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 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)
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
self.server.execute_command('ZADD', self.key, score, data)
def pop(self, timeout=0):
"""
Pop a request
timeout not support in this queue class
"""
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 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):
"""Initialize the duplicates filter.
Parameters
----------
server : redis.StrictRedis
The redis server instance.
key : str
Redis key Where to store fingerprints.
debug : bool, optional
Whether to log filtered requests.
"""
self.server = server
self.key = key
self.debug = debug
self.logdupes = True
@classmethod
def from_settings(cls, settings):
"""Returns an instance from given settings.
This uses by default the key ``dupefilter:<timestamp>``. When using the
``scrapy_redis.scheduler.Scheduler`` class, this method is not used as
it needs to pass the spider name in the key.
Parameters
----------
settings : scrapy.settings.Settings
Returns
-------
RFPDupeFilter
A RFPDupeFilter instance.
"""
server = get_redis_from_settings(settings)
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):
"""Returns instance from crawler.
Parameters
----------
crawler : scrapy.crawler.Crawler
Returns
-------
RFPDupeFilter
Instance of RFPDupeFilter.
"""
return cls.from_settings(crawler.settings)
def request_seen(self, request):
"""Returns True if request was already seen.
Parameters
----------
request : scrapy.http.Request
Returns
-------
bool
"""
fp = self.request_fingerprint(request)
added = self.server.sadd(self.key, fp)
return added == 0
def request_fingerprint(self, request):
"""Returns a fingerprint for a given request.
Parameters
----------
request : scrapy.http.Request
Returns
-------
str
"""
return request_fingerprint(request)
def close(self, reason=''):
"""Delete data on close. Called by Scrapy's scheduler.
Parameters
----------
reason : str, optional
"""
self.clear()
def clear(self):
"""Clears fingerprints data."""
self.server.delete(self.key)
def log(self, request, spider):
"""Logs given request.
Parameters
----------
request : scrapy.http.Request
spider : scrapy.spiders.Spider
"""
if self.debug:
msg = "Filtered duplicate request: %(request) s"
self.logger.debug(msg, {'request': request}, extra={'spider': spider})
elif self.logdupes:
msg = ("Filtered duplicate request %(request) s"
"- no more duplicates will be shown"
"(see DUPEFILTER_DEBUG to show all duplicates)")
self.logger.debug(msg, {'request': request}, extra={'spider': spider})
self.logdupes = False
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
