mirror of https://github.com/scrapy/scrapy.git
87 lines
2.4 KiB
Python
87 lines
2.4 KiB
Python
"""
|
|
Base class for Scrapy spiders
|
|
|
|
See documentation in docs/topics/spiders.rst
|
|
"""
|
|
from scrapy import log
|
|
from scrapy.http import Request
|
|
from scrapy.utils.trackref import object_ref
|
|
from scrapy.utils.url import url_is_from_spider
|
|
from scrapy.utils.deprecate import warn_when_subclassed
|
|
|
|
|
|
class Spider(object_ref):
|
|
"""Base class for scrapy spiders. All spiders must inherit from this
|
|
class.
|
|
"""
|
|
|
|
name = None
|
|
|
|
def __init__(self, name=None, **kwargs):
|
|
if name is not None:
|
|
self.name = name
|
|
elif not getattr(self, 'name', None):
|
|
raise ValueError("%s must have a name" % type(self).__name__)
|
|
self.__dict__.update(kwargs)
|
|
if not hasattr(self, 'start_urls'):
|
|
self.start_urls = []
|
|
|
|
def log(self, message, level=log.DEBUG, **kw):
|
|
"""Log the given messages at the given log level. Always use this
|
|
method to send log messages from your spider
|
|
"""
|
|
log.msg(message, spider=self, level=level, **kw)
|
|
|
|
def set_crawler(self, crawler):
|
|
assert not hasattr(self, '_crawler'), "Spider already bounded to %s" % crawler
|
|
self._crawler = crawler
|
|
|
|
@property
|
|
def crawler(self):
|
|
assert hasattr(self, '_crawler'), "Spider not bounded to any crawler"
|
|
return self._crawler
|
|
|
|
@property
|
|
def settings(self):
|
|
return self.crawler.settings
|
|
|
|
def start_requests(self):
|
|
for url in self.start_urls:
|
|
yield self.make_requests_from_url(url)
|
|
|
|
def make_requests_from_url(self, url):
|
|
return Request(url, dont_filter=True)
|
|
|
|
def parse(self, response):
|
|
raise NotImplementedError
|
|
|
|
@classmethod
|
|
def handles_request(cls, request):
|
|
return url_is_from_spider(request.url, cls)
|
|
|
|
def __str__(self):
|
|
return "<%s %r at 0x%0x>" % (type(self).__name__, self.name, id(self))
|
|
|
|
__repr__ = __str__
|
|
|
|
|
|
class BaseSpider(Spider):
|
|
__metaclass__ = warn_when_subclassed(
|
|
4, # == len([object, object_ref, Spider, BaseSpider])
|
|
"scrapy.spider.BaseSpider was deprecated. "
|
|
"Please inherit from scrapy.spider.Spider."
|
|
)
|
|
|
|
|
|
class ObsoleteClass(object):
|
|
def __init__(self, message):
|
|
self.message = message
|
|
|
|
def __getattr__(self, name):
|
|
raise AttributeError(self.message)
|
|
|
|
spiders = ObsoleteClass("""
|
|
"from scrapy.spider import spiders" no longer works - use "from scrapy.project import crawler" and then access crawler.spiders attribute"
|
|
""")
|
|
|