Created
January 25, 2010 17:24
-
-
Save rmax/286045 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import unittest | |
| from scrapy.contrib_exp.spiders.url import UrlSpider, UrlMatcher | |
| from scrapy.contrib_exp.url.extractor import SgmlUrlExtractor | |
| from scrapy.http import HtmlResponse, Request | |
| def test_callable(response): | |
| pass | |
| def capitalize_urls(urls): | |
| for url in urls: | |
| yield url.upper() | |
| class TesSpider(UrlSpider): | |
| url_extractors = [ | |
| SgmlUrlExtractor(), | |
| ] | |
| url_processors = [ | |
| capitalize_urls, | |
| ] | |
| url_matchers = [ | |
| UrlMatcher(r'URL1', 'testmethod', 'argument'), | |
| UrlMatcher(r'URL2', test_callable, kwargument='argument'), | |
| ] | |
| def testmethod(self, response): | |
| return Request('URL3') | |
| response_body = ''' | |
| <html> | |
| <head></head> | |
| <body> | |
| <a href="url1">Link1</a> | |
| <a href="url2">Link2</a> | |
| </body> | |
| </html> | |
| ''' | |
| class UrlSpiderTest(unittest.TestCase): | |
| def setUp(self): | |
| self.s = TesSpider() | |
| self.r = HtmlResponse('url', body=response_body) | |
| def _compare_requests(self, reqs, other_reqs): | |
| self.assertEquals(len(reqs), len(other_reqs)) | |
| for i, r in enumerate(reqs): | |
| self.assertEquals(r.url, other_reqs[i].url) | |
| def test_compile_matchers(self): | |
| self.assertEquals(self.s._url_matchers[0].callback, self.s.testmethod) | |
| self.assertEquals(self.s._url_matchers[1].callback, test_callable) | |
| def test_extract_urls(self): | |
| self.assertEquals(self.s._extract_urls(self.r), ['url1', 'url2']) | |
| def test_process_urls(self): | |
| urls = ['url1', 'url2'] | |
| purls = [url for url in self.s._process_urls(urls)] | |
| self.assertEquals(purls, ['URL1', 'URL2']) | |
| def test_response_downloaded(self): | |
| reqs = [Request('URL1'), Request('URL2')] | |
| res = [r for r in self.s._response_downloaded(self.r)] | |
| self._compare_requests(res, reqs) | |
| for i, r in enumerate(res): | |
| callbacks = r.deferred.callbacks[0][0] | |
| matcher = self.s._url_matchers[i] | |
| self.assertEquals(callbacks[0], self.s._response_downloaded) | |
| self.assertEquals(callbacks[1], (matcher.callback,)) | |
| self.assertEquals(callbacks[2], {'cb_args': matcher.cb_args, | |
| 'cb_kwargs': matcher.cb_kwargs}) | |
| def test_response_downloaded_with_callback(self): | |
| reqs = [Request('URL3'), Request('URL1'), Request('URL2')] | |
| res = [r for r in \ | |
| self.s._response_downloaded(self.r, callback=self.s.testmethod)] | |
| self._compare_requests(res, reqs) | |
| def test_parse(self): | |
| res1 = [r for r in self.s._response_downloaded(self.r)] | |
| res2 = [r for r in self.s.parse(self.r)] | |
| self._compare_requests(res1, res2) | |
| if __name__ == '__main__': | |
| unittest.main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment