def test_download_file_success(self):
url = "file://" + os.path.join(HTML_FN, "cnn_article.html")
article = Article(url=url)
article.download()
self.assertEqual(article.download_state, ArticleDownloadState.SUCCESS)
self.assertEqual(article.download_exception_msg, None)
self.assertEqual(75406, len(article.html))
def check_url(args):
"""
:param (basestr, basestr) url, res_filename:
:return: (pubdate_failed, fulltext_failed)
"""
url, res_filename = args
pubdate_failed, fulltext_failed = False, False
html = mock_resource_with(res_filename, 'html')
try:
a = Article(url)
a.download(html)
a.parse()
if a.publish_date is None:
pubdate_failed = True
except Exception:
print('<< URL: %s parse ERROR >>' % url)
traceback.print_exc()
pubdate_failed, fulltext_failed = True, True
else:
correct_text = mock_resource_with(res_filename, 'txt')
if not (a.text == correct_text):
# print('Diff: ', simplediff.diff(correct_text, a.text))
# `correct_text` holds the reason of failure if failure
print('%s -- %s -- %s' %
('Fulltext failed', res_filename, correct_text.strip()))
fulltext_failed = True
# TODO: assert statements are commented out for full-text
# extraction tests because we are constantly tweaking the
# algorithm and improving
# assert a.text == correct_text
return pubdate_failed, fulltext_failed
def test_meta_refresh_no_url_redirect(self):
config = Configuration()
config.follow_meta_refresh = True
article = Article('', config=config)
html = mock_resource_with('ap_meta_refresh', 'html')
article.download(input_html=html)
article.parse()
self.assertEqual(article.title, 'News from The Associated Press')
def test_thai_fulltext_extract(self):
url = 'https://prachatai.com/journal/2019/01/80642'
article = Article(url=url, language='th')
html = mock_resource_with('thai_article', 'html')
article.download(html)
article.parse()
text = mock_resource_with('thai', 'txt')
self.assertEqual(text, article.text)
self.assertEqual(text, fulltext(article.html, 'th'))
def test_japanese_fulltext_extract2(self):
url = 'http://www.afpbb.com/articles/-/3178894'
article = Article(url=url, language='ja')
html = mock_resource_with('japanese_article2', 'html')
article.download(html)
article.parse()
text = mock_resource_with('japanese2', 'txt')
self.assertEqual(text, article.text)
self.assertEqual(text, fulltext(article.html, 'ja'))
def test_japanese_fulltext_extract(self):
url = 'https://www.nikkei.com/article/DGXMZO31897660Y8A610C1000000/?n_cid=DSTPCS001'
article = Article(url=url, language='ja')
html = mock_resource_with('japanese_article', 'html')
article.download(html)
article.parse()
text = mock_resource_with('japanese', 'txt')
self.assertEqual(text, article.text)
self.assertEqual(text, fulltext(article.html, 'ja'))
def test_chinese_fulltext_extract(self):
url = 'http://news.sohu.com/20050601/n225789219.shtml'
article = Article(url=url, language='zh')
html = mock_resource_with('chinese_article', 'html')
article.download(html)
article.parse()
text = mock_resource_with('chinese', 'txt')
self.assertEqual(text, article.text)
self.assertEqual(text, fulltext(article.html, 'zh'))
def test_download_file_failure(self):
url = "file://" + os.path.join(HTML_FN, "does_not_exist.html")
article = Article(url=url)
article.download()
self.assertEqual(0, len(article.html))
self.assertEqual(article.download_state,
ArticleDownloadState.FAILED_RESPONSE)
self.assertEqual(article.download_exception_msg,
"No such file or directory")
def test_spanish_fulltext_extract(self):
url = 'http://ultimahora.es/mallorca/noticia/noticias/local/fiscal' \
'ia-anticorrupcion-estudia-recurre-imputacion-infanta.html'
article = Article(url=url, language='es')
html = mock_resource_with('spanish_article', 'html')
article.download(html)
article.parse()
text = mock_resource_with('spanish', 'txt')
self.assertEqual(text, article.text)
self.assertEqual(text, fulltext(article.html, 'es'))
def test_meta_refresh_redirect(self):
# TODO: We actually hit example.com in this unit test ... which is bad
# Figure out how to mock an actual redirect
config = Configuration()
config.follow_meta_refresh = True
article = Article('', config=config)
html = mock_resource_with('google_meta_refresh', 'html')
article.download(input_html=html)
article.parse()
self.assertEqual(article.title, 'Example Domain')
def test_arabic_fulltext_extract(self):
url = 'http://arabic.cnn.com/2013/middle_east/8/3/syria.clashes/' \
'index.html'
article = Article(url=url)
html = mock_resource_with('arabic_article', 'html')
article.download(html)
article.parse()
self.assertEqual('ar', article.meta_lang)
text = mock_resource_with('arabic', 'txt')
self.assertEqual(text, article.text)
self.assertEqual(text, fulltext(article.html, 'ar'))
def test_article_pdf_ignoring(self):
empty_pdf = "%PDF-" # empty PDF constant
a = Article(url='http://www.technik-medien.at/ePaper_Download/'
'IoT4Industry+Business_2018-10-31_2018-03.pdf',
ignored_content_types_defaults={
"application/pdf": empty_pdf,
"application/x-pdf": empty_pdf,
"application/x-bzpdf": empty_pdf,
"application/x-gzpdf": empty_pdf
})
a.download()
self.assertEqual(empty_pdf, a.html)
def get_news(url):
article = Article(url, language="hi")
try:
article.download()
article.parse()
article.nlp()
except ArticleException:
logger.exception(f"Error: Download timeout: {url}")
return
data = {
"date": article.publish_date,
"title": article.title,
"keywords": article.keywords,
"summary": article.summary,
"text": article.text,
"img_url": article.top_image,
"video": article.movies,
"url": url,
}
logger.info(f"Got news:{prettify(data)}")
return data
def test_article_pdf_fetching(self):
a = Article(
url=
'https://www.adobe.com/pdf/pdfs/ISO32000-1PublicPatentLicense.pdf')
a.download()
self.assertNotEqual('%PDF-', a.html)
class ArticleTestCase(unittest.TestCase):
def setup_stage(self, stage_name):
stages = OrderedDict([
('initial', lambda: None),
('download', lambda: self.article.download(
mock_resource_with('cnn_article', 'html'))),
('parse', lambda: self.article.parse()),
('meta', lambda: None), # Alias for nlp
('nlp', lambda: self.article.nlp())
])
assert stage_name in stages
for name, action in stages.items():
if name == stage_name:
break
action()
def setUp(self):
"""Called before the first test case of this unit begins
"""
self.article = Article(
url='http://www.cnn.com/2013/11/27/travel/weather-'
'thanksgiving/index.html?iref=allsearch')
@print_test
def test_url(self):
self.assertEqual(
'http://www.cnn.com/2013/11/27/travel/weather-'
'thanksgiving/index.html?iref=allsearch', self.article.url)
@print_test
def test_download_html(self):
self.setup_stage('download')
html = mock_resource_with('cnn_article', 'html')
self.article.download(html)
self.assertEqual(self.article.download_state,
ArticleDownloadState.SUCCESS)
self.assertEqual(self.article.download_exception_msg, None)
self.assertEqual(75406, len(self.article.html))
@print_test
def test_meta_refresh_redirect(self):
# TODO: We actually hit example.com in this unit test ... which is bad
# Figure out how to mock an actual redirect
config = Configuration()
config.follow_meta_refresh = True
article = Article('', config=config)
html = mock_resource_with('google_meta_refresh', 'html')
article.download(input_html=html)
article.parse()
self.assertEqual(article.title, 'Example Domain')
@print_test
def test_meta_refresh_no_url_redirect(self):
config = Configuration()
config.follow_meta_refresh = True
article = Article('', config=config)
html = mock_resource_with('ap_meta_refresh', 'html')
article.download(input_html=html)
article.parse()
self.assertEqual(article.title, 'News from The Associated Press')
@print_test
def test_pre_download_parse(self):
"""Calling `parse()` before `download()` should yield an error
"""
article = Article(self.article.url)
self.assertRaises(ArticleException, article.parse)
@print_test
def test_parse_html(self):
self.setup_stage('parse')
AUTHORS = [
'Chien-Ming Wang', 'Dana A. Ford', 'James S.A. Corey',
'Tom Watkins'
]
TITLE = 'After storm, forecasters see smooth sailing for Thanksgiving'
LEN_IMGS = 46
META_LANG = 'en'
META_SITE_NAME = 'CNN'
self.article.parse()
self.article.nlp()
text = mock_resource_with('cnn', 'txt')
self.assertEqual(text, self.article.text)
self.assertEqual(text, fulltext(self.article.html))
# NOTE: top_img extraction requires an internet connection
# unlike the rest of this test file
TOP_IMG = ('http://i2.cdn.turner.com/cnn/dam/assets/131129200805-'
'01-weather-1128-story-top.jpg')
self.assertEqual(TOP_IMG, self.article.top_img)
self.assertCountEqual(AUTHORS, self.article.authors)
self.assertEqual(TITLE, self.article.title)
self.assertEqual(LEN_IMGS, len(self.article.imgs))
self.assertEqual(META_LANG, self.article.meta_lang)
self.assertEqual(META_SITE_NAME, self.article.meta_site_name)
self.assertEqual('2013-11-27 00:00:00', str(self.article.publish_date))
@print_test
def test_meta_type_extraction(self):
self.setup_stage('meta')
meta_type = self.article.extractor.get_meta_type(
self.article.clean_doc)
self.assertEqual('article', meta_type)
@print_test
def test_meta_extraction(self):
self.setup_stage('meta')
meta = self.article.extractor.get_meta_data(self.article.clean_doc)
META_DATA = defaultdict(
dict, {
'medium':
'news',
'googlebot':
'noarchive',
'pubdate':
'2013-11-27T08:36:32Z',
'title':
'After storm, forecasters see smooth sailing for Thanksgiving - CNN.com',
'og': {
'site_name': 'CNN',
'description':
'A strong storm struck much of the eastern United States on Wednesday, complicating holiday plans for many of the 43 million Americans expected to travel.',
'title':
'After storm, forecasters see smooth sailing for Thanksgiving',
'url':
'http://www.cnn.com/2013/11/27/travel/weather-thanksgiving/index.html',
'image':
'http://i2.cdn.turner.com/cnn/dam/assets/131129200805-01-weather-1128-story-top.jpg',
'type': 'article'
},
'section':
'travel',
'author':
'Dana A. Ford, James S.A. Corey, Chien-Ming Wang, and Tom Watkins, CNN',
'robots':
'index,follow',
'vr': {
'canonical':
'http://edition.cnn.com/2013/11/27/travel/weather-thanksgiving/index.html'
},
'source':
'CNN',
'fb': {
'page_id': 18793419640,
'app_id': 80401312489
},
'keywords':
'winter storm,holiday travel,Thanksgiving storm,Thanksgiving winter storm',
'article': {
'publisher': 'https://www.facebook.com/cnninternational'
},
'lastmod':
'2013-11-28T02:03:23Z',
'twitter': {
'site': {
'identifier': '@CNNI',
'id': 2097571
},
'card': 'summary',
'creator': {
'identifier': '@cnntravel',
'id': 174377718
}
},
'viewport':
'width=1024',
'news_keywords':
'winter storm,holiday travel,Thanksgiving storm,Thanksgiving winter storm'
})
self.assertDictEqual(META_DATA, meta)
# if the value for a meta key is another dict, that dict ought to be
# filled with keys and values
dict_values = [v for v in list(meta.values()) if isinstance(v, dict)]
self.assertTrue(all([len(d) > 0 for d in dict_values]))
# there are exactly 5 top-level "og:type" type keys
is_dict = lambda v: isinstance(v, dict)
self.assertEqual(5, len([i for i in meta.values() if is_dict(i)]))
# there are exactly 12 top-level "pubdate" type keys
is_string = lambda v: isinstance(v, str)
self.assertEqual(12, len([i for i in meta.values() if is_string(i)]))
@print_test
def test_pre_download_nlp(self):
"""Test running NLP algos before even downloading the article
"""
self.setup_stage('initial')
new_article = Article(self.article.url)
self.assertRaises(ArticleException, new_article.nlp)
@print_test
def test_pre_parse_nlp(self):
"""Test running NLP algos before parsing the article
"""
self.setup_stage('parse')
self.assertRaises(ArticleException, self.article.nlp)
@print_test
def test_nlp_body(self):
self.setup_stage('nlp')
self.article.nlp()
KEYWORDS = [
'balloons', 'delays', 'flight', 'forecasters', 'good', 'sailing',
'smooth', 'storm', 'thanksgiving', 'travel', 'weather', 'winds',
'york'
]
SUMMARY = mock_resource_with('cnn_summary', 'txt')
self.assertEqual(SUMMARY, self.article.summary)
self.assertCountEqual(KEYWORDS, self.article.keywords)