import logging
from twisted.internet import task
from scrapy import signals
from scrapy.exceptions import NotConfigured
logger = logging.getLogger(__name__)
[docs]class LogStats:
"""Log basic scraping stats periodically"""
def __init__(self, stats, interval=60.0):
self.stats = stats
self.interval = interval
self.multiplier = 60.0 / self.interval
self.task = None
@classmethod
def from_crawler(cls, crawler):
interval = crawler.settings.getfloat("LOGSTATS_INTERVAL")
if not interval:
raise NotConfigured
o = cls(crawler.stats, interval)
crawler.signals.connect(o.spider_opened, signal=signals.spider_opened)
crawler.signals.connect(o.spider_closed, signal=signals.spider_closed)
return o
def spider_opened(self, spider):
self.pagesprev = 0
self.itemsprev = 0
self.task = task.LoopingCall(self.log, spider)
self.task.start(self.interval)
def log(self, spider):
items = self.stats.get_value("item_scraped_count", 0)
pages = self.stats.get_value("response_received_count", 0)
irate = (items - self.itemsprev) * self.multiplier
prate = (pages - self.pagesprev) * self.multiplier
self.pagesprev, self.itemsprev = pages, items
msg = (
"Crawled %(pages)d pages (at %(pagerate)d pages/min), "
"scraped %(items)d items (at %(itemrate)d items/min)"
)
log_args = {
"pages": pages,
"pagerate": prate,
"items": items,
"itemrate": irate,
}
logger.info(msg, log_args, extra={"spider": spider})
def spider_closed(self, spider, reason):
if self.task and self.task.running:
self.task.stop()