res = requests.get(link,).content.decode('utf8') html_ = etree.HTML(res) # 选取所有需要剔除的元素 for del_element in html_.xpath('//*[@>): # 这里必须定位至父节点删除子节点,不允许“自杀” del_element.getparent().remove(del_element) result = html_.xpath('string(//*[@>'')
res = requests.get(link,).content.decode('utf8') html_ = etree.HTML(res) # 选取所有需要剔除的元素 for del_element in html_.xpath('//*[@>): # 这里必须定位至父节点删除子节点,不允许“自杀” del_element.getparent().remove(del_element) result = html_.xpath('string(//*[@>'')
相关文章: