def get_topn_words_from_urls(urls,topn,save_reports = False):
htmls = [html_utils.get_html(url) for url in urls]
# 汇总文本
summary_atricle = '\n'.join([parse_report_article(html) for html in htmls])
if save_reports:
with open('reports.txt','w+') as fout:
fout.write(summary_atricle)
return cut_text_utils.get_topn_words(summary_atricle,topn)
def get_topn_words(url,topn):
html = html_utils.get_html(url)
article = parse_report_article(html)
return cut_text_utils.get_topn_words(article,topn)