diff options
| author | Yuval Adam <yuv.adm@gmail.com> | 2014-01-24 23:38:03 +0100 |
|---|---|---|
| committer | Yuval Adam <yuv.adm@gmail.com> | 2014-01-24 23:38:03 +0100 |
| commit | d8d555b1fbc6a641c33265ee60ee872748437c4b (patch) | |
| tree | 0b5f77ec590353faad8c66f9280c6e147a13cebb | |
| parent | 6de121365a40194b24834e01abf32d2aaac23786 (diff) | |
Normalize APIs and tests
| -rw-r--r-- | newsdiff/core/parsers/base.py | 4 | ||||
| -rw-r--r-- | newsdiff/core/parsers/haaretz.py | 4 | ||||
| -rw-r--r-- | newsdiff/core/tests/tests.py | 5 |
3 files changed, 7 insertions, 6 deletions
diff --git a/newsdiff/core/parsers/base.py b/newsdiff/core/parsers/base.py index dae2949..532568a 100644 --- a/newsdiff/core/parsers/base.py +++ b/newsdiff/core/parsers/base.py @@ -26,10 +26,10 @@ class HtmlSoupParser(object): soup = self.get_page(url) self.parse_article(url, soup) - def parse_homepage(soup): + def parse_homepage(self, soup): raise NotImplementedError - def parse_article(self, url): + def parse_article(self, url, soup): raise NotImplementedError def clean_article_href(self, href): diff --git a/newsdiff/core/parsers/haaretz.py b/newsdiff/core/parsers/haaretz.py index d154fb9..8928663 100644 --- a/newsdiff/core/parsers/haaretz.py +++ b/newsdiff/core/parsers/haaretz.py @@ -15,8 +15,8 @@ class HaaretzParser(HtmlSoupParser): BASE_URL = 'http://www.haaretz.co.il' HOMEPAGE_URL = BASE_URL + '/' - ARTICLE_HREF_PATTERN = re.compile(r'''^(http:\/\/www\.haaretz\.co\.il)?/((news|opinions|magazine|captain)/[a-zA-Z0-9\-\/]*(\.premium-)?)?\d\.\d+(#article_comments)?$''') - ARTICLE_ID_PATTERN = re.compile(r'1.[0-9]+') + ARTICLE_HREF_PATTERN = re.compile(r'''^(http:\/\/www\.haaretz\.co\.il)?/((news|opinions|magazine|captain)/[a-zA-Z0-9\-\/]*(\.premium-)?)?1\.\d+(#article_comments)?$''') + ARTICLE_ID_PATTERN = re.compile(r'1\.\d+') ARTICLE_MODEL = HaaretzArticle IMAGE_MODEL = HaaretzImage diff --git a/newsdiff/core/tests/tests.py b/newsdiff/core/tests/tests.py index 6f91aad..b30b143 100644 --- a/newsdiff/core/tests/tests.py +++ b/newsdiff/core/tests/tests.py @@ -26,10 +26,11 @@ class HaaretzParsingTestCase(TestCase): def test_parse_article(self): article_id = '1.2198200' + article_url = '{}/{}'.format(self.parser.BASE_URL, article_id) soup = self._get_soup('{}.html'.format(article_id)) - self.parser.parse_article(article_id, soup) + self.parser.parse_article(article_url, soup) article = HaaretzArticle.objects.get(haaretz_id=article_id) - self.assertEqual(article.url, 'http://www.haaretz.co.il/{}'.format(article_id)) + self.assertEqual(article.url, article_url) images = article.images self.assertEqual(images.count(), 2) |