def get_perspectives(url):
'''Get different perspectives on the topic covered by article.
Args:
url: A string.
Returns:
A JSON-encoded string representing other articles with different
perspectives than the original article.
Format: a list of Article.to_dict()s, each with an additional 'sentences'
attribute. 'sentences' contains a list of sentences with semantically
different words that were extracted from the corresponding article's body.
'''
article = url_to_article(url)
if article:
article_topic = extract_keywords.extract_keywords(article.headline)
related_articles = query_all_news_orgs(article_topic)
return compare_articles.compare.to_all_articles(article, related_articles)
def get_perspectives(url):
'''Get different perspectives on the topic covered by article.
Args:
url: A string.
Returns:
A JSON-encoded string representing other articles with different
perspectives than the original article.
Format: a list of Article.to_dict()s, each with an additional 'sentences'
attribute. 'sentences' contains a list of sentences with semantically
different words that were extracted from the corresponding article's body.
'''
article = url_to_article(url)
if article:
headline = article.headline
body = article.body
org = article.news_org
article_topic = extract_keywords.extract_keywords(headline)
(NP_to_sentence, VP_to_sentence, NPs, VPs, NP_synsets, VP_synsets) = \
get_article_phrases(body, org)
n = len(NEWS_ORGS)
with futures.ProcessPoolExecutor(max_workers=n) as executor:
comparisons = executor.map(get_comparison, NEWS_ORGS,
[article_topic] * n,
[NP_to_sentence] * n,
[VP_to_sentence] * n, [NPs] * n,
[VPs] * n, [NP_synsets] * n,
[VP_synsets] * n, [1] * n)
compared_articles_by_org = list(comparisons)
# flatten from list of lists of articles (separated by news org) to list
# of articles
compared_articles = [
article for org_articles in compared_articles_by_org
for article in org_articles
]
return json.dumps(compared_articles)
else:
return json.dumps("Not a recognized article")
def get_perspectives(url):
'''Get different perspectives on the topic covered by article.
Args:
url: A URLencoded string.
Returns:
A JSON-encoded string representing other articles with different
perspectives than the original article.
Format: a list of Article.to_dict()s, each with an additional 'sentences'
attribute. 'sentences' contains a list of sentences with semantically
different words that were extracted from the corresponding article's body.
'''
article = url_to_article(urldecode(url))
if article:
headline = article.headline
body = article.body
org = article.news_org
article_topic = extract_keywords.extract_keywords(headline)
(NP_to_sentence, VP_to_sentence, NPs, VPs, NP_synsets, VP_synsets) = \
get_article_phrases(body, org)
n = len(NEWS_ORGS)
with futures.ProcessPoolExecutor(max_workers=n) as executor:
comparisons = executor.map(get_comparison, NEWS_ORGS,
[NP_to_sentence]*n, [VP_to_sentence]*n,
[NPs]*n, [VPs]*n,
[NP_synsets]*n, [VP_synsets]*n,
[article_topic]*n, [headline]*n, [org]*n)
compared_articles_by_org = list(comparisons)
# flatten from list of lists of articles (separated by news org) to list
# of articles
compared_articles = [article for org_articles in compared_articles_by_org
for article in org_articles if article]
return json.dumps(compared_articles)
else:
return json.dumps({"Error": "Not a recognized article"})
from save_full_words import save_full_words
from extract_keywords import extract_keywords
if __name__ == "__main__":
weibo_name = input("请输入需要对评论内容进行分词的微博名：")
save_full_words(weibo_name)
extract_keywords(weibo_name)
def test_extract_keywords(self): headline = 'What really happened with NBC and Ayman Mohyeldin?' res = extract_keywords.extract_keywords(headline) self.assertEqual(res, 'nbc ayman mohyeldin')
def test_extract_keywords(self):
headline = 'What really happened with NBC and Ayman Mohyeldin?'
res = extract_keywords.extract_keywords(headline)
self.assertEqual(res, 'nbc ayman mohyeldin')
