我想提取脚本标记之间给出的数据。我也为此制作了一个正则表达式,但它没有在这个字符串上工作 -
<script>
var arrowimages = {
down: ['downarrowclass', 'Images/arrow-down.gif', 23],
right: ['rightarrowclass', 'Images/submenu-pointer.png']
}
var jqueryslidemenu = {
animateduration: {
over: 400,
out: 400
}, //duration of slide in/ out animation, in milliseconds
buildmenu: function (menuid, arrowsvar) {
jQuery(document).ready(function ($) {
var $mainmenu = $("#" + menuid + ">ul")
var $headers = $mainmenu.find("ul").parent()
$headers.each(function (i) {
var $curobj = $(this)
var $subul = $(this).find('ul:eq(0)')
this._dimensions = {
w: this.offsetWidth,
h: this.offsetHeight,
subulw: $subul.outerWidth(),
subulh: $subul.outerHeight()
}
this.istopheader = $curobj.parents("ul").length == 1 ? true : false
$subul.css({
top: this.istopheader ? this._dimensions.h + "px" : 0
})
$curobj.children("a:eq(0)").css(this.istopheader ? {
paddingRight: arrowsvar.down[2]
} : {}).append(
'<img src="' + (this.istopheader ? arrowsvar.down[1] : arrowsvar.right[1]) + '" class="' + (this.istopheader ? arrowsvar.down[0] : arrowsvar.right[0]) + '" style="border:0;top:12px;" />'
)
$curobj.hover(
function (e) {
var $targetul = $(this).children("ul:eq(0)")
this._offsets = {
left: $(this).offset().left,
top: $(this).offset().top
}
var menuleft = this.istopheader ? 0 : this._dimensions.w
menuleft = (this._offsets.left + menuleft + this._dimensions.subulw > $(window).width()) ? (this.istopheader ? -this._dimensions.subulw + this._dimensions.w : -this._dimensions.w) : menuleft
if($targetul.queue().length <= 1) //if 1 or less queued animations
$targetul.css({
left: menuleft + "px",
width: this._dimensions.subulw + 'px'
}).slideDown(jqueryslidemenu.animateduration.over)
},
function (e) {
var $targetul = $(this).children("ul:eq(0)")
$targetul.slideUp(jqueryslidemenu.animateduration.out)
}
) //end hover
$curobj.click(function () {
$(this).children("ul:eq(0)").hide()
})
}) //end $headers.each()
$mainmenu.find("ul").css({
display: 'none',
visibility: 'visible'
})
}) //end document.ready
}
}
//build menu with ID="myslidemenu" on page:
jqueryslidemenu.buildmenu("myjquerymenu", arrowimages)
</script>
我的正则表达式是 - <script[^>]*>(.*?)</script>
其他正常的脚本标记(如<script type="text/javascript" src="JsFiles/jquery.min.js"></script>
)由我的正则表达式检索,但我不知道为什么它不能处理该特定的字符串。我需要文本之间的数据来修改数据,因此也需要分组。我也尝试过jsoup来完成这项任务 -
Elements scripts = doc.select("script");
for(Element script: scripts) {
System.out.println("src " + script);
String lineread = script.toString();
String data = script.data();
if(!data.isEmpty()) {
System.out.println(data);
Pattern p = Pattern.compile("\\\"([^\\\"]*)\\\"|'([^']*)'");
Matcher m = p.matcher(lineread);
while(m.find()) {
if(m.group(0).contains(".axd") || m.group(0).contains(".JPG") || m.group(0).contains(".jpg") || m.group(0).contains(".jpeg") || m.group(0).contains(".png") || m.group(0).contains(".js") || m.group(0).contains(".ico") || m.group(0).contains(".gif")) {
System.out.println("m.g(0) " + m.group(0));
System.out.println("m.g(1) " + m.group(1));
String changepath;
Pattern p1 = Pattern.compile("src=(.*?)>|src=\"(.*?)\"");
Matcher m1 = p1.matcher(m.group(0));
if(m1.find()) {
if(m1.group(0).contains(".axd") || m1.group(0).contains(".JPG") || m1.group(0).contains(".jpg") || m1.group(0).contains(".jpeg") || m1.group(0).contains(".png") || m1.group(0).contains(".js") || m1.group(0).contains(".ico") || m1.group(0).contains(".gif")) {
System.out.println("inner " + m1.group(0));
changepath = "\"" + main_url + "" + m1.group(1).replace("\"", "").replace("'", "") + "\"";
lineread = lineread.replace(m1.group(1), changepath);
System.out.println("data " + lineread);
}
} else {
changepath = "\"" + main_url + "" + m.group(0).replace("\"", "").replace("'", "") + "\"";
lineread = lineread.replace(m.group(0), changepath);
System.out.println("data in src " + lineread);
}
}
}
script = script.text(lineread);
System.out.println("final script " + script);
}
}
但问题在于我在脚本中获得的值(最后一个变量)删除了脚本标记之间数据中存在的所有空格。
所以基本上我想要一个正则表达式来获取脚本标记之间的数据,或者如何在不丢失第二个解决方案空间的情况下获取数据。
答案 0 :(得分:0)
你可以使用lib js2xml。 https://github.com/redapple/js2xml
import js2xml
jscode = """var arrowimages = {
down: ['downarrowclass', 'Images/arrow-down.gif', 23],
right: ['rightarrowclass', 'Images/submenu-pointer.png']
}
var jqueryslidemenu = {
animateduration: {
over: 400,
out: 400
}, //duration of slide in/ out animation, in milliseconds
buildmenu: function (menuid, arrowsvar) {
jQuery(document).ready(function ($) {
var $mainmenu = $("#" + menuid + ">ul")
var $headers = $mainmenu.find("ul").parent()
$headers.each(function (i) {
var $curobj = $(this)
var $subul = $(this).find('ul:eq(0)')
this._dimensions = {
w: this.offsetWidth,
h: this.offsetHeight,
subulw: $subul.outerWidth(),
subulh: $subul.outerHeight()
}
this.istopheader = $curobj.parents("ul").length == 1 ? true : false
$subul.css({
top: this.istopheader ? this._dimensions.h + "px" : 0
})
$curobj.children("a:eq(0)").css(this.istopheader ? {
paddingRight: arrowsvar.down[2]
} : {}).append(
'<img src="' + (this.istopheader ? arrowsvar.down[1] : arrowsvar.right[1]) + '" class="' + (this.istopheader ? arrowsvar.down[0] : arrowsvar.right[0]) + '" style="border:0;top:12px;" />'
)
$curobj.hover(
function (e) {
var $targetul = $(this).children("ul:eq(0)")
this._offsets = {
left: $(this).offset().left,
top: $(this).offset().top
}
var menuleft = this.istopheader ? 0 : this._dimensions.w
menuleft = (this._offsets.left + menuleft + this._dimensions.subulw > $(window).width()) ? (this.istopheader ? -this._dimensions.subulw + this._dimensions.w : -this._dimensions.w) : menuleft
if($targetul.queue().length <= 1) //if 1 or less queued animations
$targetul.css({
left: menuleft + "px",
width: this._dimensions.subulw + 'px'
}).slideDown(jqueryslidemenu.animateduration.over)
},
function (e) {
var $targetul = $(this).children("ul:eq(0)")
$targetul.slideUp(jqueryslidemenu.animateduration.out)
}
) //end hover
$curobj.click(function () {
$(this).children("ul:eq(0)").hide()
})
}) //end $headers.each()
$mainmenu.find("ul").css({
display: 'none',
visibility: 'visible'
})
}) //end document.ready
}
}
//build menu with ID="myslidemenu" on page:
jqueryslidemenu.buildmenu("myjquerymenu", arrowimages)"""
parsed = js2xml.parse(jscode)
print js2xml.pretty_print(parsed)
示例输出:
<program>
<var name="arrowimages">
<object>
<property name="down">
<array>
<string>downarrowclass</string>
<string>Images/arrow-down.gif</string>
<number value="23"/>
</array>
</property>
<property name="right">
<array>
<string>rightarrowclass</string>
<string>Images/submenu-pointer.png</string>
</array>
</property>
</object>
</var>
然后你可以解析XML。 (使用xpath更容易)
此致 纳尔逊。
答案 1 :(得分:0)
请尝试使用data()
方法,而不是使用html()
方法。
第String data = script.data();
行变为String data = script.html()
。
另一方面,如果您想更改脚本标记的src
属性,您可以简单地告诉Jsoup为您找到它们:
Elements scripts = doc.select("script[src]");
for(Element script: scripts) {
String src = script.attr("src");
if (src.contains(".axd")) {
script.attr("src", main_url + src);
}
}