Java FileIO.readAsList方法代码示例

import happy.coding.io.FileIO; //导入方法依赖的package包/类
public void crawl_web_pages() throws Exception
{
	String filePath = "./src/main/resources/mtime.txt";
	List<String> urls = FileIO.readAsList(filePath);

	for (String url : urls)
	{
		String html = URLReader.read(url);
		Document doc = Jsoup.parse(html);
		String name = doc.select("span[property=v:itemreviewed]").text();
		name = Strings.filterWebString(name, '_');

		String dirPath = dir + name + "/";
		FileIO.makeDirectory(dirPath);
		FileIO.writeString(dirPath + name + ".html", html);
	}
}
 

import happy.coding.io.FileIO; //导入方法依赖的package包/类
public static void getAllUsers() throws Exception {
	String filePath = FileIO.getResource("dvd.ciao.txt");
	List<String> urls = FileIO.readAsList(filePath);

	String dir = Systems.getDesktop() + "dvd.ciao.co.uk\\";
	String userFile = dir + "users.txt";
	Map<String, String> userMap = new HashMap<>();
	for (String url : urls) {
		// each category
		String[] data = url.split(": ");
		String category = data[0];
		String dirPath = FileIO.makeDirPath(dir, category);

		// users
		String userPath = dirPath + "users.txt";
		List<String> users = FileIO.readAsList(userPath);
		for (String line : users) {
			String[] d = line.split(",");
			userMap.put(d[0], d[1]);
		}
	}

	FileIO.writeMap(userFile, userMap);
}
 

import happy.coding.io.FileIO; //导入方法依赖的package包/类
protected void load_proxy() throws Exception
{
	proxy = new HashMap<>();

	String path = FileIO.getResource("proxy.txt");

	List<String> lines = FileIO.readAsList(path);
	for (String line : lines)
	{
		String[] data = line.split(":");
		String host = data[0];
		int port = Integer.parseInt(data[1]);

		proxy.put(host, port);
	}

	hosts = new ArrayList<>(proxy.keySet());
}
 

import happy.coding.io.FileIO; //导入方法依赖的package包/类
/**
 * Concate all the dvd ratings about the products in a specific category
 * 
 * @param url
 * @throws Exception
 */
public void run_category_ratings(String url) throws Exception {
	String[] data = url.split(": ");
	String category = data[0];

	String catPath = FileIO.makeDirPath(desktop, domain, category);
	File Dir = new File(catPath);
	File[] prodDirs = Dir.listFiles();
	int tk = prodDirs.length;

	String ratingFile = catPath + "movie-ratings.txt";
	FileIO.deleteFile(ratingFile);

	for (int k = 0; k < tk; k++) {
		File prodDir = prodDirs[k];
		// for each product
		String productID = prodDir.getName();
		if (productID.equals("webPages"))
			continue;
		if (!prodDir.isDirectory())
			continue;

		Logs.debug("{}: {} ({}/{})", new Object[] { category, productID,
				(k + 1), tk });

		String prodPath = FileIO.makeDirPath(catPath, productID);
		String dvdPath = prodPath + "dvd-ratings.txt";
		if (!FileIO.exist(dvdPath))
			continue;

		List<String> dvd_ratings = FileIO.readAsList(dvdPath);

		FileIO.writeList(ratingFile, dvd_ratings, null, true);
	}
}
 

import happy.coding.io.FileIO; //导入方法依赖的package包/类
public static void getAllRatings() throws Exception {
	String filePath = FileIO.getResource("dvd.ciao.txt");
	List<String> urls = FileIO.readAsList(filePath);

	String dir = Systems.getDesktop() + "dvd.ciao.co.uk\\";
	String ratingFile = dir + "ratings.txt";
	String reviewFile = dir + "review-ratings.txt";
	FileIO.deleteFile(ratingFile);
	FileIO.deleteFile(reviewFile);

	for (String url : urls) {
		// each category
		String[] data = url.split(": ");
		String category = data[0];
		String dirPath = FileIO.makeDirPath(dir, category);

		// ratings
		String ratingPath = dirPath + "ratings.txt";
		List<String> ratings = FileIO.readAsList(ratingPath);

		FileIO.writeList(ratingFile, ratings, null, true);

		// reviews
		String reviewPath = dirPath + "review-ratings.txt";
		List<String> reviews = FileIO.readAsList(reviewPath);

		FileIO.writeList(reviewFile, reviews, null, true);
	}
}
 

import happy.coding.io.FileIO; //导入方法依赖的package包/类
public static void crawl_data() throws Exception
{
	String filePath = FileIO.getResource("gewara.txt");

	List<String> urls = FileIO.readAsList(filePath);
	String[] tasks = { "comments" };

	int nd = 4;
	for (String task : tasks)
	{
		Logs.info("Current task: " + task);
		for (int i = 0; i < urls.size(); i += nd)
		{
			Thread[] tds = new Thread[nd];

			boolean flag = false;
			for (int j = 0; j < nd; j++)
			{
				if (i + j >= urls.size())
				{
					flag = true;
					break;
				}

				String url = urls.get(i + j).trim();
				tds[j] = new Thread(new GewaraCrawler(url, task, i + j + 1));
				tds[j].start();
			}

			for (Thread td : tds)
			{
				if (td != null) td.join();
			}

			if (flag) break;
		}
	}
}
 

import happy.coding.io.FileIO; //导入方法依赖的package包/类
public static void crawl_data() throws Exception
{
	String filePath = FileIO.getResource("douban.txt");

	List<String> urls = FileIO.readAsList(filePath);
	String[] tasks = { "reviews" };

	int nd = 4;
	for (String task : tasks)
	{
		Logs.info("Current task: " + task);
		for (int i = 0; i < urls.size(); i += nd)
		{
			Thread[] tds = new Thread[nd];

			boolean flag = false;
			for (int j = 0; j < nd; j++)
			{
				if (i + j >= urls.size())
				{
					flag = true;
					break;
				}

				String url = urls.get(i + j).trim();
				tds[j] = new Thread(new DoubanCrawler(url, task, i + j + 1));
				tds[j].start();
			}

			for (Thread td : tds)
			{
				if (td != null) td.join();
			}

			if (flag) break;
		}
	}
}
 

import happy.coding.io.FileIO; //导入方法依赖的package包/类
public static void crawl_data() throws Exception {
	if (Debug.OFF) {
		// home page
		CiaoCrawler cc = new CiaoCrawler();
		cc.run_home_page();
		return;
	}

	String sourceFile = "users.txt"; // "dvd.ciao.txt"
	String filePath = FileIO.getResource(sourceFile);
	List<String> urls = FileIO.readAsList(filePath);

	String[] tasks = { "users" };

	int nd = 8;
	for (String task : tasks) {
		Logs.info("Current task: " + task);
		for (int i = 0; i < urls.size(); i += nd) {
			Thread[] tds = new Thread[nd];

			boolean flag = false;
			for (int j = 0; j < nd; j++) {
				if (i + j >= urls.size()) {
					flag = true;
					break;
				}

				String url = urls.get(i + j).trim();
				tds[j] = new Thread(new CiaoCrawler(url, task, i + j + 1));
				tds[j].start();
			}

			for (Thread td : tds) {
				if (td != null)
					td.join();
			}

			if (flag)
				break;
		}
	}
}
 

import happy.coding.io.FileIO; //导入方法依赖的package包/类
public void run_products(String url) throws Exception {
	String[] data = url.split(": ");
	String category = data[0];
	// String link = data[1];

	String dirPath = FileIO.makeDirPath(desktop, domain, category);
	List<String> links = FileIO.readAsList(dirPath + "movies.txt");
	int tk = links.size();
	for (int k = 0; k < tk; k++) {
		String link = links.get(k);
		String[] d = link.split("::");
		String id = d[0];
		String name = d[1];
		String productLink = d[2];
		int idx = productLink.lastIndexOf("/");
		String p1 = productLink.substring(0, idx) + "/Reviews";
		String reviewLink = p1 + productLink.substring(idx);

		// create folder
		String path = FileIO.makeDirectory(dirPath, id);

		// product page
		String html = null;

		String pagePath = path + id + ".html";
		if (!FileIO.exist(pagePath)) {
			html = read_url(productLink);
			FileIO.deleteFile(path + name + ".html");
			FileIO.writeString(pagePath, html);
		}

		// product reviews
		// get first page anyway to identify the maximum pages
		path = FileIO.makeDirectory(path, "Reviews");
		String reviewPath = path + "page_1.html";
		if (FileIO.exist(reviewPath)) {
			html = FileIO.readAsString(reviewPath);
		} else {
			html = read_url(reviewLink);
			FileIO.writeString(reviewPath, html);
		}
		Logs.debug(category + ": " + id + " (" + (k + 1) + "/" + tk + ")"
				+ ": page " + 1);

		Document doc = Jsoup.parse(html);
		Elements nav = doc.select("div#Pagination");

		if (!nav.isEmpty()) {
			int maxPage = 1;

			Elements last = nav.select("li.last");
			if (!last.isEmpty())
				maxPage = Integer.parseInt(last.first().text()); // more
																	// than
																	// 11
																	// pages
			else
				maxPage = Integer.parseInt(nav.select("li").last().text()); // less
																			// or
																			// equal
																			// 11
																			// pages

			for (int i = 2; i <= maxPage; i++) {
				String filePath = path + "page_" + i + ".html";
				if (FileIO.exist(filePath))
					continue;

				reviewLink = reviewLink + "/Start/" + ((i - 1) * 15);
				html = read_url(reviewLink);
				FileIO.writeString(filePath, html);

				Logs.debug(category + ": " + id + " (" + (k + 1) + "/" + tk
						+ ")" + ": page " + i + "/" + maxPage);
			}
		}
	}

}
 

import happy.coding.io.FileIO; //导入方法依赖的package包/类
public static void parseCategoryPages() throws Exception {
	String filePath = FileIO.getResource("dvd.ciao.txt");
	List<String> urls = FileIO.readAsList(filePath);

	String dir = Systems.getDesktop() + "dvd.ciao.co.uk\\";
	for (String url : urls) {
		// each category
		String[] data = url.split(": ");
		String category = data[0];
		String dirCate = FileIO.makeDirPath(dir, category);
		String dirPath = FileIO.makeDirPath(dir, category, "webPages");

		// clear
		FileIO.deleteFile(dirCate + "movies.txt");

		File dirs = new File(dirPath);
		for (File f : dirs.listFiles()) {
			// each web page
			String html = FileIO.readAsString(dirPath + f.getName());
			Document doc = Jsoup.parse(html);

			Logs.debug(category + ": " + f.getName());

			List<String> movies = new ArrayList<>();
			Elements products = doc.select("td.prodInfo");
			for (Element product : products) {
				// each product
				Element prod = product.select("p.prodName").first();
				String name = prod.text();
				String link = prod.select("a").first().attr("href");
				String id = link.substring(link.lastIndexOf("_") + 1);

				// number of user reviews
				prod = product.select("p.prodRating").first();
				String cnt = prod.select(".userReviewsCount").text()
						.replace("(", "").replace(")", "");
				int count = 0;
				if (!cnt.isEmpty())
					count = Integer.parseInt(cnt);

				// do not consider movies without any reviews
				if (count > 0) {
					String movie = id + "::" + name + "::" + link;
					movies.add(movie);
				}
			}

			FileIO.writeList(dirCate + "movies.txt", movies, null, true);
		}
	}

}
 

import happy.coding.io.FileIO; //导入方法依赖的package包/类
public static void getAllTrust() throws Exception {

		Map<String, String> users = new HashMap<>();
		List<String> userLines = FileIO.readAsList(FileIO
				.getResource("users.txt"));
		for (String line : userLines) {
			String[] data = line.split(",");
			users.put(data[1], data[0]);
		}

		String usersPath = FileIO.makeDirPath(desktop, domain,
				"users.ciao.co.uk");
		FileIO.deleteFile(usersPath + "trust.txt");

		File dir = new File(usersPath);
		File[] files = dir.listFiles();

		for (int i = 0, n = files.length; i < n; i++) {
			// for each user
			File userFile = files[i];
			final String userID = userFile.getName();

			String html = null;
			Document doc = null;
			List<String> friends = new ArrayList<>();
			File[] pages = userFile.listFiles();
			for (int j = 0, m = pages.length; j < m; j++) {
				// for each trust page
				File file = pages[j];
				String name = file.getName();
				if (name.startsWith("friends")) {
					html = FileIO.readAsString(file.getPath());
					doc = Jsoup.parse(html);
					Element trustTable = doc.select("form table.trust").first();
					Elements trs = trustTable.select("tbody tr");
					for (Element tr : trs) {
						Element td = tr.select("td").get(1);
						Element a = td.select("a").first();
						String link = a.attr("href");
						if (users.containsKey(link)) {
							friends.add(users.get(link));
						}
					}
				}
			}

			FileIO.writeList(usersPath + "trust.txt", friends,
					new Converter<String, String>() {

						@Override
						public String transform(String friend) {
							return userID + "," + friend + ",1";
						}
					}, true);
		}

	}
 

import happy.coding.io.FileIO; //导入方法依赖的package包/类
public static void parseReviewPages() throws Exception {
	String filePath = FileIO.getResource("dvd.ciao.txt");
	List<String> urls = FileIO.readAsList(filePath);

	String dir = Systems.getDesktop() + "dvd.ciao.co.uk\\";
	for (String url : urls) {
		// each category
		String[] data = url.split(": ");
		String category = data[0];
		String dirCate = FileIO.makeDirPath(dir, category);

		File dirs = new File(dirCate);
		for (File f : dirs.listFiles()) {
			// each product folder
			if (f.getName().equals("webPages"))
				continue;
			if (!f.isDirectory())
				continue;

			String prodPath = FileIO.makeDirPath(dirCate, f.getName());
			String revwPath = FileIO.makeDirPath(prodPath, "Reviews");

			List<String> reviews = new ArrayList<>();
			File reviewDirs = new File(revwPath);

			for (File rf : reviewDirs.listFiles()) {
				// each review page
				String html = FileIO.readAsString(rf.getPath());
				Document doc = Jsoup.parse(html);

				Elements es = doc.select("div.m-shortReviewSnippet");
				for (Element e : es) {
					Element a = e.select(
							"p.m-shet-review-title a.ReviewTitle").first();
					if (a == null)
						continue; // some reviews do not have specific link
									// to detailed contents

					// url
					String link = a.attr("href");

					int idx = link.lastIndexOf("_");
					String id = link.substring(idx + 1);

					reviews.add(id + "::" + link);
				}
			}

			FileIO.writeList(prodPath + "reviews.txt", reviews, null, false);
		}

	}

}