Блог

Я использую Scrapy с BloomFilter, и через 10 минут у меня возникает эта ошибка в цикле :

 2016-10-03 18:03:34 [twisted] CRITICAL: 
Traceback (most recent call last):
  File "/usr/local/lib/python2.7/dist-packages/twisted/internet/task.py", line 517, in _oneWorkUnit
    result = next(self._iterator)
  File "/usr/local/lib/python2.7/dist-packages/scrapy/utils/defer.py", line 63, in <genexpr>
    work = (callable(elem, *args, **named) for elem in iterable)
  File "/usr/local/lib/python2.7/dist-packages/scrapy/core/scraper.py", line 183, in _process_spidermw_output
    self.crawler.engine.crawl(request=output, spider=spider)
  File "/usr/local/lib/python2.7/dist-packages/scrapy/core/engine.py", line 209, in crawl
    self.schedule(request, spider)
  File "/usr/local/lib/python2.7/dist-packages/scrapy/core/engine.py", line 215, in schedule
    if not self.slot.scheduler.enqueue_request(request):
  File "/usr/local/lib/python2.7/dist-packages/scrapy/core/scheduler.py", line 54, in enqueue_request
    if not request.dont_filter and self.df.request_seen(request):
  File "dirbot/custom_filters.py", line 20, in request_seen
    self.fingerprints.add(fp)
  File "/usr/local/lib/python2.7/dist-packages/pybloom/pybloom.py", line 182, in add
    raise IndexError("BloomFilter is at capacity")
IndexError: BloomFilter is at capacity
  

filter.py :

 from pybloom import BloomFilter
from scrapy.utils.job import job_dir
from scrapy.dupefilters import BaseDupeFilter

class BLOOMDupeFilter(BaseDupeFilter):
    """Request Fingerprint duplicates filter"""

    def __init__(self, path=None):
        self.file = None
        self.fingerprints = BloomFilter(2000000, 0.00001)

    @classmethod
    def from_settings(cls, settings):
        return cls(job_dir(settings))

    def request_seen(self, request):
        fp = request.url
        if fp in self.fingerprints:
            return True
        self.fingerprints.add(fp)

    def close(self, reason):
        self.fingerprints = None
  

Я ищу в Google все возможности, но ничего не работает.
Спасибо за вашу помощь.

Используйте pybloom.ScalableBloomFilter вместо BloomFilter .

 from pybloom import ScalableBloomFilter
from scrapy.utils.job import job_dir
from scrapy.dupefilters import BaseDupeFilter

class BLOOMDupeFilter(BaseDupeFilter):
    """Request Fingerprint duplicates filter"""

    def __init__(self, 
                 path=None, 
                 initial_capacity=2000000, 
                 error_rate=0.00001,
                 mode=ScalableBloomFilter.SMALL_SET_GROWTH):
        self.file = None
        self.fingerprints = ScalableBloomFilter(
            initial_capacity, error_rate, mode)