1
0
mirror of https://github.com/scrapy/scrapy.git synced 2025-02-24 07:43:48 +00:00
scrapy/tests/test_spidermiddleware_offsite.py
Νικόλαος-Διγενής Καραγιάννης 1cffa99e0d tests+doc for subdomains in offsite middleware
2016-01-26 12:49:43 +02:00

71 lines
2.7 KiB
Python

from unittest import TestCase
from six.moves.urllib.parse import urlparse
from scrapy.http import Response, Request
from scrapy.spiders import Spider
from scrapy.spidermiddlewares.offsite import OffsiteMiddleware
from scrapy.utils.test import get_crawler
class TestOffsiteMiddleware(TestCase):
def setUp(self):
crawler = get_crawler(Spider)
self.spider = crawler._create_spider(**self._get_spiderargs())
self.mw = OffsiteMiddleware.from_crawler(crawler)
self.mw.spider_opened(self.spider)
def _get_spiderargs(self):
return dict(name='foo', allowed_domains=['scrapytest.org', 'scrapy.org', 'scrapy.test.org'])
def test_process_spider_output(self):
res = Response('http://scrapytest.org')
onsite_reqs = [Request('http://scrapytest.org/1'),
Request('http://scrapy.org/1'),
Request('http://sub.scrapy.org/1'),
Request('http://offsite.tld/letmepass', dont_filter=True),
Request('http://scrapy.test.org/')]
offsite_reqs = [Request('http://scrapy2.org'),
Request('http://offsite.tld/'),
Request('http://offsite.tld/scrapytest.org'),
Request('http://offsite.tld/rogue.scrapytest.org'),
Request('http://rogue.scrapytest.org.haha.com'),
Request('http://roguescrapytest.org'),
Request('http://test.org/'),
Request('http://notscrapy.test.org/')]
reqs = onsite_reqs + offsite_reqs
out = list(self.mw.process_spider_output(res, reqs, self.spider))
self.assertEquals(out, onsite_reqs)
class TestOffsiteMiddleware2(TestOffsiteMiddleware):
def _get_spiderargs(self):
return dict(name='foo', allowed_domains=None)
def test_process_spider_output(self):
res = Response('http://scrapytest.org')
reqs = [Request('http://a.com/b.html'), Request('http://b.com/1')]
out = list(self.mw.process_spider_output(res, reqs, self.spider))
self.assertEquals(out, reqs)
class TestOffsiteMiddleware3(TestOffsiteMiddleware2):
def _get_spider(self):
return Spider('foo')
class TestOffsiteMiddleware4(TestOffsiteMiddleware3):
def _get_spider(self):
bad_hostname = urlparse('http:////scrapytest.org').hostname
return dict(name='foo', allowed_domains=['scrapytest.org', None, bad_hostname])
def test_process_spider_output(self):
res = Response('http://scrapytest.org')
reqs = [Request('http://scrapytest.org/1')]
out = list(self.mw.process_spider_output(res, reqs, self.spider))
self.assertEquals(out, reqs)