def get_main_text(html):
main_text = Document(html).summary()
main_text = BeautifulSoup(main_text).getText()
# 处理空行
r = re.compile(r'\n+', re.M | re.S)
main_text = r.sub('\n', main_text)
# 去除首行回车
if main_text.find('\n') == 0:
main_text = main_text.replace('\n', '', 1)
return main_text
