用jsoup,xpath网络爬取视频和小说资源

小说资源规则:

"{" +
  "\"baseUrl\":\"https://www.biquge.biz/\"," +
  "\"siteName\":\"笔趣阁biz\"," +
  "\"ruleBookAuthor\":\"[email protected]@text\"," +
  "\"ruleBookContent\":\"\"," +
  "\"ruleBookInfoInit\":\"id.intro@text\"," +
  "\"ruleBookKind\":\"\"," +
  "\"ruleBookLastChapter\":\"[email protected]@text\"," +
  "\"ruleBookName\":\"[email protected]@text\"," +
  "\"ruleBookUrlPattern\":\"\"," +
  "\"ruleCoverUrl\":\"[email protected]@src\"," +
  "\"ruleChapterList\":\"[email protected]\"," +
  "\"ruleChapterName\":\"tag.a@text\"," +
  "\"ruleChapterUrl\":\"tag.a@href\"," +
  "\"ruleChapterUrlType\":\"1\"," +
  "\"ruleContentUrl\":\"id.content@textNodes\"," +
  "\"ruleContentUrlNext\":\"\"," +
  "\"ruleSearchAuthor\":\"[email protected]@text\"," +
  "\"ruleSearchCoverUrl\":\"[email protected]@src\"," +
  "\"ruleSearchIntroduce\":\"\"," +
  "\"ruleSearchKind\":\"[email protected]@text\"," +
  "\"ruleSearchLastChapter\":\"[email protected]@text\"," +
  "\"ruleSearchList\":\"class.result-item result-game-item\"," +
  "\"ruleSearchName\":\"class.result-item-title [email protected]@text\"," +
  "\"ruleSearchNoteUrl\":\"class.result-item-title [email protected]@href\"," +
  "\"ruleSearchUrl\":\"search.php?keyword=ruleKeyword|UTF-8\"" +
 

"

 

视频资源规则:

{" +
  "\"params\":{\"submit\":\"search\",\"wd\":\"searchKey\"}," +
  "\"sourceType\":\"0\"," +
  "\"ruleSearchList\":\"[email protected]\"," +
  "\"ruleSearchName\":\"tag.a@text\"," +
  "\"ruleSearchNoteUrl\":\"tag.a@href\"," +
  "\"ruleSearchUrl\":\"/index.php?m=vod-search\"," +
  "\"ruleSeriesList\":\"[email protected]\"," +
  "\"ruleItem\":\"li\"," +
  "\"ruleSeriesName\":\"li@text\"," +
  "\"ruleSeriesNoteUrl\":\" \"," +
  "\"rulePlayType\":\"h3@text\"," +
  "\"ruleTypeList\":\"h3\"," +
  "\"ruleVideoName\":\"[email protected]@text\"," +
  "\"ruleVideoImage\":\"[email protected]@src\"," +
  "\"siteName\":\"135资源网\"," +
  "\"videoSourceUrl\":\"http://135zy0.com\"" +
  "}

 

部分解析代码:

/**
  * 获取Elements
  */
  private Elements getElements(Element temp, String rule) {
  Elements elements = new Elements();
  if (temp == null || isEmpty(rule)) {
  return elements;
  }
  SourceRule sourceRule = new SourceRule(rule);
  String elementsType;
  String[] ruleStrS;
  if (sourceRule.elementsRule.contains("&")) {
  elementsType = "&";
  ruleStrS = sourceRule.elementsRule.split("&+");
  } else if (sourceRule.elementsRule.contains("%")) {
  elementsType = "%";
  ruleStrS = sourceRule.elementsRule.split("%+");
  } else {
  elementsType = "|";
  if (sourceRule.isCss) {
  ruleStrS = sourceRule.elementsRule.split("\\|\\|");
  } else {
  ruleStrS = sourceRule.elementsRule.split("\\|+");
  }
  }
  List elementsList = new ArrayList<>();
  if (sourceRule.isCss) {
  for (String ruleStr : ruleStrS) {
  Elements tempS = temp.select(ruleStr);
  elementsList.add(tempS);
  if (tempS.size() > 0 && elementsType.equals("|")) {
  break;
  }
  }
  } else {
  for (String ruleStr : ruleStrS) {
  Elements tempS = getElementsSingle(temp, ruleStr);
  elementsList.add(tempS);
  if (tempS.size() > 0 && elementsType.equals("|")) {
  break;
  }
  }
  }
  if (elementsList.size() > 0) {
  if ("%".equals(elementsType)) {
  for (int i = 0; i < elementsList.get(0).size(); i++) {
  for (Elements es : elementsList) {
  if (i < es.size()) {
  elements.add(es.get(i));
  }
  }
  }
  } else {
  for (Elements es : elementsList) {
  elements.addAll(es);
  }
  }
  }
  return elements;
  }

 

连接:https://www.jianguoyun.com/p/DavujFIQ4pj8Bxj1w7YC

GitHub:https://github.com/Kangzhengwei/leisure

欢迎各位指教。

你可能感兴趣的:(用jsoup,xpath网络爬取视频和小说资源)