数据导入方法,添加初始对象处理

This commit is contained in:
Yucheng Hu 2017-07-23 11:09:48 -04:00
parent 7b08de5d8a
commit 98a493cf8c

View File

@ -1,35 +1,22 @@
package com.usvisatrack.services;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Date;
import java.util.Iterator;
import java.util.List;
import java.util.UUID;
import org.apache.commons.cli.CommandLine;
import org.apache.commons.cli.CommandLineParser;
import org.apache.commons.cli.GnuParser;
import org.apache.commons.httpclient.util.URIUtil;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.FilenameUtils;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.http.HttpResponse;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.HttpClientBuilder;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.google.gson.JsonArray;
import com.google.gson.JsonElement;
import com.google.gson.JsonObject;
import com.usvisatrack.core.dao.model.Visa;
import com.usvisatrack.core.factories.VisaFactory;
import com.usvisatrack.services.common.DataCrawl;
/**
@ -87,6 +74,37 @@ public class VisaImporter extends DataCrawl {
private void crawlWebItem() {
logger.error("Crawl Web Data to load item info.");
List<Visa> visaList = new ArrayList<Visa>();
Document doc = null;
try {
doc = Jsoup.connect("https://www.checkee.info/main.php?dispdate=2017-07").get();
Elements newsHeadlines = doc.select("table");
Element table = newsHeadlines.get(6);
int i = 0;
for (Element row : table.select("tr")) {
i++;
Elements tds = row.select("td");
if (!StringUtils.equalsIgnoreCase("ID", tds.get(1).text())) {
Visa visa = new Visa();
visa.setMajor(StringUtils.trimToEmpty(tds.get(5).text()));
logger.debug("[{}]", visa.getMajor());
VisaFactory.save(visa);
}
if (i == 2)
break;
}
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}