Learn more  » Push, build, and install  RubyGems npm packages Python packages Maven artifacts PHP packages Go Modules Bower components Debian packages RPM packages NuGet packages

hemamaps / Scrapy   python

Repository URL to install this package:

Version: 1.1.1 

/ downloadermiddlewares / stats.py

from scrapy.exceptions import NotConfigured
from scrapy.utils.request import request_httprepr
from scrapy.utils.response import response_httprepr

class DownloaderStats(object):

    def __init__(self, stats):
        self.stats = stats

    @classmethod
    def from_crawler(cls, crawler):
        if not crawler.settings.getbool('DOWNLOADER_STATS'):
            raise NotConfigured
        return cls(crawler.stats)

    def process_request(self, request, spider):
        self.stats.inc_value('downloader/request_count', spider=spider)
        self.stats.inc_value('downloader/request_method_count/%s' % request.method, spider=spider)
        reqlen = len(request_httprepr(request))
        self.stats.inc_value('downloader/request_bytes', reqlen, spider=spider)

    def process_response(self, request, response, spider):
        self.stats.inc_value('downloader/response_count', spider=spider)
        self.stats.inc_value('downloader/response_status_count/%s' % response.status, spider=spider)
        reslen = len(response_httprepr(response))
        self.stats.inc_value('downloader/response_bytes', reslen, spider=spider)
        return response

    def process_exception(self, request, exception, spider):
        ex_class = "%s.%s" % (exception.__class__.__module__, exception.__class__.__name__)
        self.stats.inc_value('downloader/exception_count', spider=spider)
        self.stats.inc_value('downloader/exception_type_count/%s' % ex_class, spider=spider)