sed提取两个关键字之间的内容_python提取文本指定内容

<table> 
	<thead> 
		<tr> 
			<th>ID</th> 
			<th>名称</th> 
			<th>电话</th> 
			<th>说明</th> 
			<th>类型</th> 
			<th>位置</th> 
		</tr> 
	</thead> 
	<tbody> 
		<tr> 
			<td>1</td> 
			<td>11</td> 
			<td>111111</td> 
			<td>1111111</td> 
			<td>11111111</td> 
			<td>111111111</td> 
		</tr> 
		<tr> 
			<td>2</td> 
			<td>22</td> 
			<td></td> 
			<td></td> 
			<td>22222222</td> 
			<td>222222222</td> 
		</tr> 
	</tbody> 
</table>

res = html.xpath('//tbody/tr/td/text()')
print(res)

['1', '11', '111111', '1111111', '11111111', '111111111', '2', '22', '22222222', '222222222', ...]

res = html.xpath('//tbody/tr/td')
print(res)

[<Element td at 0x93cd9c8>, <Element td at 0x93cdbc8>, <Element td at 0x93cdd48>, <Element td at 0x93cd708>, <Element td at 0x93cddc8>, <Element td at 0x93d74c8>, <Element td at 0x93d7d08>, <Element td at 0x93d7048>, <Element td at 0x93d7288>, <Element td at 0x93d7548>, <Element td at 0x93d7888>, <Element td at 0x93d7388>]

res2 = [res[s : s + 6] for s in range(0, len(res), 6)]		#将大list分割成多个小list，每个小list包含6个td节点
print(res2)

[[<Element td at 0x93cdb48>, <Element td at 0x93cd788>, <Element td at 0x93cd848>, <Element td at 0x93cdd08>, <Element td at 0x93cdf88>, <Element td at 0x93d7e48>], [<Element td at 0x93d7e08>, <Element td at 0x93d7388>, <Element td at 0x93d7888>, <Element td at 0x93d7548>, <Element td at 0x93d7808>, <Element td at 0x93d7288>]]

		for x in res2:
			res3 = []
			for y in x:
				res4 = y.xpath('text()')
				res3.append(str(res4).strip("[']"))
			res3 = res3[:2] + res3[4:]				#只保留除了第3、4个td标签外的其他4个td标签的数据
			print(res3)

['1', '11', '11111111', '111111111']
['2', '22', '22222222', '222222222']