本文整理了Java中org.jsoup.Connection.get()
方法的一些代码示例,展示了Connection.get()
的具体用法。这些代码示例主要来源于Github
/Stackoverflow
/Maven
等平台,是从一些精选项目中提取出来的代码,具有较强的参考意义,能在一定程度帮忙到你。Connection.get()
方法的具体详情如下:
包路径:org.jsoup.Connection
类名称:Connection
方法名:get
[英]Execute the request as a GET, and parse the result.
[中]将请求作为GET执行,并解析结果。
代码示例来源:origin: ChinaSilence/any-video
private String getOpenId(String accessToken) throws IOException{
String url = openIdUri + accessToken;
Document document = Jsoup.connect(url).get();
String resultText = document.text();
Matcher matcher = Pattern.compile("\"openid\":\"(.*?)\"").matcher(resultText);
if (matcher.find()){
return matcher.group(1);
}
return null;
}
代码示例来源:origin: deeplearning4j/dl4j-examples
/**
* Get a list of all URLs in a page for zip files
*/
public static List<String> getZipUrlsFromPage(String url) {
List<String> out = new ArrayList<>();
try {
Document doc = Jsoup.connect(url).get();
Elements links = doc.select("a[href]");
for (Element e : links) {
String s = e.attr("href");
if (s.endsWith(".zip")) {
if (s.startsWith("http")) {
//Absolute link
out.add(s);
} else {
//Relative link
out.add(e.baseUri() + s);
}
}
}
} catch (IOException e) {
throw new RuntimeException(e);
}
return out;
}
代码示例来源:origin: RipMeApp/ripme
private String vscoImageToURL(String url) throws IOException{
Document page = Jsoup.connect(url).userAgent(USER_AGENT)
.get();
//create Elements filled only with Elements with the "meta" tag.
Elements metaTags = page.getElementsByTag("meta");
String result = "";
for(Element metaTag : metaTags){
//find URL inside meta-tag with property of "og:image"
if (metaTag.attr("property").equals("og:image")){
String givenURL = metaTag.attr("content");
givenURL = givenURL.replaceAll("\\?h=[0-9]+", "");//replace the "?h=xxx" tag at the end of the URL (where each x is a number)
result = givenURL;
LOGGER.debug("Found image URL: " + givenURL);
break;//immediately stop after getting URL (there should only be 1 image to be downloaded)
}
}
//Means website changed, things need to be fixed.
if (result.isEmpty()){
LOGGER.error("Could not find image URL at: " + url);
}
return result;
}
代码示例来源:origin: loklak/loklak_server
/**
* Article API
* @param URL
* @param JSONObject genericScraperData
* @return genericScraperData
*/
public JSONObject articleAPI (String url, JSONObject genericScraperData) throws MalformedURLException{
URL qurl = new URL(url);
String data = "";
try {
data = null;// ArticleExtractor.INSTANCE.getText(qurl);
genericScraperData.put("query", qurl);
genericScraperData.put("data", data);
genericScraperData.put("NLP", "true");
}
catch (Exception e) {
if ("".equals(data)) {
try {
Document htmlPage = Jsoup.connect(url).get();
data = htmlPage.text();
genericScraperData.put("query", qurl);
genericScraperData.put("data", data);
genericScraperData.put("NLP", "false");
} catch (Exception ex) {}
}
}
return genericScraperData;
}
代码示例来源:origin: wangdan/AisenWeiBo
public static VideoBean getVideoFromWeipai(VideoBean video) throws Exception {
Document dom = Jsoup.connect(video.getLongUrl()).get();
video.setIdStr(KeyGenerator.generateMD5(video.getShortUrl()));
Elements divs = dom.select("div[class=video_img WscaleH]");
if (divs != null && divs.size() > 0) {
video.setImage(divs.get(0).attr("data-url"));
}
divs = dom.select("video#video");
if (divs != null && divs.size() > 0) {
video.setVideoUrl(divs.get(0).attr("src"));
}
return video;
}
代码示例来源:origin: wangdan/AisenWeiBo
public static VideoBean getVideoFromSinaVideo(VideoBean video) throws Exception {
Document dom = Jsoup.connect(video.getLongUrl()).get();
video.setIdStr(KeyGenerator.generateMD5(video.getShortUrl()));
Elements divs = dom.select("video.video");
if (divs != null && divs.size() > 0) {
String src = divs.get(0).attr("src");
src = src.replace("amp;", "");
video.setVideoUrl(src);
}
divs = dom.select("img.poster");
if (divs != null && divs.size() > 0) {
video.setImage(divs.get(0).attr("src"));
}
return video;
}
代码示例来源:origin: org.jsoup/jsoup
/**
Fetch a URL, and parse it as HTML. Provided for compatibility; in most cases use {@link #connect(String)} instead.
<p>
The encoding character set is determined by the content-type header or http-equiv meta tag, or falls back to {@code UTF-8}.
@param url URL to fetch (with a GET). The protocol must be {@code http} or {@code https}.
@param timeoutMillis Connection and read timeout, in milliseconds. If exceeded, IOException is thrown.
@return The parsed HTML.
@throws java.net.MalformedURLException if the request URL is not a HTTP or HTTPS URL, or is otherwise malformed
@throws HttpStatusException if the response is not OK and HTTP response errors are not ignored
@throws UnsupportedMimeTypeException if the response mime type is not supported and those errors are not ignored
@throws java.net.SocketTimeoutException if the connection times out
@throws IOException if a connection or read error occurs
@see #connect(String)
*/
public static Document parse(URL url, int timeoutMillis) throws IOException {
Connection con = HttpConnection.connect(url);
con.timeout(timeoutMillis);
return con.get();
}
代码示例来源:origin: wangdan/AisenWeiBo
public static VideoBean getVideoFromMeipai(VideoBean video) throws Exception {
Document dom = Jsoup.connect(video.getLongUrl()).get();
Elements divs = dom.select("div#mediaPlayer");
if (divs != null && divs.size() > 0) {
Element div = divs.get(0);
video.setVideoUrl(div.attr("data-video"));
video.setImage(div.attr("data-poster"));
}
video.setIdStr(KeyGenerator.generateMD5(video.getShortUrl()));
return video;
}
代码示例来源:origin: ChinaSilence/any-video
private QQToken getToken(String tokenAccessApi) throws IOException{
Document document = Jsoup.connect(tokenAccessApi).get();
String tokenResult = document.text();
String[] results = tokenResult.split("&");
if (results.length == 3){
QQToken qqToken = new QQToken();
String accessToken = results[0].replace("access_token=", "");
int expiresIn = Integer.valueOf(results[1].replace("expires_in=", ""));
String refreshToken = results[2].replace("refresh_token=", "");
qqToken.setAccessToken(accessToken);
qqToken.setExpiresIn(expiresIn);
qqToken.setRefresh_token(refreshToken);
return qqToken;
}
return null;
}
代码示例来源:origin: RipMeApp/ripme
private JSONArray getPageUrls() {
String postURL = "http://www.tsumino.com/Read/Load";
try {
// This sessionId will expire and need to be replaced
cookies.put("ASP.NET_SessionId","c4rbzccf0dvy3e0cloolmlkq");
Document doc = Jsoup.connect(postURL).data("q", getAlbumID()).userAgent(USER_AGENT).cookies(cookies).referrer("http://www.tsumino.com/Read/View/" + getAlbumID()).get();
String jsonInfo = doc.html().replaceAll("<html>","").replaceAll("<head></head>", "").replaceAll("<body>", "").replaceAll("</body>", "")
.replaceAll("</html>", "").replaceAll("\n", "");
JSONObject json = new JSONObject(jsonInfo);
return json.getJSONArray("reader_page_urls");
} catch (IOException e) {
LOGGER.info(e);
sendUpdate(RipStatusMessage.STATUS.DOWNLOAD_ERRORED, "Unable to download album, please compete the captcha at http://www.tsumino.com/Read/Auth/"
+ getAlbumID() + " and try again");
return null;
}
}
代码示例来源:origin: jtablesaw/tablesaw
public String tableToCsv(String url) throws IOException {
Document doc = Jsoup.connect(url).get();
Elements tables = doc.select("table");
if (tables.size() != 1) {
throw new IllegalStateException(
"Reading html to table currently works if there is exactly 1 html table on the page. "
+ " The URL you passed has " + tables.size()
+ ". You may file a feature request with the URL if you'd like your pagae to be supported");
}
Element table = tables.get(0);
CsvWriterSettings settings = new CsvWriterSettings();
StringWriter stringWriter = new StringWriter();
CsvWriter csvWriter = new CsvWriter(stringWriter, settings);
for (Element row : table.select("tr")) {
Elements headerCells = row.getElementsByTag("th");
Elements cells = row.getElementsByTag("td");
String[] nextLine = Stream.concat(headerCells.stream(), cells.stream())
.map(Element::text).toArray(String[]::new);
csvWriter.writeRow(nextLine);
}
return stringWriter.toString();
}
}
代码示例来源:origin: loklak/loklak_server
public static SusiThought locationWiseTime(String query) {
Document html = null;
JSONArray arr = new JSONArray();
try {
html = Jsoup.connect("http://www.timeanddate.com/worldclock/results.html?query=" + query).get();
} catch (IOException e) {
DAO.severe(e);
}
Elements locations = html.select("td");
int i = 0;
for (Element e : locations) {
if (i % 2 == 0) {
JSONObject obj = new JSONObject();
String l = e.getElementsByTag("a").text();
obj.put("location", l);
String t = e.nextElementSibling().text();
obj.put("time", t);
arr.put(obj);
}
i++;
}
SusiThought json = new SusiThought();
json.setData(arr);
return json;
}
代码示例来源:origin: ChinaSilence/any-video
public static Document getDocWithPC(String url) {
try {
return Jsoup.connect(url).userAgent(UA_PC).timeout(TIME_OUT).ignoreContentType(true).get();
} catch (IOException e) {
log.error(ERROR_DESC + url);
throw new AnyException(ERROR_DESC + url);
}
}
代码示例来源:origin: RipMeApp/ripme
private static Document getDocument(String strUrl) throws IOException {
return Jsoup.connect(strUrl)
.userAgent(USER_AGENT)
.timeout(10 * 1000)
.maxBodySize(0)
.get();
}
代码示例来源:origin: ChinaSilence/any-video
public static Document getDocWithPhone(String url) {
try {
return Jsoup.connect(url).userAgent(UA_PHONE).timeout(TIME_OUT).ignoreContentType(true).validateTLSCertificates(false).get();
} catch (IOException e) {
log.error(ERROR_DESC + url);
throw new AnyException(ERROR_DESC + url);
}
}
代码示例来源:origin: ChinaSilence/any-video
public static Document getDocWithPhone(String url, String cookie) {
try {
return Jsoup.connect(url).userAgent(UA_PHONE).timeout(TIME_OUT).header("Cookie", cookie).ignoreContentType(true).get();
} catch (IOException e) {
log.error(ERROR_DESC + url);
throw new AnyException(ERROR_DESC + url);
}
}
代码示例来源:origin: ChinaSilence/any-video
/**
* 获取片段播放的 key
*/
private String videoKey(String vid, String filename, String format) {
try {
Document document = Jsoup.connect(KEY_API).header("Cookie", COOKIE)
.data("vid", vid).data("platform", PLATFORM)
.data("otype", "json")
.data("filename", filename).data("sdtfrom", SDTFROM)
.data("format", format).data("guid", GUID).ignoreContentType(true).get();
String result = document.text().replace("QZOutputJson=", "");
System.out.println(result);
result = result.substring(0, result.length() - 1);
return JSONObject.parseObject(result).getString("key");
} catch (IOException e) {
log.info("request tencent video part api error, vid : " + vid);
throw new AnyException("request tencent api error, vid : " + vid);
}
}
}
代码示例来源:origin: ChinaSilence/any-video
private Document requestAPI(String keyword) {
try {
return Jsoup.connect(api).userAgent(ua).ignoreContentType(true).data("wd", keyword).get();
} catch (IOException e) {
throw new AnyException(ExceptionEnum.VIDEO_SEARCH_ERROR);
}
}
代码示例来源:origin: wangdan/AisenWeiBo
@Override
public String workInBackground(Void... p) throws TaskException {
try {
AccountBean accountBean = AccountUtils.getLogedinAccount();
if (TextUtils.isEmpty(accountBean.getAccount()) || TextUtils.isEmpty(accountBean.getPassword()))
throw new TaskException("", getString(R.string.account_fillaccount_faild));
String js = FileUtils.readAssetsFile("mobile.js", GlobalContext.getInstance());
js = js.replace("%username%", accountBean.getAccount());
js = js.replace("%password%", accountBean.getPassword());
Document dom = Jsoup.connect(url).get();
String html = dom.toString();
html = html.replace("</head>", js + "</head>");
return html;
} catch (Exception e) {
e.printStackTrace();
}
throw new TaskException("", getString(R.string.account_fillaccount_faild));
}
代码示例来源:origin: ChinaSilence/any-video
/**
* 调用腾讯接口,获取视频信息
*/
private String videoInfo(String vid) {
try {
Document document = Jsoup.connect(VIDEO_API).header("Cookie", COOKIE)
.data("vids", vid).data("platform", PLATFORM)
.data("sdtfrom", SDTFROM)
.data("format", "10209")
.data("otype", "json").data("defn", "fhd")
.data("defaultfmt", "fhd").data("guid", GUID).ignoreContentType(true).get();
String result = document.text().replace("QZOutputJson=", "");
return result.substring(0, result.length() - 1);
} catch (IOException e) {
log.info("request tencent api error, vid : " + vid);
throw new AnyException("request tencent api error, vid : " + vid);
}
}
内容来源于网络,如有侵权,请联系作者删除!