Python Source.category_urls方法代码示例

# 需要导入模块: from newspaper import Source [as 别名]
# 或者: from newspaper.Source import category_urls [as 别名]
    def test_cache_categories(self):
        """
        builds two same source objects in a row examines speeds of both
        """
        s = Source("http://yahoo.com")
        s.download()
        s.parse()
        s.set_categories()

        saved_urls = s.category_urls()
        s.categories = []  # reset and try again with caching
        s.set_categories()
        assert sorted(s.category_urls()) == sorted(saved_urls)

# 需要导入模块: from newspaper import Source [as 别名]
# 或者: from newspaper.Source import category_urls [as 别名]
    def test_cache_categories(self):
        """Builds two same source objects in a row examines speeds of both
        """
        url = 'http://uk.yahoo.com'
        mock_response_with(url, 'yahoo_main_site')
        s = Source(url)
        s.download()
        s.parse()
        s.set_categories()

        saved_urls = s.category_urls()
        s.categories = []
        s.set_categories()
        assert sorted(s.category_urls()) == sorted(saved_urls)

# 需要导入模块: from newspaper import Source [as 别名]
# 或者: from newspaper.Source import category_urls [as 别名]
    def test_cache_categories(self):
        """Builds two same source objects in a row examines speeds of both
        """
        url = 'http://uk.yahoo.com'
        html = mock_resource_with('yahoo_main_site', 'html')
        s = Source(url)
        s.download()
        s.parse()
        s.set_categories()

        saved_urls = s.category_urls()
        s.categories = []
        s.set_categories()
        self.assertCountEqual(saved_urls, s.category_urls())

# 需要导入模块: from newspaper import Source [as 别名]
# 或者: from newspaper.Source import category_urls [as 别名]
    def test_source_build(self):
        """
        builds a source object, validates it has no errors, prints out
        all valid categories and feed urls
        """
        DESC = """CNN.com delivers the latest breaking news and information on the latest top stories, weather, business, entertainment, politics, and more. For in-depth coverage, CNN.com provides special reports, video, audio, photo galleries, and interactive guides."""
        BRAND = "cnn"

        config = Configuration()
        config.verbose = False
        s = Source("http://cnn.com", config=config)
        s.clean_memo_cache()
        s.build()

        assert s.brand == BRAND
        assert s.description == DESC

        # For this test case and a few more, I don't believe you can actually
        # assert two values to equal eachother because some values are ever changing.

        # Insead, i'm just going to print some stuff out so it is just as easy to take
        # a glance and see if it looks OK.

        print "\t\tWe have %d articles currently!" % s.size()
        print
        print "\t\t%s categories are: %s" % (s.url, str(s.category_urls()))

# 需要导入模块: from newspaper import Source [as 别名]
# 或者: from newspaper.Source import category_urls [as 别名]
    def test_source_build(self):
        """
        builds a source object, validates it has no errors, prints out
        all valid categories and feed urls
        """
        DESC = ('CNN.com International delivers breaking news from across '
                'the globe and information on the latest top stories, '
                'business, sports and entertainment headlines. Follow the '
                'news as it happens through: special reports, videos, '
                'audio, photo galleries plus interactive maps and timelines.')
        CATEGORY_URLS = [
            u'http://cnn.com/ASIA', u'http://connecttheworld.blogs.cnn.com',
            u'http://cnn.com/HLN', u'http://cnn.com/MIDDLEEAST',
            u'http://cnn.com', u'http://ireport.cnn.com',
            u'http://cnn.com/video', u'http://transcripts.cnn.com',
            u'http://cnn.com/espanol',
            u'http://partners.cnn.com', u'http://www.cnn.com',
            u'http://cnn.com/US', u'http://cnn.com/EUROPE',
            u'http://cnn.com/TRAVEL', u'http://cnn.com/cnni',
            u'http://cnn.com/SPORT', u'http://cnn.com/mostpopular',
            u'http://arabic.cnn.com', u'http://cnn.com/WORLD',
            u'http://cnn.com/LATINAMERICA', u'http://us.cnn.com',
            u'http://travel.cnn.com', u'http://mexico.cnn.com',
            u'http://cnn.com/SHOWBIZ', u'http://edition.cnn.com',
            u'http://amanpour.blogs.cnn.com', u'http://money.cnn.com',
            u'http://cnn.com/tools/index.html', u'http://cnnespanol.cnn.com',
            u'http://cnn.com/CNNI', u'http://business.blogs.cnn.com',
            u'http://cnn.com/AFRICA', u'http://cnn.com/TECH',
            u'http://cnn.com/BUSINESS']
        FEEDS = [u'http://rss.cnn.com/rss/edition.rss']
        BRAND = 'cnn'

        s = Source('http://cnn.com', verbose=False, memoize_articles=False)
        url_re = re.compile(".*cnn\.com")
        mock_response_with(url_re, 'cnn_main_site')
        s.clean_memo_cache()
        s.build()

        assert s.brand == BRAND
        assert s.description == DESC
        assert s.size() == 241
        assert s.category_urls() == CATEGORY_URLS
        # TODO: A lot of the feed extraction is NOT being tested because feeds
        # are primarly extracted from the HTML of category URLs. We lose this
        # effect by just mocking CNN's main page HTML. Warning: tedious fix.
        assert s.feed_urls() == FEEDS