我正在尝试使用网站上提供的以下库
https://pypi.org/project/text-summarizer/
从 text_summarizer 导入摘要器
正如网站所告知的,我已经使用下面的语法安装了 text_summarizer 包,当在 python 中加载它时,我收到错误 导入错误:无法导入名称“summarizer”
如果这个软件包有效,任何人都可以帮助我吗
检查是否有循环依赖项导入。这可能与这里的问题的答案相同:ImportError: Cannot import name X
试试这个
import bs4 as bs
import urllib.request
import re
import nltk
impfile = ""
number_of_sentences_in_summary = 7
max_words_in_sentence = 20
import sys, getopt
## From https://stackabuse.com/text-summarization-with-nltk-in-python/
## NLTK install instructions are at https://www.nltk.org/
number_of_sentences_in_summary = int(sys.argv[1])
max_words_in_sentence = int(sys.argv[2])
scraped_data = urllib.request.urlopen(sys.argv[3])
scraped_data = urllib.request.urlopen('https://en.wikipedia.org/wiki/Artificial_intelligence')
article = scraped_data.read()
parsed_article = bs.BeautifulSoup(article,'lxml')
paragraphs = parsed_article.find_all('p')
article_text = ""
for p in paragraphs:
article_text += p.text
# Removing Square Brackets and Extra Spaces
article_text = re.sub(r'\[[0-9]*\]', ' ', article_text)
article_text = re.sub(r'\s+', ' ', article_text)
# Removing special characters and digits
formatted_article_text = re.sub('[^a-zA-Z]', ' ', article_text )
formatted_article_text = re.sub(r'\s+', ' ', formatted_article_text)
sentence_list = nltk.sent_tokenize(article_text)
stopwords = nltk.corpus.stopwords.words('english')
#stopwords = nltk.corpus.stopwords.words('hungarian')
word_frequencies = {}
for word in nltk.word_tokenize(formatted_article_text):
if word not in stopwords:
if word not in word_frequencies.keys():
word_frequencies[word] = 1
else:
word_frequencies[word] += 1
maximum_frequncy = max(word_frequencies.values())
for word in word_frequencies.keys():
word_frequencies[word] = (word_frequencies[word]/maximum_frequncy)
sentence_scores = {}
for sent in sentence_list:
for word in nltk.word_tokenize(sent.lower()):
if word in word_frequencies.keys():
if len(sent.split(' ')) < max_words_in_sentence:
if sent not in sentence_scores.keys():
sentence_scores[sent] = word_frequencies[word]
else:
sentence_scores[sent] += word_frequencies[word]
import heapq
summary_sentences = heapq.nlargest(number_of_sentences_in_summary, sentence_scores, key=sentence_scores.get)
summary = '\n'.join(summary_sentences)
print(summary)