Question

我开始在groovy中编写一些脚本。我写了这个脚本，它基本上解析了一个html页面并对数据做了一些事情。

现在，我使用HTTPBuilder来执行http请求。每当我尝试执行此类请求时，都会收到此错误：

Caught: java.lang.IllegalAccessError: tried to access class groovyx.net.http.StringHashMap from class groovyx.net.http.HTTPBuilder
java.lang.IllegalAccessError: tried to access class groovyx.net.http.StringHashMap from class groovyx.net.http.HTTPBuilder
    at groovyx.net.http.HTTPBuilder.<init>(HTTPBuilder.java:177)
    at groovyx.net.http.HTTPBuilder.<init>(HTTPBuilder.java:218)
    at Main$_main_closure1.doCall(Main.groovy:30)
    at Main.main(Main.groovy:24)
    at com.intellij.rt.execution.application.AppMain.main(AppMain.java:143)

以下是主要类的代码：

// Grap HTTPBuilder component from maven repository
@Grab(group='org.codehaus.groovy.modules.http-builder',
        module='http-builder', version='0.5.2')
// import of HttpBuilder related stuff
import groovyx.net.http.*
import parsers.Parser
import parsers.WuantoParser
import parsers.Row

class Main {

    static mapOfParsers = [:]
    static void main(args) {
        List<Row> results = new ArrayList<>()

        // Initiating the parsers for the ebay-keywords websites
        println "Initiating Parsers..."
        initiateParsers()

        println "Parsing Websites..."
        mapOfParsers.each { key, parser ->
            switch (key) {
                case Constants.Parsers.WUANTO_PARSER:
                    println "Parsing Url: $Constants.Url.WUANTO_ROOT_CAT_URL"
                    println "Retrieving Html Content..."

                    def http = new HTTPBuilder(Constants.Url.WUANTO_ROOT_CAT_URL)
                    def html = http.get([:])

                    println "Parsing Html Content..."

                    results.addAll(((Parser) parser).parseHtml(html))
                    break
            }
        }

        results.each {
            println it
        }
    }

    static void initiateParsers() {
        mapOfParsers.put(Constants.Parsers.WUANTO_PARSER , new WuantoParser())
    }

    static void writeToFile(List<Row> rows) {
        File file = "output.txt"

        rows.each {
            file.write it.toString()
        }
    }

}

Answer 1

好吧，让我们看看这里。我尝试在您的代码段中运行代码，但http构建器依赖项版本0.5.2已经过时，并且在我的groovy脚本指向的存储库中无法访问。所以我用更新版本0.7.1替换它。

此外，代码中http.get返回的html变量值实际上是一种解析格式。即它不是文本，而是一个常规的NodeChild对象。这是因为http构建器默认情况下执行html解析，如果需要，你必须明确地告诉它返回纯文本（即使它返回一个阅读器而不是文本）。

以下有些重组和重写的代码版本演示了这个想法：

var text = $.trim($('.amount').html());
var res = text.split(" "); 
var num = parseInt(res[0]) + 1;
text = num + " "+ res[1];
$('.amount').html(text);

运行以上打印：

// Grap HTTPBuilder component from maven repository
@Grab('org.codehaus.groovy.modules.http-builder:http-builder:0.7.1')

import groovyx.net.http.*
import groovy.xml.XmlUtil
import static groovyx.net.http.ContentType.*

class MyParser { 
  def parseHtml(html) {
    [html]
  }
}


def mapOfParsers = [:]
mapOfParsers["WUANTO_PARSER"] = new MyParser()

result = []
mapOfParsers.each { key, parser ->
    switch (key) {
        case "WUANTO_PARSER":
            // just a sample url which returns some html data
            def url = "https://httpbin.org/links/10/0"

            def http = new HTTPBuilder(url)
            def html = http.get([:])

            // the object returned from http.get is of type 
            // http://docs.groovy-lang.org/latest/html/api/groovy/util/slurpersupport/NodeChild.html
            // this is a parsed format which is navigable in groovy 
            println "extracting HEAD.TITLE text: " + html.HEAD.TITLE.text()

            println "class of returned object ${html.getClass().name}"
            println "First 100 characters parsed and formatted:\n ${XmlUtil.serialize(html).take(100)}"

            // forcing the returned type to be plain text
            def reader = http.get(contentType : TEXT)

            // what is returned now is a reader, we can get the text in groovy 
            // via reader.text
            def text = reader.text
            println "Now we are getting text, 100 first characters plain text:\n ${text.take(100)}"

            result.addAll parser.parseHtml(text)
            break
    }
}

result.each { 
    println "result length ${it.length()}"
}

（为简洁起见，省略了一些来自XmlUtil.serialize的警告）。

这些都没有解释为什么你会得到你所获得的例外，但也许上述内容可以让你解锁并解决问题。

IllegalAccessException试图访问StringHashMap - Groovy

1 个答案: