mirror of https://github.com/scrapy/scrapy.git
58 lines
1.8 KiB
Python
58 lines
1.8 KiB
Python
import inspect
|
|
|
|
import six
|
|
|
|
from scrapy import log
|
|
from scrapy.spider import Spider
|
|
from scrapy.utils.misc import arg_to_iter
|
|
|
|
|
|
def iterate_spider_output(result):
|
|
return arg_to_iter(result)
|
|
|
|
|
|
def iter_spider_classes(module):
|
|
"""Return an iterator over all spider classes defined in the given module
|
|
that can be instantiated (ie. which have name)
|
|
"""
|
|
# this needs to be imported here until get rid of the spider manager
|
|
# singleton in scrapy.spider.spiders
|
|
from scrapy.spider import Spider
|
|
|
|
for obj in six.itervalues(vars(module)):
|
|
if inspect.isclass(obj) and \
|
|
issubclass(obj, Spider) and \
|
|
obj.__module__ == module.__name__ and \
|
|
getattr(obj, 'name', None):
|
|
yield obj
|
|
|
|
def spidercls_for_request(spiderloader, request, default_spidercls=None,
|
|
log_none=False, log_multiple=False):
|
|
"""Return a spider class that handles the given Request.
|
|
|
|
This will look for the spiders that can handle the given request (using
|
|
the spider loader) and return a Spider class if (and only if) there is
|
|
only one Spider able to handle the Request.
|
|
|
|
If multiple spiders (or no spider) are found, it will return the
|
|
default_spidercls passed. It can optionally log if multiple or no spiders
|
|
are found.
|
|
"""
|
|
snames = spiderloader.find_by_request(request)
|
|
if len(snames) == 1:
|
|
return spiderloader.load(snames[0])
|
|
|
|
if len(snames) > 1 and log_multiple:
|
|
log.msg(format='More than one spider can handle: %(request)s - %(snames)s',
|
|
level=log.ERROR, request=request, snames=', '.join(snames))
|
|
|
|
if len(snames) == 0 and log_none:
|
|
log.msg(format='Unable to find spider that handles: %(request)s',
|
|
level=log.ERROR, request=request)
|
|
|
|
return default_spidercls
|
|
|
|
|
|
class DefaultSpider(Spider):
|
|
name = 'default'
|