/*
* 将前面产生的Prepare的BatchJob文件 添加上起始标志，并且重新生成新的文件，（不含Prepare的后缀了）
* */
public static void createAllOtherCityBatchJobReadyFile() {
// 提取所有的城市和子域名的对应关系
initCityAndSubdomainList();
for (Pair pair : cityAndSubdomainList) {
String URL_SUBDOMAIN = pair.getValue();
String CITY_PINYING = URL_SUBDOMAIN.toUpperCase().charAt(0) + URL_SUBDOMAIN.substring(1);
String BATCH_FILE_PREPARE_PATH =
"./data/batch/"
+ SITE_NAME_PINYING
+ "/"
+ SITE_NAME_PINYING
+ CITY_PINYING
+ TYPE_PINYING
+ "BatchCreateJobFilePrepare.txt";
String BATCH_FILE_READY_PATH =
"./data/batch/"
+ SITE_NAME_PINYING
+ "/"
+ SITE_NAME_PINYING
+ CITY_PINYING
+ TYPE_PINYING
+ "BatchCreateJobFile.txt";
String fileContent = FileUtil.getDataFile2StrKeepReturn(BATCH_FILE_PREPARE_PATH, "utf-8");
fileContent = "^" + "\n" + fileContent + "$" + "\n";
FileUtil.writeStr2File(fileContent, BATCH_FILE_READY_PATH, "utf-8");
System.out.println(BATCH_FILE_READY_PATH + " is completed!");
}
}
/*
* http://www.anjuke.com/index/ 上的所有其它城市，（除去 北京 上海） 但是 包括 广州 深圳
* */
@Test
public void allOtherCityWhole() {
Element elem =
ParserUtil.parseUrlWithRegexAndResultIndex(ALL_OTHER_CITY_URL, ALL_OTHER_CITY_REGEX, 0);
Elements elements = ParserUtil.parseElementWithRegex(elem, "a");
StringBuffer sb = new StringBuffer();
for (Element element : elements) {
String href = element.attr("href");
String word = element.text();
if (!(word.equals("北京") || word.equals("上海"))) {
sb.append(href);
sb.append(",");
sb.append(word);
sb.append("\n");
}
}
System.out.println(sb.toString());
FileUtil.writeStr2File(sb.toString(), ALL_OTHER_CITY_FILE_PATH, "utf-8");
}
// 提取所有的城市和子域名的对应关系
public static void initCityAndSubdomainList() {
String content = FileUtil.getDataFile2StrKeepReturn(ALL_OTHER_CITY_FILE_PATH, "utf-8");
String[] lineArr = content.split("\n");
cityAndSubdomainList = new ArrayList<Pair>();
// 提取所有的城市和子域名的对应关系
for (String line : lineArr) {
String[] attrArr = line.split(",");
String href = attrArr[0];
String city = attrArr[1];
String subDomain =
href.substring(href.lastIndexOf("/") + 1, href.indexOf(".", href.lastIndexOf("/")));
Pair pair = new Pair();
pair.setKey(city);
pair.setValue(subDomain);
cityAndSubdomainList.add(pair);
System.out.println(city + " : " + subDomain);
}
System.out.println("/----------------------------------------------------------------/");
System.out.println("all cities and their subdomains extraction is completed!");
System.out.println("/----------------------------------------------------------------/");
}