"""
Scrapy extension for collecting scraping stats
"""
import logging
import pprint
logger = logging.getLogger(__name__)
[docs]class StatsCollector:
def __init__(self, crawler):
self._dump = crawler.settings.getbool("STATS_DUMP")
self._stats = {}
[docs] def get_value(self, key, default=None, spider=None):
return self._stats.get(key, default)
[docs] def get_stats(self, spider=None):
return self._stats
[docs] def set_value(self, key, value, spider=None):
self._stats[key] = value
[docs] def set_stats(self, stats, spider=None):
self._stats = stats
[docs] def inc_value(self, key, count=1, start=0, spider=None):
d = self._stats
d[key] = d.setdefault(key, start) + count
[docs] def max_value(self, key, value, spider=None):
self._stats[key] = max(self._stats.setdefault(key, value), value)
[docs] def min_value(self, key, value, spider=None):
self._stats[key] = min(self._stats.setdefault(key, value), value)
[docs] def clear_stats(self, spider=None):
self._stats.clear()
[docs] def open_spider(self, spider):
pass
[docs] def close_spider(self, spider, reason):
if self._dump:
logger.info(
"Dumping Scrapy stats:\n" + pprint.pformat(self._stats),
extra={"spider": spider},
)
self._persist_stats(self._stats, spider)
def _persist_stats(self, stats, spider):
pass
[docs]class MemoryStatsCollector(StatsCollector):
def __init__(self, crawler):
super().__init__(crawler)
self.spider_stats = {}
def _persist_stats(self, stats, spider):
self.spider_stats[spider.name] = stats
[docs]class DummyStatsCollector(StatsCollector):
def get_value(self, key, default=None, spider=None):
return default
def set_value(self, key, value, spider=None):
pass
def set_stats(self, stats, spider=None):
pass
def inc_value(self, key, count=1, start=0, spider=None):
pass
def max_value(self, key, value, spider=None):
pass
def min_value(self, key, value, spider=None):
pass