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 

/ core / downloader / handlers / __init__.py

"""Download handlers for different schemes"""

import logging
from twisted.internet import defer
import six
from scrapy.exceptions import NotSupported, NotConfigured
from scrapy.utils.httpobj import urlparse_cached
from scrapy.utils.misc import load_object
from scrapy.utils.python import without_none_values
from scrapy import signals


logger = logging.getLogger(__name__)


class DownloadHandlers(object):

    def __init__(self, crawler):
        self._crawler = crawler
        self._schemes = {}  # stores acceptable schemes on instancing
        self._handlers = {}  # stores instanced handlers for schemes
        self._notconfigured = {}  # remembers failed handlers
        handlers = without_none_values(
            crawler.settings.getwithbase('DOWNLOAD_HANDLERS'))
        for scheme, clspath in six.iteritems(handlers):
            self._schemes[scheme] = clspath

        crawler.signals.connect(self._close, signals.engine_stopped)

    def _get_handler(self, scheme):
        """Lazy-load the downloadhandler for a scheme
        only on the first request for that scheme.
        """
        if scheme in self._handlers:
            return self._handlers[scheme]
        if scheme in self._notconfigured:
            return None
        if scheme not in self._schemes:
            self._notconfigured[scheme] = 'no handler available for that scheme'
            return None

        path = self._schemes[scheme]
        try:
            dhcls = load_object(path)
            dh = dhcls(self._crawler.settings)
        except NotConfigured as ex:
            self._notconfigured[scheme] = str(ex)
            return None
        except Exception as ex:
            logger.error('Loading "%(clspath)s" for scheme "%(scheme)s"',
                         {"clspath": path, "scheme": scheme},
                         exc_info=True,  extra={'crawler': self._crawler})
            self._notconfigured[scheme] = str(ex)
            return None
        else:
            self._handlers[scheme] = dh
        return self._handlers[scheme]

    def download_request(self, request, spider):
        scheme = urlparse_cached(request).scheme
        handler = self._get_handler(scheme)
        if not handler:
            raise NotSupported("Unsupported URL scheme '%s': %s" %
                               (scheme, self._notconfigured[scheme]))
        return handler.download_request(request, spider)

    @defer.inlineCallbacks
    def _close(self, *_a, **_kw):
        for dh in self._handlers.values():
            if hasattr(dh, 'close'):
                yield dh.close()