java 解析html body_java讀取html文件，並獲取body中所有的標簽以及內容

packagecom.lmt.service.file;importjava.io.BufferedReader;importjava.io.File;importjava.io.FileInputStream;importjava.io.InputStreamReader;importjava.io.Reader;importorg.springframework.stereotype.Component;importcom.lmt.config.UrlConstants;

@Componentpublic classParseFile {/*** 解析html文件

*@paramfile

*@return

*/

publicString readHtml(File file){

String body= "";try{

FileInputStream iStream= newFileInputStream(file);

Reader reader= newInputStreamReader(iStream);

BufferedReader htmlReader= newBufferedReader(reader);

String line;boolean found = false;while (!found && (line = htmlReader.readLine()) != null) {if (line.toLowerCase().indexOf("

的前面可能存在空格

found = true;

}

}

found= false;while (!found && (line = htmlReader.readLine()) != null) {if (line.toLowerCase().indexOf("

found= true;

}else{//如果存在圖片，則將相對路徑轉換為絕對路徑

String lowerCaseLine =line.toLowerCase();if (lowerCaseLine.contains("src")) {//這里是定義圖片的訪問路徑

String directory = "D:/test";//如果路徑名不以反斜杠結尾，則手動添加反斜杠

/*if (!directory.endsWith("\\")) {

directory = directory + "\\";

}*/

//line = line.substring(0, lowerCaseLine.indexOf("src") + 5) + directory + line.substring(lowerCaseLine.indexOf("src") + 5);

/*String filename = extractFilename(line);

line = line.substring(0, lowerCaseLine.indexOf("src") + 5) + directory + filename + line.substring(line.indexOf(filename) + filename.length());*/

//如果該行存在多個元素，則分行進行替代

String[] splitLines = line.split("

for (int i = 0; i < splitLines.length; i++) {if (splitLines[i].toLowerCase().startsWith("src")) {

splitLines[i]= splitLines[i].substring(0, splitLines[i].toLowerCase().indexOf("src") + 5)+directory+ splitLines[i].substring(splitLines[i].toLowerCase().indexOf("src") + 5);

}

}//最后進行拼接

line = "";for (int i = 0; i < splitLines.length - 1; i++) { //循環次數要-1，因為最后一個字符串后不需要添加

line = line + splitLines[i] + "

}

line= line + splitLines[splitLines.length - 1];

}

body= body + line + "\n";

}

}

htmlReader.close();//System.out.println(body);

}catch(Exception e) {

e.printStackTrace();

}returnbody;

}/***

*@paramhtmlLine 一行html片段，包含元素

*@return文件名*/

public staticString extractFilename(String htmlLine) {int srcIndex = htmlLine.toLowerCase().indexOf("src=");if (srcIndex == -1) { //圖片不存在，返回空字符串

return "";

}else{

String htmlSrc= htmlLine.substring(srcIndex + 4);char splitChar = '\"'; //默認為雙引號，但也有可能為單引號

if (htmlSrc.charAt(0) == '\'') {

splitChar= '\'';

}

String[] firstSplit=htmlSrc.split(String.valueOf(splitChar));

String path= firstSplit[1]; //第0位為空字符串

String[] secondSplit = path.split("[/\\\\]"); //匹配正斜杠或反斜杠

return secondSplit[secondSplit.length - 1];

}

}

}