![[求助] python 如何爬取 网页上调用JS函数打开的视频链接](/aiimages/%5B%E6%B1%82%E5%8A%A9%5D+python+%E5%A6%82%E4%BD%95%E7%88%AC%E5%8F%96+%E7%BD%91%E9%A1%B5%E4%B8%8A%E8%B0%83%E7%94%A8JS%E5%87%BD%E6%95%B0%E6%89%93%E5%BC%80%E7%9A%84%E8%A7%86%E9%A2%91%E9%93%BE%E6%8E%A5.png)
/* ***************************
** Most of this code was kindly
** provided to me by
** Andrew Clover (and at doxdesk dot com)
** http://and.doxdesk.com/
** in response to my plea in my blog at
** http://worldtimzone.com/blog/date/2002/09/24
** It was unclear whether he created it.
*/
function utf8(wide) {
var c, s
var enc = ""
var i = 0
while(i c= wide.charCodeAt(i++)
// handle UTF-16 surrogates
if (c>=0xDC00 %26amp%26ampc<0xE000) continue
if (c>=0xD800 %26amp%26ampc<0xDC00) {
if (i>=wide.length) continue
s= wide.charCodeAt(i++)
if (s<0xDC00 || c>=0xDE00) continue
c= ((c-0xD800)<<10)+(s-0xDC00)+0x10000
}
// output value
if (c<0x80) enc += String.fromCharCode(c)
else if (c<0x800) enc += String.fromCharCode(0xC0+(c>>6),0x80+(c%26amp0x3F))
else if (c<0x10000) enc += String.fromCharCode(0xE0+(c>>12),0x80+(c>>6%26amp0x3F),0x80+(c%26amp0x3F))
else enc += String.fromCharCode(0xF0+(c>>18),0x80+(c>>12%26amp0x3F),0x80+(c>>6%26amp0x3F),0x80+(c%26amp0x3F))
}
return enc
}
var hexchars = "0123456789ABCDEF"
function toHex(n) {
return hexchars.charAt(n>>4)+hexchars.charAt(n %26amp0xF)
}
var okURIchars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_-"
function encodeURIComponentNew(s) {
var s = utf8(s)
var c
var enc = ""
for (var i= 0i if (okURIchars.indexOf(s.charAt(i))==-1)
enc += "%"+toHex(s.charCodeAt(i))
else
enc += s.charAt(i)
}
return enc
}
function URLEncode(fld)
{
if (fld == "") return false
var encodedField = ""
var s = fld
if (typeof encodeURIComponent == "function")
{
// Use javascript built-in function
// IE 5.5+ and Netscape 6+ and Mozilla
encodedField = encodeURIComponent(s)
}
else
{
// Need to mimic the javascript version
// Netscape 4 and IE 4 and IE 5.0
encodedField = encodeURIComponentNew(s)
}
//alert ("New encoding: " + encodeURIComponentNew(fld) +
// "\n escape(): " + escape(fld))
return encodedField
}
JAVA有一个public String(byte bytes[], Charset charset)函数可以用指定字节数组和编码来构造字符串。一个public byte[] getBytes(Charset charset)函数把字符串按指定编码来得到字节数组。可以用这两个函数来实现编码转换。下面是一个简单的例子，注意一下例子中的文字本身的编码，最好在自己的环境中用gb2312重新输入，不然可能是乱码。当然转换后输出肯定有一个是乱码，也肯能都是乱码。根据你的编辑器的编码格式有关。
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
public class EncodingTest
{
public static void main(String[] args)
{
try
{
String gb = new String("国标2312".getBytes(),"gb2312")
System.out.println(gb)
byte [] b = gb.getBytes("gb2312")
String ios = new String(b,"ISO-8859-1")
System.out.println(ios)
} catch (UnsupportedEncodingException e)
{
e.printStackTrace()
}
}
}
