python3 尋找文章中的高頻詞彙__python

import jiebaimport requestsfrom bs4 import BeautifulSoupfrom collections import Counterdef extract_text(url):page_source = requests.get(url).contentbs_source = BeautifulSoup(page_source)report_text = bs_source.find_all('p')text = ""for p in report_text:text += p.get_text()text += '\n'return textdef  word_frequency(text):words = [word for word in jieba.cut(text, cut_all=True) if len(word) >= 2]c = Counter(words)for word_freq in c.most_common(10):word, freq = word_freqprint(word, freq)url_2016 = 'http://www.gov.cn/guowuyuan/2016-03/05/content_5049372.htm'text_2016 = extract_text(url_2016)word_frequency(text_2016)