mirror of https://github.com/scrapy/scrapy.git
improved SpiderMiddleware's docstrings
--HG-- extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40192
This commit is contained in:
parent
c9cafd5c43
commit
037e6c2125
|
|
@ -1,12 +1,14 @@
|
|||
"""
|
||||
Limits the scheduler request queue from the point of view of the spider.
|
||||
That is, if the scheduler queue contains an equal or greater ammount of
|
||||
requests than the specified limit, the further requests generated by the
|
||||
spider will be ignored.
|
||||
RequestLimitMiddleware: Limits the scheduler request queue from the point of
|
||||
view of the spider. That is, if the scheduler queue contains an equal or
|
||||
greater ammount of requests than the specified limit, the new requests
|
||||
(generated by the spider) will be ignored.
|
||||
|
||||
The limit is setted from the spider attribute "requests_queue_size". If not
|
||||
found, from the scrapy setting "REQUESTS_QUEUE_SIZE". If not found, no limit
|
||||
will be applied. If given a value of 0, no limit will be applied.
|
||||
"""
|
||||
|
||||
from scrapy.core.engine import scrapyengine
|
||||
from scrapy.conf import settings
|
||||
from scrapy.http import Request
|
||||
|
|
|
|||
|
|
@ -1,3 +1,8 @@
|
|||
"""
|
||||
OffsiteMiddleware: Filters out Requests for URLs outside the domains covered by
|
||||
the spider.
|
||||
"""
|
||||
|
||||
from scrapy.core import log
|
||||
from scrapy.http import Request
|
||||
from scrapy.utils.url import url_is_from_spider
|
||||
|
|
|
|||
|
|
@ -1,7 +1,11 @@
|
|||
"""
|
||||
RefererMiddleware: populates Request referer field, based on the Response which
|
||||
originated it.
|
||||
"""
|
||||
|
||||
from scrapy.core import log
|
||||
from scrapy.http import Request
|
||||
|
||||
|
||||
class CrawlMiddleware(object):
|
||||
def process_result(self, response, result, spider):
|
||||
def _set_referer(r):
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
"""
|
||||
Scrapemiddlware to restrict crawling to only some particular URLs
|
||||
RestrictMiddleware: restricts crawling to fixed set of particular URLs
|
||||
"""
|
||||
|
||||
from scrapy.http import Request
|
||||
|
|
|
|||
|
|
@ -1,11 +1,13 @@
|
|||
"""
|
||||
UrlLengthMiddleware: Filters out requests with URLs longer than URLLENGTH_LIMIT
|
||||
"""
|
||||
|
||||
from scrapy.core import log
|
||||
from scrapy.http import Request
|
||||
from scrapy.core.exceptions import NotConfigured
|
||||
from scrapy.conf import settings
|
||||
|
||||
class UrlLengthMiddleware(object):
|
||||
"""This middleware discard requests with URLs longer than URLLENGTH_LIMIT"""
|
||||
|
||||
def __init__(self):
|
||||
self.maxlength = settings.getint('URLLENGTH_LIMIT')
|
||||
if not self.maxlength:
|
||||
|
|
|
|||
Loading…
Reference in New Issue