def get_article_info(url):
try:
a = Article(url, fetch_images=False)
a.download()
a.parse()
# Not doing a.nlp() to be more efficient.
text_keyws = list(nlp.keywords(a.text).keys())
title_keyws = list(nlp.keywords(a.title).keys())
keyws = list(set(title_keyws + text_keyws))
if 'published_time' in a.meta_data['article']:
published_time = a.meta_data['article']['published_time']
else:
published_time = ''
return {'keywords': keyws, 'c_link': a.canonical_link, 'published_time': published_time, 'title': a.title}
except:
return {'keywords': [], 'c_link': a.canonical_link, 'published_time': '', 'title': ''}
def _new_summarize(text='', max_sents=5):
summaries = []
sentences = split_sentences(text)
keys = keywords(text)
# Score sentences, and use the top 5 or max_sents sentences
ranks = nlp.score(sentences, keys).most_common(max_sents)
for rank in ranks:
summaries.append(rank[0])
summaries.sort(key=lambda summary: summary[0])
return [summary[1] for summary in summaries]
def ProcessArticle(urlStr, domain, htmlStr, cursor):
config = Configuration()
extractor = ContentExtractor(config)
clean_doc = config.get_parser().fromstring(htmlStr)
title = extractor.get_title(clean_doc)
authors = extractor.get_authors(clean_doc)
text = fulltext(htmlStr)
text_keyws = list(nlp.keywords(text).keys())
title_keyws = list(nlp.keywords(title).keys())
keyws = list(set(title_keyws + text_keyws))
summary_sents = nlp.summarize(title=title,
text=text,
max_sents=config.MAX_SUMMARY_SENT)
summary = '\n'.join(summary_sents)
if len(text) == 0:
OnArticleProcessError(urlStr)
else:
StoreToDatabase(urlStr, domain, title, authors, text, keyws, summary,
cursor)
def _new_summarize( text='', max_sents=5):
summaries = []
sentences = split_sentences(text)
keys = keywords(text)
# Score sentences, and use the top 5 or max_sents sentences
ranks = nlp.score(sentences, keys).most_common(max_sents)
for rank in ranks:
summaries.append(rank[0])
summaries.sort(key=lambda summary: summary[0])
return [summary[1] for summary in summaries]
def evaluate_newspaper_summary(self, title, text, sentences, language):
# get newspaper's nlp scores
# https://github.com/codelucas/newspaper/blob/master/newspaper/article.py#L372
nlp.load_stopwords(language)
# call to: nlp.summarize(title=article.title, text=article.text, max_sents=max_sents)
# https://github.com/codelucas/newspaper/blob/master/newspaper/nlp.py#L40
title_words = nlp.split_words(title)
most_frequent = nlp.keywords(text)
nlp_scores = self.normalize_scores(
nlp.score(sentences, title_words, most_frequent))
# Return a dictionary of tuple<sentence index, setence text> to score
# ie. { (0, 'A new poll suggests that the Toronto Raptors...') : 0.144, ... }
return nlp_scores
filename='teesta_setal_input.csv'
currentdirpath=os.getcwd()
file_path=os.path.join(os.getcwd(),filename)
with open(file_path,'r+' ) as reports_file:
reader = csv.reader(reports_file, delimiter='\t')
for row in reader:
article = row[0]
summary_sentents=nlp.summarize(text = article)
summary = '\n'.join(summary_sentents)
row.append(summary)
textkeys=keywords(article).keys()
row.append(textkeys)
with open((os.path.join(os.getcwd(),'final_tee.csv')),'a') as newfile:
writer = csv.writer(newfile, delimiter='\t')
try:
writer.writerow(row)
except Exception, e:
pass
data = []
filename = 'teesta_setal_input.csv'
currentdirpath = os.getcwd()
file_path = os.path.join(os.getcwd(), filename)
with open(file_path, 'r+') as reports_file:
reader = csv.reader(reports_file, delimiter='\t')
for row in reader:
article = row[0]
summary_sentents = nlp.summarize(text=article)
summary = '\n'.join(summary_sentents)
row.append(summary)
textkeys = keywords(article).keys()
row.append(textkeys)
with open((os.path.join(os.getcwd(), 'final_tee.csv')),
'a') as newfile:
writer = csv.writer(newfile, delimiter='\t')
try:
writer.writerow(row)
except Exception, e:
pass
def text_keywords():
text_to_clean = request.args.get('text_to_clean')
keywords = nlp.keywords(text_to_clean)
return jsonify(keywords)
article.top_image = '' if re.search(
'favicon', article.top_image) else article.top_image
with open('../detector/tl_stopwords.txt', 'r') as f:
TL_STOPWORDS = f.read().splitlines()
STOP_WORDS = ENGLISH_STOP_WORDS.union(TL_STOPWORDS)
cleaned_body = ' '.join([
word for word in body.split()
if word.lower() not in STOP_WORDS
])
cleaned_title = ' '.join([
word for word in title.split()
if word.lower() not in STOP_WORDS
])
text_keyws = list(keywords(cleaned_body).keys())
title_keyws = list(keywords(cleaned_title).keys())
keyws = list(set(title_keyws + text_keyws))
summary = summarize(title=article.title,
text=body,
max_sents=3)
# keywords = []
# for key, value in article.keywords.items():
# keywords.append({
# 'word': key,
# 'score': value
# })
# keywords = sorted(
def nlp_wrapper(text):
"""Keyword extraction wrapper
"""
nlp.load_stopwords('en')
return ' '.join(list(nlp.keywords(text).keys()))
def summarize(self, html, percent_sentences):
if (percent_sentences is None or percent_sentences > 100
or percent_sentences < 0):
percent_sentences = 15
article = self.process_html(html)
# remove title from the text, if it appears in the text
if article.text.startswith(article.title):
article.set_text(article.text[len(article.title):])
sentences = nlp.split_sentences(article.text)
log.debug(article.text)
# remove punctuations, numbers and special characters
clean_sentences = pd.Series(sentences).str.replace("[^a-zA-Z]", " ")
clean_sentences = [s.lower() for s in clean_sentences]
clean_sentences = [
self._remove_stopwords(r.split()) for r in clean_sentences
]
# create sentence vectors
sentence_vectors = []
for i in clean_sentences:
if len(i) != 0:
v = sum([
self.word_embeddings.get(w, np.zeros((300, )))
for w in i.split()
]) / (len(i.split()) + 0.001)
else:
v = np.zeros((300, ))
sentence_vectors.append(v)
# similarity matrix
sim_mat = np.zeros([len(sentences), len(sentences)])
# initialize matrix
for i in range(len(sentences)):
for j in range(len(sentences)):
if i != j:
sim_mat[i][j] = cosine_similarity(
sentence_vectors[i].reshape(1, 300),
sentence_vectors[j].reshape(1, 300),
)[0, 0]
# convert matrix into graph
nx_graph = nx.from_numpy_array(sim_mat)
textrank_scores = self.normalize_scores(nx.pagerank(nx_graph))
# get newspaper's nlp scores
# https://github.com/codelucas/newspaper/blob/master/newspaper/article.py#L372
nlp.load_stopwords(article.config.get_language())
# call to: nlp.summarize(title=article.title, text=article.text, max_sents=max_sents)
# https://github.com/codelucas/newspaper/blob/master/newspaper/nlp.py#L40
title_words = nlp.split_words(article.title)
most_frequent = nlp.keywords(article.text)
nlp_scores = self.normalize_scores(
nlp.score(sentences, title_words, most_frequent))
totalled_scores = Counter()
for key, value in nlp_scores.items():
totalled_scores[key[0]] += value
for key, value in textrank_scores.items():
totalled_scores[key] += value
num_sentences = int(len(clean_sentences) * percent_sentences / 100)
sentence_indices = list(
map(lambda x: x[0], totalled_scores.most_common(num_sentences)))
return list(map(lambda x: sentences[x], sentence_indices))