Commit | Line | Data |
---|---|---|
8816d2f7 NR |
1 | package be.nikiroo.utils; |
2 | ||
3 | import java.io.IOException; | |
4 | import java.io.InputStream; | |
5 | import java.io.OutputStreamWriter; | |
6 | import java.net.CookieHandler; | |
7 | import java.net.CookieManager; | |
8 | import java.net.CookiePolicy; | |
9 | import java.net.CookieStore; | |
10 | import java.net.HttpCookie; | |
11 | import java.net.HttpURLConnection; | |
12 | import java.net.URL; | |
13 | import java.net.URLConnection; | |
14 | import java.net.URLEncoder; | |
15 | import java.util.Map; | |
16 | import java.util.zip.GZIPInputStream; | |
17 | ||
18 | /** | |
19 | * This class will help you download content from Internet Sites ({@link URL} | |
20 | * based). | |
21 | * <p> | |
22 | * It allows you to control some options often required on web sites that do not | |
23 | * want to simply serve HTML, but actively makes your life difficult with stupid | |
24 | * checks. | |
25 | * | |
26 | * @author niki | |
27 | */ | |
28 | public class Downloader { | |
29 | private String UA; | |
30 | private CookieManager cookies; | |
530d4062 | 31 | private TraceHandler tracer = new TraceHandler(); |
8816d2f7 NR |
32 | |
33 | /** | |
34 | * Create a new {@link Downloader}. | |
35 | * | |
36 | * @param UA | |
37 | * the User-Agent to use to download the resources -- note that | |
38 | * some websites require one, some actively blacklist real UAs | |
39 | * like the one from wget, some whitelist a couple of browsers | |
40 | * only (!) | |
41 | */ | |
42 | public Downloader(String UA) { | |
43 | this.UA = UA; | |
44 | ||
45 | cookies = new CookieManager(); | |
46 | cookies.setCookiePolicy(CookiePolicy.ACCEPT_ALL); | |
47 | CookieHandler.setDefault(cookies); | |
48 | } | |
49 | ||
530d4062 NR |
50 | /** |
51 | * The traces handler for this {@link Cache}. | |
52 | * | |
53 | * @return the traces handler | |
54 | */ | |
55 | public TraceHandler getTraceHandler() { | |
56 | return tracer; | |
57 | } | |
58 | ||
59 | /** | |
60 | * The traces handler for this {@link Cache}. | |
61 | * | |
62 | * @param tracer | |
63 | * the new traces handler | |
64 | */ | |
65 | public void setTraceHandler(TraceHandler tracer) { | |
80500544 NR |
66 | if (tracer == null) { |
67 | tracer = new TraceHandler(false, false, false); | |
68 | } | |
69 | ||
530d4062 NR |
70 | this.tracer = tracer; |
71 | } | |
72 | ||
8816d2f7 NR |
73 | /** |
74 | * Clear all the cookies currently in the jar. | |
75 | * <p> | |
76 | * As long as you don't, the cookies are kept. | |
77 | */ | |
78 | public void clearCookies() { | |
79 | cookies.getCookieStore().removeAll(); | |
80 | } | |
81 | ||
82 | /** | |
83 | * Open the given {@link URL} and update the cookies. | |
84 | * | |
85 | * @param url | |
86 | * the {@link URL} to open | |
87 | * @return the {@link InputStream} of the opened page | |
88 | * | |
89 | * @throws IOException | |
90 | * in case of I/O error | |
91 | **/ | |
92 | public InputStream open(URL url) throws IOException { | |
93 | return open(url, url, url, null, null, null, null); | |
94 | } | |
95 | ||
96 | /** | |
97 | * Open the given {@link URL} and update the cookies. | |
98 | * | |
99 | * @param url | |
100 | * the {@link URL} to open | |
530d4062 NR |
101 | * @param currentReferer |
102 | * the current referer, for websites that needs this info | |
103 | * @param cookiesValues | |
104 | * the cookies | |
8816d2f7 NR |
105 | * @param postParams |
106 | * the POST parameters | |
107 | * @param getParams | |
108 | * the GET parameters (priority over POST) | |
109 | * @param oauth | |
110 | * OAuth authorization (aka, "bearer XXXXXXX") | |
111 | * | |
112 | * @return the {@link InputStream} of the opened page | |
113 | * | |
114 | * @throws IOException | |
115 | * in case of I/O error | |
116 | */ | |
117 | public InputStream open(URL url, URL currentReferer, | |
118 | Map<String, String> cookiesValues, Map<String, String> postParams, | |
119 | Map<String, String> getParams, String oauth) throws IOException { | |
120 | return open(url, url, currentReferer, cookiesValues, postParams, | |
121 | getParams, oauth); | |
122 | } | |
123 | ||
8816d2f7 NR |
124 | /** |
125 | * Open the given {@link URL} and update the cookies. | |
126 | * | |
127 | * @param url | |
128 | * the {@link URL} to open | |
129 | * @param originalUrl | |
130 | * the original {@link URL} before any redirection occurs | |
131 | * @param postParams | |
132 | * the POST parameters | |
133 | * @param getParams | |
134 | * the GET parameters (priority over POST) | |
135 | * @param oauth | |
136 | * OAuth authorisation (aka, "bearer XXXXXXX") | |
137 | * @return the {@link InputStream} of the opened page | |
138 | * | |
139 | * @throws IOException | |
140 | * in case of I/O error | |
141 | */ | |
142 | private InputStream open(URL url, final URL originalUrl, | |
143 | URL currentReferer, Map<String, String> cookiesValues, | |
144 | Map<String, String> postParams, Map<String, String> getParams, | |
145 | String oauth) throws IOException { | |
146 | ||
530d4062 | 147 | tracer.trace("Download: " + url); |
8816d2f7 NR |
148 | |
149 | URLConnection conn = openConnectionWithCookies(url, currentReferer, | |
150 | cookiesValues); | |
151 | ||
152 | // Priority: GET over POST | |
153 | Map<String, String> params = getParams; | |
154 | if (getParams == null) { | |
155 | params = postParams; | |
156 | } | |
157 | ||
158 | if ((params != null || oauth != null) | |
159 | && conn instanceof HttpURLConnection) { | |
160 | StringBuilder requestData = null; | |
161 | if (params != null) { | |
162 | requestData = new StringBuilder(); | |
163 | for (Map.Entry<String, String> param : params.entrySet()) { | |
164 | if (requestData.length() != 0) | |
165 | requestData.append('&'); | |
166 | requestData.append(URLEncoder.encode(param.getKey(), | |
167 | "UTF-8")); | |
168 | requestData.append('='); | |
169 | requestData.append(URLEncoder.encode( | |
170 | String.valueOf(param.getValue()), "UTF-8")); | |
171 | } | |
172 | ||
173 | conn.setDoOutput(true); | |
174 | ||
175 | if (getParams == null && postParams != null) { | |
176 | ((HttpURLConnection) conn).setRequestMethod("POST"); | |
177 | } | |
178 | ||
179 | conn.setRequestProperty("Content-Type", | |
180 | "application/x-www-form-urlencoded"); | |
181 | conn.setRequestProperty("charset", "utf-8"); | |
182 | } | |
183 | ||
184 | if (oauth != null) { | |
185 | conn.setRequestProperty("Authorization", oauth); | |
186 | } | |
187 | ||
188 | if (requestData != null) { | |
0988831f NR |
189 | OutputStreamWriter writer = null; |
190 | try { | |
191 | writer = new OutputStreamWriter(conn.getOutputStream()); | |
192 | writer.write(requestData.toString()); | |
193 | writer.flush(); | |
194 | } finally { | |
195 | if (writer != null) { | |
196 | writer.close(); | |
197 | } | |
198 | } | |
8816d2f7 NR |
199 | } |
200 | } | |
201 | ||
202 | conn.connect(); | |
203 | ||
204 | // Check if redirect | |
6149689f NR |
205 | if (conn instanceof HttpURLConnection) { |
206 | int repCode = 0; | |
207 | try { | |
208 | // Can fail in some circumstances | |
209 | repCode = ((HttpURLConnection) conn).getResponseCode(); | |
210 | } catch (IOException e) { | |
211 | } | |
212 | ||
213 | if (repCode / 100 == 3) { | |
214 | String newUrl = conn.getHeaderField("Location"); | |
215 | return open(new URL(newUrl), originalUrl, currentReferer, | |
216 | cookiesValues, postParams, getParams, oauth); | |
217 | } | |
8816d2f7 NR |
218 | } |
219 | ||
220 | InputStream in = conn.getInputStream(); | |
221 | if ("gzip".equals(conn.getContentEncoding())) { | |
222 | in = new GZIPInputStream(in); | |
223 | } | |
224 | ||
225 | return in; | |
226 | } | |
227 | ||
228 | /** | |
229 | * Open a connection on the given {@link URL}, and manage the cookies that | |
230 | * come with it. | |
231 | * | |
232 | * @param url | |
233 | * the {@link URL} to open | |
234 | * | |
235 | * @return the connection | |
236 | * | |
237 | * @throws IOException | |
238 | * in case of I/O error | |
239 | */ | |
240 | private URLConnection openConnectionWithCookies(URL url, | |
241 | URL currentReferer, Map<String, String> cookiesValues) | |
242 | throws IOException { | |
243 | URLConnection conn = url.openConnection(); | |
244 | ||
245 | conn.setRequestProperty("User-Agent", UA); | |
246 | conn.setRequestProperty("Cookie", generateCookies(cookiesValues)); | |
247 | conn.setRequestProperty("Accept-Encoding", "gzip"); | |
248 | if (currentReferer != null) { | |
249 | conn.setRequestProperty("Referer", currentReferer.toString()); | |
250 | conn.setRequestProperty("Host", currentReferer.getHost()); | |
251 | } | |
252 | ||
253 | return conn; | |
254 | } | |
255 | ||
256 | /** | |
257 | * Generate the cookie {@link String} from the local {@link CookieStore} so | |
258 | * it is ready to be passed. | |
259 | * | |
260 | * @return the cookie | |
261 | */ | |
262 | private String generateCookies(Map<String, String> cookiesValues) { | |
263 | StringBuilder builder = new StringBuilder(); | |
264 | for (HttpCookie cookie : cookies.getCookieStore().getCookies()) { | |
265 | if (builder.length() > 0) { | |
266 | builder.append(';'); | |
267 | } | |
268 | ||
269 | // TODO: check if format is ok | |
270 | builder.append(cookie.toString()); | |
271 | } | |
272 | ||
273 | if (cookiesValues != null) { | |
274 | for (Map.Entry<String, String> set : cookiesValues.entrySet()) { | |
275 | if (builder.length() > 0) { | |
276 | builder.append(';'); | |
277 | } | |
278 | builder.append(set.getKey()); | |
279 | builder.append('='); | |
280 | builder.append(set.getValue()); | |
281 | } | |
282 | } | |
283 | ||
284 | return builder.toString(); | |
285 | } | |
286 | } |