]>
Commit | Line | Data |
---|---|---|
d77c3dfd FV |
1 | #!/usr/bin/env python |
2 | # -*- coding: utf-8 -*- | |
3 | ||
9e8056d5 PH |
4 | from __future__ import absolute_import |
5 | ||
4fcca4bb | 6 | import base64 |
d77c3dfd | 7 | import datetime |
ccf65f9d | 8 | import itertools |
d77c3dfd FV |
9 | import netrc |
10 | import os | |
11 | import re | |
12 | import socket | |
13 | import time | |
d77c3dfd | 14 | import email.utils |
921a1455 | 15 | import xml.etree.ElementTree |
302efc19 | 16 | import random |
17 | import math | |
6324fd1d | 18 | import operator |
d77c3dfd | 19 | |
9e8056d5 | 20 | from .utils import * |
d77c3dfd FV |
21 | |
22 | ||
23 | class InfoExtractor(object): | |
59ae15a5 | 24 | """Information Extractor class. |
d77c3dfd | 25 | |
59ae15a5 PH |
26 | Information extractors are the classes that, given a URL, extract |
27 | information about the video (or videos) the URL refers to. This | |
28 | information includes the real video URL, the video title, author and | |
cdb30764 | 29 | others. The information is stored in a dictionary which is then |
59ae15a5 PH |
30 | passed to the FileDownloader. The FileDownloader processes this |
31 | information possibly downloading the video to the file system, among | |
32 | other possible outcomes. | |
717b1f72 | 33 | |
59ae15a5 | 34 | The dictionaries must include the following fields: |
717b1f72 | 35 | |
59ae15a5 PH |
36 | id: Video identifier. |
37 | url: Final video URL. | |
59ae15a5 PH |
38 | title: Video title, unescaped. |
39 | ext: Video filename extension. | |
717b1f72 | 40 | |
59ae15a5 | 41 | The following fields are optional: |
717b1f72 | 42 | |
59ae15a5 PH |
43 | format: The video format, defaults to ext (used for --get-format) |
44 | thumbnail: Full URL to a video thumbnail image. | |
45 | description: One-line video description. | |
539679c7 PH |
46 | uploader: Full name of the video uploader. |
47 | upload_date: Video upload date (YYYYMMDD). | |
77c4beab | 48 | uploader_id: Nickname or id of the video uploader. |
6119f78c | 49 | location: Physical location of the video. |
59ae15a5 | 50 | player_url: SWF Player URL (used for rtmpdump). |
553d0974 | 51 | subtitles: The subtitle file contents. |
59ae15a5 PH |
52 | urlhandle: [internal] The urlHandle to be used to download the file, |
53 | like returned by urllib.request.urlopen | |
d77c3dfd | 54 | |
59ae15a5 | 55 | The fields should all be Unicode strings. |
9ce5d9ee | 56 | |
59ae15a5 PH |
57 | Subclasses of this one should re-define the _real_initialize() and |
58 | _real_extract() methods and define a _VALID_URL regexp. | |
59 | Probably, they should also be added to the list of extractors. | |
717b1f72 | 60 | |
59ae15a5 PH |
61 | _real_extract() must return a *list* of information dictionaries as |
62 | described above. | |
03c5b0fb | 63 | |
59ae15a5 PH |
64 | Finally, the _WORKING attribute should be set to False for broken IEs |
65 | in order to warn the users and skip the tests. | |
66 | """ | |
d77c3dfd | 67 | |
59ae15a5 PH |
68 | _ready = False |
69 | _downloader = None | |
70 | _WORKING = True | |
d77c3dfd | 71 | |
59ae15a5 PH |
72 | def __init__(self, downloader=None): |
73 | """Constructor. Receives an optional downloader.""" | |
74 | self._ready = False | |
75 | self.set_downloader(downloader) | |
d77c3dfd | 76 | |
89de9eb1 FV |
77 | @classmethod |
78 | def suitable(cls, url): | |
59ae15a5 | 79 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 | 80 | return re.match(cls._VALID_URL, url) is not None |
d77c3dfd | 81 | |
89de9eb1 FV |
82 | @classmethod |
83 | def working(cls): | |
59ae15a5 | 84 | """Getter method for _WORKING.""" |
89de9eb1 | 85 | return cls._WORKING |
03c5b0fb | 86 | |
59ae15a5 PH |
87 | def initialize(self): |
88 | """Initializes an instance (authentication, etc).""" | |
89 | if not self._ready: | |
90 | self._real_initialize() | |
91 | self._ready = True | |
d77c3dfd | 92 | |
59ae15a5 PH |
93 | def extract(self, url): |
94 | """Extracts URL information and returns it in list of dicts.""" | |
95 | self.initialize() | |
96 | return self._real_extract(url) | |
d77c3dfd | 97 | |
59ae15a5 PH |
98 | def set_downloader(self, downloader): |
99 | """Sets the downloader for this IE.""" | |
100 | self._downloader = downloader | |
d77c3dfd | 101 | |
59ae15a5 PH |
102 | def _real_initialize(self): |
103 | """Real initialization process. Redefine in subclasses.""" | |
104 | pass | |
d77c3dfd | 105 | |
59ae15a5 PH |
106 | def _real_extract(self, url): |
107 | """Real extraction process. Redefine in subclasses.""" | |
108 | pass | |
d77c3dfd | 109 | |
d0d4f277 PH |
110 | @property |
111 | def IE_NAME(self): | |
112 | return type(self).__name__[:-2] | |
d77c3dfd | 113 | |
64ce2aad PH |
114 | def _request_webpage(self, url_or_request, video_id, note=None, errnote=None): |
115 | """ Returns the response handle """ | |
d830b7c2 PH |
116 | if note is None: |
117 | note = u'Downloading video webpage' | |
927c8c49 PH |
118 | if note is not False: |
119 | self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note)) | |
d830b7c2 | 120 | try: |
64ce2aad | 121 | return compat_urllib_request.urlopen(url_or_request) |
d830b7c2 PH |
122 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
123 | if errnote is None: | |
124 | errnote = u'Unable to download webpage' | |
01951dda | 125 | raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2]) |
d830b7c2 | 126 | |
64ce2aad PH |
127 | def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): |
128 | """ Returns the data of the page as a string """ | |
129 | urlh = self._request_webpage(url_or_request, video_id, note, errnote) | |
e32b06e9 PH |
130 | content_type = urlh.headers.get('Content-Type', '') |
131 | m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) | |
132 | if m: | |
133 | encoding = m.group(1) | |
134 | else: | |
135 | encoding = 'utf-8' | |
64ce2aad | 136 | webpage_bytes = urlh.read() |
855703e5 PH |
137 | if self._downloader.params.get('dump_intermediate_pages', False): |
138 | try: | |
139 | url = url_or_request.get_full_url() | |
140 | except AttributeError: | |
141 | url = url_or_request | |
142 | self._downloader.to_screen(u'Dumping request to ' + url) | |
143 | dump = base64.b64encode(webpage_bytes).decode('ascii') | |
144 | self._downloader.to_screen(dump) | |
e32b06e9 | 145 | return webpage_bytes.decode(encoding, 'replace') |
64ce2aad | 146 | |
d830b7c2 | 147 | |
d77c3dfd | 148 | class YoutubeIE(InfoExtractor): |
59ae15a5 PH |
149 | """Information extractor for youtube.com.""" |
150 | ||
151 | _VALID_URL = r"""^ | |
152 | ( | |
153 | (?:https?://)? # http(s):// (optional) | |
154 | (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| | |
155 | tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains | |
156 | (?:.*?\#/)? # handle anchor (#/) redirect urls | |
59ae15a5 PH |
157 | (?: # the various things that can precede the ID: |
158 | (?:(?:v|embed|e)/) # v/ or embed/ or e/ | |
159 | |(?: # or the v= param in all its forms | |
160 | (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) | |
161 | (?:\?|\#!?) # the params delimiter ? or # or #! | |
3bb61659 | 162 | (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) |
59ae15a5 PH |
163 | v= |
164 | ) | |
165 | )? # optional -> youtube.com/xxxx is OK | |
166 | )? # all until now is optional -> you can pass the naked ID | |
167 | ([0-9A-Za-z_-]+) # here is it! the YouTube video ID | |
168 | (?(1).+)? # if we found the ID, everything can follow | |
169 | $""" | |
170 | _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' | |
d3f5f9f6 | 171 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' |
59ae15a5 PH |
172 | _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' |
173 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' | |
174 | _NETRC_MACHINE = 'youtube' | |
175 | # Listed in order of quality | |
176 | _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] | |
177 | _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] | |
178 | _video_extensions = { | |
179 | '13': '3gp', | |
180 | '17': 'mp4', | |
181 | '18': 'mp4', | |
182 | '22': 'mp4', | |
183 | '37': 'mp4', | |
184 | '38': 'video', # You actually don't know if this will be MOV, AVI or whatever | |
185 | '43': 'webm', | |
186 | '44': 'webm', | |
187 | '45': 'webm', | |
188 | '46': 'webm', | |
189 | } | |
190 | _video_dimensions = { | |
191 | '5': '240x400', | |
192 | '6': '???', | |
193 | '13': '???', | |
194 | '17': '144x176', | |
195 | '18': '360x640', | |
196 | '22': '720x1280', | |
197 | '34': '360x640', | |
198 | '35': '480x854', | |
199 | '37': '1080x1920', | |
200 | '38': '3072x4096', | |
201 | '43': '360x640', | |
202 | '44': '480x854', | |
203 | '45': '720x1280', | |
204 | '46': '1080x1920', | |
cdb30764 | 205 | } |
59ae15a5 PH |
206 | IE_NAME = u'youtube' |
207 | ||
89de9eb1 FV |
208 | @classmethod |
209 | def suitable(cls, url): | |
59ae15a5 | 210 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 FV |
211 | if YoutubePlaylistIE.suitable(url): return False |
212 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None | |
59ae15a5 PH |
213 | |
214 | def report_lang(self): | |
215 | """Report attempt to set language.""" | |
216 | self._downloader.to_screen(u'[youtube] Setting language') | |
217 | ||
218 | def report_login(self): | |
219 | """Report attempt to log in.""" | |
220 | self._downloader.to_screen(u'[youtube] Logging in') | |
221 | ||
222 | def report_age_confirmation(self): | |
223 | """Report attempt to confirm age.""" | |
224 | self._downloader.to_screen(u'[youtube] Confirming age') | |
225 | ||
226 | def report_video_webpage_download(self, video_id): | |
227 | """Report attempt to download video webpage.""" | |
228 | self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) | |
229 | ||
230 | def report_video_info_webpage_download(self, video_id): | |
231 | """Report attempt to download video info webpage.""" | |
232 | self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) | |
233 | ||
234 | def report_video_subtitles_download(self, video_id): | |
235 | """Report attempt to download video info webpage.""" | |
2a4093ea | 236 | self._downloader.to_screen(u'[youtube] %s: Checking available subtitles' % video_id) |
59ae15a5 | 237 | |
2a4093ea | 238 | def report_video_subtitles_request(self, video_id, sub_lang, format): |
ae608b80 | 239 | """Report attempt to download video info webpage.""" |
2a4093ea IM |
240 | self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format)) |
241 | ||
242 | def report_video_subtitles_available(self, video_id, sub_lang_list): | |
243 | """Report available subtitles.""" | |
244 | sub_lang = ",".join(list(sub_lang_list.keys())) | |
245 | self._downloader.to_screen(u'[youtube] %s: Available subtitles for video: %s' % (video_id, sub_lang)) | |
59ae15a5 PH |
246 | |
247 | def report_information_extraction(self, video_id): | |
248 | """Report attempt to extract video information.""" | |
249 | self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) | |
250 | ||
251 | def report_unavailable_format(self, video_id, format): | |
252 | """Report extracted video URL.""" | |
253 | self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) | |
254 | ||
255 | def report_rtmp_download(self): | |
256 | """Indicate the download will use the RTMP protocol.""" | |
257 | self._downloader.to_screen(u'[youtube] RTMP download detected') | |
258 | ||
ae608b80 | 259 | def _get_available_subtitles(self, video_id): |
056d8575 FV |
260 | self.report_video_subtitles_download(video_id) |
261 | request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) | |
262 | try: | |
553d0974 | 263 | sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8') |
056d8575 | 264 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
bc97f6d6 | 265 | return (u'unable to download video subtitles: %s' % compat_str(err), None) |
553d0974 IM |
266 | sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list) |
267 | sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list) | |
268 | if not sub_lang_list: | |
bc97f6d6 | 269 | return (u'video doesn\'t have subtitles', None) |
553d0974 | 270 | return sub_lang_list |
ae608b80 | 271 | |
2a4093ea IM |
272 | def _list_available_subtitles(self, video_id): |
273 | sub_lang_list = self._get_available_subtitles(video_id) | |
274 | self.report_video_subtitles_available(video_id, sub_lang_list) | |
275 | ||
9e62bc44 | 276 | def _request_subtitle(self, sub_lang, sub_name, video_id, format): |
6a205c88 JMF |
277 | """ |
278 | Return tuple: | |
279 | (error_message, sub_lang, sub) | |
280 | """ | |
2a4093ea | 281 | self.report_video_subtitles_request(video_id, sub_lang, format) |
fb778e66 | 282 | params = compat_urllib_parse.urlencode({ |
553d0974 IM |
283 | 'lang': sub_lang, |
284 | 'name': sub_name, | |
fb778e66 | 285 | 'v': video_id, |
ae608b80 | 286 | 'fmt': format, |
fb778e66 PH |
287 | }) |
288 | url = 'http://www.youtube.com/api/timedtext?' + params | |
056d8575 | 289 | try: |
553d0974 | 290 | sub = compat_urllib_request.urlopen(url).read().decode('utf-8') |
056d8575 | 291 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
bc97f6d6 | 292 | return (u'unable to download video subtitles: %s' % compat_str(err), None, None) |
553d0974 | 293 | if not sub: |
bc97f6d6 | 294 | return (u'Did not fetch video subtitles', None, None) |
553d0974 | 295 | return (None, sub_lang, sub) |
ae608b80 IM |
296 | |
297 | def _extract_subtitle(self, video_id): | |
0fb37564 JMF |
298 | """ |
299 | Return a list with a tuple: | |
300 | [(error_message, sub_lang, sub)] | |
301 | """ | |
553d0974 | 302 | sub_lang_list = self._get_available_subtitles(video_id) |
9e62bc44 | 303 | sub_format = self._downloader.params.get('subtitlesformat') |
0fb37564 JMF |
304 | if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles |
305 | return [(sub_lang_list[0], None, None)] | |
ae608b80 | 306 | if self._downloader.params.get('subtitleslang', False): |
553d0974 IM |
307 | sub_lang = self._downloader.params.get('subtitleslang') |
308 | elif 'en' in sub_lang_list: | |
309 | sub_lang = 'en' | |
ae608b80 | 310 | else: |
553d0974 IM |
311 | sub_lang = list(sub_lang_list.keys())[0] |
312 | if not sub_lang in sub_lang_list: | |
bc97f6d6 | 313 | return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)] |
ae608b80 | 314 | |
9e62bc44 | 315 | subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) |
553d0974 | 316 | return [subtitle] |
ae608b80 IM |
317 | |
318 | def _extract_all_subtitles(self, video_id): | |
553d0974 | 319 | sub_lang_list = self._get_available_subtitles(video_id) |
9e62bc44 | 320 | sub_format = self._downloader.params.get('subtitlesformat') |
ef767f9f JMF |
321 | if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles |
322 | return [(sub_lang_list[0], None, None)] | |
553d0974 IM |
323 | subtitles = [] |
324 | for sub_lang in sub_lang_list: | |
9e62bc44 | 325 | subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) |
553d0974 IM |
326 | subtitles.append(subtitle) |
327 | return subtitles | |
056d8575 | 328 | |
59ae15a5 PH |
329 | def _print_formats(self, formats): |
330 | print('Available formats:') | |
331 | for x in formats: | |
332 | print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))) | |
333 | ||
334 | def _real_initialize(self): | |
335 | if self._downloader is None: | |
336 | return | |
337 | ||
338 | username = None | |
339 | password = None | |
340 | downloader_params = self._downloader.params | |
341 | ||
342 | # Attempt to use provided username and password or .netrc data | |
343 | if downloader_params.get('username', None) is not None: | |
344 | username = downloader_params['username'] | |
345 | password = downloader_params['password'] | |
346 | elif downloader_params.get('usenetrc', False): | |
347 | try: | |
348 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
349 | if info is not None: | |
350 | username = info[0] | |
351 | password = info[2] | |
352 | else: | |
353 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
354 | except (IOError, netrc.NetrcParseError) as err: | |
2e5457be | 355 | self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) |
59ae15a5 PH |
356 | return |
357 | ||
358 | # Set language | |
359 | request = compat_urllib_request.Request(self._LANG_URL) | |
360 | try: | |
361 | self.report_lang() | |
362 | compat_urllib_request.urlopen(request).read() | |
363 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2e5457be | 364 | self._downloader.report_warning(u'unable to set language: %s' % compat_str(err)) |
59ae15a5 PH |
365 | return |
366 | ||
367 | # No authentication to be performed | |
368 | if username is None: | |
369 | return | |
370 | ||
d3f5f9f6 PH |
371 | request = compat_urllib_request.Request(self._LOGIN_URL) |
372 | try: | |
373 | login_page = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
374 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2e5457be | 375 | self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err)) |
d3f5f9f6 PH |
376 | return |
377 | ||
378 | galx = None | |
379 | dsh = None | |
380 | match = re.search(re.compile(r'<input.+?name="GALX".+?value="(.+?)"', re.DOTALL), login_page) | |
381 | if match: | |
382 | galx = match.group(1) | |
383 | ||
384 | match = re.search(re.compile(r'<input.+?name="dsh".+?value="(.+?)"', re.DOTALL), login_page) | |
385 | if match: | |
386 | dsh = match.group(1) | |
387 | ||
59ae15a5 | 388 | # Log in |
d3f5f9f6 PH |
389 | login_form_strs = { |
390 | u'continue': u'http://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', | |
391 | u'Email': username, | |
392 | u'GALX': galx, | |
393 | u'Passwd': password, | |
394 | u'PersistentCookie': u'yes', | |
395 | u'_utf8': u'霱', | |
396 | u'bgresponse': u'js_disabled', | |
397 | u'checkConnection': u'', | |
398 | u'checkedDomains': u'youtube', | |
399 | u'dnConn': u'', | |
400 | u'dsh': dsh, | |
401 | u'pstMsg': u'0', | |
402 | u'rmShown': u'1', | |
403 | u'secTok': u'', | |
404 | u'signIn': u'Sign in', | |
405 | u'timeStmp': u'', | |
406 | u'service': u'youtube', | |
407 | u'uilel': u'3', | |
408 | u'hl': u'en_US', | |
409 | } | |
410 | # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode | |
411 | # chokes on unicode | |
412 | login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items()) | |
413 | login_data = compat_urllib_parse.urlencode(login_form).encode('ascii') | |
414 | request = compat_urllib_request.Request(self._LOGIN_URL, login_data) | |
59ae15a5 PH |
415 | try: |
416 | self.report_login() | |
80d3177e | 417 | login_results = compat_urllib_request.urlopen(request).read().decode('utf-8') |
d3f5f9f6 | 418 | if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: |
2e5457be | 419 | self._downloader.report_warning(u'unable to log in: bad username or password') |
59ae15a5 PH |
420 | return |
421 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2e5457be | 422 | self._downloader.report_warning(u'unable to log in: %s' % compat_str(err)) |
59ae15a5 PH |
423 | return |
424 | ||
425 | # Confirm age | |
426 | age_form = { | |
427 | 'next_url': '/', | |
428 | 'action_confirm': 'Confirm', | |
429 | } | |
430 | request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form)) | |
431 | try: | |
432 | self.report_age_confirmation() | |
80d3177e | 433 | age_results = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 | 434 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 435 | self._downloader.report_error(u'unable to confirm age: %s' % compat_str(err)) |
59ae15a5 PH |
436 | return |
437 | ||
3bb61659 | 438 | def _extract_id(self, url): |
59ae15a5 PH |
439 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
440 | if mobj is None: | |
e5f30ade | 441 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
442 | return |
443 | video_id = mobj.group(2) | |
3bb61659 PH |
444 | return video_id |
445 | ||
446 | def _real_extract(self, url): | |
447 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter | |
448 | mobj = re.search(self._NEXT_URL_RE, url) | |
449 | if mobj: | |
450 | url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') | |
451 | video_id = self._extract_id(url) | |
59ae15a5 PH |
452 | |
453 | # Get video webpage | |
454 | self.report_video_webpage_download(video_id) | |
3bb61659 PH |
455 | url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id |
456 | request = compat_urllib_request.Request(url) | |
59ae15a5 PH |
457 | try: |
458 | video_webpage_bytes = compat_urllib_request.urlopen(request).read() | |
459 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 460 | self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
461 | return |
462 | ||
463 | video_webpage = video_webpage_bytes.decode('utf-8', 'ignore') | |
464 | ||
465 | # Attempt to extract SWF player URL | |
466 | mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) | |
467 | if mobj is not None: | |
468 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
469 | else: | |
470 | player_url = None | |
471 | ||
472 | # Get video info | |
473 | self.report_video_info_webpage_download(video_id) | |
474 | for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: | |
927c8c49 | 475 | video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' |
59ae15a5 | 476 | % (video_id, el_type)) |
927c8c49 PH |
477 | video_info_webpage = self._download_webpage(video_info_url, video_id, |
478 | note=False, | |
479 | errnote='unable to download video info webpage') | |
480 | video_info = compat_parse_qs(video_info_webpage) | |
481 | if 'token' in video_info: | |
482 | break | |
59ae15a5 PH |
483 | if 'token' not in video_info: |
484 | if 'reason' in video_info: | |
e5f30ade | 485 | self._downloader.report_error(u'YouTube said: %s' % video_info['reason'][0]) |
59ae15a5 | 486 | else: |
e5f30ade | 487 | self._downloader.report_error(u'"token" parameter not in video info for unknown reason') |
59ae15a5 PH |
488 | return |
489 | ||
490 | # Check for "rental" videos | |
491 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
e5f30ade | 492 | self._downloader.report_error(u'"rental" videos not supported') |
59ae15a5 PH |
493 | return |
494 | ||
495 | # Start extracting information | |
496 | self.report_information_extraction(video_id) | |
497 | ||
498 | # uploader | |
499 | if 'author' not in video_info: | |
e5f30ade | 500 | self._downloader.report_error(u'unable to extract uploader name') |
59ae15a5 PH |
501 | return |
502 | video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) | |
503 | ||
77c4beab FV |
504 | # uploader_id |
505 | video_uploader_id = None | |
26cf0408 | 506 | mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage) |
77c4beab FV |
507 | if mobj is not None: |
508 | video_uploader_id = mobj.group(1) | |
509 | else: | |
c9fa1cba | 510 | self._downloader.report_warning(u'unable to extract uploader nickname') |
77c4beab | 511 | |
59ae15a5 PH |
512 | # title |
513 | if 'title' not in video_info: | |
e5f30ade | 514 | self._downloader.report_error(u'unable to extract video title') |
59ae15a5 PH |
515 | return |
516 | video_title = compat_urllib_parse.unquote_plus(video_info['title'][0]) | |
517 | ||
518 | # thumbnail image | |
519 | if 'thumbnail_url' not in video_info: | |
c9fa1cba | 520 | self._downloader.report_warning(u'unable to extract video thumbnail') |
59ae15a5 PH |
521 | video_thumbnail = '' |
522 | else: # don't panic if we can't find it | |
523 | video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) | |
524 | ||
525 | # upload date | |
526 | upload_date = None | |
527 | mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL) | |
528 | if mobj is not None: | |
529 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) | |
530 | format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] | |
531 | for expression in format_expressions: | |
532 | try: | |
533 | upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') | |
534 | except: | |
535 | pass | |
536 | ||
537 | # description | |
538 | video_description = get_element_by_id("eow-description", video_webpage) | |
539 | if video_description: | |
540 | video_description = clean_html(video_description) | |
541 | else: | |
542 | video_description = '' | |
543 | ||
9e62bc44 | 544 | # subtitles |
59ae15a5 | 545 | video_subtitles = None |
ae608b80 | 546 | |
59ae15a5 | 547 | if self._downloader.params.get('writesubtitles', False): |
ae608b80 IM |
548 | video_subtitles = self._extract_subtitle(video_id) |
549 | if video_subtitles: | |
553d0974 IM |
550 | (sub_error, sub_lang, sub) = video_subtitles[0] |
551 | if sub_error: | |
bc97f6d6 | 552 | self._downloader.report_error(sub_error) |
ae608b80 IM |
553 | |
554 | if self._downloader.params.get('allsubtitles', False): | |
555 | video_subtitles = self._extract_all_subtitles(video_id) | |
556 | for video_subtitle in video_subtitles: | |
553d0974 IM |
557 | (sub_error, sub_lang, sub) = video_subtitle |
558 | if sub_error: | |
bc97f6d6 | 559 | self._downloader.report_error(sub_error) |
59ae15a5 | 560 | |
2a4093ea IM |
561 | if self._downloader.params.get('listsubtitles', False): |
562 | sub_lang_list = self._list_available_subtitles(video_id) | |
563 | return | |
59ae15a5 PH |
564 | |
565 | if 'length_seconds' not in video_info: | |
c9fa1cba | 566 | self._downloader.report_warning(u'unable to extract video duration') |
59ae15a5 PH |
567 | video_duration = '' |
568 | else: | |
569 | video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]) | |
570 | ||
571 | # token | |
572 | video_token = compat_urllib_parse.unquote_plus(video_info['token'][0]) | |
573 | ||
574 | # Decide which formats to download | |
575 | req_format = self._downloader.params.get('format', None) | |
576 | ||
577 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): | |
578 | self.report_rtmp_download() | |
579 | video_url_list = [(None, video_info['conn'][0])] | |
580 | elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: | |
581 | url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') | |
582 | url_data = [compat_parse_qs(uds) for uds in url_data_strs] | |
1a2c3c0f | 583 | url_data = [ud for ud in url_data if 'itag' in ud and 'url' in ud] |
c8c5443b | 584 | url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data) |
59ae15a5 PH |
585 | |
586 | format_limit = self._downloader.params.get('format_limit', None) | |
587 | available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats | |
588 | if format_limit is not None and format_limit in available_formats: | |
589 | format_list = available_formats[available_formats.index(format_limit):] | |
590 | else: | |
591 | format_list = available_formats | |
592 | existing_formats = [x for x in format_list if x in url_map] | |
593 | if len(existing_formats) == 0: | |
e5f30ade | 594 | self._downloader.report_error(u'no known formats available for video') |
59ae15a5 PH |
595 | return |
596 | if self._downloader.params.get('listformats', None): | |
597 | self._print_formats(existing_formats) | |
598 | return | |
599 | if req_format is None or req_format == 'best': | |
600 | video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality | |
601 | elif req_format == 'worst': | |
602 | video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality | |
603 | elif req_format in ('-1', 'all'): | |
604 | video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats | |
605 | else: | |
606 | # Specific formats. We pick the first in a slash-delimeted sequence. | |
607 | # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. | |
608 | req_formats = req_format.split('/') | |
609 | video_url_list = None | |
610 | for rf in req_formats: | |
611 | if rf in url_map: | |
612 | video_url_list = [(rf, url_map[rf])] | |
613 | break | |
614 | if video_url_list is None: | |
e5f30ade | 615 | self._downloader.report_error(u'requested format not available') |
59ae15a5 PH |
616 | return |
617 | else: | |
e5f30ade | 618 | self._downloader.report_error(u'no conn or url_encoded_fmt_stream_map information found in video info') |
59ae15a5 PH |
619 | return |
620 | ||
621 | results = [] | |
622 | for format_param, video_real_url in video_url_list: | |
623 | # Extension | |
624 | video_extension = self._video_extensions.get(format_param, 'flv') | |
625 | ||
32761d86 FV |
626 | video_format = '{0} - {1}'.format(format_param if format_param else video_extension, |
627 | self._video_dimensions.get(format_param, '???')) | |
59ae15a5 PH |
628 | |
629 | results.append({ | |
630 | 'id': video_id, | |
631 | 'url': video_real_url, | |
632 | 'uploader': video_uploader, | |
77c4beab | 633 | 'uploader_id': video_uploader_id, |
59ae15a5 PH |
634 | 'upload_date': upload_date, |
635 | 'title': video_title, | |
636 | 'ext': video_extension, | |
637 | 'format': video_format, | |
638 | 'thumbnail': video_thumbnail, | |
639 | 'description': video_description, | |
640 | 'player_url': player_url, | |
641 | 'subtitles': video_subtitles, | |
642 | 'duration': video_duration | |
643 | }) | |
644 | return results | |
d77c3dfd FV |
645 | |
646 | ||
647 | class MetacafeIE(InfoExtractor): | |
59ae15a5 PH |
648 | """Information Extractor for metacafe.com.""" |
649 | ||
650 | _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' | |
651 | _DISCLAIMER = 'http://www.metacafe.com/family_filter/' | |
652 | _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' | |
653 | IE_NAME = u'metacafe' | |
654 | ||
655 | def __init__(self, downloader=None): | |
656 | InfoExtractor.__init__(self, downloader) | |
657 | ||
658 | def report_disclaimer(self): | |
659 | """Report disclaimer retrieval.""" | |
660 | self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') | |
661 | ||
662 | def report_age_confirmation(self): | |
663 | """Report attempt to confirm age.""" | |
664 | self._downloader.to_screen(u'[metacafe] Confirming age') | |
665 | ||
666 | def report_download_webpage(self, video_id): | |
667 | """Report webpage download.""" | |
668 | self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) | |
669 | ||
670 | def report_extraction(self, video_id): | |
671 | """Report information extraction.""" | |
672 | self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) | |
673 | ||
674 | def _real_initialize(self): | |
675 | # Retrieve disclaimer | |
676 | request = compat_urllib_request.Request(self._DISCLAIMER) | |
677 | try: | |
678 | self.report_disclaimer() | |
679 | disclaimer = compat_urllib_request.urlopen(request).read() | |
680 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 681 | self._downloader.report_error(u'unable to retrieve disclaimer: %s' % compat_str(err)) |
59ae15a5 PH |
682 | return |
683 | ||
684 | # Confirm age | |
685 | disclaimer_form = { | |
686 | 'filters': '0', | |
687 | 'submit': "Continue - I'm over 18", | |
688 | } | |
689 | request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) | |
690 | try: | |
691 | self.report_age_confirmation() | |
692 | disclaimer = compat_urllib_request.urlopen(request).read() | |
693 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 694 | self._downloader.report_error(u'unable to confirm age: %s' % compat_str(err)) |
59ae15a5 PH |
695 | return |
696 | ||
697 | def _real_extract(self, url): | |
698 | # Extract id and simplified title from URL | |
699 | mobj = re.match(self._VALID_URL, url) | |
700 | if mobj is None: | |
e5f30ade | 701 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
702 | return |
703 | ||
704 | video_id = mobj.group(1) | |
705 | ||
706 | # Check if video comes from YouTube | |
707 | mobj2 = re.match(r'^yt-(.*)$', video_id) | |
708 | if mobj2 is not None: | |
709 | self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)]) | |
710 | return | |
711 | ||
712 | # Retrieve video webpage to extract further information | |
713 | request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) | |
714 | try: | |
715 | self.report_download_webpage(video_id) | |
716 | webpage = compat_urllib_request.urlopen(request).read() | |
717 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 718 | self._downloader.report_error(u'unable retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
719 | return |
720 | ||
721 | # Extract URL, uploader and title from webpage | |
722 | self.report_extraction(video_id) | |
723 | mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) | |
724 | if mobj is not None: | |
725 | mediaURL = compat_urllib_parse.unquote(mobj.group(1)) | |
726 | video_extension = mediaURL[-3:] | |
727 | ||
728 | # Extract gdaKey if available | |
729 | mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) | |
730 | if mobj is None: | |
731 | video_url = mediaURL | |
732 | else: | |
733 | gdaKey = mobj.group(1) | |
734 | video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) | |
735 | else: | |
736 | mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) | |
737 | if mobj is None: | |
e5f30ade | 738 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 PH |
739 | return |
740 | vardict = compat_parse_qs(mobj.group(1)) | |
741 | if 'mediaData' not in vardict: | |
e5f30ade | 742 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 PH |
743 | return |
744 | mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) | |
745 | if mobj is None: | |
e5f30ade | 746 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 PH |
747 | return |
748 | mediaURL = mobj.group(1).replace('\\/', '/') | |
749 | video_extension = mediaURL[-3:] | |
750 | video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) | |
751 | ||
752 | mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) | |
753 | if mobj is None: | |
e5f30ade | 754 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 PH |
755 | return |
756 | video_title = mobj.group(1).decode('utf-8') | |
757 | ||
758 | mobj = re.search(r'submitter=(.*?);', webpage) | |
759 | if mobj is None: | |
e5f30ade | 760 | self._downloader.report_error(u'unable to extract uploader nickname') |
59ae15a5 PH |
761 | return |
762 | video_uploader = mobj.group(1) | |
763 | ||
764 | return [{ | |
765 | 'id': video_id.decode('utf-8'), | |
766 | 'url': video_url.decode('utf-8'), | |
767 | 'uploader': video_uploader.decode('utf-8'), | |
768 | 'upload_date': None, | |
769 | 'title': video_title, | |
770 | 'ext': video_extension.decode('utf-8'), | |
771 | }] | |
d77c3dfd FV |
772 | |
773 | ||
774 | class DailymotionIE(InfoExtractor): | |
59ae15a5 PH |
775 | """Information Extractor for Dailymotion""" |
776 | ||
777 | _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' | |
778 | IE_NAME = u'dailymotion' | |
b17c974a | 779 | _WORKING = False |
59ae15a5 PH |
780 | |
781 | def __init__(self, downloader=None): | |
782 | InfoExtractor.__init__(self, downloader) | |
783 | ||
59ae15a5 PH |
784 | def report_extraction(self, video_id): |
785 | """Report information extraction.""" | |
786 | self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) | |
787 | ||
788 | def _real_extract(self, url): | |
789 | # Extract id and simplified title from URL | |
790 | mobj = re.match(self._VALID_URL, url) | |
791 | if mobj is None: | |
e5f30ade | 792 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
793 | return |
794 | ||
795 | video_id = mobj.group(1).split('_')[0].split('?')[0] | |
796 | ||
797 | video_extension = 'mp4' | |
798 | ||
799 | # Retrieve video webpage to extract further information | |
800 | request = compat_urllib_request.Request(url) | |
801 | request.add_header('Cookie', 'family_filter=off') | |
8e241d1a | 802 | webpage = self._download_webpage(request, video_id) |
59ae15a5 PH |
803 | |
804 | # Extract URL, uploader and title from webpage | |
805 | self.report_extraction(video_id) | |
806 | mobj = re.search(r'\s*var flashvars = (.*)', webpage) | |
807 | if mobj is None: | |
e5f30ade | 808 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 PH |
809 | return |
810 | flashvars = compat_urllib_parse.unquote(mobj.group(1)) | |
811 | ||
812 | for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: | |
813 | if key in flashvars: | |
814 | max_quality = key | |
815 | self._downloader.to_screen(u'[dailymotion] Using %s' % key) | |
816 | break | |
817 | else: | |
e5f30ade | 818 | self._downloader.report_error(u'unable to extract video URL') |
59ae15a5 PH |
819 | return |
820 | ||
821 | mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) | |
822 | if mobj is None: | |
e5f30ade | 823 | self._downloader.report_error(u'unable to extract video URL') |
59ae15a5 PH |
824 | return |
825 | ||
826 | video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/') | |
827 | ||
828 | # TODO: support choosing qualities | |
829 | ||
830 | mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage) | |
831 | if mobj is None: | |
e5f30ade | 832 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 | 833 | return |
28ca6b5a | 834 | video_title = unescapeHTML(mobj.group('title')) |
59ae15a5 PH |
835 | |
836 | video_uploader = None | |
837 | mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage) | |
838 | if mobj is None: | |
839 | # lookin for official user | |
840 | mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage) | |
841 | if mobj_official is None: | |
c9fa1cba | 842 | self._downloader.report_warning(u'unable to extract uploader nickname') |
59ae15a5 PH |
843 | else: |
844 | video_uploader = mobj_official.group(1) | |
845 | else: | |
846 | video_uploader = mobj.group(1) | |
847 | ||
848 | video_upload_date = None | |
849 | mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage) | |
850 | if mobj is not None: | |
851 | video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1) | |
852 | ||
853 | return [{ | |
28ca6b5a PH |
854 | 'id': video_id, |
855 | 'url': video_url, | |
856 | 'uploader': video_uploader, | |
59ae15a5 PH |
857 | 'upload_date': video_upload_date, |
858 | 'title': video_title, | |
28ca6b5a | 859 | 'ext': video_extension, |
59ae15a5 | 860 | }] |
d77c3dfd FV |
861 | |
862 | ||
d77c3dfd | 863 | class PhotobucketIE(InfoExtractor): |
59ae15a5 PH |
864 | """Information extractor for photobucket.com.""" |
865 | ||
866 | _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' | |
867 | IE_NAME = u'photobucket' | |
868 | ||
869 | def __init__(self, downloader=None): | |
870 | InfoExtractor.__init__(self, downloader) | |
871 | ||
872 | def report_download_webpage(self, video_id): | |
873 | """Report webpage download.""" | |
874 | self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) | |
875 | ||
876 | def report_extraction(self, video_id): | |
877 | """Report information extraction.""" | |
878 | self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) | |
879 | ||
880 | def _real_extract(self, url): | |
881 | # Extract id from URL | |
882 | mobj = re.match(self._VALID_URL, url) | |
883 | if mobj is None: | |
e5f30ade | 884 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
885 | return |
886 | ||
887 | video_id = mobj.group(1) | |
888 | ||
889 | video_extension = 'flv' | |
890 | ||
891 | # Retrieve video webpage to extract further information | |
892 | request = compat_urllib_request.Request(url) | |
893 | try: | |
894 | self.report_download_webpage(video_id) | |
895 | webpage = compat_urllib_request.urlopen(request).read() | |
896 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 897 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
898 | return |
899 | ||
900 | # Extract URL, uploader, and title from webpage | |
901 | self.report_extraction(video_id) | |
902 | mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage) | |
903 | if mobj is None: | |
e5f30ade | 904 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 PH |
905 | return |
906 | mediaURL = compat_urllib_parse.unquote(mobj.group(1)) | |
907 | ||
908 | video_url = mediaURL | |
909 | ||
910 | mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) | |
911 | if mobj is None: | |
e5f30ade | 912 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 PH |
913 | return |
914 | video_title = mobj.group(1).decode('utf-8') | |
915 | ||
916 | video_uploader = mobj.group(2).decode('utf-8') | |
917 | ||
918 | return [{ | |
919 | 'id': video_id.decode('utf-8'), | |
920 | 'url': video_url.decode('utf-8'), | |
921 | 'uploader': video_uploader, | |
922 | 'upload_date': None, | |
923 | 'title': video_title, | |
924 | 'ext': video_extension.decode('utf-8'), | |
925 | }] | |
d77c3dfd FV |
926 | |
927 | ||
928 | class YahooIE(InfoExtractor): | |
59ae15a5 PH |
929 | """Information extractor for video.yahoo.com.""" |
930 | ||
93702113 | 931 | _WORKING = False |
59ae15a5 PH |
932 | # _VALID_URL matches all Yahoo! Video URLs |
933 | # _VPAGE_URL matches only the extractable '/watch/' URLs | |
934 | _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' | |
935 | _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' | |
936 | IE_NAME = u'video.yahoo' | |
937 | ||
938 | def __init__(self, downloader=None): | |
939 | InfoExtractor.__init__(self, downloader) | |
940 | ||
941 | def report_download_webpage(self, video_id): | |
942 | """Report webpage download.""" | |
943 | self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) | |
944 | ||
945 | def report_extraction(self, video_id): | |
946 | """Report information extraction.""" | |
947 | self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) | |
948 | ||
949 | def _real_extract(self, url, new_video=True): | |
950 | # Extract ID from URL | |
951 | mobj = re.match(self._VALID_URL, url) | |
952 | if mobj is None: | |
e5f30ade | 953 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
954 | return |
955 | ||
956 | video_id = mobj.group(2) | |
957 | video_extension = 'flv' | |
958 | ||
959 | # Rewrite valid but non-extractable URLs as | |
960 | # extractable English language /watch/ URLs | |
961 | if re.match(self._VPAGE_URL, url) is None: | |
962 | request = compat_urllib_request.Request(url) | |
963 | try: | |
964 | webpage = compat_urllib_request.urlopen(request).read() | |
965 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 966 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
967 | return |
968 | ||
969 | mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) | |
970 | if mobj is None: | |
e5f30ade | 971 | self._downloader.report_error(u'Unable to extract id field') |
59ae15a5 PH |
972 | return |
973 | yahoo_id = mobj.group(1) | |
974 | ||
975 | mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) | |
976 | if mobj is None: | |
e5f30ade | 977 | self._downloader.report_error(u'Unable to extract vid field') |
59ae15a5 PH |
978 | return |
979 | yahoo_vid = mobj.group(1) | |
980 | ||
981 | url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) | |
982 | return self._real_extract(url, new_video=False) | |
983 | ||
984 | # Retrieve video webpage to extract further information | |
985 | request = compat_urllib_request.Request(url) | |
986 | try: | |
987 | self.report_download_webpage(video_id) | |
988 | webpage = compat_urllib_request.urlopen(request).read() | |
989 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 990 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
991 | return |
992 | ||
993 | # Extract uploader and title from webpage | |
994 | self.report_extraction(video_id) | |
995 | mobj = re.search(r'<meta name="title" content="(.*)" />', webpage) | |
996 | if mobj is None: | |
e5f30ade | 997 | self._downloader.report_error(u'unable to extract video title') |
59ae15a5 PH |
998 | return |
999 | video_title = mobj.group(1).decode('utf-8') | |
1000 | ||
1001 | mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage) | |
1002 | if mobj is None: | |
e5f30ade | 1003 | self._downloader.report_error(u'unable to extract video uploader') |
59ae15a5 PH |
1004 | return |
1005 | video_uploader = mobj.group(1).decode('utf-8') | |
1006 | ||
1007 | # Extract video thumbnail | |
1008 | mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage) | |
1009 | if mobj is None: | |
e5f30ade | 1010 | self._downloader.report_error(u'unable to extract video thumbnail') |
59ae15a5 PH |
1011 | return |
1012 | video_thumbnail = mobj.group(1).decode('utf-8') | |
1013 | ||
1014 | # Extract video description | |
1015 | mobj = re.search(r'<meta name="description" content="(.*)" />', webpage) | |
1016 | if mobj is None: | |
e5f30ade | 1017 | self._downloader.report_error(u'unable to extract video description') |
59ae15a5 PH |
1018 | return |
1019 | video_description = mobj.group(1).decode('utf-8') | |
1020 | if not video_description: | |
1021 | video_description = 'No description available.' | |
1022 | ||
1023 | # Extract video height and width | |
1024 | mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage) | |
1025 | if mobj is None: | |
e5f30ade | 1026 | self._downloader.report_error(u'unable to extract video height') |
59ae15a5 PH |
1027 | return |
1028 | yv_video_height = mobj.group(1) | |
1029 | ||
1030 | mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage) | |
1031 | if mobj is None: | |
e5f30ade | 1032 | self._downloader.report_error(u'unable to extract video width') |
59ae15a5 PH |
1033 | return |
1034 | yv_video_width = mobj.group(1) | |
1035 | ||
1036 | # Retrieve video playlist to extract media URL | |
1037 | # I'm not completely sure what all these options are, but we | |
1038 | # seem to need most of them, otherwise the server sends a 401. | |
1039 | yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents | |
1040 | yv_bitrate = '700' # according to Wikipedia this is hard-coded | |
1041 | request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + | |
1042 | '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + | |
1043 | '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') | |
1044 | try: | |
1045 | self.report_download_webpage(video_id) | |
1046 | webpage = compat_urllib_request.urlopen(request).read() | |
1047 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1048 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1049 | return |
1050 | ||
1051 | # Extract media URL from playlist XML | |
1052 | mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage) | |
1053 | if mobj is None: | |
e5f30ade | 1054 | self._downloader.report_error(u'Unable to extract media URL') |
59ae15a5 PH |
1055 | return |
1056 | video_url = compat_urllib_parse.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') | |
1057 | video_url = unescapeHTML(video_url) | |
1058 | ||
1059 | return [{ | |
1060 | 'id': video_id.decode('utf-8'), | |
1061 | 'url': video_url, | |
1062 | 'uploader': video_uploader, | |
1063 | 'upload_date': None, | |
1064 | 'title': video_title, | |
1065 | 'ext': video_extension.decode('utf-8'), | |
1066 | 'thumbnail': video_thumbnail.decode('utf-8'), | |
1067 | 'description': video_description, | |
1068 | }] | |
d77c3dfd FV |
1069 | |
1070 | ||
1071 | class VimeoIE(InfoExtractor): | |
59ae15a5 PH |
1072 | """Information extractor for vimeo.com.""" |
1073 | ||
1074 | # _VALID_URL matches Vimeo URLs | |
8edc2cf8 | 1075 | _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)' |
59ae15a5 PH |
1076 | IE_NAME = u'vimeo' |
1077 | ||
1078 | def __init__(self, downloader=None): | |
1079 | InfoExtractor.__init__(self, downloader) | |
1080 | ||
1081 | def report_download_webpage(self, video_id): | |
1082 | """Report webpage download.""" | |
1083 | self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) | |
1084 | ||
1085 | def report_extraction(self, video_id): | |
1086 | """Report information extraction.""" | |
1087 | self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id) | |
1088 | ||
1089 | def _real_extract(self, url, new_video=True): | |
1090 | # Extract ID from URL | |
1091 | mobj = re.match(self._VALID_URL, url) | |
1092 | if mobj is None: | |
e5f30ade | 1093 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1094 | return |
1095 | ||
8edc2cf8 PH |
1096 | video_id = mobj.group('id') |
1097 | if not mobj.group('proto'): | |
1098 | url = 'https://' + url | |
1099 | if mobj.group('direct_link'): | |
1100 | url = 'https://vimeo.com/' + video_id | |
59ae15a5 PH |
1101 | |
1102 | # Retrieve video webpage to extract further information | |
1103 | request = compat_urllib_request.Request(url, None, std_headers) | |
1104 | try: | |
1105 | self.report_download_webpage(video_id) | |
f1171f7c PH |
1106 | webpage_bytes = compat_urllib_request.urlopen(request).read() |
1107 | webpage = webpage_bytes.decode('utf-8') | |
59ae15a5 | 1108 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 1109 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1110 | return |
1111 | ||
1112 | # Now we begin extracting as much information as we can from what we | |
1113 | # retrieved. First we extract the information common to all extractors, | |
1114 | # and latter we extract those that are Vimeo specific. | |
1115 | self.report_extraction(video_id) | |
1116 | ||
1117 | # Extract the config JSON | |
59ae15a5 | 1118 | try: |
1ca63e3a | 1119 | config = webpage.split(' = {config:')[1].split(',assets:')[0] |
59ae15a5 PH |
1120 | config = json.loads(config) |
1121 | except: | |
e5f30ade | 1122 | self._downloader.report_error(u'unable to extract info section') |
59ae15a5 | 1123 | return |
cdb30764 | 1124 | |
59ae15a5 PH |
1125 | # Extract title |
1126 | video_title = config["video"]["title"] | |
1127 | ||
77c4beab | 1128 | # Extract uploader and uploader_id |
59ae15a5 | 1129 | video_uploader = config["video"]["owner"]["name"] |
77c4beab | 1130 | video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] |
59ae15a5 PH |
1131 | |
1132 | # Extract video thumbnail | |
1133 | video_thumbnail = config["video"]["thumbnail"] | |
1134 | ||
1135 | # Extract video description | |
0dcfb234 | 1136 | video_description = get_element_by_attribute("itemprop", "description", webpage) |
59ae15a5 | 1137 | if video_description: video_description = clean_html(video_description) |
dc36bc94 | 1138 | else: video_description = u'' |
59ae15a5 PH |
1139 | |
1140 | # Extract upload date | |
1141 | video_upload_date = None | |
6b3aef80 | 1142 | mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage) |
59ae15a5 | 1143 | if mobj is not None: |
6b3aef80 | 1144 | video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) |
59ae15a5 PH |
1145 | |
1146 | # Vimeo specific: extract request signature and timestamp | |
1147 | sig = config['request']['signature'] | |
1148 | timestamp = config['request']['timestamp'] | |
1149 | ||
1150 | # Vimeo specific: extract video codec and quality information | |
1151 | # First consider quality, then codecs, then take everything | |
1152 | # TODO bind to format param | |
1153 | codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')] | |
1154 | files = { 'hd': [], 'sd': [], 'other': []} | |
1155 | for codec_name, codec_extension in codecs: | |
1156 | if codec_name in config["video"]["files"]: | |
1157 | if 'hd' in config["video"]["files"][codec_name]: | |
1158 | files['hd'].append((codec_name, codec_extension, 'hd')) | |
1159 | elif 'sd' in config["video"]["files"][codec_name]: | |
1160 | files['sd'].append((codec_name, codec_extension, 'sd')) | |
1161 | else: | |
1162 | files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0])) | |
1163 | ||
1164 | for quality in ('hd', 'sd', 'other'): | |
1165 | if len(files[quality]) > 0: | |
1166 | video_quality = files[quality][0][2] | |
1167 | video_codec = files[quality][0][0] | |
1168 | video_extension = files[quality][0][1] | |
1169 | self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) | |
1170 | break | |
1171 | else: | |
e5f30ade | 1172 | self._downloader.report_error(u'no known codec found') |
59ae15a5 PH |
1173 | return |
1174 | ||
1175 | video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ | |
1176 | %(video_id, sig, timestamp, video_quality, video_codec.upper()) | |
1177 | ||
1178 | return [{ | |
1179 | 'id': video_id, | |
1180 | 'url': video_url, | |
1181 | 'uploader': video_uploader, | |
77c4beab | 1182 | 'uploader_id': video_uploader_id, |
59ae15a5 PH |
1183 | 'upload_date': video_upload_date, |
1184 | 'title': video_title, | |
1185 | 'ext': video_extension, | |
1186 | 'thumbnail': video_thumbnail, | |
1187 | 'description': video_description, | |
1188 | }] | |
d77c3dfd FV |
1189 | |
1190 | ||
f2ad10a9 | 1191 | class ArteTvIE(InfoExtractor): |
59ae15a5 PH |
1192 | """arte.tv information extractor.""" |
1193 | ||
1194 | _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' | |
1195 | _LIVE_URL = r'index-[0-9]+\.html$' | |
1196 | ||
1197 | IE_NAME = u'arte.tv' | |
1198 | ||
1199 | def __init__(self, downloader=None): | |
1200 | InfoExtractor.__init__(self, downloader) | |
1201 | ||
1202 | def report_download_webpage(self, video_id): | |
1203 | """Report webpage download.""" | |
1204 | self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id) | |
1205 | ||
1206 | def report_extraction(self, video_id): | |
1207 | """Report information extraction.""" | |
1208 | self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id) | |
1209 | ||
1210 | def fetch_webpage(self, url): | |
59ae15a5 PH |
1211 | request = compat_urllib_request.Request(url) |
1212 | try: | |
1213 | self.report_download_webpage(url) | |
1214 | webpage = compat_urllib_request.urlopen(request).read() | |
1215 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1216 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1217 | return |
1218 | except ValueError as err: | |
e5f30ade | 1219 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1220 | return |
1221 | return webpage | |
1222 | ||
1223 | def grep_webpage(self, url, regex, regexFlags, matchTuples): | |
1224 | page = self.fetch_webpage(url) | |
1225 | mobj = re.search(regex, page, regexFlags) | |
1226 | info = {} | |
1227 | ||
1228 | if mobj is None: | |
e5f30ade | 1229 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1230 | return |
1231 | ||
1232 | for (i, key, err) in matchTuples: | |
1233 | if mobj.group(i) is None: | |
1234 | self._downloader.trouble(err) | |
1235 | return | |
1236 | else: | |
1237 | info[key] = mobj.group(i) | |
1238 | ||
1239 | return info | |
1240 | ||
1241 | def extractLiveStream(self, url): | |
1242 | video_lang = url.split('/')[-4] | |
1243 | info = self.grep_webpage( | |
1244 | url, | |
1245 | r'src="(.*?/videothek_js.*?\.js)', | |
1246 | 0, | |
1247 | [ | |
1248 | (1, 'url', u'ERROR: Invalid URL: %s' % url) | |
1249 | ] | |
1250 | ) | |
1251 | http_host = url.split('/')[2] | |
1252 | next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url'))) | |
1253 | info = self.grep_webpage( | |
1254 | next_url, | |
1255 | r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' + | |
1256 | '(http://.*?\.swf).*?' + | |
1257 | '(rtmp://.*?)\'', | |
1258 | re.DOTALL, | |
1259 | [ | |
1260 | (1, 'path', u'ERROR: could not extract video path: %s' % url), | |
1261 | (2, 'player', u'ERROR: could not extract video player: %s' % url), | |
1262 | (3, 'url', u'ERROR: could not extract video url: %s' % url) | |
1263 | ] | |
1264 | ) | |
1265 | video_url = u'%s/%s' % (info.get('url'), info.get('path')) | |
1266 | ||
1267 | def extractPlus7Stream(self, url): | |
1268 | video_lang = url.split('/')[-3] | |
1269 | info = self.grep_webpage( | |
1270 | url, | |
1271 | r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', | |
1272 | 0, | |
1273 | [ | |
1274 | (1, 'url', u'ERROR: Invalid URL: %s' % url) | |
1275 | ] | |
1276 | ) | |
1277 | next_url = compat_urllib_parse.unquote(info.get('url')) | |
1278 | info = self.grep_webpage( | |
1279 | next_url, | |
1280 | r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang, | |
1281 | 0, | |
1282 | [ | |
1283 | (1, 'url', u'ERROR: Could not find <video> tag: %s' % url) | |
1284 | ] | |
1285 | ) | |
1286 | next_url = compat_urllib_parse.unquote(info.get('url')) | |
1287 | ||
1288 | info = self.grep_webpage( | |
1289 | next_url, | |
1290 | r'<video id="(.*?)".*?>.*?' + | |
1291 | '<name>(.*?)</name>.*?' + | |
1292 | '<dateVideo>(.*?)</dateVideo>.*?' + | |
1293 | '<url quality="hd">(.*?)</url>', | |
1294 | re.DOTALL, | |
1295 | [ | |
1296 | (1, 'id', u'ERROR: could not extract video id: %s' % url), | |
1297 | (2, 'title', u'ERROR: could not extract video title: %s' % url), | |
1298 | (3, 'date', u'ERROR: could not extract video date: %s' % url), | |
1299 | (4, 'url', u'ERROR: could not extract video url: %s' % url) | |
1300 | ] | |
1301 | ) | |
1302 | ||
1303 | return { | |
1304 | 'id': info.get('id'), | |
1305 | 'url': compat_urllib_parse.unquote(info.get('url')), | |
1306 | 'uploader': u'arte.tv', | |
1307 | 'upload_date': info.get('date'), | |
93702113 | 1308 | 'title': info.get('title').decode('utf-8'), |
59ae15a5 PH |
1309 | 'ext': u'mp4', |
1310 | 'format': u'NA', | |
1311 | 'player_url': None, | |
1312 | } | |
1313 | ||
1314 | def _real_extract(self, url): | |
1315 | video_id = url.split('/')[-1] | |
1316 | self.report_extraction(video_id) | |
1317 | ||
1318 | if re.search(self._LIVE_URL, video_id) is not None: | |
1319 | self.extractLiveStream(url) | |
1320 | return | |
1321 | else: | |
1322 | info = self.extractPlus7Stream(url) | |
1323 | ||
1324 | return [info] | |
f2ad10a9 CA |
1325 | |
1326 | ||
d77c3dfd | 1327 | class GenericIE(InfoExtractor): |
59ae15a5 PH |
1328 | """Generic last-resort information extractor.""" |
1329 | ||
1330 | _VALID_URL = r'.*' | |
1331 | IE_NAME = u'generic' | |
1332 | ||
1333 | def __init__(self, downloader=None): | |
1334 | InfoExtractor.__init__(self, downloader) | |
1335 | ||
1336 | def report_download_webpage(self, video_id): | |
1337 | """Report webpage download.""" | |
3d342357 PH |
1338 | if not self._downloader.params.get('test', False): |
1339 | self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') | |
59ae15a5 PH |
1340 | self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) |
1341 | ||
1342 | def report_extraction(self, video_id): | |
1343 | """Report information extraction.""" | |
1344 | self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) | |
1345 | ||
1346 | def report_following_redirect(self, new_url): | |
1347 | """Report information extraction.""" | |
1348 | self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url) | |
cdb30764 | 1349 | |
59ae15a5 PH |
1350 | def _test_redirect(self, url): |
1351 | """Check if it is a redirect, like url shorteners, in case restart chain.""" | |
1352 | class HeadRequest(compat_urllib_request.Request): | |
1353 | def get_method(self): | |
1354 | return "HEAD" | |
1355 | ||
1356 | class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler): | |
1357 | """ | |
cdb30764 | 1358 | Subclass the HTTPRedirectHandler to make it use our |
59ae15a5 PH |
1359 | HeadRequest also on the redirected URL |
1360 | """ | |
cdb30764 | 1361 | def redirect_request(self, req, fp, code, msg, headers, newurl): |
59ae15a5 | 1362 | if code in (301, 302, 303, 307): |
cdb30764 | 1363 | newurl = newurl.replace(' ', '%20') |
59ae15a5 PH |
1364 | newheaders = dict((k,v) for k,v in req.headers.items() |
1365 | if k.lower() not in ("content-length", "content-type")) | |
cdb30764 | 1366 | return HeadRequest(newurl, |
59ae15a5 | 1367 | headers=newheaders, |
cdb30764 ND |
1368 | origin_req_host=req.get_origin_req_host(), |
1369 | unverifiable=True) | |
1370 | else: | |
1371 | raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp) | |
59ae15a5 PH |
1372 | |
1373 | class HTTPMethodFallback(compat_urllib_request.BaseHandler): | |
1374 | """ | |
1375 | Fallback to GET if HEAD is not allowed (405 HTTP error) | |
1376 | """ | |
cdb30764 | 1377 | def http_error_405(self, req, fp, code, msg, headers): |
59ae15a5 PH |
1378 | fp.read() |
1379 | fp.close() | |
1380 | ||
1381 | newheaders = dict((k,v) for k,v in req.headers.items() | |
1382 | if k.lower() not in ("content-length", "content-type")) | |
cdb30764 ND |
1383 | return self.parent.open(compat_urllib_request.Request(req.get_full_url(), |
1384 | headers=newheaders, | |
1385 | origin_req_host=req.get_origin_req_host(), | |
59ae15a5 PH |
1386 | unverifiable=True)) |
1387 | ||
1388 | # Build our opener | |
cdb30764 | 1389 | opener = compat_urllib_request.OpenerDirector() |
59ae15a5 PH |
1390 | for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler, |
1391 | HTTPMethodFallback, HEADRedirectHandler, | |
7c038b3c | 1392 | compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]: |
59ae15a5 PH |
1393 | opener.add_handler(handler()) |
1394 | ||
1395 | response = opener.open(HeadRequest(url)) | |
1396 | new_url = response.geturl() | |
1397 | ||
1398 | if url == new_url: | |
1399 | return False | |
1400 | ||
1401 | self.report_following_redirect(new_url) | |
1402 | self._downloader.download([new_url]) | |
1403 | return True | |
1404 | ||
1405 | def _real_extract(self, url): | |
1406 | if self._test_redirect(url): return | |
1407 | ||
1408 | video_id = url.split('/')[-1] | |
59ae15a5 | 1409 | try: |
3d342357 | 1410 | webpage = self._download_webpage(url, video_id) |
59ae15a5 PH |
1411 | except ValueError as err: |
1412 | # since this is the last-resort InfoExtractor, if | |
1413 | # this error is thrown, it'll be thrown here | |
e5f30ade | 1414 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1415 | return |
1416 | ||
1417 | self.report_extraction(video_id) | |
1418 | # Start with something easy: JW Player in SWFObject | |
1419 | mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) | |
1420 | if mobj is None: | |
1421 | # Broaden the search a little bit | |
1422 | mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) | |
1013186a PH |
1423 | if mobj is None: |
1424 | # Broaden the search a little bit: JWPlayer JS loader | |
1425 | mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage) | |
59ae15a5 | 1426 | if mobj is None: |
e5f30ade | 1427 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1428 | return |
1429 | ||
1430 | # It's possible that one of the regexes | |
1431 | # matched, but returned an empty group: | |
1432 | if mobj.group(1) is None: | |
e5f30ade | 1433 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1434 | return |
1435 | ||
1436 | video_url = compat_urllib_parse.unquote(mobj.group(1)) | |
1437 | video_id = os.path.basename(video_url) | |
1438 | ||
1439 | # here's a fun little line of code for you: | |
1440 | video_extension = os.path.splitext(video_id)[1][1:] | |
1441 | video_id = os.path.splitext(video_id)[0] | |
1442 | ||
1443 | # it's tempting to parse this further, but you would | |
1444 | # have to take into account all the variations like | |
1445 | # Video Title - Site Name | |
1446 | # Site Name | Video Title | |
1447 | # Video Title - Tagline | Site Name | |
1448 | # and so on and so forth; it's just not practical | |
1449 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
1450 | if mobj is None: | |
e5f30ade | 1451 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 | 1452 | return |
f1171f7c | 1453 | video_title = mobj.group(1) |
59ae15a5 PH |
1454 | |
1455 | # video uploader is domain name | |
1456 | mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) | |
1457 | if mobj is None: | |
e5f30ade | 1458 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 | 1459 | return |
f1171f7c | 1460 | video_uploader = mobj.group(1) |
59ae15a5 PH |
1461 | |
1462 | return [{ | |
f1171f7c PH |
1463 | 'id': video_id, |
1464 | 'url': video_url, | |
59ae15a5 PH |
1465 | 'uploader': video_uploader, |
1466 | 'upload_date': None, | |
1467 | 'title': video_title, | |
f1171f7c | 1468 | 'ext': video_extension, |
59ae15a5 | 1469 | }] |
d77c3dfd FV |
1470 | |
1471 | ||
1472 | class YoutubeSearchIE(InfoExtractor): | |
59ae15a5 PH |
1473 | """Information Extractor for YouTube search queries.""" |
1474 | _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+' | |
1475 | _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' | |
1476 | _max_youtube_results = 1000 | |
1477 | IE_NAME = u'youtube:search' | |
1478 | ||
1479 | def __init__(self, downloader=None): | |
1480 | InfoExtractor.__init__(self, downloader) | |
1481 | ||
1482 | def report_download_page(self, query, pagenum): | |
1483 | """Report attempt to download search page with given number.""" | |
1484 | query = query.decode(preferredencoding()) | |
1485 | self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) | |
1486 | ||
1487 | def _real_extract(self, query): | |
1488 | mobj = re.match(self._VALID_URL, query) | |
1489 | if mobj is None: | |
e5f30ade | 1490 | self._downloader.report_error(u'invalid search query "%s"' % query) |
59ae15a5 PH |
1491 | return |
1492 | ||
1493 | prefix, query = query.split(':') | |
1494 | prefix = prefix[8:] | |
1495 | query = query.encode('utf-8') | |
1496 | if prefix == '': | |
1497 | self._download_n_results(query, 1) | |
1498 | return | |
1499 | elif prefix == 'all': | |
1500 | self._download_n_results(query, self._max_youtube_results) | |
1501 | return | |
1502 | else: | |
1503 | try: | |
1504 | n = int(prefix) | |
1505 | if n <= 0: | |
e5f30ade | 1506 | self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query)) |
59ae15a5 PH |
1507 | return |
1508 | elif n > self._max_youtube_results: | |
2e5457be | 1509 | self._downloader.report_warning(u'ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) |
59ae15a5 PH |
1510 | n = self._max_youtube_results |
1511 | self._download_n_results(query, n) | |
1512 | return | |
1513 | except ValueError: # parsing prefix as integer fails | |
1514 | self._download_n_results(query, 1) | |
1515 | return | |
1516 | ||
1517 | def _download_n_results(self, query, n): | |
1518 | """Downloads a specified number of results for a query""" | |
1519 | ||
1520 | video_ids = [] | |
1521 | pagenum = 0 | |
1522 | limit = n | |
1523 | ||
1524 | while (50 * pagenum) < limit: | |
1525 | self.report_download_page(query, pagenum+1) | |
1526 | result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1) | |
1527 | request = compat_urllib_request.Request(result_url) | |
1528 | try: | |
d1b7a243 | 1529 | data = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 | 1530 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 1531 | self._downloader.report_error(u'unable to download API page: %s' % compat_str(err)) |
59ae15a5 PH |
1532 | return |
1533 | api_response = json.loads(data)['data'] | |
1534 | ||
9e07cf29 J |
1535 | if not 'items' in api_response: |
1536 | self._downloader.trouble(u'[youtube] No video results') | |
1537 | return | |
1538 | ||
59ae15a5 PH |
1539 | new_ids = list(video['id'] for video in api_response['items']) |
1540 | video_ids += new_ids | |
1541 | ||
1542 | limit = min(n, api_response['totalItems']) | |
1543 | pagenum += 1 | |
1544 | ||
1545 | if len(video_ids) > n: | |
1546 | video_ids = video_ids[:n] | |
1547 | for id in video_ids: | |
1548 | self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) | |
1549 | return | |
d77c3dfd FV |
1550 | |
1551 | ||
1552 | class GoogleSearchIE(InfoExtractor): | |
59ae15a5 PH |
1553 | """Information Extractor for Google Video search queries.""" |
1554 | _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+' | |
1555 | _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' | |
1556 | _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)' | |
1557 | _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"' | |
1558 | _max_google_results = 1000 | |
1559 | IE_NAME = u'video.google:search' | |
1560 | ||
1561 | def __init__(self, downloader=None): | |
1562 | InfoExtractor.__init__(self, downloader) | |
1563 | ||
1564 | def report_download_page(self, query, pagenum): | |
1565 | """Report attempt to download playlist page with given number.""" | |
1566 | query = query.decode(preferredencoding()) | |
1567 | self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) | |
1568 | ||
1569 | def _real_extract(self, query): | |
1570 | mobj = re.match(self._VALID_URL, query) | |
1571 | if mobj is None: | |
e5f30ade | 1572 | self._downloader.report_error(u'invalid search query "%s"' % query) |
59ae15a5 PH |
1573 | return |
1574 | ||
1575 | prefix, query = query.split(':') | |
1576 | prefix = prefix[8:] | |
1577 | query = query.encode('utf-8') | |
1578 | if prefix == '': | |
1579 | self._download_n_results(query, 1) | |
1580 | return | |
1581 | elif prefix == 'all': | |
1582 | self._download_n_results(query, self._max_google_results) | |
1583 | return | |
1584 | else: | |
1585 | try: | |
1586 | n = int(prefix) | |
1587 | if n <= 0: | |
e5f30ade | 1588 | self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query)) |
59ae15a5 PH |
1589 | return |
1590 | elif n > self._max_google_results: | |
2e5457be | 1591 | self._downloader.report_warning(u'gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) |
59ae15a5 PH |
1592 | n = self._max_google_results |
1593 | self._download_n_results(query, n) | |
1594 | return | |
1595 | except ValueError: # parsing prefix as integer fails | |
1596 | self._download_n_results(query, 1) | |
1597 | return | |
1598 | ||
1599 | def _download_n_results(self, query, n): | |
1600 | """Downloads a specified number of results for a query""" | |
1601 | ||
1602 | video_ids = [] | |
1603 | pagenum = 0 | |
1604 | ||
1605 | while True: | |
1606 | self.report_download_page(query, pagenum) | |
1607 | result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum*10) | |
1608 | request = compat_urllib_request.Request(result_url) | |
1609 | try: | |
1610 | page = compat_urllib_request.urlopen(request).read() | |
1611 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1612 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1613 | return |
1614 | ||
1615 | # Extract video identifiers | |
1616 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
1617 | video_id = mobj.group(1) | |
1618 | if video_id not in video_ids: | |
1619 | video_ids.append(video_id) | |
1620 | if len(video_ids) == n: | |
1621 | # Specified n videos reached | |
1622 | for id in video_ids: | |
1623 | self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id]) | |
1624 | return | |
1625 | ||
1626 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
1627 | for id in video_ids: | |
1628 | self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id]) | |
1629 | return | |
1630 | ||
1631 | pagenum = pagenum + 1 | |
d77c3dfd FV |
1632 | |
1633 | ||
1634 | class YahooSearchIE(InfoExtractor): | |
59ae15a5 | 1635 | """Information Extractor for Yahoo! Video search queries.""" |
93702113 FV |
1636 | |
1637 | _WORKING = False | |
59ae15a5 PH |
1638 | _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+' |
1639 | _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' | |
1640 | _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' | |
1641 | _MORE_PAGES_INDICATOR = r'\s*Next' | |
1642 | _max_yahoo_results = 1000 | |
1643 | IE_NAME = u'video.yahoo:search' | |
1644 | ||
1645 | def __init__(self, downloader=None): | |
1646 | InfoExtractor.__init__(self, downloader) | |
1647 | ||
1648 | def report_download_page(self, query, pagenum): | |
1649 | """Report attempt to download playlist page with given number.""" | |
1650 | query = query.decode(preferredencoding()) | |
1651 | self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) | |
1652 | ||
1653 | def _real_extract(self, query): | |
1654 | mobj = re.match(self._VALID_URL, query) | |
1655 | if mobj is None: | |
e5f30ade | 1656 | self._downloader.report_error(u'invalid search query "%s"' % query) |
59ae15a5 PH |
1657 | return |
1658 | ||
1659 | prefix, query = query.split(':') | |
1660 | prefix = prefix[8:] | |
1661 | query = query.encode('utf-8') | |
1662 | if prefix == '': | |
1663 | self._download_n_results(query, 1) | |
1664 | return | |
1665 | elif prefix == 'all': | |
1666 | self._download_n_results(query, self._max_yahoo_results) | |
1667 | return | |
1668 | else: | |
1669 | try: | |
1670 | n = int(prefix) | |
1671 | if n <= 0: | |
e5f30ade | 1672 | self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query)) |
59ae15a5 PH |
1673 | return |
1674 | elif n > self._max_yahoo_results: | |
2e5457be | 1675 | self._downloader.report_warning(u'yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) |
59ae15a5 PH |
1676 | n = self._max_yahoo_results |
1677 | self._download_n_results(query, n) | |
1678 | return | |
1679 | except ValueError: # parsing prefix as integer fails | |
1680 | self._download_n_results(query, 1) | |
1681 | return | |
1682 | ||
1683 | def _download_n_results(self, query, n): | |
1684 | """Downloads a specified number of results for a query""" | |
1685 | ||
1686 | video_ids = [] | |
1687 | already_seen = set() | |
1688 | pagenum = 1 | |
1689 | ||
1690 | while True: | |
1691 | self.report_download_page(query, pagenum) | |
1692 | result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum) | |
1693 | request = compat_urllib_request.Request(result_url) | |
1694 | try: | |
1695 | page = compat_urllib_request.urlopen(request).read() | |
1696 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1697 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1698 | return |
1699 | ||
1700 | # Extract video identifiers | |
1701 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
1702 | video_id = mobj.group(1) | |
1703 | if video_id not in already_seen: | |
1704 | video_ids.append(video_id) | |
1705 | already_seen.add(video_id) | |
1706 | if len(video_ids) == n: | |
1707 | # Specified n videos reached | |
1708 | for id in video_ids: | |
1709 | self._downloader.download(['http://video.yahoo.com/watch/%s' % id]) | |
1710 | return | |
1711 | ||
1712 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
1713 | for id in video_ids: | |
1714 | self._downloader.download(['http://video.yahoo.com/watch/%s' % id]) | |
1715 | return | |
1716 | ||
1717 | pagenum = pagenum + 1 | |
d77c3dfd FV |
1718 | |
1719 | ||
1720 | class YoutubePlaylistIE(InfoExtractor): | |
59ae15a5 PH |
1721 | """Information Extractor for YouTube playlists.""" |
1722 | ||
6324fd1d FV |
1723 | _VALID_URL = r"""(?: |
1724 | (?:https?://)? | |
1725 | (?:\w+\.)? | |
1726 | youtube\.com/ | |
1727 | (?: | |
89de9eb1 FV |
1728 | (?:course|view_play_list|my_playlists|artist|playlist|watch) |
1729 | \? (?:.*?&)*? (?:p|a|list)= | |
6324fd1d | 1730 | | p/ |
6324fd1d | 1731 | ) |
89de9eb1 FV |
1732 | ((?:PL|EC|UU)?[0-9A-Za-z-_]{10,}) |
1733 | .* | |
1734 | | | |
1735 | ((?:PL|EC|UU)[0-9A-Za-z-_]{10,}) | |
1736 | )""" | |
6324fd1d FV |
1737 | _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/playlists/%s?max-results=%i&start-index=%i&v=2&alt=json' |
1738 | _MAX_RESULTS = 50 | |
59ae15a5 PH |
1739 | IE_NAME = u'youtube:playlist' |
1740 | ||
1741 | def __init__(self, downloader=None): | |
1742 | InfoExtractor.__init__(self, downloader) | |
1743 | ||
89de9eb1 FV |
1744 | @classmethod |
1745 | def suitable(cls, url): | |
6324fd1d | 1746 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 | 1747 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None |
6324fd1d | 1748 | |
59ae15a5 PH |
1749 | def report_download_page(self, playlist_id, pagenum): |
1750 | """Report attempt to download playlist page with given number.""" | |
1751 | self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) | |
1752 | ||
1753 | def _real_extract(self, url): | |
1754 | # Extract playlist id | |
6324fd1d | 1755 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
59ae15a5 | 1756 | if mobj is None: |
e5f30ade | 1757 | self._downloader.report_error(u'invalid url: %s' % url) |
59ae15a5 PH |
1758 | return |
1759 | ||
6324fd1d | 1760 | # Download playlist videos from API |
89de9eb1 | 1761 | playlist_id = mobj.group(1) or mobj.group(2) |
6324fd1d FV |
1762 | page_num = 1 |
1763 | videos = [] | |
59ae15a5 PH |
1764 | |
1765 | while True: | |
6324fd1d FV |
1766 | self.report_download_page(playlist_id, page_num) |
1767 | ||
1768 | url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, self._MAX_RESULTS * (page_num - 1) + 1) | |
59ae15a5 | 1769 | try: |
6324fd1d | 1770 | page = compat_urllib_request.urlopen(url).read().decode('utf8') |
59ae15a5 | 1771 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 1772 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1773 | return |
1774 | ||
6324fd1d FV |
1775 | try: |
1776 | response = json.loads(page) | |
1777 | except ValueError as err: | |
e5f30ade | 1778 | self._downloader.report_error(u'Invalid JSON in API response: ' + compat_str(err)) |
6324fd1d | 1779 | return |
59ae15a5 | 1780 | |
89de9eb1 | 1781 | if not 'feed' in response or not 'entry' in response['feed']: |
e5f30ade | 1782 | self._downloader.report_error(u'Got a malformed response from YouTube API') |
89de9eb1 FV |
1783 | return |
1784 | videos += [ (entry['yt$position']['$t'], entry['content']['src']) | |
1785 | for entry in response['feed']['entry'] | |
1786 | if 'content' in entry ] | |
6324fd1d FV |
1787 | |
1788 | if len(response['feed']['entry']) < self._MAX_RESULTS: | |
59ae15a5 | 1789 | break |
6324fd1d | 1790 | page_num += 1 |
59ae15a5 | 1791 | |
691db5ba | 1792 | videos = [v[1] for v in sorted(videos)] |
6324fd1d | 1793 | total = len(videos) |
9789a05c | 1794 | |
59ae15a5 PH |
1795 | playliststart = self._downloader.params.get('playliststart', 1) - 1 |
1796 | playlistend = self._downloader.params.get('playlistend', -1) | |
1797 | if playlistend == -1: | |
6324fd1d | 1798 | videos = videos[playliststart:] |
59ae15a5 | 1799 | else: |
6324fd1d | 1800 | videos = videos[playliststart:playlistend] |
59ae15a5 | 1801 | |
6324fd1d | 1802 | if len(videos) == total: |
9789a05c FV |
1803 | self._downloader.to_screen(u'[youtube] PL %s: Found %i videos' % (playlist_id, total)) |
1804 | else: | |
6324fd1d | 1805 | self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(videos))) |
9789a05c | 1806 | |
6324fd1d FV |
1807 | for video in videos: |
1808 | self._downloader.download([video]) | |
59ae15a5 | 1809 | return |
d77c3dfd FV |
1810 | |
1811 | ||
902b2a0a | 1812 | class YoutubeChannelIE(InfoExtractor): |
59ae15a5 PH |
1813 | """Information Extractor for YouTube channels.""" |
1814 | ||
1815 | _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$" | |
1816 | _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en' | |
9789a05c | 1817 | _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}" |
59ae15a5 PH |
1818 | IE_NAME = u'youtube:channel' |
1819 | ||
1820 | def report_download_page(self, channel_id, pagenum): | |
1821 | """Report attempt to download channel page with given number.""" | |
1822 | self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum)) | |
1823 | ||
1824 | def _real_extract(self, url): | |
1825 | # Extract channel id | |
1826 | mobj = re.match(self._VALID_URL, url) | |
1827 | if mobj is None: | |
e5f30ade | 1828 | self._downloader.report_error(u'invalid url: %s' % url) |
59ae15a5 PH |
1829 | return |
1830 | ||
1831 | # Download channel pages | |
1832 | channel_id = mobj.group(1) | |
1833 | video_ids = [] | |
1834 | pagenum = 1 | |
1835 | ||
1836 | while True: | |
1837 | self.report_download_page(channel_id, pagenum) | |
1838 | url = self._TEMPLATE_URL % (channel_id, pagenum) | |
1839 | request = compat_urllib_request.Request(url) | |
1840 | try: | |
9789a05c | 1841 | page = compat_urllib_request.urlopen(request).read().decode('utf8') |
59ae15a5 | 1842 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 1843 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1844 | return |
1845 | ||
1846 | # Extract video identifiers | |
1847 | ids_in_page = [] | |
1848 | for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page): | |
1849 | if mobj.group(1) not in ids_in_page: | |
1850 | ids_in_page.append(mobj.group(1)) | |
1851 | video_ids.extend(ids_in_page) | |
1852 | ||
9789a05c | 1853 | if self._MORE_PAGES_INDICATOR not in page: |
59ae15a5 PH |
1854 | break |
1855 | pagenum = pagenum + 1 | |
1856 | ||
9789a05c FV |
1857 | self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) |
1858 | ||
59ae15a5 PH |
1859 | for id in video_ids: |
1860 | self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) | |
1861 | return | |
902b2a0a FV |
1862 | |
1863 | ||
d77c3dfd | 1864 | class YoutubeUserIE(InfoExtractor): |
59ae15a5 | 1865 | """Information Extractor for YouTube users.""" |
d77c3dfd | 1866 | |
59ae15a5 PH |
1867 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)' |
1868 | _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' | |
1869 | _GDATA_PAGE_SIZE = 50 | |
1870 | _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' | |
1871 | _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]' | |
1872 | IE_NAME = u'youtube:user' | |
d77c3dfd | 1873 | |
59ae15a5 PH |
1874 | def __init__(self, downloader=None): |
1875 | InfoExtractor.__init__(self, downloader) | |
d77c3dfd | 1876 | |
59ae15a5 PH |
1877 | def report_download_page(self, username, start_index): |
1878 | """Report attempt to download user page.""" | |
1879 | self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % | |
1880 | (username, start_index, start_index + self._GDATA_PAGE_SIZE)) | |
d77c3dfd | 1881 | |
59ae15a5 PH |
1882 | def _real_extract(self, url): |
1883 | # Extract username | |
1884 | mobj = re.match(self._VALID_URL, url) | |
1885 | if mobj is None: | |
e5f30ade | 1886 | self._downloader.report_error(u'invalid url: %s' % url) |
59ae15a5 | 1887 | return |
d77c3dfd | 1888 | |
59ae15a5 | 1889 | username = mobj.group(1) |
d77c3dfd | 1890 | |
59ae15a5 PH |
1891 | # Download video ids using YouTube Data API. Result size per |
1892 | # query is limited (currently to 50 videos) so we need to query | |
1893 | # page by page until there are no video ids - it means we got | |
1894 | # all of them. | |
d77c3dfd | 1895 | |
59ae15a5 PH |
1896 | video_ids = [] |
1897 | pagenum = 0 | |
d77c3dfd | 1898 | |
59ae15a5 PH |
1899 | while True: |
1900 | start_index = pagenum * self._GDATA_PAGE_SIZE + 1 | |
1901 | self.report_download_page(username, start_index) | |
d77c3dfd | 1902 | |
59ae15a5 | 1903 | request = compat_urllib_request.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)) |
d77c3dfd | 1904 | |
59ae15a5 | 1905 | try: |
80d3177e | 1906 | page = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 | 1907 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 1908 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 | 1909 | return |
d77c3dfd | 1910 | |
59ae15a5 PH |
1911 | # Extract video identifiers |
1912 | ids_in_page = [] | |
d77c3dfd | 1913 | |
59ae15a5 PH |
1914 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): |
1915 | if mobj.group(1) not in ids_in_page: | |
1916 | ids_in_page.append(mobj.group(1)) | |
d77c3dfd | 1917 | |
59ae15a5 | 1918 | video_ids.extend(ids_in_page) |
d77c3dfd | 1919 | |
59ae15a5 PH |
1920 | # A little optimization - if current page is not |
1921 | # "full", ie. does not contain PAGE_SIZE video ids then | |
1922 | # we can assume that this page is the last one - there | |
1923 | # are no more ids on further pages - no need to query | |
1924 | # again. | |
d77c3dfd | 1925 | |
59ae15a5 PH |
1926 | if len(ids_in_page) < self._GDATA_PAGE_SIZE: |
1927 | break | |
d77c3dfd | 1928 | |
59ae15a5 | 1929 | pagenum += 1 |
d77c3dfd | 1930 | |
59ae15a5 PH |
1931 | all_ids_count = len(video_ids) |
1932 | playliststart = self._downloader.params.get('playliststart', 1) - 1 | |
1933 | playlistend = self._downloader.params.get('playlistend', -1) | |
d77c3dfd | 1934 | |
59ae15a5 PH |
1935 | if playlistend == -1: |
1936 | video_ids = video_ids[playliststart:] | |
1937 | else: | |
1938 | video_ids = video_ids[playliststart:playlistend] | |
d77c3dfd | 1939 | |
59ae15a5 PH |
1940 | self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" % |
1941 | (username, all_ids_count, len(video_ids))) | |
d77c3dfd | 1942 | |
59ae15a5 PH |
1943 | for video_id in video_ids: |
1944 | self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id]) | |
d77c3dfd FV |
1945 | |
1946 | ||
eeeb4daa | 1947 | class BlipTVUserIE(InfoExtractor): |
59ae15a5 | 1948 | """Information Extractor for blip.tv users.""" |
eeeb4daa | 1949 | |
59ae15a5 PH |
1950 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' |
1951 | _PAGE_SIZE = 12 | |
1952 | IE_NAME = u'blip.tv:user' | |
eeeb4daa | 1953 | |
59ae15a5 PH |
1954 | def __init__(self, downloader=None): |
1955 | InfoExtractor.__init__(self, downloader) | |
eeeb4daa | 1956 | |
59ae15a5 PH |
1957 | def report_download_page(self, username, pagenum): |
1958 | """Report attempt to download user page.""" | |
1959 | self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' % | |
1960 | (self.IE_NAME, username, pagenum)) | |
eeeb4daa | 1961 | |
59ae15a5 PH |
1962 | def _real_extract(self, url): |
1963 | # Extract username | |
1964 | mobj = re.match(self._VALID_URL, url) | |
1965 | if mobj is None: | |
e5f30ade | 1966 | self._downloader.report_error(u'invalid url: %s' % url) |
59ae15a5 | 1967 | return |
eeeb4daa | 1968 | |
59ae15a5 | 1969 | username = mobj.group(1) |
eeeb4daa | 1970 | |
59ae15a5 | 1971 | page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' |
eeeb4daa | 1972 | |
59ae15a5 | 1973 | request = compat_urllib_request.Request(url) |
eeeb4daa | 1974 | |
59ae15a5 PH |
1975 | try: |
1976 | page = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
1977 | mobj = re.search(r'data-users-id="([^"]+)"', page) | |
1978 | page_base = page_base % mobj.group(1) | |
1979 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1980 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 | 1981 | return |
eeeb4daa JCGS |
1982 | |
1983 | ||
59ae15a5 PH |
1984 | # Download video ids using BlipTV Ajax calls. Result size per |
1985 | # query is limited (currently to 12 videos) so we need to query | |
1986 | # page by page until there are no video ids - it means we got | |
1987 | # all of them. | |
eeeb4daa | 1988 | |
59ae15a5 PH |
1989 | video_ids = [] |
1990 | pagenum = 1 | |
eeeb4daa | 1991 | |
59ae15a5 PH |
1992 | while True: |
1993 | self.report_download_page(username, pagenum) | |
450e7099 PH |
1994 | url = page_base + "&page=" + str(pagenum) |
1995 | request = compat_urllib_request.Request( url ) | |
59ae15a5 PH |
1996 | try: |
1997 | page = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
1998 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1999 | self._downloader.report_error(u'unable to download webpage: %s' % str(err)) |
59ae15a5 | 2000 | return |
eeeb4daa | 2001 | |
59ae15a5 PH |
2002 | # Extract video identifiers |
2003 | ids_in_page = [] | |
eeeb4daa | 2004 | |
59ae15a5 PH |
2005 | for mobj in re.finditer(r'href="/([^"]+)"', page): |
2006 | if mobj.group(1) not in ids_in_page: | |
2007 | ids_in_page.append(unescapeHTML(mobj.group(1))) | |
eeeb4daa | 2008 | |
59ae15a5 | 2009 | video_ids.extend(ids_in_page) |
eeeb4daa | 2010 | |
59ae15a5 PH |
2011 | # A little optimization - if current page is not |
2012 | # "full", ie. does not contain PAGE_SIZE video ids then | |
2013 | # we can assume that this page is the last one - there | |
2014 | # are no more ids on further pages - no need to query | |
2015 | # again. | |
eeeb4daa | 2016 | |
59ae15a5 PH |
2017 | if len(ids_in_page) < self._PAGE_SIZE: |
2018 | break | |
eeeb4daa | 2019 | |
59ae15a5 | 2020 | pagenum += 1 |
eeeb4daa | 2021 | |
59ae15a5 PH |
2022 | all_ids_count = len(video_ids) |
2023 | playliststart = self._downloader.params.get('playliststart', 1) - 1 | |
2024 | playlistend = self._downloader.params.get('playlistend', -1) | |
eeeb4daa | 2025 | |
59ae15a5 PH |
2026 | if playlistend == -1: |
2027 | video_ids = video_ids[playliststart:] | |
2028 | else: | |
2029 | video_ids = video_ids[playliststart:playlistend] | |
eeeb4daa | 2030 | |
59ae15a5 PH |
2031 | self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" % |
2032 | (self.IE_NAME, username, all_ids_count, len(video_ids))) | |
eeeb4daa | 2033 | |
59ae15a5 PH |
2034 | for video_id in video_ids: |
2035 | self._downloader.download([u'http://blip.tv/'+video_id]) | |
eeeb4daa JCGS |
2036 | |
2037 | ||
d77c3dfd | 2038 | class DepositFilesIE(InfoExtractor): |
59ae15a5 PH |
2039 | """Information extractor for depositfiles.com""" |
2040 | ||
2041 | _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' | |
59ae15a5 PH |
2042 | |
2043 | def report_download_webpage(self, file_id): | |
2044 | """Report webpage download.""" | |
2045 | self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) | |
2046 | ||
2047 | def report_extraction(self, file_id): | |
2048 | """Report information extraction.""" | |
2049 | self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) | |
2050 | ||
2051 | def _real_extract(self, url): | |
2052 | file_id = url.split('/')[-1] | |
2053 | # Rebuild url in english locale | |
2054 | url = 'http://depositfiles.com/en/files/' + file_id | |
2055 | ||
2056 | # Retrieve file webpage with 'Free download' button pressed | |
2057 | free_download_indication = { 'gateway_result' : '1' } | |
2058 | request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication)) | |
2059 | try: | |
2060 | self.report_download_webpage(file_id) | |
2061 | webpage = compat_urllib_request.urlopen(request).read() | |
2062 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2063 | self._downloader.report_error(u'Unable to retrieve file webpage: %s' % compat_str(err)) |
59ae15a5 PH |
2064 | return |
2065 | ||
2066 | # Search for the real file URL | |
2067 | mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage) | |
2068 | if (mobj is None) or (mobj.group(1) is None): | |
2069 | # Try to figure out reason of the error. | |
2070 | mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL) | |
2071 | if (mobj is not None) and (mobj.group(1) is not None): | |
2072 | restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() | |
e5f30ade | 2073 | self._downloader.report_error(u'%s' % restriction_message) |
59ae15a5 | 2074 | else: |
e5f30ade | 2075 | self._downloader.report_error(u'unable to extract download URL from: %s' % url) |
59ae15a5 PH |
2076 | return |
2077 | ||
2078 | file_url = mobj.group(1) | |
2079 | file_extension = os.path.splitext(file_url)[1][1:] | |
2080 | ||
2081 | # Search for file title | |
2082 | mobj = re.search(r'<b title="(.*?)">', webpage) | |
2083 | if mobj is None: | |
e5f30ade | 2084 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 PH |
2085 | return |
2086 | file_title = mobj.group(1).decode('utf-8') | |
2087 | ||
2088 | return [{ | |
2089 | 'id': file_id.decode('utf-8'), | |
2090 | 'url': file_url.decode('utf-8'), | |
2091 | 'uploader': None, | |
2092 | 'upload_date': None, | |
2093 | 'title': file_title, | |
2094 | 'ext': file_extension.decode('utf-8'), | |
2095 | }] | |
d77c3dfd FV |
2096 | |
2097 | ||
2098 | class FacebookIE(InfoExtractor): | |
59ae15a5 PH |
2099 | """Information Extractor for Facebook""" |
2100 | ||
59ae15a5 PH |
2101 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' |
2102 | _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' | |
2103 | _NETRC_MACHINE = 'facebook' | |
59ae15a5 PH |
2104 | IE_NAME = u'facebook' |
2105 | ||
59ae15a5 PH |
2106 | def report_login(self): |
2107 | """Report attempt to log in.""" | |
b954070d | 2108 | self._downloader.to_screen(u'[%s] Logging in' % self.IE_NAME) |
59ae15a5 PH |
2109 | |
2110 | def _real_initialize(self): | |
2111 | if self._downloader is None: | |
2112 | return | |
2113 | ||
2114 | useremail = None | |
2115 | password = None | |
2116 | downloader_params = self._downloader.params | |
2117 | ||
2118 | # Attempt to use provided username and password or .netrc data | |
2119 | if downloader_params.get('username', None) is not None: | |
2120 | useremail = downloader_params['username'] | |
2121 | password = downloader_params['password'] | |
2122 | elif downloader_params.get('usenetrc', False): | |
2123 | try: | |
2124 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
2125 | if info is not None: | |
2126 | useremail = info[0] | |
2127 | password = info[2] | |
2128 | else: | |
2129 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
2130 | except (IOError, netrc.NetrcParseError) as err: | |
2e5457be | 2131 | self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) |
59ae15a5 PH |
2132 | return |
2133 | ||
2134 | if useremail is None: | |
2135 | return | |
2136 | ||
2137 | # Log in | |
2138 | login_form = { | |
2139 | 'email': useremail, | |
2140 | 'pass': password, | |
2141 | 'login': 'Log+In' | |
2142 | } | |
2143 | request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) | |
2144 | try: | |
2145 | self.report_login() | |
2146 | login_results = compat_urllib_request.urlopen(request).read() | |
2147 | if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: | |
2e5457be | 2148 | self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') |
59ae15a5 PH |
2149 | return |
2150 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2e5457be | 2151 | self._downloader.report_warning(u'unable to log in: %s' % compat_str(err)) |
59ae15a5 PH |
2152 | return |
2153 | ||
2154 | def _real_extract(self, url): | |
2155 | mobj = re.match(self._VALID_URL, url) | |
2156 | if mobj is None: | |
e5f30ade | 2157 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2158 | return |
2159 | video_id = mobj.group('ID') | |
2160 | ||
b954070d PH |
2161 | url = 'https://www.facebook.com/video/video.php?v=%s' % video_id |
2162 | webpage = self._download_webpage(url, video_id) | |
2163 | ||
32c96387 | 2164 | BEFORE = '{swf.addParam(param[0], param[1]);});\n' |
b954070d PH |
2165 | AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' |
2166 | m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) | |
2167 | if not m: | |
2168 | raise ExtractorError(u'Cannot parse data') | |
2169 | data = dict(json.loads(m.group(1))) | |
edba5137 PH |
2170 | params_raw = compat_urllib_parse.unquote(data['params']) |
2171 | params = json.loads(params_raw) | |
32c96387 PH |
2172 | video_data = params['video_data'][0] |
2173 | video_url = video_data.get('hd_src') | |
7796e8c2 | 2174 | if not video_url: |
32c96387 | 2175 | video_url = video_data['sd_src'] |
7796e8c2 PH |
2176 | if not video_url: |
2177 | raise ExtractorError(u'Cannot find video URL') | |
32c96387 PH |
2178 | video_duration = int(video_data['video_duration']) |
2179 | thumbnail = video_data['thumbnail_src'] | |
b954070d PH |
2180 | |
2181 | m = re.search('<h2 class="uiHeaderTitle">([^<]+)</h2>', webpage) | |
2182 | if not m: | |
2183 | raise ExtractorError(u'Cannot find title in webpage') | |
2184 | video_title = unescapeHTML(m.group(1)) | |
2185 | ||
2186 | info = { | |
2187 | 'id': video_id, | |
2188 | 'title': video_title, | |
2189 | 'url': video_url, | |
2190 | 'ext': 'mp4', | |
2191 | 'duration': video_duration, | |
32c96387 | 2192 | 'thumbnail': thumbnail, |
b954070d PH |
2193 | } |
2194 | return [info] | |
59ae15a5 | 2195 | |
d77c3dfd FV |
2196 | |
2197 | class BlipTVIE(InfoExtractor): | |
59ae15a5 PH |
2198 | """Information extractor for blip.tv""" |
2199 | ||
2200 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' | |
2201 | _URL_EXT = r'^.*\.([a-z0-9]+)$' | |
2202 | IE_NAME = u'blip.tv' | |
2203 | ||
2204 | def report_extraction(self, file_id): | |
2205 | """Report information extraction.""" | |
2206 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) | |
2207 | ||
2208 | def report_direct_download(self, title): | |
2209 | """Report information extraction.""" | |
2210 | self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title)) | |
2211 | ||
2212 | def _real_extract(self, url): | |
2213 | mobj = re.match(self._VALID_URL, url) | |
2214 | if mobj is None: | |
e5f30ade | 2215 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2216 | return |
2217 | ||
f7b567ff PH |
2218 | urlp = compat_urllib_parse_urlparse(url) |
2219 | if urlp.path.startswith('/play/'): | |
7f9d41a5 JCGS |
2220 | request = compat_urllib_request.Request(url) |
2221 | response = compat_urllib_request.urlopen(request) | |
2222 | redirecturl = response.geturl() | |
f7b567ff PH |
2223 | rurlp = compat_urllib_parse_urlparse(redirecturl) |
2224 | file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2] | |
2225 | url = 'http://blip.tv/a/a-' + file_id | |
2226 | return self._real_extract(url) | |
2227 | ||
7f9d41a5 | 2228 | |
59ae15a5 PH |
2229 | if '?' in url: |
2230 | cchar = '&' | |
2231 | else: | |
2232 | cchar = '?' | |
2233 | json_url = url + cchar + 'skin=json&version=2&no_wrap=1' | |
55c05398 | 2234 | request = compat_urllib_request.Request(json_url) |
3446dfb7 | 2235 | request.add_header('User-Agent', 'iTunes/10.6.1') |
59ae15a5 PH |
2236 | self.report_extraction(mobj.group(1)) |
2237 | info = None | |
2238 | try: | |
2239 | urlh = compat_urllib_request.urlopen(request) | |
2240 | if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download | |
2241 | basename = url.split('/')[-1] | |
2242 | title,ext = os.path.splitext(basename) | |
2243 | title = title.decode('UTF-8') | |
2244 | ext = ext.replace('.', '') | |
2245 | self.report_direct_download(title) | |
2246 | info = { | |
2247 | 'id': title, | |
2248 | 'url': url, | |
2249 | 'uploader': None, | |
2250 | 'upload_date': None, | |
2251 | 'title': title, | |
2252 | 'ext': ext, | |
2253 | 'urlhandle': urlh | |
2254 | } | |
2255 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
3446dfb7 | 2256 | raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) |
59ae15a5 PH |
2257 | if info is None: # Regular URL |
2258 | try: | |
55c05398 PH |
2259 | json_code_bytes = urlh.read() |
2260 | json_code = json_code_bytes.decode('utf-8') | |
59ae15a5 | 2261 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 2262 | self._downloader.report_error(u'unable to read video info webpage: %s' % compat_str(err)) |
59ae15a5 PH |
2263 | return |
2264 | ||
2265 | try: | |
2266 | json_data = json.loads(json_code) | |
2267 | if 'Post' in json_data: | |
2268 | data = json_data['Post'] | |
2269 | else: | |
2270 | data = json_data | |
2271 | ||
2272 | upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') | |
2273 | video_url = data['media']['url'] | |
2274 | umobj = re.match(self._URL_EXT, video_url) | |
2275 | if umobj is None: | |
2276 | raise ValueError('Can not determine filename extension') | |
2277 | ext = umobj.group(1) | |
2278 | ||
2279 | info = { | |
2280 | 'id': data['item_id'], | |
2281 | 'url': video_url, | |
2282 | 'uploader': data['display_name'], | |
2283 | 'upload_date': upload_date, | |
2284 | 'title': data['title'], | |
2285 | 'ext': ext, | |
2286 | 'format': data['media']['mimeType'], | |
2287 | 'thumbnail': data['thumbnailUrl'], | |
2288 | 'description': data['description'], | |
3446dfb7 PH |
2289 | 'player_url': data['embedUrl'], |
2290 | 'user_agent': 'iTunes/10.6.1', | |
59ae15a5 PH |
2291 | } |
2292 | except (ValueError,KeyError) as err: | |
e5f30ade | 2293 | self._downloader.report_error(u'unable to parse video information: %s' % repr(err)) |
59ae15a5 PH |
2294 | return |
2295 | ||
59ae15a5 | 2296 | return [info] |
d77c3dfd FV |
2297 | |
2298 | ||
2299 | class MyVideoIE(InfoExtractor): | |
59ae15a5 PH |
2300 | """Information Extractor for myvideo.de.""" |
2301 | ||
2302 | _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' | |
2303 | IE_NAME = u'myvideo' | |
2304 | ||
2305 | def __init__(self, downloader=None): | |
2306 | InfoExtractor.__init__(self, downloader) | |
cdb30764 | 2307 | |
59ae15a5 PH |
2308 | def report_extraction(self, video_id): |
2309 | """Report information extraction.""" | |
2310 | self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id) | |
2311 | ||
2312 | def _real_extract(self,url): | |
2313 | mobj = re.match(self._VALID_URL, url) | |
2314 | if mobj is None: | |
e5f30ade | 2315 | self._download.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2316 | return |
2317 | ||
2318 | video_id = mobj.group(1) | |
2319 | ||
2320 | # Get video webpage | |
5f955171 PH |
2321 | webpage_url = 'http://www.myvideo.de/watch/%s' % video_id |
2322 | webpage = self._download_webpage(webpage_url, video_id) | |
59ae15a5 PH |
2323 | |
2324 | self.report_extraction(video_id) | |
7decf895 | 2325 | mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/.*?\.jpg\'', |
59ae15a5 PH |
2326 | webpage) |
2327 | if mobj is None: | |
e5f30ade | 2328 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 PH |
2329 | return |
2330 | video_url = mobj.group(1) + ('/%s.flv' % video_id) | |
2331 | ||
2332 | mobj = re.search('<title>([^<]+)</title>', webpage) | |
2333 | if mobj is None: | |
e5f30ade | 2334 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 PH |
2335 | return |
2336 | ||
2337 | video_title = mobj.group(1) | |
2338 | ||
2339 | return [{ | |
2340 | 'id': video_id, | |
2341 | 'url': video_url, | |
2342 | 'uploader': None, | |
2343 | 'upload_date': None, | |
2344 | 'title': video_title, | |
2345 | 'ext': u'flv', | |
2346 | }] | |
d77c3dfd FV |
2347 | |
2348 | class ComedyCentralIE(InfoExtractor): | |
59ae15a5 PH |
2349 | """Information extractor for The Daily Show and Colbert Report """ |
2350 | ||
ca6849e6 | 2351 | # urls can be abbreviations like :thedailyshow or :colbert |
cdb30764 | 2352 | # urls for episodes like: |
ca6849e6 | 2353 | # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day |
2354 | # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news | |
cdb30764 | 2355 | # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524 |
ca6849e6 | 2356 | _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport) |
2357 | |(https?://)?(www\.)? | |
2358 | (?P<showname>thedailyshow|colbertnation)\.com/ | |
2359 | (full-episodes/(?P<episode>.*)| | |
2360 | (?P<clip> | |
2361 | (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) | |
2362 | |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))))) | |
cdb30764 | 2363 | $""" |
59ae15a5 PH |
2364 | |
2365 | _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] | |
2366 | ||
2367 | _video_extensions = { | |
2368 | '3500': 'mp4', | |
2369 | '2200': 'mp4', | |
2370 | '1700': 'mp4', | |
2371 | '1200': 'mp4', | |
2372 | '750': 'mp4', | |
2373 | '400': 'mp4', | |
2374 | } | |
2375 | _video_dimensions = { | |
2376 | '3500': '1280x720', | |
2377 | '2200': '960x540', | |
2378 | '1700': '768x432', | |
2379 | '1200': '640x360', | |
2380 | '750': '512x288', | |
2381 | '400': '384x216', | |
2382 | } | |
2383 | ||
89de9eb1 FV |
2384 | @classmethod |
2385 | def suitable(cls, url): | |
ca6849e6 | 2386 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 | 2387 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None |
ca6849e6 | 2388 | |
59ae15a5 PH |
2389 | def report_extraction(self, episode_id): |
2390 | self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) | |
2391 | ||
32635ec6 PH |
2392 | def report_config_download(self, episode_id, media_id): |
2393 | self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration for %s' % (episode_id, media_id)) | |
59ae15a5 PH |
2394 | |
2395 | def report_index_download(self, episode_id): | |
2396 | self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) | |
2397 | ||
59ae15a5 PH |
2398 | def _print_formats(self, formats): |
2399 | print('Available formats:') | |
2400 | for x in formats: | |
2401 | print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???'))) | |
2402 | ||
2403 | ||
2404 | def _real_extract(self, url): | |
ca6849e6 | 2405 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
59ae15a5 | 2406 | if mobj is None: |
e5f30ade | 2407 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2408 | return |
2409 | ||
2410 | if mobj.group('shortname'): | |
2411 | if mobj.group('shortname') in ('tds', 'thedailyshow'): | |
2412 | url = u'http://www.thedailyshow.com/full-episodes/' | |
2413 | else: | |
2414 | url = u'http://www.colbertnation.com/full-episodes/' | |
ca6849e6 | 2415 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
59ae15a5 PH |
2416 | assert mobj is not None |
2417 | ||
ca6849e6 | 2418 | if mobj.group('clip'): |
2419 | if mobj.group('showname') == 'thedailyshow': | |
2420 | epTitle = mobj.group('tdstitle') | |
2421 | else: | |
2422 | epTitle = mobj.group('cntitle') | |
2423 | dlNewest = False | |
59ae15a5 | 2424 | else: |
ca6849e6 | 2425 | dlNewest = not mobj.group('episode') |
2426 | if dlNewest: | |
2427 | epTitle = mobj.group('showname') | |
2428 | else: | |
2429 | epTitle = mobj.group('episode') | |
59ae15a5 PH |
2430 | |
2431 | req = compat_urllib_request.Request(url) | |
2432 | self.report_extraction(epTitle) | |
2433 | try: | |
2434 | htmlHandle = compat_urllib_request.urlopen(req) | |
2435 | html = htmlHandle.read() | |
93148102 | 2436 | webpage = html.decode('utf-8') |
59ae15a5 | 2437 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 2438 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 PH |
2439 | return |
2440 | if dlNewest: | |
2441 | url = htmlHandle.geturl() | |
ca6849e6 | 2442 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
59ae15a5 | 2443 | if mobj is None: |
e5f30ade | 2444 | self._downloader.report_error(u'Invalid redirected URL: ' + url) |
59ae15a5 PH |
2445 | return |
2446 | if mobj.group('episode') == '': | |
e5f30ade | 2447 | self._downloader.report_error(u'Redirected URL is still not specific: ' + url) |
59ae15a5 PH |
2448 | return |
2449 | epTitle = mobj.group('episode') | |
2450 | ||
93148102 | 2451 | mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage) |
59ae15a5 PH |
2452 | |
2453 | if len(mMovieParams) == 0: | |
2454 | # The Colbert Report embeds the information in a without | |
2455 | # a URL prefix; so extract the alternate reference | |
2456 | # and then add the URL prefix manually. | |
2457 | ||
93148102 | 2458 | altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage) |
59ae15a5 | 2459 | if len(altMovieParams) == 0: |
e5f30ade | 2460 | self._downloader.report_error(u'unable to find Flash URL in webpage ' + url) |
59ae15a5 PH |
2461 | return |
2462 | else: | |
2463 | mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] | |
cdb30764 | 2464 | |
59ae15a5 PH |
2465 | uri = mMovieParams[0][1] |
2466 | indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri}) | |
2467 | self.report_index_download(epTitle) | |
2468 | try: | |
2469 | indexXml = compat_urllib_request.urlopen(indexUrl).read() | |
2470 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2471 | self._downloader.report_error(u'unable to download episode index: ' + compat_str(err)) |
59ae15a5 PH |
2472 | return |
2473 | ||
2474 | results = [] | |
2475 | ||
2476 | idoc = xml.etree.ElementTree.fromstring(indexXml) | |
2477 | itemEls = idoc.findall('.//item') | |
7717ae19 | 2478 | for partNum,itemEl in enumerate(itemEls): |
59ae15a5 PH |
2479 | mediaId = itemEl.findall('./guid')[0].text |
2480 | shortMediaId = mediaId.split(':')[-1] | |
2481 | showId = mediaId.split(':')[-2].replace('.com', '') | |
2482 | officialTitle = itemEl.findall('./title')[0].text | |
2483 | officialDate = itemEl.findall('./pubDate')[0].text | |
2484 | ||
2485 | configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + | |
2486 | compat_urllib_parse.urlencode({'uri': mediaId})) | |
2487 | configReq = compat_urllib_request.Request(configUrl) | |
32635ec6 | 2488 | self.report_config_download(epTitle, shortMediaId) |
59ae15a5 PH |
2489 | try: |
2490 | configXml = compat_urllib_request.urlopen(configReq).read() | |
2491 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2492 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 PH |
2493 | return |
2494 | ||
2495 | cdoc = xml.etree.ElementTree.fromstring(configXml) | |
2496 | turls = [] | |
2497 | for rendition in cdoc.findall('.//rendition'): | |
2498 | finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) | |
2499 | turls.append(finfo) | |
2500 | ||
2501 | if len(turls) == 0: | |
c9fa1cba | 2502 | self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found') |
59ae15a5 | 2503 | continue |
cdb30764 | 2504 | |
59ae15a5 PH |
2505 | if self._downloader.params.get('listformats', None): |
2506 | self._print_formats([i[0] for i in turls]) | |
2507 | return | |
2508 | ||
2509 | # For now, just pick the highest bitrate | |
32635ec6 | 2510 | format,rtmp_video_url = turls[-1] |
59ae15a5 PH |
2511 | |
2512 | # Get the format arg from the arg stream | |
2513 | req_format = self._downloader.params.get('format', None) | |
2514 | ||
2515 | # Select format if we can find one | |
2516 | for f,v in turls: | |
2517 | if f == req_format: | |
32635ec6 | 2518 | format, rtmp_video_url = f, v |
59ae15a5 PH |
2519 | break |
2520 | ||
32635ec6 PH |
2521 | m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url) |
2522 | if not m: | |
2523 | raise ExtractorError(u'Cannot transform RTMP url') | |
2524 | base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' | |
2525 | video_url = base + m.group('finalid') | |
59ae15a5 | 2526 | |
7717ae19 | 2527 | effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1) |
59ae15a5 PH |
2528 | info = { |
2529 | 'id': shortMediaId, | |
2530 | 'url': video_url, | |
2531 | 'uploader': showId, | |
2532 | 'upload_date': officialDate, | |
2533 | 'title': effTitle, | |
2534 | 'ext': 'mp4', | |
2535 | 'format': format, | |
2536 | 'thumbnail': None, | |
2537 | 'description': officialTitle, | |
59ae15a5 | 2538 | } |
59ae15a5 | 2539 | results.append(info) |
cdb30764 | 2540 | |
59ae15a5 | 2541 | return results |
d77c3dfd FV |
2542 | |
2543 | ||
2544 | class EscapistIE(InfoExtractor): | |
59ae15a5 PH |
2545 | """Information extractor for The Escapist """ |
2546 | ||
2547 | _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$' | |
2548 | IE_NAME = u'escapist' | |
2549 | ||
2550 | def report_extraction(self, showName): | |
2551 | self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName) | |
2552 | ||
2553 | def report_config_download(self, showName): | |
2554 | self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName) | |
2555 | ||
2556 | def _real_extract(self, url): | |
2557 | mobj = re.match(self._VALID_URL, url) | |
2558 | if mobj is None: | |
e5f30ade | 2559 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2560 | return |
2561 | showName = mobj.group('showname') | |
2562 | videoId = mobj.group('episode') | |
2563 | ||
2564 | self.report_extraction(showName) | |
2565 | try: | |
2566 | webPage = compat_urllib_request.urlopen(url) | |
2567 | webPageBytes = webPage.read() | |
2568 | m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type']) | |
2569 | webPage = webPageBytes.decode(m.group(1) if m else 'utf-8') | |
2570 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2571 | self._downloader.report_error(u'unable to download webpage: ' + compat_str(err)) |
59ae15a5 PH |
2572 | return |
2573 | ||
2574 | descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) | |
2575 | description = unescapeHTML(descMatch.group(1)) | |
2576 | imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) | |
2577 | imgUrl = unescapeHTML(imgMatch.group(1)) | |
2578 | playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage) | |
2579 | playerUrl = unescapeHTML(playerUrlMatch.group(1)) | |
2580 | configUrlMatch = re.search('config=(.*)$', playerUrl) | |
2581 | configUrl = compat_urllib_parse.unquote(configUrlMatch.group(1)) | |
2582 | ||
2583 | self.report_config_download(showName) | |
2584 | try: | |
93702113 FV |
2585 | configJSON = compat_urllib_request.urlopen(configUrl) |
2586 | m = re.match(r'text/html; charset="?([^"]+)"?', configJSON.headers['Content-Type']) | |
2587 | configJSON = configJSON.read().decode(m.group(1) if m else 'utf-8') | |
59ae15a5 | 2588 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 2589 | self._downloader.report_error(u'unable to download configuration: ' + compat_str(err)) |
59ae15a5 PH |
2590 | return |
2591 | ||
2592 | # Technically, it's JavaScript, not JSON | |
2593 | configJSON = configJSON.replace("'", '"') | |
2594 | ||
2595 | try: | |
2596 | config = json.loads(configJSON) | |
2597 | except (ValueError,) as err: | |
e5f30ade | 2598 | self._downloader.report_error(u'Invalid JSON in configuration file: ' + compat_str(err)) |
59ae15a5 PH |
2599 | return |
2600 | ||
2601 | playlist = config['playlist'] | |
2602 | videoUrl = playlist[1]['url'] | |
2603 | ||
2604 | info = { | |
2605 | 'id': videoId, | |
2606 | 'url': videoUrl, | |
2607 | 'uploader': showName, | |
2608 | 'upload_date': None, | |
2609 | 'title': showName, | |
47dcd621 | 2610 | 'ext': 'mp4', |
59ae15a5 PH |
2611 | 'thumbnail': imgUrl, |
2612 | 'description': description, | |
2613 | 'player_url': playerUrl, | |
2614 | } | |
2615 | ||
2616 | return [info] | |
d77c3dfd | 2617 | |
d77c3dfd | 2618 | class CollegeHumorIE(InfoExtractor): |
59ae15a5 PH |
2619 | """Information extractor for collegehumor.com""" |
2620 | ||
0eb0faa2 | 2621 | _WORKING = False |
59ae15a5 PH |
2622 | _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$' |
2623 | IE_NAME = u'collegehumor' | |
2624 | ||
799c0763 | 2625 | def report_manifest(self, video_id): |
59ae15a5 | 2626 | """Report information extraction.""" |
799c0763 | 2627 | self._downloader.to_screen(u'[%s] %s: Downloading XML manifest' % (self.IE_NAME, video_id)) |
59ae15a5 PH |
2628 | |
2629 | def report_extraction(self, video_id): | |
2630 | """Report information extraction.""" | |
2631 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
2632 | ||
2633 | def _real_extract(self, url): | |
2634 | mobj = re.match(self._VALID_URL, url) | |
2635 | if mobj is None: | |
e5f30ade | 2636 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2637 | return |
2638 | video_id = mobj.group('videoid') | |
2639 | ||
59ae15a5 PH |
2640 | info = { |
2641 | 'id': video_id, | |
59ae15a5 PH |
2642 | 'uploader': None, |
2643 | 'upload_date': None, | |
2644 | } | |
2645 | ||
2646 | self.report_extraction(video_id) | |
799c0763 | 2647 | xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id |
59ae15a5 PH |
2648 | try: |
2649 | metaXml = compat_urllib_request.urlopen(xmlUrl).read() | |
2650 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2651 | self._downloader.report_error(u'unable to download video info XML: %s' % compat_str(err)) |
59ae15a5 PH |
2652 | return |
2653 | ||
2654 | mdoc = xml.etree.ElementTree.fromstring(metaXml) | |
2655 | try: | |
2656 | videoNode = mdoc.findall('./video')[0] | |
2657 | info['description'] = videoNode.findall('./description')[0].text | |
2658 | info['title'] = videoNode.findall('./caption')[0].text | |
59ae15a5 | 2659 | info['thumbnail'] = videoNode.findall('./thumbnail')[0].text |
799c0763 | 2660 | manifest_url = videoNode.findall('./file')[0].text |
59ae15a5 | 2661 | except IndexError: |
c9fa1cba | 2662 | self._downloader.report_error(u'Invalid metadata XML file') |
59ae15a5 PH |
2663 | return |
2664 | ||
799c0763 PH |
2665 | manifest_url += '?hdcore=2.10.3' |
2666 | self.report_manifest(video_id) | |
2667 | try: | |
2668 | manifestXml = compat_urllib_request.urlopen(manifest_url).read() | |
2669 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2670 | self._downloader.report_error(u'unable to download video info XML: %s' % compat_str(err)) |
799c0763 PH |
2671 | return |
2672 | ||
2673 | adoc = xml.etree.ElementTree.fromstring(manifestXml) | |
2674 | try: | |
2675 | media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] | |
2676 | node_id = media_node.attrib['url'] | |
2677 | video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text | |
2678 | except IndexError as err: | |
c9fa1cba | 2679 | self._downloader.report_error(u'Invalid manifest file') |
799c0763 PH |
2680 | return |
2681 | ||
2682 | url_pr = compat_urllib_parse_urlparse(manifest_url) | |
2683 | url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1' | |
2684 | ||
2685 | info['url'] = url | |
2686 | info['ext'] = 'f4f' | |
59ae15a5 | 2687 | return [info] |
d77c3dfd FV |
2688 | |
2689 | ||
2690 | class XVideosIE(InfoExtractor): | |
59ae15a5 | 2691 | """Information extractor for xvideos.com""" |
d77c3dfd | 2692 | |
59ae15a5 PH |
2693 | _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' |
2694 | IE_NAME = u'xvideos' | |
d77c3dfd | 2695 | |
59ae15a5 PH |
2696 | def report_extraction(self, video_id): |
2697 | """Report information extraction.""" | |
2698 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
d77c3dfd | 2699 | |
59ae15a5 PH |
2700 | def _real_extract(self, url): |
2701 | mobj = re.match(self._VALID_URL, url) | |
2702 | if mobj is None: | |
e5f30ade | 2703 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 | 2704 | return |
8588a86f | 2705 | video_id = mobj.group(1) |
d77c3dfd | 2706 | |
5f955171 | 2707 | webpage = self._download_webpage(url, video_id) |
d77c3dfd | 2708 | |
59ae15a5 | 2709 | self.report_extraction(video_id) |
d77c3dfd FV |
2710 | |
2711 | ||
59ae15a5 PH |
2712 | # Extract video URL |
2713 | mobj = re.search(r'flv_url=(.+?)&', webpage) | |
2714 | if mobj is None: | |
e5f30ade | 2715 | self._downloader.report_error(u'unable to extract video url') |
59ae15a5 | 2716 | return |
8588a86f | 2717 | video_url = compat_urllib_parse.unquote(mobj.group(1)) |
d77c3dfd FV |
2718 | |
2719 | ||
59ae15a5 PH |
2720 | # Extract title |
2721 | mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage) | |
2722 | if mobj is None: | |
e5f30ade | 2723 | self._downloader.report_error(u'unable to extract video title') |
59ae15a5 | 2724 | return |
8588a86f | 2725 | video_title = mobj.group(1) |
d77c3dfd FV |
2726 | |
2727 | ||
59ae15a5 PH |
2728 | # Extract video thumbnail |
2729 | mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage) | |
2730 | if mobj is None: | |
e5f30ade | 2731 | self._downloader.report_error(u'unable to extract video thumbnail') |
59ae15a5 | 2732 | return |
8588a86f | 2733 | video_thumbnail = mobj.group(0) |
d77c3dfd | 2734 | |
59ae15a5 PH |
2735 | info = { |
2736 | 'id': video_id, | |
2737 | 'url': video_url, | |
2738 | 'uploader': None, | |
2739 | 'upload_date': None, | |
2740 | 'title': video_title, | |
2741 | 'ext': 'flv', | |
2742 | 'thumbnail': video_thumbnail, | |
2743 | 'description': None, | |
2744 | } | |
d77c3dfd | 2745 | |
59ae15a5 | 2746 | return [info] |
d77c3dfd FV |
2747 | |
2748 | ||
2749 | class SoundcloudIE(InfoExtractor): | |
59ae15a5 PH |
2750 | """Information extractor for soundcloud.com |
2751 | To access the media, the uid of the song and a stream token | |
2752 | must be extracted from the page source and the script must make | |
2753 | a request to media.soundcloud.com/crossdomain.xml. Then | |
2754 | the media can be grabbed by requesting from an url composed | |
2755 | of the stream token and uid | |
2756 | """ | |
2757 | ||
2758 | _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)' | |
2759 | IE_NAME = u'soundcloud' | |
2760 | ||
2761 | def __init__(self, downloader=None): | |
2762 | InfoExtractor.__init__(self, downloader) | |
2763 | ||
8fd3afd5 | 2764 | def report_resolve(self, video_id): |
59ae15a5 | 2765 | """Report information extraction.""" |
8fd3afd5 | 2766 | self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id)) |
59ae15a5 PH |
2767 | |
2768 | def report_extraction(self, video_id): | |
2769 | """Report information extraction.""" | |
8fd3afd5 | 2770 | self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id)) |
59ae15a5 PH |
2771 | |
2772 | def _real_extract(self, url): | |
2773 | mobj = re.match(self._VALID_URL, url) | |
2774 | if mobj is None: | |
e5f30ade | 2775 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2776 | return |
2777 | ||
2778 | # extract uploader (which is in the url) | |
15c8d833 | 2779 | uploader = mobj.group(1) |
59ae15a5 | 2780 | # extract simple title (uploader + slug of song title) |
15c8d833 | 2781 | slug_title = mobj.group(2) |
59ae15a5 PH |
2782 | simple_title = uploader + u'-' + slug_title |
2783 | ||
8fd3afd5 | 2784 | self.report_resolve('%s/%s' % (uploader, slug_title)) |
59ae15a5 | 2785 | |
8fd3afd5 PH |
2786 | url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title) |
2787 | resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28' | |
2788 | request = compat_urllib_request.Request(resolv_url) | |
59ae15a5 | 2789 | try: |
8fd3afd5 PH |
2790 | info_json_bytes = compat_urllib_request.urlopen(request).read() |
2791 | info_json = info_json_bytes.decode('utf-8') | |
59ae15a5 | 2792 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 2793 | self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
2794 | return |
2795 | ||
8fd3afd5 PH |
2796 | info = json.loads(info_json) |
2797 | video_id = info['id'] | |
59ae15a5 PH |
2798 | self.report_extraction('%s/%s' % (uploader, slug_title)) |
2799 | ||
8fd3afd5 | 2800 | streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28' |
c7214f9a | 2801 | request = compat_urllib_request.Request(streams_url) |
8fd3afd5 PH |
2802 | try: |
2803 | stream_json_bytes = compat_urllib_request.urlopen(request).read() | |
2804 | stream_json = stream_json_bytes.decode('utf-8') | |
2805 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2806 | self._downloader.report_error(u'unable to download stream definitions: %s' % compat_str(err)) |
b4cd069d | 2807 | return |
59ae15a5 | 2808 | |
8fd3afd5 | 2809 | streams = json.loads(stream_json) |
c7214f9a | 2810 | mediaURL = streams['http_mp3_128_url'] |
59ae15a5 PH |
2811 | |
2812 | return [{ | |
c7214f9a | 2813 | 'id': info['id'], |
59ae15a5 | 2814 | 'url': mediaURL, |
c7214f9a PH |
2815 | 'uploader': info['user']['username'], |
2816 | 'upload_date': info['created_at'], | |
2817 | 'title': info['title'], | |
59ae15a5 | 2818 | 'ext': u'mp3', |
c7214f9a | 2819 | 'description': info['description'], |
59ae15a5 | 2820 | }] |
d77c3dfd | 2821 | |
5011cded | 2822 | class SoundcloudSetIE(InfoExtractor): |
2823 | """Information extractor for soundcloud.com sets | |
2824 | To access the media, the uid of the song and a stream token | |
2825 | must be extracted from the page source and the script must make | |
2826 | a request to media.soundcloud.com/crossdomain.xml. Then | |
2827 | the media can be grabbed by requesting from an url composed | |
2828 | of the stream token and uid | |
2829 | """ | |
2830 | ||
2831 | _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)' | |
2832 | IE_NAME = u'soundcloud' | |
2833 | ||
2834 | def __init__(self, downloader=None): | |
2835 | InfoExtractor.__init__(self, downloader) | |
2836 | ||
2837 | def report_resolve(self, video_id): | |
2838 | """Report information extraction.""" | |
2839 | self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id)) | |
2840 | ||
2841 | def report_extraction(self, video_id): | |
2842 | """Report information extraction.""" | |
2843 | self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id)) | |
2844 | ||
2845 | def _real_extract(self, url): | |
2846 | mobj = re.match(self._VALID_URL, url) | |
2847 | if mobj is None: | |
2848 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2849 | return | |
2850 | ||
2851 | # extract uploader (which is in the url) | |
2852 | uploader = mobj.group(1) | |
2853 | # extract simple title (uploader + slug of song title) | |
2854 | slug_title = mobj.group(2) | |
2855 | simple_title = uploader + u'-' + slug_title | |
2856 | ||
2857 | self.report_resolve('%s/sets/%s' % (uploader, slug_title)) | |
2858 | ||
2859 | url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title) | |
2860 | resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28' | |
2861 | request = compat_urllib_request.Request(resolv_url) | |
2862 | try: | |
2863 | info_json_bytes = compat_urllib_request.urlopen(request).read() | |
2864 | info_json = info_json_bytes.decode('utf-8') | |
2865 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2866 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) | |
2867 | return | |
2868 | ||
2869 | videos = [] | |
2870 | info = json.loads(info_json) | |
2871 | if 'errors' in info: | |
2872 | for err in info['errors']: | |
2873 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err['error_message'])) | |
2874 | return | |
2875 | ||
2876 | for track in info['tracks']: | |
2877 | video_id = track['id'] | |
2878 | self.report_extraction('%s/sets/%s' % (uploader, slug_title)) | |
2879 | ||
2880 | streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28' | |
2881 | request = compat_urllib_request.Request(streams_url) | |
2882 | try: | |
2883 | stream_json_bytes = compat_urllib_request.urlopen(request).read() | |
2884 | stream_json = stream_json_bytes.decode('utf-8') | |
2885 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2886 | self._downloader.trouble(u'ERROR: unable to download stream definitions: %s' % compat_str(err)) | |
2887 | return | |
2888 | ||
2889 | streams = json.loads(stream_json) | |
2890 | mediaURL = streams['http_mp3_128_url'] | |
2891 | ||
2892 | videos.append({ | |
2893 | 'id': video_id, | |
2894 | 'url': mediaURL, | |
2895 | 'uploader': track['user']['username'], | |
2896 | 'upload_date': track['created_at'], | |
2897 | 'title': track['title'], | |
2898 | 'ext': u'mp3', | |
2899 | 'description': track['description'], | |
2900 | }) | |
2901 | return videos | |
2902 | ||
d77c3dfd FV |
2903 | |
2904 | class InfoQIE(InfoExtractor): | |
59ae15a5 | 2905 | """Information extractor for infoq.com""" |
59ae15a5 | 2906 | _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' |
59ae15a5 | 2907 | |
59ae15a5 PH |
2908 | def report_extraction(self, video_id): |
2909 | """Report information extraction.""" | |
2910 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
2911 | ||
2912 | def _real_extract(self, url): | |
2913 | mobj = re.match(self._VALID_URL, url) | |
2914 | if mobj is None: | |
e5f30ade | 2915 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2916 | return |
2917 | ||
4fcca4bb | 2918 | webpage = self._download_webpage(url, video_id=url) |
59ae15a5 PH |
2919 | self.report_extraction(url) |
2920 | ||
59ae15a5 PH |
2921 | # Extract video URL |
2922 | mobj = re.search(r"jsclassref='([^']*)'", webpage) | |
2923 | if mobj is None: | |
e5f30ade | 2924 | self._downloader.report_error(u'unable to extract video url') |
59ae15a5 | 2925 | return |
4fcca4bb PH |
2926 | real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8')) |
2927 | video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id | |
59ae15a5 PH |
2928 | |
2929 | # Extract title | |
2930 | mobj = re.search(r'contentTitle = "(.*?)";', webpage) | |
2931 | if mobj is None: | |
e5f30ade | 2932 | self._downloader.report_error(u'unable to extract video title') |
59ae15a5 | 2933 | return |
4fcca4bb | 2934 | video_title = mobj.group(1) |
59ae15a5 PH |
2935 | |
2936 | # Extract description | |
2937 | video_description = u'No description available.' | |
2938 | mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage) | |
2939 | if mobj is not None: | |
4fcca4bb | 2940 | video_description = mobj.group(1) |
59ae15a5 PH |
2941 | |
2942 | video_filename = video_url.split('/')[-1] | |
2943 | video_id, extension = video_filename.split('.') | |
2944 | ||
2945 | info = { | |
2946 | 'id': video_id, | |
2947 | 'url': video_url, | |
2948 | 'uploader': None, | |
2949 | 'upload_date': None, | |
2950 | 'title': video_title, | |
2951 | 'ext': extension, # Extension is always(?) mp4, but seems to be flv | |
2952 | 'thumbnail': None, | |
2953 | 'description': video_description, | |
2954 | } | |
2955 | ||
2956 | return [info] | |
d77c3dfd FV |
2957 | |
2958 | class MixcloudIE(InfoExtractor): | |
59ae15a5 | 2959 | """Information extractor for www.mixcloud.com""" |
93702113 FV |
2960 | |
2961 | _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/ | |
59ae15a5 PH |
2962 | _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' |
2963 | IE_NAME = u'mixcloud' | |
2964 | ||
2965 | def __init__(self, downloader=None): | |
2966 | InfoExtractor.__init__(self, downloader) | |
2967 | ||
2968 | def report_download_json(self, file_id): | |
2969 | """Report JSON download.""" | |
2970 | self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME) | |
2971 | ||
2972 | def report_extraction(self, file_id): | |
2973 | """Report information extraction.""" | |
2974 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) | |
2975 | ||
2976 | def get_urls(self, jsonData, fmt, bitrate='best'): | |
2977 | """Get urls from 'audio_formats' section in json""" | |
2978 | file_url = None | |
2979 | try: | |
2980 | bitrate_list = jsonData[fmt] | |
2981 | if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list: | |
2982 | bitrate = max(bitrate_list) # select highest | |
2983 | ||
2984 | url_list = jsonData[fmt][bitrate] | |
2985 | except TypeError: # we have no bitrate info. | |
2986 | url_list = jsonData[fmt] | |
2987 | return url_list | |
2988 | ||
2989 | def check_urls(self, url_list): | |
2990 | """Returns 1st active url from list""" | |
2991 | for url in url_list: | |
2992 | try: | |
2993 | compat_urllib_request.urlopen(url) | |
2994 | return url | |
2995 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2996 | url = None | |
2997 | ||
2998 | return None | |
2999 | ||
3000 | def _print_formats(self, formats): | |
3001 | print('Available formats:') | |
3002 | for fmt in formats.keys(): | |
3003 | for b in formats[fmt]: | |
3004 | try: | |
3005 | ext = formats[fmt][b][0] | |
3006 | print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])) | |
3007 | except TypeError: # we have no bitrate info | |
3008 | ext = formats[fmt][0] | |
3009 | print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])) | |
3010 | break | |
3011 | ||
3012 | def _real_extract(self, url): | |
3013 | mobj = re.match(self._VALID_URL, url) | |
3014 | if mobj is None: | |
e5f30ade | 3015 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
3016 | return |
3017 | # extract uploader & filename from url | |
3018 | uploader = mobj.group(1).decode('utf-8') | |
3019 | file_id = uploader + "-" + mobj.group(2).decode('utf-8') | |
3020 | ||
3021 | # construct API request | |
3022 | file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json' | |
3023 | # retrieve .json file with links to files | |
3024 | request = compat_urllib_request.Request(file_url) | |
3025 | try: | |
3026 | self.report_download_json(file_url) | |
3027 | jsonData = compat_urllib_request.urlopen(request).read() | |
3028 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 3029 | self._downloader.report_error(u'Unable to retrieve file: %s' % compat_str(err)) |
59ae15a5 PH |
3030 | return |
3031 | ||
3032 | # parse JSON | |
3033 | json_data = json.loads(jsonData) | |
3034 | player_url = json_data['player_swf_url'] | |
3035 | formats = dict(json_data['audio_formats']) | |
3036 | ||
3037 | req_format = self._downloader.params.get('format', None) | |
3038 | bitrate = None | |
3039 | ||
3040 | if self._downloader.params.get('listformats', None): | |
3041 | self._print_formats(formats) | |
3042 | return | |
3043 | ||
3044 | if req_format is None or req_format == 'best': | |
3045 | for format_param in formats.keys(): | |
3046 | url_list = self.get_urls(formats, format_param) | |
3047 | # check urls | |
3048 | file_url = self.check_urls(url_list) | |
3049 | if file_url is not None: | |
3050 | break # got it! | |
3051 | else: | |
99b0a129 | 3052 | if req_format not in formats: |
e5f30ade | 3053 | self._downloader.report_error(u'format is not available') |
59ae15a5 PH |
3054 | return |
3055 | ||
3056 | url_list = self.get_urls(formats, req_format) | |
3057 | file_url = self.check_urls(url_list) | |
3058 | format_param = req_format | |
3059 | ||
3060 | return [{ | |
3061 | 'id': file_id.decode('utf-8'), | |
3062 | 'url': file_url.decode('utf-8'), | |
3063 | 'uploader': uploader.decode('utf-8'), | |
3064 | 'upload_date': None, | |
3065 | 'title': json_data['name'], | |
3066 | 'ext': file_url.split('.')[-1].decode('utf-8'), | |
3067 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), | |
3068 | 'thumbnail': json_data['thumbnail_url'], | |
3069 | 'description': json_data['description'], | |
3070 | 'player_url': player_url.decode('utf-8'), | |
3071 | }] | |
d77c3dfd FV |
3072 | |
3073 | class StanfordOpenClassroomIE(InfoExtractor): | |
59ae15a5 PH |
3074 | """Information extractor for Stanford's Open ClassRoom""" |
3075 | ||
3076 | _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' | |
3077 | IE_NAME = u'stanfordoc' | |
3078 | ||
3079 | def report_download_webpage(self, objid): | |
3080 | """Report information extraction.""" | |
3081 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid)) | |
3082 | ||
3083 | def report_extraction(self, video_id): | |
3084 | """Report information extraction.""" | |
3085 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3086 | ||
3087 | def _real_extract(self, url): | |
3088 | mobj = re.match(self._VALID_URL, url) | |
3089 | if mobj is None: | |
f0bad2b0 | 3090 | raise ExtractorError(u'Invalid URL: %s' % url) |
59ae15a5 PH |
3091 | |
3092 | if mobj.group('course') and mobj.group('video'): # A specific video | |
3093 | course = mobj.group('course') | |
3094 | video = mobj.group('video') | |
3095 | info = { | |
3096 | 'id': course + '_' + video, | |
3097 | 'uploader': None, | |
3098 | 'upload_date': None, | |
3099 | } | |
3100 | ||
3101 | self.report_extraction(info['id']) | |
3102 | baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' | |
3103 | xmlUrl = baseUrl + video + '.xml' | |
3104 | try: | |
3105 | metaXml = compat_urllib_request.urlopen(xmlUrl).read() | |
3106 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 3107 | self._downloader.report_error(u'unable to download video info XML: %s' % compat_str(err)) |
59ae15a5 PH |
3108 | return |
3109 | mdoc = xml.etree.ElementTree.fromstring(metaXml) | |
3110 | try: | |
3111 | info['title'] = mdoc.findall('./title')[0].text | |
3112 | info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text | |
3113 | except IndexError: | |
c9fa1cba | 3114 | self._downloader.report_error(u'Invalid metadata XML file') |
59ae15a5 PH |
3115 | return |
3116 | info['ext'] = info['url'].rpartition('.')[2] | |
3117 | return [info] | |
3118 | elif mobj.group('course'): # A course page | |
3119 | course = mobj.group('course') | |
3120 | info = { | |
3121 | 'id': course, | |
3122 | 'type': 'playlist', | |
3123 | 'uploader': None, | |
3124 | 'upload_date': None, | |
3125 | } | |
3126 | ||
f0bad2b0 PH |
3127 | coursepage = self._download_webpage(url, info['id'], |
3128 | note='Downloading course info page', | |
3129 | errnote='Unable to download course info page') | |
59ae15a5 PH |
3130 | |
3131 | m = re.search('<h1>([^<]+)</h1>', coursepage) | |
3132 | if m: | |
3133 | info['title'] = unescapeHTML(m.group(1)) | |
3134 | else: | |
3135 | info['title'] = info['id'] | |
3136 | ||
3137 | m = re.search('<description>([^<]+)</description>', coursepage) | |
3138 | if m: | |
3139 | info['description'] = unescapeHTML(m.group(1)) | |
3140 | ||
3141 | links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) | |
3142 | info['list'] = [ | |
3143 | { | |
3144 | 'type': 'reference', | |
3145 | 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), | |
3146 | } | |
3147 | for vpage in links] | |
3148 | results = [] | |
3149 | for entry in info['list']: | |
3150 | assert entry['type'] == 'reference' | |
3151 | results += self.extract(entry['url']) | |
3152 | return results | |
59ae15a5 PH |
3153 | else: # Root page |
3154 | info = { | |
3155 | 'id': 'Stanford OpenClassroom', | |
3156 | 'type': 'playlist', | |
3157 | 'uploader': None, | |
3158 | 'upload_date': None, | |
3159 | } | |
3160 | ||
3161 | self.report_download_webpage(info['id']) | |
3162 | rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' | |
3163 | try: | |
3164 | rootpage = compat_urllib_request.urlopen(rootURL).read() | |
3165 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 3166 | self._downloader.report_error(u'unable to download course info page: ' + compat_str(err)) |
59ae15a5 PH |
3167 | return |
3168 | ||
3169 | info['title'] = info['id'] | |
3170 | ||
3171 | links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage)) | |
3172 | info['list'] = [ | |
3173 | { | |
3174 | 'type': 'reference', | |
3175 | 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), | |
3176 | } | |
3177 | for cpage in links] | |
3178 | ||
3179 | results = [] | |
3180 | for entry in info['list']: | |
3181 | assert entry['type'] == 'reference' | |
3182 | results += self.extract(entry['url']) | |
3183 | return results | |
d77c3dfd FV |
3184 | |
3185 | class MTVIE(InfoExtractor): | |
59ae15a5 PH |
3186 | """Information extractor for MTV.com""" |
3187 | ||
3188 | _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$' | |
3189 | IE_NAME = u'mtv' | |
3190 | ||
59ae15a5 PH |
3191 | def report_extraction(self, video_id): |
3192 | """Report information extraction.""" | |
3193 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3194 | ||
3195 | def _real_extract(self, url): | |
3196 | mobj = re.match(self._VALID_URL, url) | |
3197 | if mobj is None: | |
e5f30ade | 3198 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
3199 | return |
3200 | if not mobj.group('proto'): | |
3201 | url = 'http://' + url | |
3202 | video_id = mobj.group('videoid') | |
59ae15a5 | 3203 | |
5f955171 | 3204 | webpage = self._download_webpage(url, video_id) |
59ae15a5 PH |
3205 | |
3206 | mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage) | |
3207 | if mobj is None: | |
e5f30ade | 3208 | self._downloader.report_error(u'unable to extract song name') |
59ae15a5 PH |
3209 | return |
3210 | song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1')) | |
3211 | mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage) | |
3212 | if mobj is None: | |
e5f30ade | 3213 | self._downloader.report_error(u'unable to extract performer') |
59ae15a5 PH |
3214 | return |
3215 | performer = unescapeHTML(mobj.group(1).decode('iso-8859-1')) | |
cdb30764 | 3216 | video_title = performer + ' - ' + song_name |
59ae15a5 PH |
3217 | |
3218 | mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage) | |
3219 | if mobj is None: | |
e5f30ade | 3220 | self._downloader.report_error(u'unable to mtvn_uri') |
59ae15a5 PH |
3221 | return |
3222 | mtvn_uri = mobj.group(1) | |
3223 | ||
3224 | mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage) | |
3225 | if mobj is None: | |
e5f30ade | 3226 | self._downloader.report_error(u'unable to extract content id') |
59ae15a5 PH |
3227 | return |
3228 | content_id = mobj.group(1) | |
3229 | ||
3230 | videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri | |
3231 | self.report_extraction(video_id) | |
3232 | request = compat_urllib_request.Request(videogen_url) | |
3233 | try: | |
3234 | metadataXml = compat_urllib_request.urlopen(request).read() | |
3235 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 3236 | self._downloader.report_error(u'unable to download video metadata: %s' % compat_str(err)) |
59ae15a5 PH |
3237 | return |
3238 | ||
3239 | mdoc = xml.etree.ElementTree.fromstring(metadataXml) | |
3240 | renditions = mdoc.findall('.//rendition') | |
3241 | ||
3242 | # For now, always pick the highest quality. | |
3243 | rendition = renditions[-1] | |
3244 | ||
3245 | try: | |
3246 | _,_,ext = rendition.attrib['type'].partition('/') | |
3247 | format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate'] | |
3248 | video_url = rendition.find('./src').text | |
3249 | except KeyError: | |
3250 | self._downloader.trouble('Invalid rendition field.') | |
3251 | return | |
3252 | ||
3253 | info = { | |
3254 | 'id': video_id, | |
3255 | 'url': video_url, | |
3256 | 'uploader': performer, | |
3257 | 'upload_date': None, | |
3258 | 'title': video_title, | |
3259 | 'ext': ext, | |
3260 | 'format': format, | |
3261 | } | |
3262 | ||
3263 | return [info] | |
6de7ef9b | 3264 | |
302efc19 | 3265 | |
302efc19 | 3266 | class YoukuIE(InfoExtractor): |
59ae15a5 | 3267 | _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html' |
59ae15a5 PH |
3268 | |
3269 | def report_download_webpage(self, file_id): | |
3270 | """Report webpage download.""" | |
a34dd63b | 3271 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, file_id)) |
59ae15a5 PH |
3272 | |
3273 | def report_extraction(self, file_id): | |
3274 | """Report information extraction.""" | |
a34dd63b | 3275 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) |
59ae15a5 PH |
3276 | |
3277 | def _gen_sid(self): | |
3278 | nowTime = int(time.time() * 1000) | |
3279 | random1 = random.randint(1000,1998) | |
3280 | random2 = random.randint(1000,9999) | |
3281 | ||
3282 | return "%d%d%d" %(nowTime,random1,random2) | |
3283 | ||
3284 | def _get_file_ID_mix_string(self, seed): | |
3285 | mixed = [] | |
3286 | source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890") | |
3287 | seed = float(seed) | |
3288 | for i in range(len(source)): | |
3289 | seed = (seed * 211 + 30031 ) % 65536 | |
3290 | index = math.floor(seed / 65536 * len(source) ) | |
3291 | mixed.append(source[int(index)]) | |
3292 | source.remove(source[int(index)]) | |
3293 | #return ''.join(mixed) | |
3294 | return mixed | |
3295 | ||
3296 | def _get_file_id(self, fileId, seed): | |
3297 | mixed = self._get_file_ID_mix_string(seed) | |
3298 | ids = fileId.split('*') | |
3299 | realId = [] | |
3300 | for ch in ids: | |
3301 | if ch: | |
3302 | realId.append(mixed[int(ch)]) | |
3303 | return ''.join(realId) | |
3304 | ||
3305 | def _real_extract(self, url): | |
3306 | mobj = re.match(self._VALID_URL, url) | |
3307 | if mobj is None: | |
e5f30ade | 3308 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
3309 | return |
3310 | video_id = mobj.group('ID') | |
3311 | ||
3312 | info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id | |
3313 | ||
3314 | request = compat_urllib_request.Request(info_url, None, std_headers) | |
3315 | try: | |
3316 | self.report_download_webpage(video_id) | |
3317 | jsondata = compat_urllib_request.urlopen(request).read() | |
3318 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 3319 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
3320 | return |
3321 | ||
3322 | self.report_extraction(video_id) | |
3323 | try: | |
8f6f40d9 PH |
3324 | jsonstr = jsondata.decode('utf-8') |
3325 | config = json.loads(jsonstr) | |
59ae15a5 PH |
3326 | |
3327 | video_title = config['data'][0]['title'] | |
3328 | seed = config['data'][0]['seed'] | |
3329 | ||
3330 | format = self._downloader.params.get('format', None) | |
1a2c3c0f | 3331 | supported_format = list(config['data'][0]['streamfileids'].keys()) |
59ae15a5 PH |
3332 | |
3333 | if format is None or format == 'best': | |
3334 | if 'hd2' in supported_format: | |
3335 | format = 'hd2' | |
3336 | else: | |
3337 | format = 'flv' | |
3338 | ext = u'flv' | |
3339 | elif format == 'worst': | |
3340 | format = 'mp4' | |
3341 | ext = u'mp4' | |
3342 | else: | |
3343 | format = 'flv' | |
3344 | ext = u'flv' | |
3345 | ||
3346 | ||
3347 | fileid = config['data'][0]['streamfileids'][format] | |
e2a8ff24 | 3348 | keys = [s['k'] for s in config['data'][0]['segs'][format]] |
8f6f40d9 | 3349 | except (UnicodeDecodeError, ValueError, KeyError): |
e5f30ade | 3350 | self._downloader.report_error(u'unable to extract info section') |
59ae15a5 PH |
3351 | return |
3352 | ||
3353 | files_info=[] | |
3354 | sid = self._gen_sid() | |
3355 | fileid = self._get_file_id(fileid, seed) | |
3356 | ||
3357 | #column 8,9 of fileid represent the segment number | |
3358 | #fileid[7:9] should be changed | |
3359 | for index, key in enumerate(keys): | |
3360 | ||
3361 | temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:]) | |
3362 | download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) | |
3363 | ||
3364 | info = { | |
3365 | 'id': '%s_part%02d' % (video_id, index), | |
3366 | 'url': download_url, | |
3367 | 'uploader': None, | |
3368 | 'upload_date': None, | |
3369 | 'title': video_title, | |
3370 | 'ext': ext, | |
3371 | } | |
3372 | files_info.append(info) | |
3373 | ||
3374 | return files_info | |
5dc846fa FV |
3375 | |
3376 | ||
6de7ef9b | 3377 | class XNXXIE(InfoExtractor): |
59ae15a5 PH |
3378 | """Information extractor for xnxx.com""" |
3379 | ||
caec7618 | 3380 | _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)' |
59ae15a5 PH |
3381 | IE_NAME = u'xnxx' |
3382 | VIDEO_URL_RE = r'flv_url=(.*?)&' | |
3383 | VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM' | |
3384 | VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&' | |
3385 | ||
3386 | def report_webpage(self, video_id): | |
3387 | """Report information extraction""" | |
3388 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
3389 | ||
3390 | def report_extraction(self, video_id): | |
3391 | """Report information extraction""" | |
3392 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3393 | ||
3394 | def _real_extract(self, url): | |
3395 | mobj = re.match(self._VALID_URL, url) | |
3396 | if mobj is None: | |
e5f30ade | 3397 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 | 3398 | return |
bec102a8 | 3399 | video_id = mobj.group(1) |
59ae15a5 PH |
3400 | |
3401 | self.report_webpage(video_id) | |
3402 | ||
3403 | # Get webpage content | |
3404 | try: | |
bec102a8 PH |
3405 | webpage_bytes = compat_urllib_request.urlopen(url).read() |
3406 | webpage = webpage_bytes.decode('utf-8') | |
59ae15a5 | 3407 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 3408 | self._downloader.report_error(u'unable to download video webpage: %s' % err) |
59ae15a5 PH |
3409 | return |
3410 | ||
3411 | result = re.search(self.VIDEO_URL_RE, webpage) | |
3412 | if result is None: | |
e5f30ade | 3413 | self._downloader.report_error(u'unable to extract video url') |
59ae15a5 | 3414 | return |
bec102a8 | 3415 | video_url = compat_urllib_parse.unquote(result.group(1)) |
59ae15a5 PH |
3416 | |
3417 | result = re.search(self.VIDEO_TITLE_RE, webpage) | |
3418 | if result is None: | |
e5f30ade | 3419 | self._downloader.report_error(u'unable to extract video title') |
59ae15a5 | 3420 | return |
bec102a8 | 3421 | video_title = result.group(1) |
59ae15a5 PH |
3422 | |
3423 | result = re.search(self.VIDEO_THUMB_RE, webpage) | |
3424 | if result is None: | |
e5f30ade | 3425 | self._downloader.report_error(u'unable to extract video thumbnail') |
59ae15a5 | 3426 | return |
bec102a8 | 3427 | video_thumbnail = result.group(1) |
59ae15a5 PH |
3428 | |
3429 | return [{ | |
3430 | 'id': video_id, | |
3431 | 'url': video_url, | |
3432 | 'uploader': None, | |
3433 | 'upload_date': None, | |
3434 | 'title': video_title, | |
3435 | 'ext': 'flv', | |
3436 | 'thumbnail': video_thumbnail, | |
3437 | 'description': None, | |
3438 | }] | |
fd873c69 FV |
3439 | |
3440 | ||
d443aca8 | 3441 | class GooglePlusIE(InfoExtractor): |
59ae15a5 PH |
3442 | """Information extractor for plus.google.com.""" |
3443 | ||
93702113 | 3444 | _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)' |
59ae15a5 PH |
3445 | IE_NAME = u'plus.google' |
3446 | ||
3447 | def __init__(self, downloader=None): | |
3448 | InfoExtractor.__init__(self, downloader) | |
3449 | ||
3450 | def report_extract_entry(self, url): | |
3451 | """Report downloading extry""" | |
93702113 | 3452 | self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url) |
59ae15a5 PH |
3453 | |
3454 | def report_date(self, upload_date): | |
3455 | """Report downloading extry""" | |
3456 | self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date) | |
3457 | ||
3458 | def report_uploader(self, uploader): | |
3459 | """Report downloading extry""" | |
93702113 | 3460 | self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader) |
59ae15a5 PH |
3461 | |
3462 | def report_title(self, video_title): | |
3463 | """Report downloading extry""" | |
93702113 | 3464 | self._downloader.to_screen(u'[plus.google] Title: %s' % video_title) |
59ae15a5 PH |
3465 | |
3466 | def report_extract_vid_page(self, video_page): | |
3467 | """Report information extraction.""" | |
93702113 | 3468 | self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page) |
59ae15a5 PH |
3469 | |
3470 | def _real_extract(self, url): | |
3471 | # Extract id from URL | |
3472 | mobj = re.match(self._VALID_URL, url) | |
3473 | if mobj is None: | |
e5f30ade | 3474 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
3475 | return |
3476 | ||
3477 | post_url = mobj.group(0) | |
93702113 | 3478 | video_id = mobj.group(1) |
59ae15a5 PH |
3479 | |
3480 | video_extension = 'flv' | |
3481 | ||
3482 | # Step 1, Retrieve post webpage to extract further information | |
3483 | self.report_extract_entry(post_url) | |
3484 | request = compat_urllib_request.Request(post_url) | |
3485 | try: | |
93702113 | 3486 | webpage = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 | 3487 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 3488 | self._downloader.report_error(u'Unable to retrieve entry webpage: %s' % compat_str(err)) |
59ae15a5 PH |
3489 | return |
3490 | ||
3491 | # Extract update date | |
3492 | upload_date = None | |
3493 | pattern = 'title="Timestamp">(.*?)</a>' | |
3494 | mobj = re.search(pattern, webpage) | |
3495 | if mobj: | |
3496 | upload_date = mobj.group(1) | |
3497 | # Convert timestring to a format suitable for filename | |
3498 | upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") | |
3499 | upload_date = upload_date.strftime('%Y%m%d') | |
3500 | self.report_date(upload_date) | |
3501 | ||
3502 | # Extract uploader | |
3503 | uploader = None | |
3504 | pattern = r'rel\="author".*?>(.*?)</a>' | |
3505 | mobj = re.search(pattern, webpage) | |
3506 | if mobj: | |
3507 | uploader = mobj.group(1) | |
3508 | self.report_uploader(uploader) | |
3509 | ||
3510 | # Extract title | |
3511 | # Get the first line for title | |
3512 | video_title = u'NA' | |
3513 | pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]' | |
3514 | mobj = re.search(pattern, webpage) | |
3515 | if mobj: | |
3516 | video_title = mobj.group(1) | |
3517 | self.report_title(video_title) | |
3518 | ||
3519 | # Step 2, Stimulate clicking the image box to launch video | |
3520 | pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]' | |
3521 | mobj = re.search(pattern, webpage) | |
3522 | if mobj is None: | |
e5f30ade | 3523 | self._downloader.report_error(u'unable to extract video page URL') |
59ae15a5 PH |
3524 | |
3525 | video_page = mobj.group(1) | |
3526 | request = compat_urllib_request.Request(video_page) | |
3527 | try: | |
93702113 | 3528 | webpage = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 | 3529 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 3530 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
3531 | return |
3532 | self.report_extract_vid_page(video_page) | |
3533 | ||
3534 | ||
3535 | # Extract video links on video page | |
3536 | """Extract video links of all sizes""" | |
3537 | pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"' | |
3538 | mobj = re.findall(pattern, webpage) | |
3539 | if len(mobj) == 0: | |
e5f30ade | 3540 | self._downloader.report_error(u'unable to extract video links') |
59ae15a5 PH |
3541 | |
3542 | # Sort in resolution | |
3543 | links = sorted(mobj) | |
3544 | ||
3545 | # Choose the lowest of the sort, i.e. highest resolution | |
3546 | video_url = links[-1] | |
3547 | # Only get the url. The resolution part in the tuple has no use anymore | |
3548 | video_url = video_url[-1] | |
3549 | # Treat escaped \u0026 style hex | |
93702113 FV |
3550 | try: |
3551 | video_url = video_url.decode("unicode_escape") | |
3552 | except AttributeError: # Python 3 | |
3553 | video_url = bytes(video_url, 'ascii').decode('unicode-escape') | |
59ae15a5 PH |
3554 | |
3555 | ||
3556 | return [{ | |
93702113 | 3557 | 'id': video_id, |
59ae15a5 | 3558 | 'url': video_url, |
93702113 FV |
3559 | 'uploader': uploader, |
3560 | 'upload_date': upload_date, | |
3561 | 'title': video_title, | |
3562 | 'ext': video_extension, | |
59ae15a5 | 3563 | }] |
4cc3d074 PH |
3564 | |
3565 | class NBAIE(InfoExtractor): | |
3566 | _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$' | |
3567 | IE_NAME = u'nba' | |
3568 | ||
4cc3d074 PH |
3569 | def _real_extract(self, url): |
3570 | mobj = re.match(self._VALID_URL, url) | |
3571 | if mobj is None: | |
e5f30ade | 3572 | self._downloader.report_error(u'invalid URL: %s' % url) |
4cc3d074 PH |
3573 | return |
3574 | ||
3575 | video_id = mobj.group(1) | |
3576 | if video_id.endswith('/index.html'): | |
3577 | video_id = video_id[:-len('/index.html')] | |
3578 | ||
5f955171 | 3579 | webpage = self._download_webpage(url, video_id) |
4cc3d074 PH |
3580 | |
3581 | video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' | |
3582 | def _findProp(rexp, default=None): | |
3583 | m = re.search(rexp, webpage) | |
3584 | if m: | |
3585 | return unescapeHTML(m.group(1)) | |
3586 | else: | |
3587 | return default | |
3588 | ||
3589 | shortened_video_id = video_id.rpartition('/')[2] | |
3590 | title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '') | |
3591 | info = { | |
3592 | 'id': shortened_video_id, | |
3593 | 'url': video_url, | |
3594 | 'ext': 'mp4', | |
3595 | 'title': title, | |
3596 | 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'), | |
3597 | 'description': _findProp(r'<div class="description">(.*?)</h1>'), | |
3598 | } | |
3599 | return [info] | |
0b40544f DV |
3600 | |
3601 | class JustinTVIE(InfoExtractor): | |
3602 | """Information extractor for justin.tv and twitch.tv""" | |
2ab1c5ed DV |
3603 | # TODO: One broadcast may be split into multiple videos. The key |
3604 | # 'broadcast_id' is the same for all parts, and 'broadcast_part' | |
3605 | # starts at 1 and increases. Can we treat all parts as one video? | |
3606 | ||
4096b609 DV |
3607 | _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/ |
3608 | ([^/]+)(?:/b/([^/]+))?/?(?:\#.*)?$""" | |
3609 | _JUSTIN_PAGE_LIMIT = 100 | |
0b40544f DV |
3610 | IE_NAME = u'justin.tv' |
3611 | ||
3612 | def report_extraction(self, file_id): | |
3613 | """Report information extraction.""" | |
3614 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) | |
3615 | ||
4096b609 DV |
3616 | def report_download_page(self, channel, offset): |
3617 | """Report attempt to download a single page of videos.""" | |
3618 | self._downloader.to_screen(u'[%s] %s: Downloading video information from %d to %d' % | |
3619 | (self.IE_NAME, channel, offset, offset + self._JUSTIN_PAGE_LIMIT)) | |
3620 | ||
2ab1c5ed DV |
3621 | # Return count of items, list of *valid* items |
3622 | def _parse_page(self, url): | |
0b40544f | 3623 | try: |
2ab1c5ed | 3624 | urlh = compat_urllib_request.urlopen(url) |
0b40544f DV |
3625 | webpage_bytes = urlh.read() |
3626 | webpage = webpage_bytes.decode('utf-8', 'ignore') | |
3627 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 3628 | self._downloader.report_error(u'unable to download video info JSON: %s' % compat_str(err)) |
0b40544f | 3629 | return |
cdb30764 | 3630 | |
0b40544f | 3631 | response = json.loads(webpage) |
fa1bf9c6 | 3632 | if type(response) != list: |
3633 | error_text = response.get('error', 'unknown error') | |
e5f30ade | 3634 | self._downloader.report_error(u'Justin.tv API: %s' % error_text) |
fa1bf9c6 | 3635 | return |
0b40544f DV |
3636 | info = [] |
3637 | for clip in response: | |
3638 | video_url = clip['video_file_url'] | |
3639 | if video_url: | |
3640 | video_extension = os.path.splitext(video_url)[1][1:] | |
fa1bf9c6 | 3641 | video_date = re.sub('-', '', clip['start_time'][:10]) |
3642 | video_uploader_id = clip.get('user_id', clip.get('channel_id')) | |
97f194c1 PH |
3643 | video_id = clip['id'] |
3644 | video_title = clip.get('title', video_id) | |
0b40544f | 3645 | info.append({ |
97f194c1 | 3646 | 'id': video_id, |
0b40544f | 3647 | 'url': video_url, |
97f194c1 | 3648 | 'title': video_title, |
fa1bf9c6 | 3649 | 'uploader': clip.get('channel_name', video_uploader_id), |
3650 | 'uploader_id': video_uploader_id, | |
0b40544f DV |
3651 | 'upload_date': video_date, |
3652 | 'ext': video_extension, | |
3653 | }) | |
2ab1c5ed DV |
3654 | return (len(response), info) |
3655 | ||
3656 | def _real_extract(self, url): | |
3657 | mobj = re.match(self._VALID_URL, url) | |
3658 | if mobj is None: | |
e5f30ade | 3659 | self._downloader.report_error(u'invalid URL: %s' % url) |
2ab1c5ed | 3660 | return |
cdb30764 | 3661 | |
2ab1c5ed DV |
3662 | api = 'http://api.justin.tv' |
3663 | video_id = mobj.group(mobj.lastindex) | |
3664 | paged = False | |
3665 | if mobj.lastindex == 1: | |
3666 | paged = True | |
3667 | api += '/channel/archives/%s.json' | |
3668 | else: | |
fa1bf9c6 | 3669 | api += '/broadcast/by_archive/%s.json' |
2ab1c5ed | 3670 | api = api % (video_id,) |
cdb30764 | 3671 | |
2ab1c5ed | 3672 | self.report_extraction(video_id) |
cdb30764 | 3673 | |
2ab1c5ed DV |
3674 | info = [] |
3675 | offset = 0 | |
4096b609 DV |
3676 | limit = self._JUSTIN_PAGE_LIMIT |
3677 | while True: | |
3678 | if paged: | |
3679 | self.report_download_page(video_id, offset) | |
2ab1c5ed DV |
3680 | page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) |
3681 | page_count, page_info = self._parse_page(page_url) | |
3682 | info.extend(page_info) | |
3683 | if not paged or page_count != limit: | |
3684 | break | |
3685 | offset += limit | |
0b40544f | 3686 | return info |
21a9c6aa PH |
3687 | |
3688 | class FunnyOrDieIE(InfoExtractor): | |
3689 | _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$' | |
21a9c6aa | 3690 | |
21a9c6aa PH |
3691 | def _real_extract(self, url): |
3692 | mobj = re.match(self._VALID_URL, url) | |
3693 | if mobj is None: | |
e5f30ade | 3694 | self._downloader.report_error(u'invalid URL: %s' % url) |
21a9c6aa PH |
3695 | return |
3696 | ||
3697 | video_id = mobj.group('id') | |
5f955171 | 3698 | webpage = self._download_webpage(url, video_id) |
21a9c6aa PH |
3699 | |
3700 | m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL) | |
3701 | if not m: | |
e5f30ade | 3702 | self._downloader.report_error(u'unable to find video information') |
21a9c6aa | 3703 | video_url = unescapeHTML(m.group('url')) |
21a9c6aa | 3704 | |
7decf895 | 3705 | m = re.search(r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", webpage, flags=re.DOTALL) |
21a9c6aa | 3706 | if not m: |
bfdf4692 PH |
3707 | m = re.search(r'<title>(?P<title>[^<]+?)</title>', webpage) |
3708 | if not m: | |
3709 | self._downloader.trouble(u'Cannot find video title') | |
7decf895 | 3710 | title = clean_html(m.group('title')) |
21a9c6aa PH |
3711 | |
3712 | m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage) | |
3713 | if m: | |
3714 | desc = unescapeHTML(m.group('desc')) | |
3715 | else: | |
3716 | desc = None | |
3717 | ||
3718 | info = { | |
3719 | 'id': video_id, | |
3720 | 'url': video_url, | |
3721 | 'ext': 'mp4', | |
3722 | 'title': title, | |
3723 | 'description': desc, | |
3724 | } | |
3725 | return [info] | |
d0d4f277 | 3726 | |
e314ba67 | 3727 | class SteamIE(InfoExtractor): |
6324fd1d | 3728 | _VALID_URL = r"""http://store.steampowered.com/ |
e314ba67 JMF |
3729 | (?P<urltype>video|app)/ #If the page is only for videos or for a game |
3730 | (?P<gameID>\d+)/? | |
3731 | (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID | |
3732 | """ | |
4aeae91f | 3733 | |
89de9eb1 FV |
3734 | @classmethod |
3735 | def suitable(cls, url): | |
e314ba67 | 3736 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 | 3737 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None |
5f955171 | 3738 | |
e314ba67 JMF |
3739 | def _real_extract(self, url): |
3740 | m = re.match(self._VALID_URL, url, re.VERBOSE) | |
3741 | urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\}," | |
3742 | gameID = m.group('gameID') | |
3743 | videourl = 'http://store.steampowered.com/video/%s/' % gameID | |
5f955171 | 3744 | webpage = self._download_webpage(videourl, gameID) |
e314ba67 | 3745 | mweb = re.finditer(urlRE, webpage) |
5e9d042d JMF |
3746 | namesRE = r'<span class="title">(?P<videoName>.+?)</span>' |
3747 | titles = re.finditer(namesRE, webpage) | |
60bd48b1 JMF |
3748 | thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">' |
3749 | thumbs = re.finditer(thumbsRE, webpage) | |
e314ba67 | 3750 | videos = [] |
60bd48b1 | 3751 | for vid,vtitle,thumb in zip(mweb,titles,thumbs): |
e314ba67 | 3752 | video_id = vid.group('videoID') |
5f955171 PH |
3753 | title = vtitle.group('videoName') |
3754 | video_url = vid.group('videoURL') | |
60bd48b1 | 3755 | video_thumb = thumb.group('thumbnail') |
e314ba67 | 3756 | if not video_url: |
e5f30ade | 3757 | self._downloader.report_error(u'Cannot find video url for %s' % video_id) |
e314ba67 JMF |
3758 | info = { |
3759 | 'id':video_id, | |
3760 | 'url':video_url, | |
3761 | 'ext': 'flv', | |
60bd48b1 JMF |
3762 | 'title': unescapeHTML(title), |
3763 | 'thumbnail': video_thumb | |
e314ba67 JMF |
3764 | } |
3765 | videos.append(info) | |
3766 | return videos | |
ef0c8d5f | 3767 | |
278986ea | 3768 | class UstreamIE(InfoExtractor): |
ef0c8d5f | 3769 | _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)' |
278986ea | 3770 | IE_NAME = u'ustream' |
ef0c8d5f | 3771 | |
278986ea JMF |
3772 | def _real_extract(self, url): |
3773 | m = re.match(self._VALID_URL, url) | |
3774 | video_id = m.group('videoID') | |
3775 | video_url = u'http://tcdn.ustream.tv/video/%s' % video_id | |
d830b7c2 | 3776 | webpage = self._download_webpage(url, video_id) |
278986ea JMF |
3777 | m = re.search(r'data-title="(?P<title>.+)"',webpage) |
3778 | title = m.group('title') | |
3779 | m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage) | |
3780 | uploader = m.group('uploader') | |
3781 | info = { | |
3782 | 'id':video_id, | |
3783 | 'url':video_url, | |
3784 | 'ext': 'flv', | |
3785 | 'title': title, | |
3786 | 'uploader': uploader | |
3787 | } | |
3788 | return [info] | |
4aeae91f | 3789 | |
40634747 | 3790 | class WorldStarHipHopIE(InfoExtractor): |
64c78d50 | 3791 | _VALID_URL = r'http://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)' |
40634747 JMS |
3792 | IE_NAME = u'WorldStarHipHop' |
3793 | ||
3794 | def _real_extract(self, url): | |
40634747 JMS |
3795 | _src_url = r"""(http://hw-videos.*(?:mp4|flv))""" |
3796 | ||
3b221c54 | 3797 | webpage_src = compat_urllib_request.urlopen(url).read() |
b3bcca08 | 3798 | webpage_src = webpage_src.decode('utf-8') |
40634747 JMS |
3799 | |
3800 | mobj = re.search(_src_url, webpage_src) | |
3801 | ||
08ec0af7 JMS |
3802 | m = re.match(self._VALID_URL, url) |
3803 | video_id = m.group('id') | |
3804 | ||
40634747 JMS |
3805 | if mobj is not None: |
3806 | video_url = mobj.group() | |
3807 | if 'mp4' in video_url: | |
b3bcca08 | 3808 | ext = 'mp4' |
40634747 | 3809 | else: |
b3bcca08 | 3810 | ext = 'flv' |
40634747 | 3811 | else: |
08ec0af7 JMS |
3812 | self._downloader.trouble(u'ERROR: Cannot find video url for %s' % video_id) |
3813 | return | |
40634747 JMS |
3814 | |
3815 | _title = r"""<title>(.*)</title>""" | |
3816 | ||
3817 | mobj = re.search(_title, webpage_src) | |
fa41fbd3 | 3818 | |
40634747 JMS |
3819 | if mobj is not None: |
3820 | title = mobj.group(1) | |
40634747 | 3821 | else: |
b3bcca08 | 3822 | title = 'World Start Hip Hop - %s' % time.ctime() |
40634747 JMS |
3823 | |
3824 | _thumbnail = r"""rel="image_src" href="(.*)" />""" | |
40634747 JMS |
3825 | mobj = re.search(_thumbnail, webpage_src) |
3826 | ||
3827 | # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video. | |
3828 | if mobj is not None: | |
3829 | thumbnail = mobj.group(1) | |
3830 | else: | |
3831 | _title = r"""candytitles.*>(.*)</span>""" | |
3832 | mobj = re.search(_title, webpage_src) | |
3833 | if mobj is not None: | |
3834 | title = mobj.group(1) | |
3835 | thumbnail = None | |
fa41fbd3 | 3836 | |
b3bcca08 | 3837 | results = [{ |
64c78d50 | 3838 | 'id': video_id, |
b3bcca08 JMS |
3839 | 'url' : video_url, |
3840 | 'title' : title, | |
3841 | 'thumbnail' : thumbnail, | |
3842 | 'ext' : ext, | |
3843 | }] | |
40634747 JMS |
3844 | return results |
3845 | ||
ca0a0bbe PH |
3846 | class RBMARadioIE(InfoExtractor): |
3847 | _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$' | |
3848 | ||
3849 | def _real_extract(self, url): | |
3850 | m = re.match(self._VALID_URL, url) | |
3851 | video_id = m.group('videoID') | |
3852 | ||
3853 | webpage = self._download_webpage(url, video_id) | |
3854 | m = re.search(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>', webpage) | |
3855 | if not m: | |
3856 | raise ExtractorError(u'Cannot find metadata') | |
3857 | json_data = m.group(1) | |
3858 | ||
3859 | try: | |
3860 | data = json.loads(json_data) | |
3861 | except ValueError as e: | |
3862 | raise ExtractorError(u'Invalid JSON: ' + str(e)) | |
3863 | ||
3864 | video_url = data['akamai_url'] + '&cbr=256' | |
3865 | url_parts = compat_urllib_parse_urlparse(video_url) | |
3866 | video_ext = url_parts.path.rpartition('.')[2] | |
3867 | info = { | |
3868 | 'id': video_id, | |
3869 | 'url': video_url, | |
3870 | 'ext': video_ext, | |
3871 | 'title': data['title'], | |
3872 | 'description': data.get('teaser_text'), | |
3873 | 'location': data.get('country_of_origin'), | |
3874 | 'uploader': data.get('host', {}).get('name'), | |
3875 | 'uploader_id': data.get('host', {}).get('slug'), | |
187f491a | 3876 | 'thumbnail': data.get('image', {}).get('large_url_2x'), |
ca0a0bbe PH |
3877 | 'duration': data.get('duration'), |
3878 | } | |
3879 | return [info] | |
4aeae91f | 3880 | |
991ba7fa JC |
3881 | |
3882 | class YouPornIE(InfoExtractor): | |
3883 | """Information extractor for youporn.com.""" | |
991ba7fa | 3884 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)' |
6324fd1d | 3885 | |
991ba7fa JC |
3886 | def _print_formats(self, formats): |
3887 | """Print all available formats""" | |
565f7519 | 3888 | print(u'Available formats:') |
ca6710ee JC |
3889 | print(u'ext\t\tformat') |
3890 | print(u'---------------------------------') | |
991ba7fa | 3891 | for format in formats: |
ca6710ee | 3892 | print(u'%s\t\t%s' % (format['ext'], format['format'])) |
991ba7fa JC |
3893 | |
3894 | def _specific(self, req_format, formats): | |
3895 | for x in formats: | |
3896 | if(x["format"]==req_format): | |
3897 | return x | |
3898 | return None | |
3899 | ||
991ba7fa JC |
3900 | def _real_extract(self, url): |
3901 | mobj = re.match(self._VALID_URL, url) | |
3902 | if mobj is None: | |
e5f30ade | 3903 | self._downloader.report_error(u'invalid URL: %s' % url) |
991ba7fa JC |
3904 | return |
3905 | ||
ca6710ee | 3906 | video_id = mobj.group('videoid') |
991ba7fa | 3907 | |
629fcdd1 PH |
3908 | req = compat_urllib_request.Request(url) |
3909 | req.add_header('Cookie', 'age_verified=1') | |
3910 | webpage = self._download_webpage(req, video_id) | |
991ba7fa JC |
3911 | |
3912 | # Get the video title | |
e711babb | 3913 | result = re.search(r'<h1.*?>(?P<title>.*)</h1>', webpage) |
991ba7fa | 3914 | if result is None: |
e711babb | 3915 | raise ExtractorError(u'Unable to extract video title') |
ca6710ee | 3916 | video_title = result.group('title').strip() |
991ba7fa JC |
3917 | |
3918 | # Get the video date | |
e711babb | 3919 | result = re.search(r'Date:</label>(?P<date>.*) </li>', webpage) |
991ba7fa | 3920 | if result is None: |
2e5457be | 3921 | self._downloader.report_warning(u'unable to extract video date') |
629fcdd1 PH |
3922 | upload_date = None |
3923 | else: | |
3924 | upload_date = result.group('date').strip() | |
991ba7fa JC |
3925 | |
3926 | # Get the video uploader | |
e711babb | 3927 | result = re.search(r'Submitted:</label>(?P<uploader>.*)</li>', webpage) |
991ba7fa | 3928 | if result is None: |
2e5457be | 3929 | self._downloader.report_warning(u'unable to extract uploader') |
629fcdd1 PH |
3930 | video_uploader = None |
3931 | else: | |
3932 | video_uploader = result.group('uploader').strip() | |
3933 | video_uploader = clean_html( video_uploader ) | |
991ba7fa JC |
3934 | |
3935 | # Get all of the formats available | |
ca6710ee JC |
3936 | DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' |
3937 | result = re.search(DOWNLOAD_LIST_RE, webpage) | |
991ba7fa | 3938 | if result is None: |
629fcdd1 | 3939 | raise ExtractorError(u'Unable to extract download list') |
ca6710ee | 3940 | download_list_html = result.group('download_list').strip() |
991ba7fa JC |
3941 | |
3942 | # Get all of the links from the page | |
ca6710ee JC |
3943 | LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">' |
3944 | links = re.findall(LINK_RE, download_list_html) | |
991ba7fa | 3945 | if(len(links) == 0): |
629fcdd1 | 3946 | raise ExtractorError(u'ERROR: no known formats available for video') |
6324fd1d FV |
3947 | |
3948 | self._downloader.to_screen(u'[youporn] Links found: %d' % len(links)) | |
991ba7fa JC |
3949 | |
3950 | formats = [] | |
3951 | for link in links: | |
3952 | ||
3953 | # A link looks like this: | |
3954 | # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0 | |
3955 | # A path looks like this: | |
3956 | # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4 | |
ca6710ee JC |
3957 | video_url = unescapeHTML( link ) |
3958 | path = compat_urllib_parse_urlparse( video_url ).path | |
991ba7fa JC |
3959 | extension = os.path.splitext( path )[1][1:] |
3960 | format = path.split('/')[4].split('_')[:2] | |
3961 | size = format[0] | |
3962 | bitrate = format[1] | |
3963 | format = "-".join( format ) | |
3964 | title = u'%s-%s-%s' % (video_title, size, bitrate) | |
3965 | ||
3966 | formats.append({ | |
3967 | 'id': video_id, | |
3968 | 'url': video_url, | |
3969 | 'uploader': video_uploader, | |
3970 | 'upload_date': upload_date, | |
3971 | 'title': title, | |
3972 | 'ext': extension, | |
3973 | 'format': format, | |
3974 | 'thumbnail': None, | |
3975 | 'description': None, | |
3976 | 'player_url': None | |
3977 | }) | |
3978 | ||
3979 | if self._downloader.params.get('listformats', None): | |
3980 | self._print_formats(formats) | |
3981 | return | |
3982 | ||
3983 | req_format = self._downloader.params.get('format', None) | |
991ba7fa JC |
3984 | self._downloader.to_screen(u'[youporn] Format: %s' % req_format) |
3985 | ||
991ba7fa JC |
3986 | if req_format is None or req_format == 'best': |
3987 | return [formats[0]] | |
3988 | elif req_format == 'worst': | |
3989 | return [formats[-1]] | |
3990 | elif req_format in ('-1', 'all'): | |
3991 | return formats | |
3992 | else: | |
3993 | format = self._specific( req_format, formats ) | |
3994 | if result is None: | |
e5f30ade | 3995 | self._downloader.report_error(u'requested format not available') |
991ba7fa JC |
3996 | return |
3997 | return [format] | |
3998 | ||
6324fd1d | 3999 | |
991ba7fa JC |
4000 | |
4001 | class PornotubeIE(InfoExtractor): | |
4002 | """Information extractor for pornotube.com.""" | |
991ba7fa | 4003 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' |
991ba7fa | 4004 | |
991ba7fa JC |
4005 | def _real_extract(self, url): |
4006 | mobj = re.match(self._VALID_URL, url) | |
4007 | if mobj is None: | |
e5f30ade | 4008 | self._downloader.report_error(u'invalid URL: %s' % url) |
991ba7fa JC |
4009 | return |
4010 | ||
ca6710ee JC |
4011 | video_id = mobj.group('videoid') |
4012 | video_title = mobj.group('title') | |
991ba7fa JC |
4013 | |
4014 | # Get webpage content | |
ca6710ee | 4015 | webpage = self._download_webpage(url, video_id) |
991ba7fa JC |
4016 | |
4017 | # Get the video URL | |
ca6710ee JC |
4018 | VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' |
4019 | result = re.search(VIDEO_URL_RE, webpage) | |
991ba7fa | 4020 | if result is None: |
e5f30ade | 4021 | self._downloader.report_error(u'unable to extract video url') |
991ba7fa | 4022 | return |
ca6710ee | 4023 | video_url = compat_urllib_parse.unquote(result.group('url')) |
991ba7fa JC |
4024 | |
4025 | #Get the uploaded date | |
ca6710ee JC |
4026 | VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' |
4027 | result = re.search(VIDEO_UPLOADED_RE, webpage) | |
991ba7fa | 4028 | if result is None: |
e5f30ade | 4029 | self._downloader.report_error(u'unable to extract video title') |
991ba7fa | 4030 | return |
ca6710ee | 4031 | upload_date = result.group('date') |
991ba7fa JC |
4032 | |
4033 | info = {'id': video_id, | |
4034 | 'url': video_url, | |
4035 | 'uploader': None, | |
4036 | 'upload_date': upload_date, | |
4037 | 'title': video_title, | |
4038 | 'ext': 'flv', | |
565f7519 | 4039 | 'format': 'flv'} |
991ba7fa JC |
4040 | |
4041 | return [info] | |
4042 | ||
991ba7fa JC |
4043 | class YouJizzIE(InfoExtractor): |
4044 | """Information extractor for youjizz.com.""" | |
ca6710ee | 4045 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$' |
991ba7fa | 4046 | |
991ba7fa | 4047 | def _real_extract(self, url): |
ca6710ee JC |
4048 | mobj = re.match(self._VALID_URL, url) |
4049 | if mobj is None: | |
e5f30ade | 4050 | self._downloader.report_error(u'invalid URL: %s' % url) |
991ba7fa | 4051 | return |
ca6710ee JC |
4052 | |
4053 | video_id = mobj.group('videoid') | |
4054 | ||
4055 | # Get webpage content | |
4056 | webpage = self._download_webpage(url, video_id) | |
991ba7fa JC |
4057 | |
4058 | # Get the video title | |
db16276b | 4059 | result = re.search(r'<title>(?P<title>.*)</title>', webpage) |
991ba7fa | 4060 | if result is None: |
db16276b | 4061 | raise ExtractorError(u'ERROR: unable to extract video title') |
ca6710ee | 4062 | video_title = result.group('title').strip() |
991ba7fa JC |
4063 | |
4064 | # Get the embed page | |
db16276b | 4065 | result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage) |
991ba7fa | 4066 | if result is None: |
db16276b | 4067 | raise ExtractorError(u'ERROR: unable to extract embed page') |
991ba7fa | 4068 | |
ca6710ee JC |
4069 | embed_page_url = result.group(0).strip() |
4070 | video_id = result.group('videoid') | |
6324fd1d | 4071 | |
ca6710ee JC |
4072 | webpage = self._download_webpage(embed_page_url, video_id) |
4073 | ||
991ba7fa | 4074 | # Get the video URL |
db16276b | 4075 | result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', webpage) |
991ba7fa | 4076 | if result is None: |
db16276b | 4077 | raise ExtractorError(u'ERROR: unable to extract video url') |
ca6710ee | 4078 | video_url = result.group('source') |
991ba7fa JC |
4079 | |
4080 | info = {'id': video_id, | |
4081 | 'url': video_url, | |
991ba7fa JC |
4082 | 'title': video_title, |
4083 | 'ext': 'flv', | |
4084 | 'format': 'flv', | |
991ba7fa JC |
4085 | 'player_url': embed_page_url} |
4086 | ||
4087 | return [info] | |
4088 | ||
ccf65f9d PH |
4089 | class EightTracksIE(InfoExtractor): |
4090 | IE_NAME = '8tracks' | |
25580f32 | 4091 | _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' |
ccf65f9d PH |
4092 | |
4093 | def _real_extract(self, url): | |
4094 | mobj = re.match(self._VALID_URL, url) | |
4095 | if mobj is None: | |
4096 | raise ExtractorError(u'Invalid URL: %s' % url) | |
4097 | playlist_id = mobj.group('id') | |
4098 | ||
4099 | webpage = self._download_webpage(url, playlist_id) | |
4100 | ||
2a9983b7 | 4101 | m = re.search(r"PAGE.mix = (.*?);\n", webpage, flags=re.DOTALL) |
ccf65f9d PH |
4102 | if not m: |
4103 | raise ExtractorError(u'Cannot find trax information') | |
4104 | json_like = m.group(1) | |
4105 | data = json.loads(json_like) | |
4106 | ||
4107 | session = str(random.randint(0, 1000000000)) | |
4108 | mix_id = data['id'] | |
4109 | track_count = data['tracks_count'] | |
4110 | first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) | |
4111 | next_url = first_url | |
4112 | res = [] | |
4113 | for i in itertools.count(): | |
4114 | api_json = self._download_webpage(next_url, playlist_id, | |
4115 | note=u'Downloading song information %s/%s' % (str(i+1), track_count), | |
4116 | errnote=u'Failed to download song information') | |
4117 | api_data = json.loads(api_json) | |
4118 | track_data = api_data[u'set']['track'] | |
4119 | info = { | |
4120 | 'id': track_data['id'], | |
4121 | 'url': track_data['track_file_stream_url'], | |
da4de959 PH |
4122 | 'title': track_data['performer'] + u' - ' + track_data['name'], |
4123 | 'raw_title': track_data['name'], | |
4124 | 'uploader_id': data['user']['login'], | |
ccf65f9d PH |
4125 | 'ext': 'm4a', |
4126 | } | |
4127 | res.append(info) | |
4128 | if api_data['set']['at_last_track']: | |
4129 | break | |
4130 | next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id']) | |
4131 | return res | |
991ba7fa | 4132 | |
da06e2da OK |
4133 | class KeekIE(InfoExtractor): |
4134 | _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)' | |
4135 | IE_NAME = u'keek' | |
4136 | ||
4137 | def _real_extract(self, url): | |
4138 | m = re.match(self._VALID_URL, url) | |
4139 | video_id = m.group('videoID') | |
4140 | video_url = u'http://cdn.keek.com/keek/video/%s' % video_id | |
4141 | thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id | |
4142 | webpage = self._download_webpage(url, video_id) | |
f4381ab8 | 4143 | m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage) |
f0877a44 | 4144 | title = unescapeHTML(m.group('title')) |
f10b2a9c FV |
4145 | m = re.search(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', webpage) |
4146 | uploader = clean_html(m.group('uploader')) | |
da06e2da | 4147 | info = { |
f10b2a9c FV |
4148 | 'id': video_id, |
4149 | 'url': video_url, | |
da06e2da OK |
4150 | 'ext': 'mp4', |
4151 | 'title': title, | |
4152 | 'thumbnail': thumbnail, | |
4153 | 'uploader': uploader | |
f0877a44 | 4154 | } |
da06e2da OK |
4155 | return [info] |
4156 | ||
3a468f2d | 4157 | class TEDIE(InfoExtractor): |
414638cd JMF |
4158 | _VALID_URL=r'''http://www.ted.com/ |
4159 | ( | |
4160 | ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist | |
4161 | | | |
4162 | ((?P<type_talk>talks)) # We have a simple talk | |
4163 | ) | |
4164 | /(?P<name>\w+) # Here goes the name and then ".html" | |
4165 | ''' | |
4166 | ||
89de9eb1 FV |
4167 | @classmethod |
4168 | def suitable(cls, url): | |
414638cd | 4169 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 | 4170 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None |
414638cd | 4171 | |
3a468f2d | 4172 | def _real_extract(self, url): |
414638cd JMF |
4173 | m=re.match(self._VALID_URL, url, re.VERBOSE) |
4174 | if m.group('type_talk'): | |
4175 | return [self._talk_info(url)] | |
4176 | else : | |
4177 | playlist_id=m.group('playlist_id') | |
4178 | name=m.group('name') | |
4179 | self._downloader.to_screen(u'[%s] Getting info of playlist %s: "%s"' % (self.IE_NAME,playlist_id,name)) | |
4180 | return self._playlist_videos_info(url,name,playlist_id) | |
4181 | ||
4182 | def _talk_video_link(self,mediaSlug): | |
4183 | '''Returns the video link for that mediaSlug''' | |
4184 | return 'http://download.ted.com/talks/%s.mp4' % mediaSlug | |
4185 | ||
4186 | def _playlist_videos_info(self,url,name,playlist_id=0): | |
4187 | '''Returns the videos of the playlist''' | |
4188 | video_RE=r''' | |
4189 | <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)" | |
4190 | ([.\s]*?)data-playlist_item_id="(\d+)" | |
4191 | ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)" | |
4192 | ''' | |
c85538db | 4193 | video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>' |
414638cd JMF |
4194 | webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage') |
4195 | m_videos=re.finditer(video_RE,webpage,re.VERBOSE) | |
4196 | m_names=re.finditer(video_name_RE,webpage) | |
4197 | info=[] | |
4198 | for m_video, m_name in zip(m_videos,m_names): | |
c85538db JMF |
4199 | video_id=m_video.group('video_id') |
4200 | talk_url='http://www.ted.com%s' % m_name.group('talk_url') | |
4201 | info.append(self._talk_info(talk_url,video_id)) | |
414638cd | 4202 | return info |
c85538db | 4203 | |
414638cd JMF |
4204 | def _talk_info(self, url, video_id=0): |
4205 | """Return the video for the talk in the url""" | |
4206 | m=re.match(self._VALID_URL, url,re.VERBOSE) | |
4207 | videoName=m.group('name') | |
4208 | webpage=self._download_webpage(url, video_id, 'Downloading \"%s\" page' % videoName) | |
4209 | # If the url includes the language we get the title translated | |
7decf895 | 4210 | title_RE=r'<span id="altHeadline" >(?P<title>.*)</span>' |
3a468f2d JMF |
4211 | title=re.search(title_RE, webpage).group('title') |
4212 | info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?) | |
4213 | "id":(?P<videoID>[\d]+).*? | |
4214 | "mediaSlug":"(?P<mediaSlug>[\w\d]+?)"''' | |
c85538db JMF |
4215 | thumb_RE=r'</span>[\s.]*</div>[\s.]*<img src="(?P<thumbnail>.*?)"' |
4216 | thumb_match=re.search(thumb_RE,webpage) | |
3a468f2d JMF |
4217 | info_match=re.search(info_RE,webpage,re.VERBOSE) |
4218 | video_id=info_match.group('videoID') | |
4219 | mediaSlug=info_match.group('mediaSlug') | |
414638cd | 4220 | video_url=self._talk_video_link(mediaSlug) |
3a468f2d | 4221 | info = { |
414638cd JMF |
4222 | 'id': video_id, |
4223 | 'url': video_url, | |
3a468f2d | 4224 | 'ext': 'mp4', |
c85538db JMF |
4225 | 'title': title, |
4226 | 'thumbnail': thumb_match.group('thumbnail') | |
414638cd JMF |
4227 | } |
4228 | return info | |
da06e2da | 4229 | |
58994225 | 4230 | class MySpassIE(InfoExtractor): |
1ad5d872 | 4231 | _VALID_URL = r'http://www.myspass.de/.*' |
6324fd1d | 4232 | |
1ad5d872 | 4233 | def _real_extract(self, url): |
4234 | META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s' | |
58994225 | 4235 | |
1ad5d872 | 4236 | # video id is the last path element of the URL |
4237 | # usually there is a trailing slash, so also try the second but last | |
4238 | url_path = compat_urllib_parse_urlparse(url).path | |
4239 | url_parent_path, video_id = os.path.split(url_path) | |
4240 | if not video_id: | |
4241 | _, video_id = os.path.split(url_parent_path) | |
6324fd1d | 4242 | |
1ad5d872 | 4243 | # get metadata |
4244 | metadata_url = META_DATA_URL_TEMPLATE % video_id | |
4245 | metadata_text = self._download_webpage(metadata_url, video_id) | |
4246 | metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8')) | |
6324fd1d | 4247 | |
1ad5d872 | 4248 | # extract values from metadata |
4249 | url_flv_el = metadata.find('url_flv') | |
4250 | if url_flv_el is None: | |
e5f30ade | 4251 | self._downloader.report_error(u'unable to extract download url') |
1ad5d872 | 4252 | return |
4253 | video_url = url_flv_el.text | |
4254 | extension = os.path.splitext(video_url)[1][1:] | |
4255 | title_el = metadata.find('title') | |
4256 | if title_el is None: | |
e5f30ade | 4257 | self._downloader.report_error(u'unable to extract title') |
1ad5d872 | 4258 | return |
4259 | title = title_el.text | |
4260 | format_id_el = metadata.find('format_id') | |
4261 | if format_id_el is None: | |
4262 | format = ext | |
4263 | else: | |
4264 | format = format_id_el.text | |
4265 | description_el = metadata.find('description') | |
4266 | if description_el is not None: | |
4267 | description = description_el.text | |
4268 | else: | |
4269 | description = None | |
4270 | imagePreview_el = metadata.find('imagePreview') | |
4271 | if imagePreview_el is not None: | |
4272 | thumbnail = imagePreview_el.text | |
4273 | else: | |
4274 | thumbnail = None | |
4275 | info = { | |
4276 | 'id': video_id, | |
4277 | 'url': video_url, | |
4278 | 'title': title, | |
4279 | 'ext': extension, | |
4280 | 'format': format, | |
4281 | 'thumbnail': thumbnail, | |
4282 | 'description': description | |
4283 | } | |
4284 | return [info] | |
4285 | ||
e32b06e9 | 4286 | class SpiegelIE(InfoExtractor): |
1f46c152 | 4287 | _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$' |
e32b06e9 PH |
4288 | |
4289 | def _real_extract(self, url): | |
4290 | m = re.match(self._VALID_URL, url) | |
4291 | video_id = m.group('videoID') | |
4292 | ||
4293 | webpage = self._download_webpage(url, video_id) | |
4294 | m = re.search(r'<div class="spVideoTitle">(.*?)</div>', webpage) | |
4295 | if not m: | |
4296 | raise ExtractorError(u'Cannot find title') | |
4297 | video_title = unescapeHTML(m.group(1)) | |
4298 | ||
4299 | xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml' | |
4300 | xml_code = self._download_webpage(xml_url, video_id, | |
4301 | note=u'Downloading XML', errnote=u'Failed to download XML') | |
4302 | ||
4303 | idoc = xml.etree.ElementTree.fromstring(xml_code) | |
4304 | last_type = idoc[-1] | |
4305 | filename = last_type.findall('./filename')[0].text | |
4306 | duration = float(last_type.findall('./duration')[0].text) | |
4307 | ||
4308 | video_url = 'http://video2.spiegel.de/flash/' + filename | |
4309 | video_ext = filename.rpartition('.')[2] | |
4310 | info = { | |
4311 | 'id': video_id, | |
4312 | 'url': video_url, | |
4313 | 'ext': video_ext, | |
4314 | 'title': video_title, | |
4315 | 'duration': duration, | |
4316 | } | |
4317 | return [info] | |
4318 | ||
0cd35867 | 4319 | class LiveLeakIE(InfoExtractor): |
43113d92 | 4320 | |
0cd35867 | 4321 | _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)' |
43113d92 | 4322 | IE_NAME = u'liveleak' |
4323 | ||
4324 | def _real_extract(self, url): | |
4325 | mobj = re.match(self._VALID_URL, url) | |
4326 | if mobj is None: | |
4327 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
4328 | return | |
4329 | ||
0cd35867 | 4330 | video_id = mobj.group('video_id') |
43113d92 | 4331 | |
4332 | webpage = self._download_webpage(url, video_id) | |
4333 | ||
0cd35867 FV |
4334 | m = re.search(r'file: "(.*?)",', webpage) |
4335 | if not m: | |
4336 | self._downloader.report_error(u'unable to find video url') | |
4337 | return | |
4338 | video_url = m.group(1) | |
4339 | ||
43113d92 | 4340 | m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage) |
4341 | if not m: | |
4342 | self._downloader.trouble(u'Cannot find video title') | |
0cd35867 | 4343 | title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip() |
43113d92 | 4344 | |
4345 | m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage) | |
4346 | if m: | |
4347 | desc = unescapeHTML(m.group('desc')) | |
4348 | else: | |
4349 | desc = None | |
4350 | ||
0cd35867 FV |
4351 | m = re.search(r'By:.*?(\w+)</a>', webpage) |
4352 | if m: | |
4353 | uploader = clean_html(m.group(1)) | |
4354 | else: | |
4355 | uploader = None | |
43113d92 | 4356 | |
4357 | info = { | |
4358 | 'id': video_id, | |
4359 | 'url': video_url, | |
4360 | 'ext': 'mp4', | |
4361 | 'title': title, | |
0cd35867 FV |
4362 | 'description': desc, |
4363 | 'uploader': uploader | |
43113d92 | 4364 | } |
4365 | ||
4366 | return [info] | |
4367 | ||
df2dedee | 4368 | class ARDIE(InfoExtractor): |
b03d65c2 PH |
4369 | _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?' |
4370 | _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>' | |
df2dedee MW |
4371 | _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)' |
4372 | ||
4373 | def _real_extract(self, url): | |
4374 | # determine video id from url | |
4375 | m = re.match(self._VALID_URL, url) | |
b03d65c2 PH |
4376 | |
4377 | numid = re.search(r'documentId=([0-9]+)', url) | |
4378 | if numid: | |
4379 | video_id = numid.group(1) | |
4380 | else: | |
4381 | video_id = m.group('video_id') | |
df2dedee MW |
4382 | |
4383 | # determine title and media streams from webpage | |
4384 | html = self._download_webpage(url, video_id) | |
4385 | title = re.search(self._TITLE, html).group('title') | |
4386 | streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)] | |
4387 | if not streams: | |
4388 | assert '"fsk"' in html | |
4389 | self._downloader.report_error(u'this video is only available after 8:00 pm') | |
4390 | return | |
4391 | ||
4392 | # choose default media type and highest quality for now | |
b03d65c2 PH |
4393 | stream = max([s for s in streams if int(s["media_type"]) == 0], |
4394 | key=lambda s: int(s["quality"])) | |
df2dedee MW |
4395 | |
4396 | # there's two possibilities: RTMP stream or HTTP download | |
4397 | info = {'id': video_id, 'title': title, 'ext': 'mp4'} | |
4398 | if stream['rtmp_url']: | |
4399 | self._downloader.to_screen(u'[%s] RTMP download detected' % self.IE_NAME) | |
4400 | assert stream['video_url'].startswith('mp4:') | |
4401 | info["url"] = stream["rtmp_url"] | |
4402 | info["play_path"] = stream['video_url'] | |
4403 | else: | |
4404 | assert stream["video_url"].endswith('.mp4') | |
4405 | info["url"] = stream["video_url"] | |
4406 | return [info] | |
4407 | ||
e32b06e9 | 4408 | |
4aeae91f PH |
4409 | def gen_extractors(): |
4410 | """ Return a list of an instance of every supported extractor. | |
4411 | The order does matter; the first extractor matched is the one handling the URL. | |
4412 | """ | |
4413 | return [ | |
4414 | YoutubePlaylistIE(), | |
4415 | YoutubeChannelIE(), | |
4416 | YoutubeUserIE(), | |
4417 | YoutubeSearchIE(), | |
4418 | YoutubeIE(), | |
4419 | MetacafeIE(), | |
4420 | DailymotionIE(), | |
4421 | GoogleSearchIE(), | |
4422 | PhotobucketIE(), | |
4423 | YahooIE(), | |
4424 | YahooSearchIE(), | |
4425 | DepositFilesIE(), | |
4426 | FacebookIE(), | |
4427 | BlipTVUserIE(), | |
4428 | BlipTVIE(), | |
4429 | VimeoIE(), | |
4430 | MyVideoIE(), | |
4431 | ComedyCentralIE(), | |
4432 | EscapistIE(), | |
4433 | CollegeHumorIE(), | |
4434 | XVideosIE(), | |
5011cded | 4435 | SoundcloudSetIE(), |
4aeae91f PH |
4436 | SoundcloudIE(), |
4437 | InfoQIE(), | |
4438 | MixcloudIE(), | |
4439 | StanfordOpenClassroomIE(), | |
4440 | MTVIE(), | |
4441 | YoukuIE(), | |
4442 | XNXXIE(), | |
18be482a JC |
4443 | YouJizzIE(), |
4444 | PornotubeIE(), | |
4445 | YouPornIE(), | |
4aeae91f PH |
4446 | GooglePlusIE(), |
4447 | ArteTvIE(), | |
4448 | NBAIE(), | |
40634747 | 4449 | WorldStarHipHopIE(), |
4aeae91f PH |
4450 | JustinTVIE(), |
4451 | FunnyOrDieIE(), | |
4aeae91f PH |
4452 | SteamIE(), |
4453 | UstreamIE(), | |
ca0a0bbe | 4454 | RBMARadioIE(), |
ccf65f9d | 4455 | EightTracksIE(), |
da06e2da | 4456 | KeekIE(), |
3a468f2d | 4457 | TEDIE(), |
58994225 | 4458 | MySpassIE(), |
e32b06e9 | 4459 | SpiegelIE(), |
0cd35867 | 4460 | LiveLeakIE(), |
df2dedee | 4461 | ARDIE(), |
4aeae91f PH |
4462 | GenericIE() |
4463 | ] |