefilter_cls)( server=self.server, key=self.dupefilter_key % {'spider': spider.name}, debug=spider.settings.getbool('DUPEFILTER_DEBUG'), ) except TypeError as e: raise ValueError("Failed to instantiate dupefilter class '%s': %s", self.dupefilter_cls, e) if self.flush_on_start: self.flush() # notice if there are requests already in the queue to resume the crawl if len(self.queue): spider.log("Resuming crawl (%d requests scheduled)" % len(self.queue)) def close(self, reason): if not self.persist: self.flush() def flush(self): self.df.clear() self.queue.clear() def enqueue_request(self, request): if not request.dont_filter and self.df.request_seen(request): self.df.log(request, self.spider) return False if self.stats: self.stats.inc_value('scheduler/enqueued/redis', spider=self.spider) self.queue.push(request) return True def next_request(self): block_pop_timeout = self.idle_before_close request = self.queue.pop(block_pop_timeout) if request and self.stats: self.stats.inc_value('scheduler/dequeued/redis', spider=self.spider) return request def has_pending_requests(self): return len(self) > 0
class Base(object): """Per-spider base queue class""" def __init__(self, server, spider, key, serializer=None): """Initialize per-spider redis queue. Parameters ---------- server : StrictRedis Redis client instance. spider : Spider Scrapy spider instance. key: str Redis key where to put and get messages. serializer : object Serializer object with ``loads`` and ``dumps`` methods. """ if serializer is None: # Backward compatibility. # TODO: deprecate pickle. serializer = picklecompat if not hasattr(serializer, 'loads'): raise TypeError("serializer does not implement 'loads' function: %r" % serializer) if not hasattr(serializer, 'dumps'): raise TypeError("serializer '%s' does not implement 'dumps' function: %r" % serializer) self.server = server self.spider = spider self.key = key % {'spider': spider.name} self.serializer = serializer def _encode_request(self, request): """Encode a request object""" obj = request_to_dict(request, self.spider) return self.serializer.dumps(obj) def _decode_request(self, encoded_request): """Decode an request previously encoded""" obj = self.serializer.loads(encoded_request) return request_from_dict(obj, self.spider) def __len__(self): """Return the length of the queue""" raise NotImplementedError def push(self, request): """Push a request""" raise NotImplementedError def pop(self, timeout=0): """Pop a request""" raise NotImplementedError def clear(self): """Clear queue/stack""" self.server.delete(self.key) class FifoQueue(Base): """Per-spider FIFO queue""" def __len__(self): """Return the length of the queue""" return self.server.llen(self.key) def push(self, request): """Push a request""" self.server.lpush(self.key, self._encode_request(request)) def pop(self, timeout=0): """Pop a request""" if timeout > 0: data = self.server.brpop(self.key, timeout) if isinstance(data, tuple): data = data[1] else: data = self.server.rpop(self.key) if data: return self._decode_request(data) class PriorityQueue(Base): """Per-spider priority queue abstraction using redis' sorted set""" def __len__(self): """Return the length of the queue""" return self.server.zcard(self.key) def push(self, request): """Push a request""" data = self._encode_request(request) score = -request.priority # We don't use zadd method as the order of arguments change depending on # whether the class is Redis or StrictRedis, and the option of using # kwargs only accepts strings, not bytes. self.server.execute_command('ZADD', self.key, score, data) def pop(self, timeout=0): """ Pop a request timeout not support in this queue class """ # use atomic range/remove using multi/exec pipe = self.server.pipeline() pipe.multi() pipe.zrange(self.key, 0, 0).zremrangebyrank(self.key, 0, 0) results, count = pipe.execute() if results: return self._decode_request(results[0]) class LifoQueue(Base): """Per-spider LIFO queue.""" def __len__(self): """Return the length of the stack""" return self.server.llen(self.key) def push(self, request): """Push a request""" self.server.lpush(self.key, self._encode_request(request)) def pop(self, timeout=0): """Pop a request""" if timeout > 0: data = self.server.blpop(self.key, timeout) if isinstance(data, tuple): data = data[1] else: data = self.server.lpop(self.key) if data: return self._decode_request(data) # TODO: Deprecate the use of these names. SpiderQueue = FifoQueue SpiderStack = LifoQueue SpiderPriorityQueue = PriorityQueue # 爬虫爬取数据时存在层级和优先级：爬虫中间件实现
使用scrapy-redis组件
# ############ 连接redis 信息 ################# REDIS_HOST = '127.0.0.1' # 主机名 REDIS_PORT = 6379 # 端口 # REDIS_URL = 'redis://user:pass@hostname:9001' # 连接URL（优先于以上配置） REDIS_PARAMS = {} # Redis连接参数 默认：REDIS_PARAMS = {'socket_timeout': 30,'socket_connect_timeout': 30,'retry_on_timeout': True,'encoding': REDIS_ENCODING,}） # REDIS_PARAMS['redis_cls'] = 'myproject.RedisClient' # 指定连接Redis的Python模块 默认：redis.StrictRedis REDIS_ENCODING = "utf-8" # 自定义去重规则 DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
# ############ 连接redis 信息 ################# REDIS_HOST = '127.0.0.1' # 主机名 REDIS_PORT = 6379 # 端口 # REDIS_URL = 'redis://user:pass@hostname:9001' # 连接URL（优先于以上配置） REDIS_PARAMS = {} # Redis连接参数 默认：REDIS_PARAMS = {'socket_timeout': 30,'socket_connect_timeout': 30,'retry_on_timeout': True,'encoding': REDIS_ENCODING,}） # REDIS_PARAMS['redis_cls'] = 'myproject.RedisClient' # 指定连接Redis的Python模块 默认：redis.StrictRedis REDIS_ENCODING = "utf-8" # 有引擎来执行：自定义调度器 SCHEDULER = "scrapy_redis.scheduler.Scheduler" SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.LifoQueue' # 默认使用优先级队列（默认广度优先），其他：PriorityQueue（有序集合），FifoQueue（列表）、LifoQueue（列表） SCHEDULER_QUEUE_KEY = '%(spider)s:requests' # 调度器中请求存放在redis中的key SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat" # 对保存到redis中的数据进行序列化，默认使用pickle SCHEDULER_PERSIST = True # 是否在关闭时候保留原来的调度器和去重记录，True=保留，False=清空 SCHEDULER_FLUSH_ON_START = False # 是否在开始之前清空 调度器和去重记录，True=清空，False=不清空 # SCHEDULER_IDLE_BEFORE_CLOSE = 10 # 去调度器中获取数据时，如果为空，最多等待时间（最后没数据，未获取到）。 SCHEDULER_DUPEFILTER_KEY = '%(spider)s:dupefilter' # 去重规则，在redis中保存时对应的key chouti:dupefilter SCHEDULER_DUPEFILTER_CLASS = 'scrapy.dupefilter.RFPDupeFilter' # 去重规则对应处理的类 # 去重规则对应处理的类 DUPEFILTER_DEBUG = False
# ############ 连接redis 信息 ################# REDIS_HOST = '127.0.0.1' # 主机名 REDIS_PORT = 6379 # 端口 # REDIS_URL = 'redis://user:pass@hostname:9001' # 连接URL（优先于以上配置） REDIS_PARAMS = {} # Redis连接参数 默认：REDIS_PARAMS = {'socket_timeout': 30,'socket_connect_timeout': 30,'retry_on_timeout': True,'encoding': REDIS_ENCODING,}） # REDIS_PARAMS['redis_cls'] = 'myproject.RedisClient' # 指定连接Redis的Python模块 默认：redis.StrictRedis REDIS_ENCODING = "utf-8" # 有引擎来执行：自定义调度器 SCHEDULER = "scrapy_redis.scheduler.Scheduler" SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.LifoQueue' # 默认使用优先级队列（默认广度优先），其他：PriorityQueue（有序集合），FifoQueue（列表）、LifoQueue（列表） SCHEDULER_QUEUE_KEY = '%(spider)s:requests' # 调度器中请求存放在redis中的key SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat" # 对保存到redis中的数据进行序列化，默认使用pickle SCHEDULER_PERSIST = True # 是否在关闭时候保留原来的调度器和去重记录，True=保留，False=清空 SCHEDULER_FLUSH_ON_START = False # 是否在开始之前清空 调度器和去重记录，True=清空，False=不清空 # SCHEDULER_IDLE_BEFORE_CLOSE = 10 # 去调度器中获取数据时，如果为空，最多等待时间（最后没数据，未获取到）。 SCHEDULER_DUPEFILTER_KEY = '%(spider)s:dupefilter' # 去重规则，在redis中保存时对应的key chouti:dupefilter SCHEDULER_DUPEFILTER_CLASS = 'scrapy_redis.dupefilter.RFPDupeFilter' # 去重规则对应处理的类 DUPEFILTER_DEBUG = False
# ############ 连接redis 信息 ################# REDIS_HOST = '127.0.0.1' # 主机名 REDIS_PORT = 6379 # 端口 # REDIS_URL = 'redis://user:pass@hostname:9001' # 连接URL（优先于以上配置） REDIS_PARAMS = {} # Redis连接参数 默认：REDIS_PARAMS = {'socket_timeout': 30,'socket_connect_timeout': 30,'retry_on_timeout': True,'encoding': REDIS_ENCODING,}） # REDIS_PARAMS['redis_cls'] = 'myproject.RedisClient' # 指定连接Redis的Python模块 默认：redis.StrictRedis REDIS_ENCODING = "utf-8" ITEM_PIPELINES = { 'scrapy_redis.pipelines.RedisPipeline': 300, }
DIS_HOST = '127.0.0.1' # 主机名 REDIS_PORT = 6379 # 端口 # REDIS_URL = 'redis://user:pass@hostname:9001' # 连接URL（优先于以上配置） REDIS_PARAMS = {} # Redis连接参数 默认：REDIS_PARAMS = {'socket_timeout': 30,'socket_connect_timeout': 30,'retry_on_timeout': True,'encoding': REDIS_ENCODING,}） # REDIS_PARAMS['redis_cls'] = 'myproject.RedisClient' # 指定连接Redis的Python模块 默认：redis.StrictRedis REDIS_ENCODING = "utf-8" DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter" # 有引擎来执行：自定义调度器 SCHEDULER = "scrapy_redis.scheduler.Scheduler" SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.LifoQueue' # 默认使用优先级队列（默认广度优先），其他：PriorityQueue（有序集合），FifoQueue（列表）、LifoQueue（列表） SCHEDULER_QUEUE_KEY = '%(spider)s:requests' # 调度器中请求存放在redis中的key SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat" # 对保存到redis中的数据进行序列化，默认使用pickle SCHEDULER_PERSIST = True # 是否在关闭时候保留原来的调度器和去重记录，True=保留，False=清空 SCHEDULER_FLUSH_ON_START = False # 是否在开始之前清空 调度器和去重记录，True=清空，False=不清空 # SCHEDULER_IDLE_BEFORE_CLOSE = 10 # 去调度器中获取数据时，如果为空，最多等待时间（最后没数据，未获取到）。 SCHEDULER_DUPEFILTER_KEY = '%(spider)s:dupefilter' # 去重规则，在redis中保存时对应的key chouti:dupefilter SCHEDULER_DUPEFILTER_CLASS = 'scrapy_redis.dupefilter.RFPDupeFilter' # 去重规则对应处理的类 DUPEFILTER_DEBUG = False
# 配置： REDIS_START_URLS_BATCH_SIZE = 1 # REDIS_START_URLS_AS_SET = True # 把起始url放到redis的集合 REDIS_START_URLS_AS_SET = False # 把起始url放到redis的列表 # 爬虫： from scrapy_redis.spiders import RedisSpider from scrapy.http import Request from ..items import WenwenItem class ChoutiSpider(RedisSpider): name = 'chouti' allowed_domains = ['chouti.com'] def parse(self, response): # 随着深度的增加、优先级一直在递减 print(response) # 放置起始URL： import redis conn = redis.Redis(host='127.0.0.1', port=6379) # 起始url的Key： chouti:start_urls conn.lpush("chouti:start_urls", 'https://dig.chouti.com/r/ask/hot/12')
PS：深度和优先级相关
DEPTH_PRIORITY = 1
