def text_keyword_abstract(article, keywords_len, sentences_len):
tr4w = TextRank4Keyword()
tr4w.analyze(text=article, lower=True, window=2)
keywords = []
for item in tr4w.get_keywords(keywords_len, word_min_len=2):
keywords.append(item.word)
keywords = ' '.join(keywords)
tr4s = TextRank4Sentence()
tr4s.analyze(text=article, lower=True, source='all_filters')
abstract = []
for item in tr4s.get_key_sentences(num=sentences_len):
abstract.append(item.sentence)
return keywords, abstract
def keyword(self):
keyword1 = jieba.analyse.textrank(self.cut, topK=5, withWeight=True)
keyword2 = jieba.analyse.extract_tags(self.cut,
topK=5,
withWeight=True)
print('Key word for jieba_textrank:')
for m in keyword1:
print(m[0], m[1])
print('\nKey word for jieba_TF-IDF:')
for n in keyword2:
print(n[0], n[1])
print('\nKey word for textrank4zh:')
keyword3 = TextRank4Keyword()
keyword3.analyze(text=self.cut, lower=True, window=2)
for i in keyword3.get_keywords(5):
print(i.word, i.weight)
def key_word_extraction(articles):
key_word = []
num_key_word = 5
tr4w = TextRank4Keyword()
for i in range(len(articles)):
temp_key_word = []
tr4w.analyze(text=articles[i],
lower=True,
window=3,
vertex_source='all_filters',
edge_source='all_filters')
for j in range(num_key_word):
temp_key_word.append(
tr4w.get_keywords(num=num_key_word)[j]['word'])
key_word.append(temp_key_word)
return key_word
def getKeyWordsByTitle(max_num=10, startColum=None, endColum=None):
# 每天最多的关键词个数
# max_num = 7
# pd显示所有行、列
pd.set_option('display.max_rows', None) # 行
pd.set_option('display.max_columns', None) # 列
# 加载需要的keyword
keyword = pd.read_csv('../data/keyword_title.csv')['word'].values.tolist()
# 加载title
data_arr = pd.read_csv('../data/RenMinTitle_all_2020_04_06.csv').iloc[
startColum:endColum, :30].values
# 每天化为1条，转为1维数据
data_list = []
for arr in data_arr:
data_list.append(' '.join(arr))
print(data_list)
# 生成日期列表
# date_list = netUtil.getDateList(len(data_list))
# 构建二维矩阵，按天存储关键词
keywords_allday_list = []
# 存储所有的关键词，用来构建连接矩阵
keywords_all_set = set()
# 获取每天的关键词
for day_title in data_list:
day_keywords_list = []
words = TextRank4Keyword()
words.analyze(text=day_title, lower=True, window=3)
keywords_dic_list = words.get_keywords(40, word_min_len=2)
for one_dic in keywords_dic_list:
# 下面注释是为了挑选出名词
# s_tags = SnowNLP(one_dic['word']).tags
# print('---')
# flag = 0
# for tag in s_tags:
# if tag[1] == 'n':
# flag = 1
# print(tag)
# if one_dic['word'] in keyword:
# if flag == 1:
if one_dic['word'] in keyword:
day_keywords_list.append(one_dic['word'])
keywords_all_set.add(one_dic['word'])
if len(day_keywords_list) >= max_num:
break
keywords_allday_list.append(day_keywords_list)
return keywords_allday_list
def process(self, ):
for i in self.text:
self.article += i.getText() + '\n'
self.article = self.article.strip()
keywords = []
abstract = []
##关键词
tr4w = TextRank4Keyword()
tr4w.analyze(text=self.article, lower=True, window=2)
for item in tr4w.get_keywords(4, word_min_len=1):
keywords.append(item.word)
##摘要
tr4s = TextRank4Sentence()
tr4s.analyze(text=self.article, lower=True, source = 'all_filters')
for item in tr4s.get_key_sentences(num=3):
abstract.append(item.sentence)
return keywords, abstract
def compute_texttank(df, filepath):
writer = pd.ExcelWriter(filepath)
for names in df:
all_re = []
test_df = df[names]
text_all = concat_all(df=test_df[:5]) # 原本test_df為了demo改為test_df[:5]
tr4w = TextRank4Keyword()
tr4w.analyze(text=text_all, lower=True, window=6)
for item in tr4w.get_keywords(num=100, word_min_len=2):
all_re.append([item.word, item.weight])
df_result = pd.DataFrame(all_re)
df_result.columns = ['關鍵詞', 'Textrank分數']
df_result.to_excel(writer, sheet_name=names)
writer.save()
def get_textRank_kp(file_name, topk):
json_file = open(file_name, 'r', encoding='utf-8')
textRank_kp = []
for line in json_file.readlines():
json_data = json.loads(line)
cur_content = json_data['title'].strip().lower(
) + ' ' + json_data['abstract'].strip().lower()
tr4w = TextRank4Keyword()
tr4w.analyze(text=cur_content, lower=True, window=2)
keywords_list = []
for item in tr4w.get_keywords(topk, word_min_len=1):
keywords_list.append(item.word)
kp_list = get_kp(cur_content, keywords_list)
# textRank_kp = tr4w.get_keyphrases(keywords_num=20, min_occur_num=2)
textRank_kp.append(kp_list)
json_file.close()
return textRank_kp
def getKeyword(text, keywords_num=20):
"""对text提取关键词，关键词个数为keywords_num, 关键短语也顺便提取。
关键短语在文中的最少出现次数为 phrase_min_num=5,没有再减。
返回关键字的列表（item.word, item.weight）和关键短语列表
"""
tr4w = TextRank4Keyword()
# 对文本进行分析，设定窗口大小为2，并将英文单词小写
tr4w.analyze(text=text, lower=True, window=2)
kw = tr4w.get_keywords(num=keywords_num, word_min_len=1)
mon = 5
while(mon>0):
kp = tr4w.get_keyphrases(keywords_num=keywords_num, min_occur_num=mon)
if len(kp) > 0:
print(mon)
break
mon -= 1
return kw, kp
def get_words_list(path='../data/countryComment.csv'):
tr4w = TextRank4Keyword()
# 获取评论
comments = pd.read_csv(path)['评论内容'].values
# 划分分词
word_list = []
for comment in comments:
tr4w.analyze(text=comment)
words = tr4w.words_all_filters
words = sum(words, []) # 二维转一维
word_list.append(words)
print(word_list)
words = sum(word_list, [])
words = pd.DataFrame(words)
words.to_csv('../data/words.csv', index=False)
print('words.csv文件保存成功！')
return words
def generator(self,text):
tr4w = TextRank4Keyword(stop_words_file='/home/ubuntu/HITChat/stopword.txt') # 导入停止词
#使用词性过滤，文本小，窗口为3
tr4w.train(text=text, speech_tag_filter=False, lower=True, window=3)
key = []
origin = []
with open("/home/ubuntu/HITChat/userarticle.txt","r") as f:
for line in f.readlines():
origin.append(line.strip())
for word in tr4w.get_keywords(10, word_min_len=2):
key.append(word)
if len(origin) <= 200:
with open("/home/ubuntu/HITChat/userarticle.txt","a") as f:
for i in range(len(key)):
if key[i] not in origin:
f.write(key[i]+"\n")
return key
def get_chinese_keywords(text):
tr4w = TextRank4Keyword()
tr4w.analyze(text=text, lower=True, window=5)
keywords_ = []
for item in tr4w.get_keywords(10, word_min_len=2):
# print(item.word, item.weight)
keywords_.append(item.word)
# print()
# print( '关键短语：' )
keyphrases = []
for phrase in tr4w.get_keyphrases(keywords_num=20, min_occur_num=2):
keyphrases.append(phrase)
return keywords_, keyphrases
def fit_transform(self, theta=0.5):
datMat = self.loadData(self.data)
word_segmentation = []
for i in range(len(datMat)):
word_segmentation.append(self.word_segment(datMat[i]))
print(
"............................................................................................"
)
print('文本已经分词完毕 !')
# 得到文本数据的空间向量表示
corpus_tfidf = self.get_Tfidf_vector_representation(word_segmentation)
# corpus_tfidf = self.get_Doc2vec_vector_representation(word_segmentation)
dictTopic, clusterTopic = self.single_pass(corpus_tfidf, datMat, theta)
print(
"............................................................................................"
)
print("得到的主题数量有: {} 个 ...".format(len(dictTopic)))
print(
"............................................................................................\n"
)
# 按聚类语句数量对主题进行排序，找到重要的聚类群
clusterTopic_list = sorted(clusterTopic.items(),
key=lambda x: len(x[1]),
reverse=True)
for k in clusterTopic_list[:30]:
cluster_title = '\n'.join(k[1])
# print(''.join(cluster_title))
# 得到每个聚类中的的主题关键词
word = TextRank4Keyword()
word.analyze(''.join(self.word_segment(''.join(cluster_title))),
window=5,
lower=True)
w_list = word.get_keywords(num=10, word_min_len=2)
sentence = TextRank4Sentence()
sentence.analyze('\n'.join(k[1]), lower=True)
s_list = sentence.get_key_sentences(num=3, sentence_min_len=5)[:30]
print("【主题索引】:{} \n【主题声量】：{} \n【主题关键词】： {} \n【主题中心句】 ：\n{}".format(
k[0], len(k[1]), ','.join([i.word for i in w_list]),
'\n'.join([i.sentence for i in s_list])))
print('\n')
print("【标题】：", '\n'.join([content[:20] for content in k[1]]))
print(
"-------------------------------------------------------------------------"
)
def text_keyword_abstract(article, keywords_len, sentences_len):
tr4w = TextRank4Keyword()
tr4w.analyze(text=article, lower=True, window=2)
keywords = []
for item in tr4w.get_keywords(keywords_len, word_min_len=2):
keywords.append(item.word)
keywords = ' '.join(keywords)
sentences = article.split('.')
first_sentence = sentences[0]
tr4s = TextRank4Sentence()
tr4s.analyze(text=article, lower=True, source='all_filters')
abstract = []
for item in tr4s.get_key_sentences(num=sentences_len):
if item.sentence != first_sentence:
abstract.append(item.sentence + '.')
abstract = '\n'.join(abstract)
return keywords #, abstract
def keywords_extraction(text, num, word_min_len):
tr4w = TextRank4Keyword(allow_speech_tags=['n', 'nr', 'nrfg', 'ns', 'nt', 'nz'])
# allow_speech_tags --词性列表，用于过滤某些词性的词
tr4w.analyze(text=text, window=2, lower=True, vertex_source='all_filters', edge_source='no_stop_words',
pagerank_config={'alpha': 0.85, })
# text -- 文本内容，字符串
# window -- 窗口大小，int，用来构造单词之间的边。默认值为2
# lower -- 是否将英文文本转换为小写，默认值为False
# vertex_source -- 选择使用words_no_filter, words_no_stop_words, words_all_filters中的哪一个来构造pagerank对应的图中的节点
# -- 默认值为`'all_filters'`，可选值为`'no_filter', 'no_stop_words', 'all_filters'
# edge_source -- 选择使用words_no_filter, words_no_stop_words, words_all_filters中的哪一个来构造pagerank对应的图中的节点之间的边
# -- 默认值为`'no_stop_words'`，可选值为`'no_filter', 'no_stop_words', 'all_filters'`。边的构造要结合`window`参数
# pagerank_config -- pagerank算法参数配置，阻尼系数为0.85
keywords = tr4w.get_keywords(num=num, word_min_len=word_min_len)
# num -- 返回关键词数量
# word_min_len -- 词的最小长度，默认值为1
return keywords
def nlp(contents):
tr4w = TextRank4Keyword()
tr4w.analyze(text=''.join(i for i in contents),
lower=True,
window=2)
tr4s = TextRank4Sentence()
tr4s.analyze(text=''.join(i for i in contents),
lower=True,
source='all_filters')
keyword = [item for item in tr4w.get_keywords(20, word_min_len=1)]
keyphase = [
item for item in tr4w.get_keyphrases(keywords_num=20,
min_occur_num=2)
]
keysentence = [item for item in tr4s.get_key_sentences(num=3)]
return keyword, keyphase, keysentence
def sina_keyword_abstract(article, keywords_len, sentences_len):
# 抽取关键词
tr4w = TextRank4Keyword()
tr4w.analyze(text=article, lower=True, window=2)
keywords = []
for item in tr4w.get_keywords(keywords_len, word_min_len=1):
keywords.append(item.word)
# 抽取摘要
tr4s = TextRank4Sentence()
tr4s.analyze(text=article, lower=True, source='all_filters')
abstract = []
for item in tr4s.get_key_sentences(num=sentences_len):
if str(item.sentence).startswith('原标题') or str(item.sentence).startswith('责任编辑') or str(
item.sentence).startswith('来源'):
continue
abstract.append(item.sentence + '。')
abstract = '\n'.join(abstract)
return keywords, abstract
def contain_word(query, key_query):
import_html_dir = Path.cwd().parent / 'html' / query
index_csv_dir = Path.cwd().parent / 'csv' / f'{query}.csv'
export_dir = Path.cwd().parent / 'category'
if not export_dir.exists():
export_dir.mkdir()
export_html_dir = Path.cwd().parent / 'category' / query
if not export_html_dir.exists():
export_html_dir.mkdir()
index = pd.read_csv(index_csv_dir)
for key, value in key_query.items():
with open(os.path.join(f'{key}.csv'), 'w',
encoding='utf-8-sig') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(["title", "url"])
for i in range(len(index)):
url = index.iloc[i, 2]
title = index.iloc[i, 1]
html_file = codecs.open(os.path.join(import_html_dir, f'{title}.html'),
'r', 'utf-8').read()
end = 'media_tool_meta tips_global_primary meta_primary'
html_file = html_file[:html_file.rfind(end)]
text = BeautifulSoup(html_file, features="lxml").get_text() #转化为txt
tr4w = TextRank4Keyword()
tr4w.analyze(text=text, lower=True, window=2)
list_key = []
for key_word in tr4w.get_keywords(10, word_min_len=2):
list_key.append(key_word.word)
textrank = analyse.textrank
keywords = textrank(text, 10)
for keyword in keywords:
list_key.append(keyword)
list_key = set(list_key)
print(title, list_key)
for key, value in key_query.items():
if not list_key.isdisjoint(value):
print(title, key)
with open(os.path.join(export_html_dir, f'{key}.csv'),
'a',
encoding='utf-8-sig') as csvfile:
writer = csv.writer(csvfile)
writer.writerows([(title, url)])
def Keyword():
text = codecs.open('/Users/liamtheron/Desktop/Deloiite/test.txt',
'r',
encoding='utf-8').read()
tr4w = TextRank4Keyword()
tr4s = TextRank4Sentence()
tr4w.analyze(text=text, lower=True, window=2)
tr4s.analyze(text=text, lower=True)
print('<关键词>：')
for item in tr4w.get_keywords(20, word_min_len=1):
print(item.word, item.weight)
print()
print('<关键短语>：')
for phrase in tr4w.get_keyphrases(keywords_num=20, min_occur_num=2):
print(phrase)
print()
print('<摘要>：')
for item in tr4s.get_key_sentences(num=3):
print(item.index, item.weight, item.sentence)
def zhihu_exec():
Qlink = request.form.get('Qlink', '')
Client = zhihu_oauth.ZhihuClient()
Client.load_token('token.pkl')
me = Client.me()
question = Client.question(int(Qlink))
with open(os.path.join(os.path.join('projhorus','static'),'question_%s_result.txt' % Qlink),'w') as f:
for i in question.answers:
tr4w = TextRank4Keyword()
tr4w.analyze(text=i.content, lower=True, window=2)
f.write(u'<--------------------关键词-------------------->\n')
for item in tr4w.get_keywords(20, word_min_len=1):
f.write(str(item.word) +' '+ str(item.weight)+'\n')
f.write(u'<--------------------关键短语-------------------->\n')
for phrase in tr4w.get_keyphrases(keywords_num=20, min_occur_num=2):
f.write(phrase+'\n')
global FLAG
FLAG = '/static/question_%s_result.txt' % Qlink
return redirect('/')
def textrank_keyWords(cat):
df_u8 = pd.read_csv('contents/' + cat + '_u8.csv', encoding="utf_8_sig")
df_gb = pd.read_csv('contents/' + cat + '_gb.csv', encoding="GB2312")
content = []
for i in range(len(df_gb['content'])):
tempStr = str(df_gb['title'][i]).strip() + ' ' + str(
df_gb['content'][i]).strip()
content.append(tempStr)
for i in range(len(df_u8['content'])):
content.append(
str(df_u8['title'][i]).strip() + ' ' +
str(df_u8['content'][i]).strip())
words = {}
tr4w = TextRank4Keyword(stop_words_file='stopWords.txt')
randomList = []
for i in range(500):
randomList.append(random.randint(0, len(content) - 1))
for i in randomList:
tr4w.analyze(text=content[i], lower=True, window=2)
for item in tr4w.get_keywords(5, word_min_len=1):
if item.word not in stopList and item.word not in specStop:
if item.word not in words.keys():
words[item.word] = item.weight
else:
words[item.word] = words[item.word] + item.weight
sorted_by_value = sorted(words.items(), key=lambda kv: kv[1], reverse=True)
#print(cat + ':')
tags = []
frequency = []
for l in sorted_by_value[0:20]:
f = l[1]
w = l[0]
frequency.append(float(f) * 1000)
tags.append(w)
total_text = {}
for i in range(len(tags)):
total_text[tags[i]] = int(frequency[i])
wordcloud = WordCloud(font_path='C:/WINDOWS/Fonts/STKAITI.TTF',
background_color='white').fit_words(total_text)
wordcloud.to_file('wordcloud/' + cat + '_tr.jpg')
def action_two():
import pandas as pd
from textrank4zh import TextRank4Keyword, TextRank4Sentence
news = pd.read_table('textrank/news.txt', encoding='GB18030', header=None)
strings = ''
for index in range(news.shape[0]):
strings += news.loc[index, 0]
tr4w = TextRank4Keyword()
tr4w.analyze(text=strings, lower=True, window=3)
print('关键词：')
for item in tr4w.get_keywords(20, word_min_len=2):
print(item.word, item.weight)
tr4s = TextRank4Sentence()
tr4s.analyze(text=strings, lower=True, source='all_filters')
print('摘要：')
# 重要性较高的三个句子
for item in tr4s.get_key_sentences(num=3):
print(item.weight, item.sentence)
def get_summary(self, data, flag=0):
text = "".join(data)
if flag == 0:
tr4w = TextRank4Keyword()
tr4w.analyze(text=text, lower=True, window=2)
#ret = tr4w.get_keywords()
ret = tr4w.get_keyphrases(keywords_num=12, min_occur_num=0)
if len(ret) > 0:
return ret[0]
else:
return ""
else:
tr4s = TextRank4Sentence()
tr4s.analyze(text=text, lower=True)
ret = tr4s.get_key_sentences(num=6, sentence_min_len=4)
if len(ret) >= 0:
return ret[0]['sentence']
else:
return ""
def textSummary(fileName, finalName):
text = codecs.open(fileName, 'r', 'utf-8').read()
tr4w = TextRank4Keyword()
tr4w.analyze(
text=text, lower=True, window=2
) # py2中text必须是utf8编码的str或者unicode对象，py3中必须是utf8编码的bytes或者str对象
# 关键词
tr4s = TextRank4Sentence()
tr4s.analyze(text=text, lower=True, source='all_filters')
sentences = {}
for item in tr4s.get_key_sentences(num=50):
if len(item.sentence) not in sentences.keys():
sentences[len(item.sentence)] = []
sentences[len(item.sentence)].append(item.sentence)
continue
sentences[len(item.sentence)].append(item.sentence)
key_sentences = []
for i in range(3):
key = max(sentences.keys())
# print(sentences[key])
key_sentences.append(sentences[key][0])
sentences.pop(key)
text = re.split(
pattern=
r'[\u3000-\u301e\ufe10-\ufe19\ufe30-\ufe44\ufe50-\ufe6b\uff01-\uffee]',
string=text)
ks = []
for te in text:
for k in key_sentences:
if str(te) in str(k) and str(k) not in ks:
ks.append(k)
line = ''
for k in ks:
line += k + " "
fw = codecs.open(finalName + "output.txt", 'a', 'utf-8')
fw.write(line)
def get_textrank4zh_keywords_phrase(contents):
"""
获取文本关键字短语，这个功能有点不完善，不好用
:param contents: string
:return: dict of list [{x},{x}]
"""
# 定义返回前20个关键词短语
topK = 20
tr4w = TextRank4Keyword()
tr4w.analyze(text=contents, lower=True)
# logger.info('使用textrank4zh提取关键词短语，默认提取20个')
# print('关键短语：')
# for phrase in tr4w.get_keyphrases(keywords_num=20, min_occur_num=2):
# print(phrase)
result = tr4w.get_keyphrases(keywords_num=topK, min_occur_num=2)
return result
def generate_keywords(text, number):
"""
textrank4zh: 针对中文文本的TextRank算法实现，用于提取关键词和摘要。 https://github.com/letiantian/TextRank4ZH
pyhanlp: HanLP自然语言处理工具包的python接口，实现TextRank关键词提取算法。 https://github.com/hankcs/pyhanlp
jieba: jieba分词工具包，实现TF-IDF算法，TextRank算法的关键词抽取。 https://github.com/fxsjy/jieba
:param text: 文本
:param number: 关键词个数
:return: 关键词字典
"""
keywords = {}
tr4w = TextRank4Keyword()
tr4w.analyze(text=text, lower=True, window=2)
for item in tr4w.get_keywords(number, word_min_len=1):
keywords.setdefault('textrankzh', []).append(item.word)
tr4s = TextRank4Sentence()
tr4s.analyze(text=text, lower=True, source='all_filters')
abstract = ""
TextRankKeyword = JClass('com.hankcs.hanlp.summary.TextRankKeyword')
for item in tr4s.get_key_sentences(num=2):
abstract += item.sentence
tr4w.analyze(text=abstract, lower=True, window=2)
for item in tr4w.get_keywords(number, word_min_len=1):
keywords.setdefault('textrank_abs', []).append(item.word)
for item in HanLP.extractKeyword(text, number):
keywords.setdefault('hanlp', []).append(item)
for item in HanLP.extractKeyword(abstract, number):
keywords.setdefault('hanlp_abs', []).append(item)
for item in jieba.analyse.extract_tags(text, topK=number, withWeight=False, allowPOS=()):
keywords.setdefault('tfidf', []).append(item)
for item in jieba.analyse.textrank(text, topK=number, withWeight=False, allowPOS=('ns', 'n', 'vn', 'v')):
keywords.setdefault('jiebarank', []).append(item)
for item in jieba.analyse.extract_tags(abstract, topK=number, withWeight=False, allowPOS=()):
keywords.setdefault('tfidf_abs', []).append(item)
for item in jieba.analyse.textrank(abstract, topK=number, withWeight=False, allowPOS=('ns', 'n', 'vn', 'v')):
keywords.setdefault('jiebarank_abs', []).append(item)
return keywords
def extract_key_information(self,
num_key_word=30,
num_key_phrase=20,
num_key_sentence=5):
text = ''.join(self.article_list)
# 创建分词类的实例
tr4w = TextRank4Keyword()
# 对文本进行分析，设定窗口大小为2，并将英文单词小写
tr4w.analyze(text=text, lower=True, window=2)
with open(self.rule_reference_filename, "a") as f:
# 从关键词列表中获取前20个关键词
f.write(
'###########################关 键 词##################################'
+ '\n')
for item in tr4w.get_keywords(num=num_key_word, word_min_len=1):
if item.word in self.stopwords or item.word in self.filter_dictionary:
continue
else:
f.write(item.word + '\t' + str(item.weight) + '\n')
with open(self.rule_reference_filename, "a") as f:
# 从关键短语列表中获取20个关键短语
f.write(
'##########################关 键 短 语##################################'
+ '\n')
for phrase in tr4w.get_keyphrases(keywords_num=num_key_phrase,
min_occur_num=2):
f.write(phrase + '\n')
# 创建分句类的实例
tr4s = TextRank4Sentence()
# 英文单词小写，进行词性过滤并剔除停用词
tr4s.analyze(text=text, lower=True, source='all_filters')
with open(self.rule_reference_filename, "a") as f:
# 从关键短语列表中获取5关键短语
f.write(
'###########################关 键 句##################################'
+ '\n')
for item in tr4s.get_key_sentences(num=num_key_sentence):
f.write(
str(item.index) + str(item.weight) + str(item.sentence) +
'\n')
f.write('----------------' + '\n')
def textRank_ppt(url,num_abs):
"""
:param url:
:param num_abs: 生成ppt张数
:return:
"""
title,texts = article_extract(url)
tr4w = TextRank4Keyword()
tr4w.analyze(text=texts ,lower=True, window=2) # py2中text必须是utf8编码的str或者unicode对象，py3中必须是utf8编码的bytes或者str对象
tr4s = TextRank4Sentence()
tr4s.analyze(text=texts, lower=True, source = 'all_filters')
print( '关键词：' )
key_words = ""
for item in tr4w.get_keywords(7, word_min_len=2):
print(item.word, item.weight)
key_words = key_words + item.word + "\n"
#ppt generate
prs = Presentation()
slide1, body_shape1 = ppt1.add_slide(prs=prs,slide_title=title, style_number=0)
slide2, body_shape2 = ppt1.add_slide(prs=prs, style_number=1,slide_title="关键词",content="")
ppt1.add_paragraph(body_shape2,text=key_words,size=20)
i = 0
#图片生成，并添加到ppt中
extract_image.pic_extract(url)
print("句子：")
for item in tr4s.get_key_sentences(num=(num_abs-2)*2):
if i % 2 == 0:
slide3, body_shape3 = ppt1.add_slide(prs=prs, style_number=1,slide_title="摘要",content="")
try:
ppt1.add_picture(slide2=slide3,pic_path="image1/image_"+str(i)+".jpg")
except:
print("no picture")
i += 1
# print(len(item.sentence),item.index)
ppt1.add_paragraph(body_shape3,text=item.sentence,size=20)
prs.save('test.pptx')
print("ppt 已生成")
def extractKeywordFromUser(sentence, targetNum):
textrank = TextRank4Keyword()
s = sentence
textrank.analyze(text=s, lower=True, window=2)
keywords = [
item.word for item in textrank.get_keywords(targetNum, word_min_len=1)
]
candidatewords = []
candidatescores = []
if len(keywords) < targetNum:
for keyword in keywords:
wordlist, scorelist = synonyms.nearby(keyword)
candidatewords.extend(wordlist)
candidatescores.extend(scorelist)
sortedIndex = np.argsort([-i for i in candidatescores])
sortedIndex = [
sortedIndex[i] for i in range(len(sortedIndex))
if not candidatescores[sortedIndex[i]] == 1
]
for i in range(targetNum - len(keywords)):
keywords.append(candidatewords[sortedIndex[i]])
return keywords
def main(self, content, label, window=2, k=20):
"""
The function is used to exract keywords using TextRank.
@ param `content` String list of texts, which should be segmented string.
@ param `label` String/Integer list indicating the category.
@ param `window` count window.
@ param `k` top k keywords will be returned, default 10.
"""
keywords = {}
cate_content = {}
for c, l in zip(content, label):
if l in cate_content:
cate_content[l] += " " + c.replace(" ", "")
else:
cate_content[l] = c.replace(" ", "")
for item in cate_content.items():
tr4w = TextRank4Keyword()
tr4w.analyze(text=item[1], lower=True, window=window)
kws = tr4w.get_keywords(k, word_min_len=1)
keywords[item[0]] = [x.word for x in kws]
return keywords
def finalGet(content, number=5):
text = content
tr4w = TextRank4Keyword()
tr4w.analyze(text=text, lower=True, window=2)
# 得到五个关键词，能够是用户在列表中通过关键词组来对Note进行辨别
wordList = []
for phrase in tr4w.get_keyphrases(keywords_num=20, min_occur_num=2):
wordList.append(phrase)
if len(wordList) < number:
for item in tr4w.get_keywords(number - len(wordList), word_min_len=2):
wordList.append(item.word)
print(wordList)
# 得到一个合起来的摘要
summary = []
tr4s = TextRank4Sentence()
tr4s.analyze(text=text, lower=True, source='all_filters')
for item in tr4s.get_key_sentences(num=3):
summary.append(item.sentence)
print(summary)
sumText = '。'.join(summary)
print(sumText)
return (wordList, sumText)
