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 get_abstract(data, a, b, c):
"""
生成excel可以打开的的摘要文件
:param data: MySQL从取出的数据
:param a: 起始时间的
:param b: 结束时间
:param c: 话题ID
:return: null
"""
now_path = os.getcwd()
path = now_path.replace('\\', '/')
tr4s = TextRank4Sentence()
print('当前文章的摘要：')
results = []
for i in range(len(data['CONTENT'])):
# i = re.sub("[^\u4e00-\u9fa5]", '', i) # 记住只留文本？没有断句算不上摘要，这里需要用其他方式处理
# print('\u3002 \uff1b \uff0c \uff1a \u201c \u201d'
# '\uff08 \uff09 \u3001 \uff1f \u300a \u300b')
# # 。 ； ， ： “ ”（ ） 、 ？ 《 》
tmp = re.sub(
"[^\u4e00-\u9fa5\u3002\uff1b\uff0c\uff1a\u201c\u201d\uff08\uff09\u3001\uff1f\u300a\u300b0-9]",
'', data['CONTENT'][i])
tr4s.analyze(text=tmp, lower=True)
result = ''
# print()
# print('摘要：')
for item in tr4s.get_key_sentences(num=3):
# print(item.index, item.weight, item.sentence)
result += item.sentence
if len(result) != 0:
results.append([
data['UPTIME'][i], data['TITLE'][i], data['AUTHOR'][i], result
])
# data['CONTENT'][i] = results
column_name = ['更新时间', '标题/题目', '作者', '摘要']
tmp_text = pd.DataFrame(columns=column_name, data=results)
tmp_text.to_csv('./data/textrank/topic{}_{}-{}abstract.csv'.format(
c, a, b),
encoding='utf_8_sig')
print('>>>>>>>>>>>>>> 已经保存到csv等待计算或查看 >>>>>>>>>>>>>>>')
# os.startfile(now_path + '/data/textrank/topic{}_{}-{}abstract.csv'.format(c, a, b)) # 弹出工作表
# 但是这里需要完整的工作路径才行 T:/AC/Python/PublicOpinionMonitor/data/textrank/topic{}_abstract.csv
# print(results)
# print(' >>>>>> >>>>>>>>> 将在10秒后关闭excel >>>>>>> >>>>>>>> ')
time.sleep(10)
clear_all_var()
return
def abstract(fileName, step):
tr4s = TextRank4Sentence()
f = open(fileName, 'r')
text = f.readlines()
articleLen = countArticleLen(text)
text = [t.split('\n')[0].strip() for t in text]
if not judge(text): # 如果judge返回False则进入合并方法
text = ''.join(text)
text = text.replace('……', '，')
head, middles, last = splitPart(text, step)
cate, result = mergeAbstract(tr4s, text, head, middles, last)
else:
cate, result = paragramAbstarct(tr4s, text)
return cate, result, articleLen
def _36r_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):
abstract.append(item.sentence + '。')
abstract = '\n'.join(abstract)
return keywords, abstract
def get_key_sents(cont, num=3):
'''
根据内容提取摘要，
num=3,提取三段摘要，
return: 下划线拼接提取出的摘要
'''
tr4s = TextRank4Sentence()
tr4s.analyze(text=cont, lower=True, source='all_filters')
key_sents = []
summarys = []
for item in tr4s.get_key_sentences(num=num):
key_sents.append((item.index, item.weight, item.sentence))
for s in key_sents:
summarys.append(s[2])
return '_'.join(summarys)
def text_rank_subtract(content: str, n=3):
"""
传入中文字符串，使用text rank方法抽取摘要
:param content: (str)文章内容
:param n: 抽取摘要的句子数量n
:return: summary_sentences(list)摘要句子列表
"""
tr4s = TextRank4Sentence()
tr4s.analyze(text=content, lower=True, source='all_filters')
# 抽取摘要
summary_sentences = [
item.sentence for item in tr4s.get_key_sentences(num=n)
]
return summary_sentences
def cal_key_sentence(self):
# 输出重要的句子
tr4s = TextRank4Sentence()
tr4s.analyze(text=self.text, lower=True, source='all_filters')
# print('摘要：')
# 重要性较高的3个句子
for item in tr4s.get_key_sentences(
num=self.sentence_num): # sentence_num是生成关键句的个数
# index是语句在文本中位置，weight表示权重
# print('item.index, item.weight, item.sentence',item.index, item.weight, item.sentence)
# self.import_sentence.append(str(item.index) + ' ' +item.sentence)
self.import_sentence.append(item.sentence)
# print('self.import_sentence',self.import_sentence[0][2:] + self.import_sentence[1][2:] + self.import_sentence[2][2:])
print('self.import_sentence', self.import_sentence)
def __summary(self, post: dict):
'''
Summarize the post's filtered content.
Args:
post:
The dict as a collection of all desired information in a post.
'''
print(post['link'], 'nlp and takes time...')
trw = TextRank4Keyword()
trw.analyze(post['content_filtered'], lower=True)
post['keywords'] = [i.word for i in trw.get_keywords(3)]
trs = TextRank4Sentence()
trs.analyze(post['content_filtered'], lower=True)
post['summary'] = [i.sentence for i in trs.get_key_sentences(2)]
def topic_paragraph(self):
with open('./1.txt') as f:
data = f.read()
# print(data)
tr4s = TextRank4Sentence()
tr4s.analyze(text=data, lower=True, source="all_filters")
abstract = []
for item in tr4s.get_key_sentences(num=100):
if len(item.sentence) < 300:
abstract.append([item.index, item.sentence])
abstract = sorted(abstract[:1], key=lambda x: x[0])
abstract = [
"(%i) %s \n" % (i, x[i]) for i, x in enumerate(abstract, 1)
]
def getAbstarct(text, sentencesNum = 3, lists = False):
"""对text提取摘要，内容为sentencesNum个高权重句子，
返回结果默认为一个字符串，也可以是N个句子的列表"""
if sentencesNum <2:
sentencesNum = 2
tr4s = TextRank4Sentence()
tr4s.analyze(text=text, lower=True, source='all_filters')
# print('摘要为：')
ss = []
for item in tr4s.get_key_sentences(num=sentencesNum):
# 打印句子的索引、权重和内容
# print(item.index, item.weight, item.sentence)
ss.append(item.sentence)
if lists:
return ss #n个句子列表
return "。".join(ss) #默认一个字符串
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 dataframe_keyword_extraction(data):
mod = TextRank4Sentence()
label_index = data.columns.get_loc('content')
for i in range(len(data)):
res = ""
print("处理第{}条数据".format(i))
content = data.iloc[i]['content']
if (len(content) < 300):
continue
mod.analyze(text=content, lower=False, source='all_filters')
for str in mod.get_key_sentences(num=3):
if len(res) < 256:
res += str.sentence
print(res)
data.iloc[i, label_index] = res
return data
def parse_abstract_textrank(text):
import sys
try:
reload(sys)
sys.setdefaultencoding('utf-8')
except:
pass
from textrank4zh import TextRank4Keyword, TextRank4Sentence
tr4s = TextRank4Sentence()
tr4s.analyze(text=text, lower=True, source='all_filters')
res = ""
for item in tr4s.get_key_sentences(num=3):
res += item.sentence # index是语句在文本中位置，weight是权重
return res
def ks_plot(text, number):
tr4s = TextRank4Sentence()
tr4s.analyze(text, lower=True, source='no_stop_words')
data = pd.DataFrame(data=tr4s.key_sentences)
mpl.rcParams['font.sans-serif'] = [u'SimHei']
mpl.rcParams['axes.unicode_minus'] = False
plt.figure(facecolor='w')
plt.plot(data['weight'], 'ro-', lw=2, ms=5, alpha=0.7)
plt.grid(b=True)
plt.xlabel(u'句子', fontsize=14)
plt.ylabel(u'重要度', fontsize=14)
plt.title(u'句子的重要度曲线', fontsize=18)
plt.show()
key_sentences = tr4s.get_key_sentences(num=number, sentence_min_len=4)
for sentence in key_sentences:
print(sentence['weight'], sentence['sentence'])
def cal_rouge_textRank(article_lst, summ_lst):
rouge = Rouge()
tr4s = TextRank4Sentence()
rouges = np.zeros((3, 3))
cnt = 0
for article, summ in zip(*(article_lst, summ_lst)):
tr4s.analyze(text=article, lower=True, source='all_filters')
keysentence_list = list()
for item in tr4s.get_key_sentences(num=10):
s = ''.join(item.sentence)
s = re.sub("\d{4,}", '', s)
keysentence_list.append(s)
hyps = ""
for j, sentence in enumerate(keysentence_list):
if j == 0 and len(sentence) > 60:
hyps = sentence[:60]
break
if (len(hyps) + len(sentence)) <= 60:
hyps += sentence
else:
break
hyps = clean(hyps)
summ = summ.strip()
summ = clean(summ)
summ_ids, hyps_ids = word_for_rouge(summ, hyps)
rouge_score = rouge.get_scores(" ".join(hyps_ids)[:len(summ)],
" ".join(summ_ids))
rouge1 = rouge_score[0]["rouge-1"]
rouge2 = rouge_score[0]["rouge-2"]
rougel = rouge_score[0]["rouge-l"]
rouges[0] += np.array(list(rouge1.values()))
rouges[1] += np.array(list(rouge2.values()))
rouges[2] += np.array(list(rougel.values()))
cnt += 1
rouges = rouges / cnt
print("Rouge: Rouge-1 : F P R")
print("Rouge: Rouge-2 : F P R")
print("Rouge: Rouge-L : F P R")
print(rouges)
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 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 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 key_text(text):
tr4s = TextRank4Sentence()
tr4s.analyze(text=text, lower=True, source='all_filters')
import_sentence = []
for item in tr4s.get_key_sentences(num=3): # sentence_num是生成关键句的个数
# index是语句在文本中位置，weight表示权重
# print('item.index, item.weight, item.sentence',item.index, item.weight, item.sentence)
# self.import_sentence.append(str(item.index) + ' ' +item.sentence)
import_sentence.append(item.sentence)
# key_sentence = [i.sentence for i in tr4s.get_key_sentences(num=3)] # num生成关键句的个数
# 核心内容是 标题 + top-3文本本体关键句
key_sentences = import_sentence[0][2:] + import_sentence[1][
2:] + import_sentence[2][2:]
# 过长文本截断
if len(key_sentences) < 512:
return key_sentences
else:
return key_sentences[:512]
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 cctv_abstract(date):
"""从CCTV新闻联播当天的内容中抽取10个句子作为摘要
:param date: str
日期，如：20181222
:return: str
"""
news = ts_pro.cctv_news(date=date)
contents = "".join(list(news['content']))
tr4s = TextRank4Sentence()
tr4s.analyze(text=contents, lower=True, source='all_filters')
abstract = []
for i, item in enumerate(tr4s.get_key_sentences(num=10), 1):
abstract.append("(%i) %s。\n" % (i, item.sentence))
return "".join(abstract)
def get_event(text):
tr4s = TextRank4Sentence()
tr4s.analyze(text=text, lower=True, source='all_filters')
for item in tr4s.get_key_sentences(num=len(tr4s.sentences)/2):
if '說' not in item.sentence:
index_list.append(item.index)
#print(item.index, item.weight, item.sentence)
index_list.sort()
for i in index_list:
#print(tr4w.sentences[i])
sentence_list.append(tr4s.sentences[i])
for i in index_list:
s = tr4s.sentences[i]
p = parse_tree(s)
tmp_list = []
for i in range(len(p)):
if p[i][6] != 'N':
tmp_list.append((p[i], s))
parse_list.append(tmp_list)
for list in parse_list:
for s in list:
index = get_index(s[0])
index.sort()
event = ''
for i in index:
for j in range(i, len(s[0])):
if s[0][j] == ':':
start = j+1
if s[0][j] == '|' or s[0][j] == ')':
end = j
break
if s[0][start:end] != '說':
event += s[0][start:end]
if len(event) != 0:
events.append(event)
return events
def summary_candidate_fin(text):
tr4s = TextRank4Sentence()
tr4s.analyze(text=text, lower=True, source='all_filters')
#設定只保留中文、英文、數字（去掉韓語日語德語，也會去掉表情符號等等）
#reference: https://zhuanlan.zhihu.com/p/84625185
rule = re.compile(u"[^a-zA-Z0-9\u4e00-\u9fa5]")
#print( '摘要：' )
tt = []
for i, item in enumerate(tr4s.get_key_sentences(num=3,
sentence_min_len=80)):
#print('第{}順位，利用textrank的第一次摘要: '.format(i+1))
#print(item.index, item.weight, item.sentence)
s = SnowNLP(item.sentence)
#print('利用snownlp再取一次的結果: ')
secnd_sn = s.summary(3)
#print(secnd_sn)
for cont in secnd_sn:
ttt = rule.sub(' ', str(cont))
if len(ttt.split(' ')) < 3 and len(ttt) > 12:
tt.append(ttt)
#print(' ')
s = SnowNLP(text)
#print('直接使用snownlp的摘要: ')
word = {}
first_sn = s.summary(3)
for cont in first_sn:
ttt = rule.sub(' ', str(cont))
if len(ttt.split(' ')) < 3 and len(ttt) > 12:
if word.get(ttt) == None:
word[ttt] = 1
tt.append(ttt)
#print(first_sn)
#print(' ')
if len(tt) == 0:
print('無適合的標題')
tt.append("無適合的標題")
return tt
return tt
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 process_introduce(self, introduce):
introduce = introduce.replace('\n', '').replace('\r', '').replace(
'\t', '').replace('\xa0', '').replace('\u3000',
'').replace(' ', '')
tr4s = TextRank4Sentence()
tr4s.analyze(text=introduce, lower=True, source='all_filters')
l = len(tr4s.get_key_sentences())
num_sentences = 3
sentences = tr4s.get_key_sentences(num=num_sentences)
sentences = sorted(sentences, key=lambda x: x.index, reverse=False)
news = []
if l >= num_sentences:
for i in range(num_sentences):
news.append(sentences[i].sentence)
else:
for i in range(l):
news.append(sentences[i].sentence)
return ''.join(news)
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 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 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_summarization(contents):
"""
获取文本摘要
:param contents: string
:return: dict of list [{x},{x}]
"""
# 定义返回前5个文本摘要
topK = 5
tr4s = TextRank4Sentence()
tr4s.analyze(text=contents, lower=True, source='all_filters')
# logger.info('使用textrank4zh提取摘要，默认提取5个')
# print('摘要：')
# for item in tr4s.get_key_sentences(num=5):
# print('文本位置：{}, 权重：{}，内容：{}'.format(item.index, item.weight, item.sentence)) # index是语句在文本中位置，weight是权重
result = tr4s.get_key_sentences(num=topK)
return result
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')
