按原样输出网页内容

ir_content = tree.xpath('//p[@align="justify"]//text()')
if ir_content == []:
ir_content = tree.xpath('//td/p/span//text()')
neirong = '\u3000\u3000'

for i in ir_content:
da = i.strip().replace(' ', '').replace('\n', '').replace('\r', '')
if len(da) == 0:
pass
else:
neirong += da
neirong += '\n'
neirong += '\u3000\u3000'
neirong = neirong.replace('"', '')
posted @ 2021-10-21 14:59  布都御魂  阅读(44)  评论(0)    收藏  举报