newswan

回复 1# lxh623

function getDic() {
	param(
		[string]$filename
	)
	$f1 = Get-Content -Encoding UTF8 ( $filename + ".xhtml" )
	$f2 = $f1 -join "`n"
	$f3 = $f2 -replace '(<span class="text_3">[^<>]+</span><span class="text_1">[(][^()]+[)]</span>)',"`n`$1`n" -split "`n"
	$f4 = $f3 -match "text_3"
	$f5 = $f4 -replace "<[^<>]+>",""
	$f5 | Out-File -Encoding utf8 ( $filename + ".txt" )
}

getDic ".\juans\F28n1071_005"
getDic ".\juans\005"
复制代码

提取 text_3 text_1 里的字符
怎么替换 005 没明白