]>
Commit | Line | Data |
---|---|---|
1 | #!/usr/bin/env python | |
2 | # -*- coding: utf-8 -*- | |
3 | ||
4 | from __future__ import absolute_import | |
5 | ||
6 | import base64 | |
7 | import datetime | |
8 | import itertools | |
9 | import netrc | |
10 | import os | |
11 | import re | |
12 | import socket | |
13 | import time | |
14 | import email.utils | |
15 | import xml.etree.ElementTree | |
16 | import random | |
17 | import math | |
18 | import operator | |
19 | ||
20 | from .utils import * | |
21 | ||
22 | ||
23 | class InfoExtractor(object): | |
24 | """Information Extractor class. | |
25 | ||
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 | |
29 | others. The information is stored in a dictionary which is then | |
30 | passed to the FileDownloader. The FileDownloader processes this | |
31 | information possibly downloading the video to the file system, among | |
32 | other possible outcomes. | |
33 | ||
34 | The dictionaries must include the following fields: | |
35 | ||
36 | id: Video identifier. | |
37 | url: Final video URL. | |
38 | title: Video title, unescaped. | |
39 | ext: Video filename extension. | |
40 | ||
41 | The following fields are optional: | |
42 | ||
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. | |
46 | uploader: Full name of the video uploader. | |
47 | upload_date: Video upload date (YYYYMMDD). | |
48 | uploader_id: Nickname or id of the video uploader. | |
49 | location: Physical location of the video. | |
50 | player_url: SWF Player URL (used for rtmpdump). | |
51 | subtitles: The subtitle file contents. | |
52 | urlhandle: [internal] The urlHandle to be used to download the file, | |
53 | like returned by urllib.request.urlopen | |
54 | ||
55 | The fields should all be Unicode strings. | |
56 | ||
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. | |
60 | ||
61 | _real_extract() must return a *list* of information dictionaries as | |
62 | described above. | |
63 | ||
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 | """ | |
67 | ||
68 | _ready = False | |
69 | _downloader = None | |
70 | _WORKING = True | |
71 | ||
72 | def __init__(self, downloader=None): | |
73 | """Constructor. Receives an optional downloader.""" | |
74 | self._ready = False | |
75 | self.set_downloader(downloader) | |
76 | ||
77 | @classmethod | |
78 | def suitable(cls, url): | |
79 | """Receives a URL and returns True if suitable for this IE.""" | |
80 | return re.match(cls._VALID_URL, url) is not None | |
81 | ||
82 | @classmethod | |
83 | def working(cls): | |
84 | """Getter method for _WORKING.""" | |
85 | return cls._WORKING | |
86 | ||
87 | def initialize(self): | |
88 | """Initializes an instance (authentication, etc).""" | |
89 | if not self._ready: | |
90 | self._real_initialize() | |
91 | self._ready = True | |
92 | ||
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) | |
97 | ||
98 | def set_downloader(self, downloader): | |
99 | """Sets the downloader for this IE.""" | |
100 | self._downloader = downloader | |
101 | ||
102 | def _real_initialize(self): | |
103 | """Real initialization process. Redefine in subclasses.""" | |
104 | pass | |
105 | ||
106 | def _real_extract(self, url): | |
107 | """Real extraction process. Redefine in subclasses.""" | |
108 | pass | |
109 | ||
110 | @property | |
111 | def IE_NAME(self): | |
112 | return type(self).__name__[:-2] | |
113 | ||
114 | def _request_webpage(self, url_or_request, video_id, note=None, errnote=None): | |
115 | """ Returns the response handle """ | |
116 | if note is None: | |
117 | self.report_download_webpage(video_id) | |
118 | elif note is not False: | |
119 | self.to_screen(u'%s: %s' % (video_id, note)) | |
120 | try: | |
121 | return compat_urllib_request.urlopen(url_or_request) | |
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' | |
125 | raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2]) | |
126 | ||
127 | def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None): | |
128 | """ Returns a tuple (page content as string, URL handle) """ | |
129 | urlh = self._request_webpage(url_or_request, video_id, note, errnote) | |
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' | |
136 | webpage_bytes = urlh.read() | |
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.to_screen(u'Dumping request to ' + url) | |
143 | dump = base64.b64encode(webpage_bytes).decode('ascii') | |
144 | self._downloader.to_screen(dump) | |
145 | content = webpage_bytes.decode(encoding, 'replace') | |
146 | return (content, urlh) | |
147 | ||
148 | def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): | |
149 | """ Returns the data of the page as a string """ | |
150 | return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0] | |
151 | ||
152 | def to_screen(self, msg): | |
153 | """Print msg to screen, prefixing it with '[ie_name]'""" | |
154 | self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg)) | |
155 | ||
156 | def report_extraction(self, id_or_name): | |
157 | """Report information extraction.""" | |
158 | self.to_screen(u'%s: Extracting information' % id_or_name) | |
159 | ||
160 | def report_download_webpage(self, video_id): | |
161 | """Report webpage download.""" | |
162 | self.to_screen(u'%s: Downloading webpage' % video_id) | |
163 | ||
164 | def report_age_confirmation(self): | |
165 | """Report attempt to confirm age.""" | |
166 | self.to_screen(u'Confirming age') | |
167 | ||
168 | #Methods for following #608 | |
169 | #They set the correct value of the '_type' key | |
170 | def video_result(self, video_info): | |
171 | """Returns a video""" | |
172 | video_info['_type'] = 'video' | |
173 | return video_info | |
174 | def url_result(self, url, ie=None): | |
175 | """Returns a url that points to a page that should be processed""" | |
176 | #TODO: ie should be the class used for getting the info | |
177 | video_info = {'_type': 'url', | |
178 | 'url': url, | |
179 | 'ie_key': ie} | |
180 | return video_info | |
181 | def playlist_result(self, entries, playlist_id=None, playlist_title=None): | |
182 | """Returns a playlist""" | |
183 | video_info = {'_type': 'playlist', | |
184 | 'entries': entries} | |
185 | if playlist_id: | |
186 | video_info['id'] = playlist_id | |
187 | if playlist_title: | |
188 | video_info['title'] = playlist_title | |
189 | return video_info | |
190 | ||
191 | ||
192 | class YoutubeIE(InfoExtractor): | |
193 | """Information extractor for youtube.com.""" | |
194 | ||
195 | _VALID_URL = r"""^ | |
196 | ( | |
197 | (?:https?://)? # http(s):// (optional) | |
198 | (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| | |
199 | tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains | |
200 | (?:.*?\#/)? # handle anchor (#/) redirect urls | |
201 | (?: # the various things that can precede the ID: | |
202 | (?:(?:v|embed|e)/) # v/ or embed/ or e/ | |
203 | |(?: # or the v= param in all its forms | |
204 | (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) | |
205 | (?:\?|\#!?) # the params delimiter ? or # or #! | |
206 | (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) | |
207 | v= | |
208 | ) | |
209 | )? # optional -> youtube.com/xxxx is OK | |
210 | )? # all until now is optional -> you can pass the naked ID | |
211 | ([0-9A-Za-z_-]+) # here is it! the YouTube video ID | |
212 | (?(1).+)? # if we found the ID, everything can follow | |
213 | $""" | |
214 | _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' | |
215 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
216 | _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' | |
217 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' | |
218 | _NETRC_MACHINE = 'youtube' | |
219 | # Listed in order of quality | |
220 | _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] | |
221 | _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] | |
222 | _video_extensions = { | |
223 | '13': '3gp', | |
224 | '17': 'mp4', | |
225 | '18': 'mp4', | |
226 | '22': 'mp4', | |
227 | '37': 'mp4', | |
228 | '38': 'video', # You actually don't know if this will be MOV, AVI or whatever | |
229 | '43': 'webm', | |
230 | '44': 'webm', | |
231 | '45': 'webm', | |
232 | '46': 'webm', | |
233 | } | |
234 | _video_dimensions = { | |
235 | '5': '240x400', | |
236 | '6': '???', | |
237 | '13': '???', | |
238 | '17': '144x176', | |
239 | '18': '360x640', | |
240 | '22': '720x1280', | |
241 | '34': '360x640', | |
242 | '35': '480x854', | |
243 | '37': '1080x1920', | |
244 | '38': '3072x4096', | |
245 | '43': '360x640', | |
246 | '44': '480x854', | |
247 | '45': '720x1280', | |
248 | '46': '1080x1920', | |
249 | } | |
250 | IE_NAME = u'youtube' | |
251 | ||
252 | @classmethod | |
253 | def suitable(cls, url): | |
254 | """Receives a URL and returns True if suitable for this IE.""" | |
255 | if YoutubePlaylistIE.suitable(url): return False | |
256 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None | |
257 | ||
258 | def report_lang(self): | |
259 | """Report attempt to set language.""" | |
260 | self.to_screen(u'Setting language') | |
261 | ||
262 | def report_login(self): | |
263 | """Report attempt to log in.""" | |
264 | self.to_screen(u'Logging in') | |
265 | ||
266 | def report_video_webpage_download(self, video_id): | |
267 | """Report attempt to download video webpage.""" | |
268 | self.to_screen(u'%s: Downloading video webpage' % video_id) | |
269 | ||
270 | def report_video_info_webpage_download(self, video_id): | |
271 | """Report attempt to download video info webpage.""" | |
272 | self.to_screen(u'%s: Downloading video info webpage' % video_id) | |
273 | ||
274 | def report_video_subtitles_download(self, video_id): | |
275 | """Report attempt to download video info webpage.""" | |
276 | self.to_screen(u'%s: Checking available subtitles' % video_id) | |
277 | ||
278 | def report_video_subtitles_request(self, video_id, sub_lang, format): | |
279 | """Report attempt to download video info webpage.""" | |
280 | self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format)) | |
281 | ||
282 | def report_video_subtitles_available(self, video_id, sub_lang_list): | |
283 | """Report available subtitles.""" | |
284 | sub_lang = ",".join(list(sub_lang_list.keys())) | |
285 | self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang)) | |
286 | ||
287 | def report_information_extraction(self, video_id): | |
288 | """Report attempt to extract video information.""" | |
289 | self.to_screen(u'%s: Extracting video information' % video_id) | |
290 | ||
291 | def report_unavailable_format(self, video_id, format): | |
292 | """Report extracted video URL.""" | |
293 | self.to_screen(u'%s: Format %s not available' % (video_id, format)) | |
294 | ||
295 | def report_rtmp_download(self): | |
296 | """Indicate the download will use the RTMP protocol.""" | |
297 | self.to_screen(u'RTMP download detected') | |
298 | ||
299 | def _get_available_subtitles(self, video_id): | |
300 | self.report_video_subtitles_download(video_id) | |
301 | request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) | |
302 | try: | |
303 | sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
304 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
305 | return (u'unable to download video subtitles: %s' % compat_str(err), None) | |
306 | sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list) | |
307 | sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list) | |
308 | if not sub_lang_list: | |
309 | return (u'video doesn\'t have subtitles', None) | |
310 | return sub_lang_list | |
311 | ||
312 | def _list_available_subtitles(self, video_id): | |
313 | sub_lang_list = self._get_available_subtitles(video_id) | |
314 | self.report_video_subtitles_available(video_id, sub_lang_list) | |
315 | ||
316 | def _request_subtitle(self, sub_lang, sub_name, video_id, format): | |
317 | """ | |
318 | Return tuple: | |
319 | (error_message, sub_lang, sub) | |
320 | """ | |
321 | self.report_video_subtitles_request(video_id, sub_lang, format) | |
322 | params = compat_urllib_parse.urlencode({ | |
323 | 'lang': sub_lang, | |
324 | 'name': sub_name, | |
325 | 'v': video_id, | |
326 | 'fmt': format, | |
327 | }) | |
328 | url = 'http://www.youtube.com/api/timedtext?' + params | |
329 | try: | |
330 | sub = compat_urllib_request.urlopen(url).read().decode('utf-8') | |
331 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
332 | return (u'unable to download video subtitles: %s' % compat_str(err), None, None) | |
333 | if not sub: | |
334 | return (u'Did not fetch video subtitles', None, None) | |
335 | return (None, sub_lang, sub) | |
336 | ||
337 | def _extract_subtitle(self, video_id): | |
338 | """ | |
339 | Return a list with a tuple: | |
340 | [(error_message, sub_lang, sub)] | |
341 | """ | |
342 | sub_lang_list = self._get_available_subtitles(video_id) | |
343 | sub_format = self._downloader.params.get('subtitlesformat') | |
344 | if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles | |
345 | return [(sub_lang_list[0], None, None)] | |
346 | if self._downloader.params.get('subtitleslang', False): | |
347 | sub_lang = self._downloader.params.get('subtitleslang') | |
348 | elif 'en' in sub_lang_list: | |
349 | sub_lang = 'en' | |
350 | else: | |
351 | sub_lang = list(sub_lang_list.keys())[0] | |
352 | if not sub_lang in sub_lang_list: | |
353 | return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)] | |
354 | ||
355 | subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) | |
356 | return [subtitle] | |
357 | ||
358 | def _extract_all_subtitles(self, video_id): | |
359 | sub_lang_list = self._get_available_subtitles(video_id) | |
360 | sub_format = self._downloader.params.get('subtitlesformat') | |
361 | if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles | |
362 | return [(sub_lang_list[0], None, None)] | |
363 | subtitles = [] | |
364 | for sub_lang in sub_lang_list: | |
365 | subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) | |
366 | subtitles.append(subtitle) | |
367 | return subtitles | |
368 | ||
369 | def _print_formats(self, formats): | |
370 | print('Available formats:') | |
371 | for x in formats: | |
372 | print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))) | |
373 | ||
374 | def _real_initialize(self): | |
375 | if self._downloader is None: | |
376 | return | |
377 | ||
378 | username = None | |
379 | password = None | |
380 | downloader_params = self._downloader.params | |
381 | ||
382 | # Attempt to use provided username and password or .netrc data | |
383 | if downloader_params.get('username', None) is not None: | |
384 | username = downloader_params['username'] | |
385 | password = downloader_params['password'] | |
386 | elif downloader_params.get('usenetrc', False): | |
387 | try: | |
388 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
389 | if info is not None: | |
390 | username = info[0] | |
391 | password = info[2] | |
392 | else: | |
393 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
394 | except (IOError, netrc.NetrcParseError) as err: | |
395 | self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) | |
396 | return | |
397 | ||
398 | # Set language | |
399 | request = compat_urllib_request.Request(self._LANG_URL) | |
400 | try: | |
401 | self.report_lang() | |
402 | compat_urllib_request.urlopen(request).read() | |
403 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
404 | self._downloader.report_warning(u'unable to set language: %s' % compat_str(err)) | |
405 | return | |
406 | ||
407 | # No authentication to be performed | |
408 | if username is None: | |
409 | return | |
410 | ||
411 | request = compat_urllib_request.Request(self._LOGIN_URL) | |
412 | try: | |
413 | login_page = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
414 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
415 | self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err)) | |
416 | return | |
417 | ||
418 | galx = None | |
419 | dsh = None | |
420 | match = re.search(re.compile(r'<input.+?name="GALX".+?value="(.+?)"', re.DOTALL), login_page) | |
421 | if match: | |
422 | galx = match.group(1) | |
423 | ||
424 | match = re.search(re.compile(r'<input.+?name="dsh".+?value="(.+?)"', re.DOTALL), login_page) | |
425 | if match: | |
426 | dsh = match.group(1) | |
427 | ||
428 | # Log in | |
429 | login_form_strs = { | |
430 | u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', | |
431 | u'Email': username, | |
432 | u'GALX': galx, | |
433 | u'Passwd': password, | |
434 | u'PersistentCookie': u'yes', | |
435 | u'_utf8': u'霱', | |
436 | u'bgresponse': u'js_disabled', | |
437 | u'checkConnection': u'', | |
438 | u'checkedDomains': u'youtube', | |
439 | u'dnConn': u'', | |
440 | u'dsh': dsh, | |
441 | u'pstMsg': u'0', | |
442 | u'rmShown': u'1', | |
443 | u'secTok': u'', | |
444 | u'signIn': u'Sign in', | |
445 | u'timeStmp': u'', | |
446 | u'service': u'youtube', | |
447 | u'uilel': u'3', | |
448 | u'hl': u'en_US', | |
449 | } | |
450 | # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode | |
451 | # chokes on unicode | |
452 | login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items()) | |
453 | login_data = compat_urllib_parse.urlencode(login_form).encode('ascii') | |
454 | request = compat_urllib_request.Request(self._LOGIN_URL, login_data) | |
455 | try: | |
456 | self.report_login() | |
457 | login_results = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
458 | if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: | |
459 | self._downloader.report_warning(u'unable to log in: bad username or password') | |
460 | return | |
461 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
462 | self._downloader.report_warning(u'unable to log in: %s' % compat_str(err)) | |
463 | return | |
464 | ||
465 | # Confirm age | |
466 | age_form = { | |
467 | 'next_url': '/', | |
468 | 'action_confirm': 'Confirm', | |
469 | } | |
470 | request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form)) | |
471 | try: | |
472 | self.report_age_confirmation() | |
473 | age_results = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
474 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
475 | raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err)) | |
476 | ||
477 | def _extract_id(self, url): | |
478 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) | |
479 | if mobj is None: | |
480 | raise ExtractorError(u'Invalid URL: %s' % url) | |
481 | video_id = mobj.group(2) | |
482 | return video_id | |
483 | ||
484 | def _real_extract(self, url): | |
485 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter | |
486 | mobj = re.search(self._NEXT_URL_RE, url) | |
487 | if mobj: | |
488 | url = 'https://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') | |
489 | video_id = self._extract_id(url) | |
490 | ||
491 | # Get video webpage | |
492 | self.report_video_webpage_download(video_id) | |
493 | url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id | |
494 | request = compat_urllib_request.Request(url) | |
495 | try: | |
496 | video_webpage_bytes = compat_urllib_request.urlopen(request).read() | |
497 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
498 | raise ExtractorError(u'Unable to download video webpage: %s' % compat_str(err)) | |
499 | ||
500 | video_webpage = video_webpage_bytes.decode('utf-8', 'ignore') | |
501 | ||
502 | # Attempt to extract SWF player URL | |
503 | mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) | |
504 | if mobj is not None: | |
505 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
506 | else: | |
507 | player_url = None | |
508 | ||
509 | # Get video info | |
510 | self.report_video_info_webpage_download(video_id) | |
511 | for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: | |
512 | video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
513 | % (video_id, el_type)) | |
514 | video_info_webpage = self._download_webpage(video_info_url, video_id, | |
515 | note=False, | |
516 | errnote='unable to download video info webpage') | |
517 | video_info = compat_parse_qs(video_info_webpage) | |
518 | if 'token' in video_info: | |
519 | break | |
520 | if 'token' not in video_info: | |
521 | if 'reason' in video_info: | |
522 | raise ExtractorError(u'YouTube said: %s' % video_info['reason'][0]) | |
523 | else: | |
524 | raise ExtractorError(u'"token" parameter not in video info for unknown reason') | |
525 | ||
526 | # Check for "rental" videos | |
527 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
528 | raise ExtractorError(u'"rental" videos not supported') | |
529 | ||
530 | # Start extracting information | |
531 | self.report_information_extraction(video_id) | |
532 | ||
533 | # uploader | |
534 | if 'author' not in video_info: | |
535 | raise ExtractorError(u'Unable to extract uploader name') | |
536 | video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) | |
537 | ||
538 | # uploader_id | |
539 | video_uploader_id = None | |
540 | mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage) | |
541 | if mobj is not None: | |
542 | video_uploader_id = mobj.group(1) | |
543 | else: | |
544 | self._downloader.report_warning(u'unable to extract uploader nickname') | |
545 | ||
546 | # title | |
547 | if 'title' not in video_info: | |
548 | raise ExtractorError(u'Unable to extract video title') | |
549 | video_title = compat_urllib_parse.unquote_plus(video_info['title'][0]) | |
550 | ||
551 | # thumbnail image | |
552 | if 'thumbnail_url' not in video_info: | |
553 | self._downloader.report_warning(u'unable to extract video thumbnail') | |
554 | video_thumbnail = '' | |
555 | else: # don't panic if we can't find it | |
556 | video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) | |
557 | ||
558 | # upload date | |
559 | upload_date = None | |
560 | mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL) | |
561 | if mobj is not None: | |
562 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) | |
563 | upload_date = unified_strdate(upload_date) | |
564 | ||
565 | # description | |
566 | video_description = get_element_by_id("eow-description", video_webpage) | |
567 | if video_description: | |
568 | video_description = clean_html(video_description) | |
569 | else: | |
570 | fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage) | |
571 | if fd_mobj: | |
572 | video_description = unescapeHTML(fd_mobj.group(1)) | |
573 | else: | |
574 | video_description = u'' | |
575 | ||
576 | # subtitles | |
577 | video_subtitles = None | |
578 | ||
579 | if self._downloader.params.get('writesubtitles', False): | |
580 | video_subtitles = self._extract_subtitle(video_id) | |
581 | if video_subtitles: | |
582 | (sub_error, sub_lang, sub) = video_subtitles[0] | |
583 | if sub_error: | |
584 | self._downloader.report_error(sub_error) | |
585 | ||
586 | if self._downloader.params.get('allsubtitles', False): | |
587 | video_subtitles = self._extract_all_subtitles(video_id) | |
588 | for video_subtitle in video_subtitles: | |
589 | (sub_error, sub_lang, sub) = video_subtitle | |
590 | if sub_error: | |
591 | self._downloader.report_error(sub_error) | |
592 | ||
593 | if self._downloader.params.get('listsubtitles', False): | |
594 | sub_lang_list = self._list_available_subtitles(video_id) | |
595 | return | |
596 | ||
597 | if 'length_seconds' not in video_info: | |
598 | self._downloader.report_warning(u'unable to extract video duration') | |
599 | video_duration = '' | |
600 | else: | |
601 | video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]) | |
602 | ||
603 | # token | |
604 | video_token = compat_urllib_parse.unquote_plus(video_info['token'][0]) | |
605 | ||
606 | # Decide which formats to download | |
607 | req_format = self._downloader.params.get('format', None) | |
608 | ||
609 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): | |
610 | self.report_rtmp_download() | |
611 | video_url_list = [(None, video_info['conn'][0])] | |
612 | elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: | |
613 | url_map = {} | |
614 | for url_data_str in video_info['url_encoded_fmt_stream_map'][0].split(','): | |
615 | url_data = compat_parse_qs(url_data_str) | |
616 | if 'itag' in url_data and 'url' in url_data: | |
617 | url = url_data['url'][0] + '&signature=' + url_data['sig'][0] | |
618 | if not 'ratebypass' in url: url += '&ratebypass=yes' | |
619 | url_map[url_data['itag'][0]] = url | |
620 | ||
621 | format_limit = self._downloader.params.get('format_limit', None) | |
622 | available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats | |
623 | if format_limit is not None and format_limit in available_formats: | |
624 | format_list = available_formats[available_formats.index(format_limit):] | |
625 | else: | |
626 | format_list = available_formats | |
627 | existing_formats = [x for x in format_list if x in url_map] | |
628 | if len(existing_formats) == 0: | |
629 | raise ExtractorError(u'no known formats available for video') | |
630 | if self._downloader.params.get('listformats', None): | |
631 | self._print_formats(existing_formats) | |
632 | return | |
633 | if req_format is None or req_format == 'best': | |
634 | video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality | |
635 | elif req_format == 'worst': | |
636 | video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality | |
637 | elif req_format in ('-1', 'all'): | |
638 | video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats | |
639 | else: | |
640 | # Specific formats. We pick the first in a slash-delimeted sequence. | |
641 | # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. | |
642 | req_formats = req_format.split('/') | |
643 | video_url_list = None | |
644 | for rf in req_formats: | |
645 | if rf in url_map: | |
646 | video_url_list = [(rf, url_map[rf])] | |
647 | break | |
648 | if video_url_list is None: | |
649 | raise ExtractorError(u'requested format not available') | |
650 | else: | |
651 | raise ExtractorError(u'no conn or url_encoded_fmt_stream_map information found in video info') | |
652 | ||
653 | results = [] | |
654 | for format_param, video_real_url in video_url_list: | |
655 | # Extension | |
656 | video_extension = self._video_extensions.get(format_param, 'flv') | |
657 | ||
658 | video_format = '{0} - {1}'.format(format_param if format_param else video_extension, | |
659 | self._video_dimensions.get(format_param, '???')) | |
660 | ||
661 | results.append({ | |
662 | 'id': video_id, | |
663 | 'url': video_real_url, | |
664 | 'uploader': video_uploader, | |
665 | 'uploader_id': video_uploader_id, | |
666 | 'upload_date': upload_date, | |
667 | 'title': video_title, | |
668 | 'ext': video_extension, | |
669 | 'format': video_format, | |
670 | 'thumbnail': video_thumbnail, | |
671 | 'description': video_description, | |
672 | 'player_url': player_url, | |
673 | 'subtitles': video_subtitles, | |
674 | 'duration': video_duration | |
675 | }) | |
676 | return results | |
677 | ||
678 | ||
679 | class MetacafeIE(InfoExtractor): | |
680 | """Information Extractor for metacafe.com.""" | |
681 | ||
682 | _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' | |
683 | _DISCLAIMER = 'http://www.metacafe.com/family_filter/' | |
684 | _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' | |
685 | IE_NAME = u'metacafe' | |
686 | ||
687 | def report_disclaimer(self): | |
688 | """Report disclaimer retrieval.""" | |
689 | self.to_screen(u'Retrieving disclaimer') | |
690 | ||
691 | def _real_initialize(self): | |
692 | # Retrieve disclaimer | |
693 | request = compat_urllib_request.Request(self._DISCLAIMER) | |
694 | try: | |
695 | self.report_disclaimer() | |
696 | disclaimer = compat_urllib_request.urlopen(request).read() | |
697 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
698 | raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err)) | |
699 | ||
700 | # Confirm age | |
701 | disclaimer_form = { | |
702 | 'filters': '0', | |
703 | 'submit': "Continue - I'm over 18", | |
704 | } | |
705 | request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) | |
706 | try: | |
707 | self.report_age_confirmation() | |
708 | disclaimer = compat_urllib_request.urlopen(request).read() | |
709 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
710 | raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err)) | |
711 | ||
712 | def _real_extract(self, url): | |
713 | # Extract id and simplified title from URL | |
714 | mobj = re.match(self._VALID_URL, url) | |
715 | if mobj is None: | |
716 | raise ExtractorError(u'Invalid URL: %s' % url) | |
717 | ||
718 | video_id = mobj.group(1) | |
719 | ||
720 | # Check if video comes from YouTube | |
721 | mobj2 = re.match(r'^yt-(.*)$', video_id) | |
722 | if mobj2 is not None: | |
723 | return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')] | |
724 | ||
725 | # Retrieve video webpage to extract further information | |
726 | webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id) | |
727 | ||
728 | # Extract URL, uploader and title from webpage | |
729 | self.report_extraction(video_id) | |
730 | mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) | |
731 | if mobj is not None: | |
732 | mediaURL = compat_urllib_parse.unquote(mobj.group(1)) | |
733 | video_extension = mediaURL[-3:] | |
734 | ||
735 | # Extract gdaKey if available | |
736 | mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) | |
737 | if mobj is None: | |
738 | video_url = mediaURL | |
739 | else: | |
740 | gdaKey = mobj.group(1) | |
741 | video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) | |
742 | else: | |
743 | mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) | |
744 | if mobj is None: | |
745 | raise ExtractorError(u'Unable to extract media URL') | |
746 | vardict = compat_parse_qs(mobj.group(1)) | |
747 | if 'mediaData' not in vardict: | |
748 | raise ExtractorError(u'Unable to extract media URL') | |
749 | mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0]) | |
750 | if mobj is None: | |
751 | raise ExtractorError(u'Unable to extract media URL') | |
752 | mediaURL = mobj.group('mediaURL').replace('\\/', '/') | |
753 | video_extension = mediaURL[-3:] | |
754 | video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) | |
755 | ||
756 | mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) | |
757 | if mobj is None: | |
758 | raise ExtractorError(u'Unable to extract title') | |
759 | video_title = mobj.group(1).decode('utf-8') | |
760 | ||
761 | mobj = re.search(r'submitter=(.*?);', webpage) | |
762 | if mobj is None: | |
763 | raise ExtractorError(u'Unable to extract uploader nickname') | |
764 | video_uploader = mobj.group(1) | |
765 | ||
766 | return [{ | |
767 | 'id': video_id.decode('utf-8'), | |
768 | 'url': video_url.decode('utf-8'), | |
769 | 'uploader': video_uploader.decode('utf-8'), | |
770 | 'upload_date': None, | |
771 | 'title': video_title, | |
772 | 'ext': video_extension.decode('utf-8'), | |
773 | }] | |
774 | ||
775 | class DailymotionIE(InfoExtractor): | |
776 | """Information Extractor for Dailymotion""" | |
777 | ||
778 | _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' | |
779 | IE_NAME = u'dailymotion' | |
780 | ||
781 | def _real_extract(self, url): | |
782 | # Extract id and simplified title from URL | |
783 | mobj = re.match(self._VALID_URL, url) | |
784 | if mobj is None: | |
785 | raise ExtractorError(u'Invalid URL: %s' % url) | |
786 | ||
787 | video_id = mobj.group(1).split('_')[0].split('?')[0] | |
788 | ||
789 | video_extension = 'mp4' | |
790 | ||
791 | # Retrieve video webpage to extract further information | |
792 | request = compat_urllib_request.Request(url) | |
793 | request.add_header('Cookie', 'family_filter=off') | |
794 | webpage = self._download_webpage(request, video_id) | |
795 | ||
796 | # Extract URL, uploader and title from webpage | |
797 | self.report_extraction(video_id) | |
798 | mobj = re.search(r'\s*var flashvars = (.*)', webpage) | |
799 | if mobj is None: | |
800 | raise ExtractorError(u'Unable to extract media URL') | |
801 | flashvars = compat_urllib_parse.unquote(mobj.group(1)) | |
802 | ||
803 | for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: | |
804 | if key in flashvars: | |
805 | max_quality = key | |
806 | self.to_screen(u'Using %s' % key) | |
807 | break | |
808 | else: | |
809 | raise ExtractorError(u'Unable to extract video URL') | |
810 | ||
811 | mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) | |
812 | if mobj is None: | |
813 | raise ExtractorError(u'Unable to extract video URL') | |
814 | ||
815 | video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/') | |
816 | ||
817 | # TODO: support choosing qualities | |
818 | ||
819 | mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage) | |
820 | if mobj is None: | |
821 | raise ExtractorError(u'Unable to extract title') | |
822 | video_title = unescapeHTML(mobj.group('title')) | |
823 | ||
824 | video_uploader = None | |
825 | mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage) | |
826 | if mobj is None: | |
827 | # lookin for official user | |
828 | mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage) | |
829 | if mobj_official is None: | |
830 | self._downloader.report_warning(u'unable to extract uploader nickname') | |
831 | else: | |
832 | video_uploader = mobj_official.group(1) | |
833 | else: | |
834 | video_uploader = mobj.group(1) | |
835 | ||
836 | video_upload_date = None | |
837 | mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage) | |
838 | if mobj is not None: | |
839 | video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1) | |
840 | ||
841 | return [{ | |
842 | 'id': video_id, | |
843 | 'url': video_url, | |
844 | 'uploader': video_uploader, | |
845 | 'upload_date': video_upload_date, | |
846 | 'title': video_title, | |
847 | 'ext': video_extension, | |
848 | }] | |
849 | ||
850 | ||
851 | class PhotobucketIE(InfoExtractor): | |
852 | """Information extractor for photobucket.com.""" | |
853 | ||
854 | # TODO: the original _VALID_URL was: | |
855 | # r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' | |
856 | # Check if it's necessary to keep the old extracion process | |
857 | _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))' | |
858 | IE_NAME = u'photobucket' | |
859 | ||
860 | def _real_extract(self, url): | |
861 | # Extract id from URL | |
862 | mobj = re.match(self._VALID_URL, url) | |
863 | if mobj is None: | |
864 | raise ExtractorError(u'Invalid URL: %s' % url) | |
865 | ||
866 | video_id = mobj.group('id') | |
867 | ||
868 | video_extension = mobj.group('ext') | |
869 | ||
870 | # Retrieve video webpage to extract further information | |
871 | webpage = self._download_webpage(url, video_id) | |
872 | ||
873 | # Extract URL, uploader, and title from webpage | |
874 | self.report_extraction(video_id) | |
875 | # We try first by looking the javascript code: | |
876 | mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P<json>.*?)\);', webpage) | |
877 | if mobj is not None: | |
878 | info = json.loads(mobj.group('json')) | |
879 | return [{ | |
880 | 'id': video_id, | |
881 | 'url': info[u'downloadUrl'], | |
882 | 'uploader': info[u'username'], | |
883 | 'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'), | |
884 | 'title': info[u'title'], | |
885 | 'ext': video_extension, | |
886 | 'thumbnail': info[u'thumbUrl'], | |
887 | }] | |
888 | ||
889 | # We try looking in other parts of the webpage | |
890 | mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage) | |
891 | if mobj is None: | |
892 | raise ExtractorError(u'Unable to extract media URL') | |
893 | mediaURL = compat_urllib_parse.unquote(mobj.group(1)) | |
894 | ||
895 | video_url = mediaURL | |
896 | ||
897 | mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) | |
898 | if mobj is None: | |
899 | raise ExtractorError(u'Unable to extract title') | |
900 | video_title = mobj.group(1).decode('utf-8') | |
901 | ||
902 | video_uploader = mobj.group(2).decode('utf-8') | |
903 | ||
904 | return [{ | |
905 | 'id': video_id.decode('utf-8'), | |
906 | 'url': video_url.decode('utf-8'), | |
907 | 'uploader': video_uploader, | |
908 | 'upload_date': None, | |
909 | 'title': video_title, | |
910 | 'ext': video_extension.decode('utf-8'), | |
911 | }] | |
912 | ||
913 | ||
914 | class YahooIE(InfoExtractor): | |
915 | """Information extractor for screen.yahoo.com.""" | |
916 | _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html' | |
917 | ||
918 | def _real_extract(self, url): | |
919 | mobj = re.match(self._VALID_URL, url) | |
920 | if mobj is None: | |
921 | raise ExtractorError(u'Invalid URL: %s' % url) | |
922 | video_id = mobj.group('id') | |
923 | webpage = self._download_webpage(url, video_id) | |
924 | m_id = re.search(r'YUI\.namespace\("Media"\)\.CONTENT_ID = "(?P<new_id>.+?)";', webpage) | |
925 | ||
926 | if m_id is None: | |
927 | # TODO: Check which url parameters are required | |
928 | info_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;lmsoverride=1;outputformat=mrss;cb=974419660;id=%s;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id | |
929 | webpage = self._download_webpage(info_url, video_id, u'Downloading info webpage') | |
930 | info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.* | |
931 | <description><!\[CDATA\[(?P<description>.*?)\]\]></description>.* | |
932 | <media:pubStart><!\[CDATA\[(?P<date>.*?)\ .*\]\]></media:pubStart>.* | |
933 | <media:content\ medium="image"\ url="(?P<thumb>.*?)"\ name="LARGETHUMB" | |
934 | ''' | |
935 | self.report_extraction(video_id) | |
936 | m_info = re.search(info_re, webpage, re.VERBOSE|re.DOTALL) | |
937 | if m_info is None: | |
938 | raise ExtractorError(u'Unable to extract video info') | |
939 | video_title = m_info.group('title') | |
940 | video_description = m_info.group('description') | |
941 | video_thumb = m_info.group('thumb') | |
942 | video_date = m_info.group('date') | |
943 | video_date = datetime.datetime.strptime(video_date, '%m/%d/%Y').strftime('%Y%m%d') | |
944 | ||
945 | # TODO: Find a way to get mp4 videos | |
946 | rest_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;element=stream;outputformat=mrss;id=%s;lmsoverride=1;bw=375;dynamicstream=1;cb=83521105;tech=flv,mp4;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id | |
947 | webpage = self._download_webpage(rest_url, video_id, u'Downloading video url webpage') | |
948 | m_rest = re.search(r'<media:content url="(?P<url>.*?)" path="(?P<path>.*?)"', webpage) | |
949 | video_url = m_rest.group('url') | |
950 | video_path = m_rest.group('path') | |
951 | if m_rest is None: | |
952 | raise ExtractorError(u'Unable to extract video url') | |
953 | ||
954 | else: # We have to use a different method if another id is defined | |
955 | long_id = m_id.group('new_id') | |
956 | info_url = 'http://video.query.yahoo.com/v1/public/yql?q=SELECT%20*%20FROM%20yahoo.media.video.streams%20WHERE%20id%3D%22' + long_id + '%22%20AND%20format%3D%22mp4%2Cflv%22%20AND%20protocol%3D%22rtmp%2Chttp%22%20AND%20plrs%3D%2286Gj0vCaSzV_Iuf6hNylf2%22%20AND%20acctid%3D%22389%22%20AND%20plidl%3D%22%22%20AND%20pspid%3D%22792700001%22%20AND%20offnetwork%3D%22false%22%20AND%20site%3D%22ivy%22%20AND%20lang%3D%22en-US%22%20AND%20region%3D%22US%22%20AND%20override%3D%22none%22%3B&env=prod&format=json&callback=YUI.Env.JSONP.yui_3_8_1_1_1368368376830_335' | |
957 | webpage = self._download_webpage(info_url, video_id, u'Downloading info json') | |
958 | json_str = re.search(r'YUI.Env.JSONP.yui.*?\((.*?)\);', webpage).group(1) | |
959 | info = json.loads(json_str) | |
960 | res = info[u'query'][u'results'][u'mediaObj'][0] | |
961 | stream = res[u'streams'][0] | |
962 | video_path = stream[u'path'] | |
963 | video_url = stream[u'host'] | |
964 | meta = res[u'meta'] | |
965 | video_title = meta[u'title'] | |
966 | video_description = meta[u'description'] | |
967 | video_thumb = meta[u'thumbnail'] | |
968 | video_date = None # I can't find it | |
969 | ||
970 | info_dict = { | |
971 | 'id': video_id, | |
972 | 'url': video_url, | |
973 | 'play_path': video_path, | |
974 | 'title':video_title, | |
975 | 'description': video_description, | |
976 | 'thumbnail': video_thumb, | |
977 | 'upload_date': video_date, | |
978 | 'ext': 'flv', | |
979 | } | |
980 | return info_dict | |
981 | ||
982 | class VimeoIE(InfoExtractor): | |
983 | """Information extractor for vimeo.com.""" | |
984 | ||
985 | # _VALID_URL matches Vimeo URLs | |
986 | _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]+)' | |
987 | IE_NAME = u'vimeo' | |
988 | ||
989 | def _real_extract(self, url, new_video=True): | |
990 | # Extract ID from URL | |
991 | mobj = re.match(self._VALID_URL, url) | |
992 | if mobj is None: | |
993 | raise ExtractorError(u'Invalid URL: %s' % url) | |
994 | ||
995 | video_id = mobj.group('id') | |
996 | if not mobj.group('proto'): | |
997 | url = 'https://' + url | |
998 | if mobj.group('direct_link'): | |
999 | url = 'https://vimeo.com/' + video_id | |
1000 | ||
1001 | # Retrieve video webpage to extract further information | |
1002 | request = compat_urllib_request.Request(url, None, std_headers) | |
1003 | webpage = self._download_webpage(request, video_id) | |
1004 | ||
1005 | # Now we begin extracting as much information as we can from what we | |
1006 | # retrieved. First we extract the information common to all extractors, | |
1007 | # and latter we extract those that are Vimeo specific. | |
1008 | self.report_extraction(video_id) | |
1009 | ||
1010 | # Extract the config JSON | |
1011 | try: | |
1012 | config = webpage.split(' = {config:')[1].split(',assets:')[0] | |
1013 | config = json.loads(config) | |
1014 | except: | |
1015 | if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): | |
1016 | raise ExtractorError(u'The author has restricted the access to this video, try with the "--referer" option') | |
1017 | else: | |
1018 | raise ExtractorError(u'Unable to extract info section') | |
1019 | ||
1020 | # Extract title | |
1021 | video_title = config["video"]["title"] | |
1022 | ||
1023 | # Extract uploader and uploader_id | |
1024 | video_uploader = config["video"]["owner"]["name"] | |
1025 | video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] | |
1026 | ||
1027 | # Extract video thumbnail | |
1028 | video_thumbnail = config["video"]["thumbnail"] | |
1029 | ||
1030 | # Extract video description | |
1031 | video_description = get_element_by_attribute("itemprop", "description", webpage) | |
1032 | if video_description: video_description = clean_html(video_description) | |
1033 | else: video_description = u'' | |
1034 | ||
1035 | # Extract upload date | |
1036 | video_upload_date = None | |
1037 | mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage) | |
1038 | if mobj is not None: | |
1039 | video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) | |
1040 | ||
1041 | # Vimeo specific: extract request signature and timestamp | |
1042 | sig = config['request']['signature'] | |
1043 | timestamp = config['request']['timestamp'] | |
1044 | ||
1045 | # Vimeo specific: extract video codec and quality information | |
1046 | # First consider quality, then codecs, then take everything | |
1047 | # TODO bind to format param | |
1048 | codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')] | |
1049 | files = { 'hd': [], 'sd': [], 'other': []} | |
1050 | for codec_name, codec_extension in codecs: | |
1051 | if codec_name in config["video"]["files"]: | |
1052 | if 'hd' in config["video"]["files"][codec_name]: | |
1053 | files['hd'].append((codec_name, codec_extension, 'hd')) | |
1054 | elif 'sd' in config["video"]["files"][codec_name]: | |
1055 | files['sd'].append((codec_name, codec_extension, 'sd')) | |
1056 | else: | |
1057 | files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0])) | |
1058 | ||
1059 | for quality in ('hd', 'sd', 'other'): | |
1060 | if len(files[quality]) > 0: | |
1061 | video_quality = files[quality][0][2] | |
1062 | video_codec = files[quality][0][0] | |
1063 | video_extension = files[quality][0][1] | |
1064 | self.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) | |
1065 | break | |
1066 | else: | |
1067 | raise ExtractorError(u'No known codec found') | |
1068 | ||
1069 | video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ | |
1070 | %(video_id, sig, timestamp, video_quality, video_codec.upper()) | |
1071 | ||
1072 | return [{ | |
1073 | 'id': video_id, | |
1074 | 'url': video_url, | |
1075 | 'uploader': video_uploader, | |
1076 | 'uploader_id': video_uploader_id, | |
1077 | 'upload_date': video_upload_date, | |
1078 | 'title': video_title, | |
1079 | 'ext': video_extension, | |
1080 | 'thumbnail': video_thumbnail, | |
1081 | 'description': video_description, | |
1082 | }] | |
1083 | ||
1084 | ||
1085 | class ArteTvIE(InfoExtractor): | |
1086 | """arte.tv information extractor.""" | |
1087 | ||
1088 | _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' | |
1089 | _LIVE_URL = r'index-[0-9]+\.html$' | |
1090 | ||
1091 | IE_NAME = u'arte.tv' | |
1092 | ||
1093 | def fetch_webpage(self, url): | |
1094 | request = compat_urllib_request.Request(url) | |
1095 | try: | |
1096 | self.report_download_webpage(url) | |
1097 | webpage = compat_urllib_request.urlopen(request).read() | |
1098 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1099 | raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err)) | |
1100 | except ValueError as err: | |
1101 | raise ExtractorError(u'Invalid URL: %s' % url) | |
1102 | return webpage | |
1103 | ||
1104 | def grep_webpage(self, url, regex, regexFlags, matchTuples): | |
1105 | page = self.fetch_webpage(url) | |
1106 | mobj = re.search(regex, page, regexFlags) | |
1107 | info = {} | |
1108 | ||
1109 | if mobj is None: | |
1110 | raise ExtractorError(u'Invalid URL: %s' % url) | |
1111 | ||
1112 | for (i, key, err) in matchTuples: | |
1113 | if mobj.group(i) is None: | |
1114 | raise ExtractorError(err) | |
1115 | else: | |
1116 | info[key] = mobj.group(i) | |
1117 | ||
1118 | return info | |
1119 | ||
1120 | def extractLiveStream(self, url): | |
1121 | video_lang = url.split('/')[-4] | |
1122 | info = self.grep_webpage( | |
1123 | url, | |
1124 | r'src="(.*?/videothek_js.*?\.js)', | |
1125 | 0, | |
1126 | [ | |
1127 | (1, 'url', u'Invalid URL: %s' % url) | |
1128 | ] | |
1129 | ) | |
1130 | http_host = url.split('/')[2] | |
1131 | next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url'))) | |
1132 | info = self.grep_webpage( | |
1133 | next_url, | |
1134 | r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' + | |
1135 | '(http://.*?\.swf).*?' + | |
1136 | '(rtmp://.*?)\'', | |
1137 | re.DOTALL, | |
1138 | [ | |
1139 | (1, 'path', u'could not extract video path: %s' % url), | |
1140 | (2, 'player', u'could not extract video player: %s' % url), | |
1141 | (3, 'url', u'could not extract video url: %s' % url) | |
1142 | ] | |
1143 | ) | |
1144 | video_url = u'%s/%s' % (info.get('url'), info.get('path')) | |
1145 | ||
1146 | def extractPlus7Stream(self, url): | |
1147 | video_lang = url.split('/')[-3] | |
1148 | info = self.grep_webpage( | |
1149 | url, | |
1150 | r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', | |
1151 | 0, | |
1152 | [ | |
1153 | (1, 'url', u'Invalid URL: %s' % url) | |
1154 | ] | |
1155 | ) | |
1156 | next_url = compat_urllib_parse.unquote(info.get('url')) | |
1157 | info = self.grep_webpage( | |
1158 | next_url, | |
1159 | r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang, | |
1160 | 0, | |
1161 | [ | |
1162 | (1, 'url', u'Could not find <video> tag: %s' % url) | |
1163 | ] | |
1164 | ) | |
1165 | next_url = compat_urllib_parse.unquote(info.get('url')) | |
1166 | ||
1167 | info = self.grep_webpage( | |
1168 | next_url, | |
1169 | r'<video id="(.*?)".*?>.*?' + | |
1170 | '<name>(.*?)</name>.*?' + | |
1171 | '<dateVideo>(.*?)</dateVideo>.*?' + | |
1172 | '<url quality="hd">(.*?)</url>', | |
1173 | re.DOTALL, | |
1174 | [ | |
1175 | (1, 'id', u'could not extract video id: %s' % url), | |
1176 | (2, 'title', u'could not extract video title: %s' % url), | |
1177 | (3, 'date', u'could not extract video date: %s' % url), | |
1178 | (4, 'url', u'could not extract video url: %s' % url) | |
1179 | ] | |
1180 | ) | |
1181 | ||
1182 | return { | |
1183 | 'id': info.get('id'), | |
1184 | 'url': compat_urllib_parse.unquote(info.get('url')), | |
1185 | 'uploader': u'arte.tv', | |
1186 | 'upload_date': unified_strdate(info.get('date')), | |
1187 | 'title': info.get('title').decode('utf-8'), | |
1188 | 'ext': u'mp4', | |
1189 | 'format': u'NA', | |
1190 | 'player_url': None, | |
1191 | } | |
1192 | ||
1193 | def _real_extract(self, url): | |
1194 | video_id = url.split('/')[-1] | |
1195 | self.report_extraction(video_id) | |
1196 | ||
1197 | if re.search(self._LIVE_URL, video_id) is not None: | |
1198 | self.extractLiveStream(url) | |
1199 | return | |
1200 | else: | |
1201 | info = self.extractPlus7Stream(url) | |
1202 | ||
1203 | return [info] | |
1204 | ||
1205 | ||
1206 | class GenericIE(InfoExtractor): | |
1207 | """Generic last-resort information extractor.""" | |
1208 | ||
1209 | _VALID_URL = r'.*' | |
1210 | IE_NAME = u'generic' | |
1211 | ||
1212 | def report_download_webpage(self, video_id): | |
1213 | """Report webpage download.""" | |
1214 | if not self._downloader.params.get('test', False): | |
1215 | self._downloader.report_warning(u'Falling back on generic information extractor.') | |
1216 | super(GenericIE, self).report_download_webpage(video_id) | |
1217 | ||
1218 | def report_following_redirect(self, new_url): | |
1219 | """Report information extraction.""" | |
1220 | self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url) | |
1221 | ||
1222 | def _test_redirect(self, url): | |
1223 | """Check if it is a redirect, like url shorteners, in case return the new url.""" | |
1224 | class HeadRequest(compat_urllib_request.Request): | |
1225 | def get_method(self): | |
1226 | return "HEAD" | |
1227 | ||
1228 | class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler): | |
1229 | """ | |
1230 | Subclass the HTTPRedirectHandler to make it use our | |
1231 | HeadRequest also on the redirected URL | |
1232 | """ | |
1233 | def redirect_request(self, req, fp, code, msg, headers, newurl): | |
1234 | if code in (301, 302, 303, 307): | |
1235 | newurl = newurl.replace(' ', '%20') | |
1236 | newheaders = dict((k,v) for k,v in req.headers.items() | |
1237 | if k.lower() not in ("content-length", "content-type")) | |
1238 | return HeadRequest(newurl, | |
1239 | headers=newheaders, | |
1240 | origin_req_host=req.get_origin_req_host(), | |
1241 | unverifiable=True) | |
1242 | else: | |
1243 | raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp) | |
1244 | ||
1245 | class HTTPMethodFallback(compat_urllib_request.BaseHandler): | |
1246 | """ | |
1247 | Fallback to GET if HEAD is not allowed (405 HTTP error) | |
1248 | """ | |
1249 | def http_error_405(self, req, fp, code, msg, headers): | |
1250 | fp.read() | |
1251 | fp.close() | |
1252 | ||
1253 | newheaders = dict((k,v) for k,v in req.headers.items() | |
1254 | if k.lower() not in ("content-length", "content-type")) | |
1255 | return self.parent.open(compat_urllib_request.Request(req.get_full_url(), | |
1256 | headers=newheaders, | |
1257 | origin_req_host=req.get_origin_req_host(), | |
1258 | unverifiable=True)) | |
1259 | ||
1260 | # Build our opener | |
1261 | opener = compat_urllib_request.OpenerDirector() | |
1262 | for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler, | |
1263 | HTTPMethodFallback, HEADRedirectHandler, | |
1264 | compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]: | |
1265 | opener.add_handler(handler()) | |
1266 | ||
1267 | response = opener.open(HeadRequest(url)) | |
1268 | new_url = response.geturl() | |
1269 | ||
1270 | if url == new_url: | |
1271 | return False | |
1272 | ||
1273 | self.report_following_redirect(new_url) | |
1274 | return new_url | |
1275 | ||
1276 | def _real_extract(self, url): | |
1277 | new_url = self._test_redirect(url) | |
1278 | if new_url: return [self.url_result(new_url)] | |
1279 | ||
1280 | video_id = url.split('/')[-1] | |
1281 | try: | |
1282 | webpage = self._download_webpage(url, video_id) | |
1283 | except ValueError as err: | |
1284 | # since this is the last-resort InfoExtractor, if | |
1285 | # this error is thrown, it'll be thrown here | |
1286 | raise ExtractorError(u'Invalid URL: %s' % url) | |
1287 | ||
1288 | self.report_extraction(video_id) | |
1289 | # Start with something easy: JW Player in SWFObject | |
1290 | mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) | |
1291 | if mobj is None: | |
1292 | # Broaden the search a little bit | |
1293 | mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) | |
1294 | if mobj is None: | |
1295 | # Broaden the search a little bit: JWPlayer JS loader | |
1296 | mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage) | |
1297 | if mobj is None: | |
1298 | raise ExtractorError(u'Invalid URL: %s' % url) | |
1299 | ||
1300 | # It's possible that one of the regexes | |
1301 | # matched, but returned an empty group: | |
1302 | if mobj.group(1) is None: | |
1303 | raise ExtractorError(u'Invalid URL: %s' % url) | |
1304 | ||
1305 | video_url = compat_urllib_parse.unquote(mobj.group(1)) | |
1306 | video_id = os.path.basename(video_url) | |
1307 | ||
1308 | # here's a fun little line of code for you: | |
1309 | video_extension = os.path.splitext(video_id)[1][1:] | |
1310 | video_id = os.path.splitext(video_id)[0] | |
1311 | ||
1312 | # it's tempting to parse this further, but you would | |
1313 | # have to take into account all the variations like | |
1314 | # Video Title - Site Name | |
1315 | # Site Name | Video Title | |
1316 | # Video Title - Tagline | Site Name | |
1317 | # and so on and so forth; it's just not practical | |
1318 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
1319 | if mobj is None: | |
1320 | raise ExtractorError(u'Unable to extract title') | |
1321 | video_title = mobj.group(1) | |
1322 | ||
1323 | # video uploader is domain name | |
1324 | mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) | |
1325 | if mobj is None: | |
1326 | raise ExtractorError(u'Unable to extract title') | |
1327 | video_uploader = mobj.group(1) | |
1328 | ||
1329 | return [{ | |
1330 | 'id': video_id, | |
1331 | 'url': video_url, | |
1332 | 'uploader': video_uploader, | |
1333 | 'upload_date': None, | |
1334 | 'title': video_title, | |
1335 | 'ext': video_extension, | |
1336 | }] | |
1337 | ||
1338 | ||
1339 | class YoutubeSearchIE(InfoExtractor): | |
1340 | """Information Extractor for YouTube search queries.""" | |
1341 | _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+' | |
1342 | _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' | |
1343 | _max_youtube_results = 1000 | |
1344 | IE_NAME = u'youtube:search' | |
1345 | ||
1346 | def report_download_page(self, query, pagenum): | |
1347 | """Report attempt to download search page with given number.""" | |
1348 | query = query.decode(preferredencoding()) | |
1349 | self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) | |
1350 | ||
1351 | def _real_extract(self, query): | |
1352 | mobj = re.match(self._VALID_URL, query) | |
1353 | if mobj is None: | |
1354 | raise ExtractorError(u'Invalid search query "%s"' % query) | |
1355 | ||
1356 | prefix, query = query.split(':') | |
1357 | prefix = prefix[8:] | |
1358 | query = query.encode('utf-8') | |
1359 | if prefix == '': | |
1360 | return self._get_n_results(query, 1) | |
1361 | elif prefix == 'all': | |
1362 | self._get_n_results(query, self._max_youtube_results) | |
1363 | else: | |
1364 | try: | |
1365 | n = int(prefix) | |
1366 | if n <= 0: | |
1367 | raise ExtractorError(u'Invalid download number %s for query "%s"' % (n, query)) | |
1368 | elif n > self._max_youtube_results: | |
1369 | self._downloader.report_warning(u'ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) | |
1370 | n = self._max_youtube_results | |
1371 | return self._get_n_results(query, n) | |
1372 | except ValueError: # parsing prefix as integer fails | |
1373 | return self._get_n_results(query, 1) | |
1374 | ||
1375 | def _get_n_results(self, query, n): | |
1376 | """Get a specified number of results for a query""" | |
1377 | ||
1378 | video_ids = [] | |
1379 | pagenum = 0 | |
1380 | limit = n | |
1381 | ||
1382 | while (50 * pagenum) < limit: | |
1383 | self.report_download_page(query, pagenum+1) | |
1384 | result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1) | |
1385 | request = compat_urllib_request.Request(result_url) | |
1386 | try: | |
1387 | data = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
1388 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1389 | raise ExtractorError(u'Unable to download API page: %s' % compat_str(err)) | |
1390 | api_response = json.loads(data)['data'] | |
1391 | ||
1392 | if not 'items' in api_response: | |
1393 | raise ExtractorError(u'[youtube] No video results') | |
1394 | ||
1395 | new_ids = list(video['id'] for video in api_response['items']) | |
1396 | video_ids += new_ids | |
1397 | ||
1398 | limit = min(n, api_response['totalItems']) | |
1399 | pagenum += 1 | |
1400 | ||
1401 | if len(video_ids) > n: | |
1402 | video_ids = video_ids[:n] | |
1403 | videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids] | |
1404 | return videos | |
1405 | ||
1406 | ||
1407 | class GoogleSearchIE(InfoExtractor): | |
1408 | """Information Extractor for Google Video search queries.""" | |
1409 | _VALID_URL = r'gvsearch(?P<prefix>|\d+|all):(?P<query>[\s\S]+)' | |
1410 | _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"' | |
1411 | _max_google_results = 1000 | |
1412 | IE_NAME = u'video.google:search' | |
1413 | ||
1414 | def _real_extract(self, query): | |
1415 | mobj = re.match(self._VALID_URL, query) | |
1416 | ||
1417 | prefix = mobj.group('prefix') | |
1418 | query = mobj.group('query') | |
1419 | if prefix == '': | |
1420 | return self._get_n_results(query, 1) | |
1421 | elif prefix == 'all': | |
1422 | return self._get_n_results(query, self._max_google_results) | |
1423 | else: | |
1424 | n = int(prefix) | |
1425 | if n <= 0: | |
1426 | raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query)) | |
1427 | elif n > self._max_google_results: | |
1428 | self._downloader.report_warning(u'gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) | |
1429 | n = self._max_google_results | |
1430 | return self._get_n_results(query, n) | |
1431 | ||
1432 | def _get_n_results(self, query, n): | |
1433 | """Get a specified number of results for a query""" | |
1434 | ||
1435 | res = { | |
1436 | '_type': 'playlist', | |
1437 | 'id': query, | |
1438 | 'entries': [] | |
1439 | } | |
1440 | ||
1441 | for pagenum in itertools.count(1): | |
1442 | result_url = u'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' % (compat_urllib_parse.quote_plus(query), pagenum*10) | |
1443 | print(result_url) | |
1444 | webpage = self._download_webpage(result_url, u'gvsearch:' + query, | |
1445 | note='Downloading result page ' + str(pagenum)) | |
1446 | ||
1447 | for mobj in re.finditer(r'<h3 class="r"><a href="([^"]+)"', webpage): | |
1448 | e = { | |
1449 | '_type': 'url', | |
1450 | 'url': mobj.group(1) | |
1451 | } | |
1452 | res['entries'].append(e) | |
1453 | ||
1454 | if (pagenum * 10 > n) or not re.search(self._MORE_PAGES_INDICATOR, webpage): | |
1455 | return res | |
1456 | ||
1457 | class YahooSearchIE(InfoExtractor): | |
1458 | """Information Extractor for Yahoo! Video search queries.""" | |
1459 | ||
1460 | _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+' | |
1461 | ||
1462 | _max_yahoo_results = 1000 | |
1463 | IE_NAME = u'screen.yahoo:search' | |
1464 | ||
1465 | def _real_extract(self, query): | |
1466 | mobj = re.match(self._VALID_URL, query) | |
1467 | if mobj is None: | |
1468 | raise ExtractorError(u'Invalid search query "%s"' % query) | |
1469 | ||
1470 | prefix, query = query.split(':') | |
1471 | prefix = prefix[8:] | |
1472 | query = query.encode('utf-8') | |
1473 | if prefix == '': | |
1474 | return self._get_n_results(query, 1) | |
1475 | elif prefix == 'all': | |
1476 | return self._get_n_results(query, self._max_yahoo_results) | |
1477 | else: | |
1478 | try: | |
1479 | n = int(prefix) | |
1480 | if n <= 0: | |
1481 | raise ExtractorError(u'Invalid download number %s for query "%s"' % (n, query)) | |
1482 | elif n > self._max_yahoo_results: | |
1483 | self._downloader.report_warning(u'yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) | |
1484 | n = self._max_yahoo_results | |
1485 | return self._get_n_results(query, n) | |
1486 | except ValueError: # parsing prefix as integer fails | |
1487 | return self._get_n_results(query, 1) | |
1488 | ||
1489 | def _get_n_results(self, query, n): | |
1490 | """Get a specified number of results for a query""" | |
1491 | ||
1492 | res = { | |
1493 | '_type': 'playlist', | |
1494 | 'id': query, | |
1495 | 'entries': [] | |
1496 | } | |
1497 | for pagenum in itertools.count(0): | |
1498 | result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30) | |
1499 | webpage = self._download_webpage(result_url, query, | |
1500 | note='Downloading results page '+str(pagenum+1)) | |
1501 | info = json.loads(webpage) | |
1502 | m = info[u'm'] | |
1503 | results = info[u'results'] | |
1504 | ||
1505 | for (i, r) in enumerate(results): | |
1506 | if (pagenum * 30) +i >= n: | |
1507 | break | |
1508 | mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r) | |
1509 | e = self.url_result('http://' + mobj.group('url'), 'Yahoo') | |
1510 | res['entries'].append(e) | |
1511 | if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )): | |
1512 | break | |
1513 | ||
1514 | return res | |
1515 | ||
1516 | ||
1517 | class YoutubePlaylistIE(InfoExtractor): | |
1518 | """Information Extractor for YouTube playlists.""" | |
1519 | ||
1520 | _VALID_URL = r"""(?: | |
1521 | (?:https?://)? | |
1522 | (?:\w+\.)? | |
1523 | youtube\.com/ | |
1524 | (?: | |
1525 | (?:course|view_play_list|my_playlists|artist|playlist|watch) | |
1526 | \? (?:.*?&)*? (?:p|a|list)= | |
1527 | | p/ | |
1528 | ) | |
1529 | ((?:PL|EC|UU)?[0-9A-Za-z-_]{10,}) | |
1530 | .* | |
1531 | | | |
1532 | ((?:PL|EC|UU)[0-9A-Za-z-_]{10,}) | |
1533 | )""" | |
1534 | _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/playlists/%s?max-results=%i&start-index=%i&v=2&alt=json' | |
1535 | _MAX_RESULTS = 50 | |
1536 | IE_NAME = u'youtube:playlist' | |
1537 | ||
1538 | @classmethod | |
1539 | def suitable(cls, url): | |
1540 | """Receives a URL and returns True if suitable for this IE.""" | |
1541 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None | |
1542 | ||
1543 | def _real_extract(self, url): | |
1544 | # Extract playlist id | |
1545 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) | |
1546 | if mobj is None: | |
1547 | raise ExtractorError(u'Invalid URL: %s' % url) | |
1548 | ||
1549 | # Download playlist videos from API | |
1550 | playlist_id = mobj.group(1) or mobj.group(2) | |
1551 | page_num = 1 | |
1552 | videos = [] | |
1553 | ||
1554 | while True: | |
1555 | url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, self._MAX_RESULTS * (page_num - 1) + 1) | |
1556 | page = self._download_webpage(url, playlist_id, u'Downloading page #%s' % page_num) | |
1557 | ||
1558 | try: | |
1559 | response = json.loads(page) | |
1560 | except ValueError as err: | |
1561 | raise ExtractorError(u'Invalid JSON in API response: ' + compat_str(err)) | |
1562 | ||
1563 | if 'feed' not in response: | |
1564 | raise ExtractorError(u'Got a malformed response from YouTube API') | |
1565 | playlist_title = response['feed']['title']['$t'] | |
1566 | if 'entry' not in response['feed']: | |
1567 | # Number of videos is a multiple of self._MAX_RESULTS | |
1568 | break | |
1569 | ||
1570 | videos += [ (entry['yt$position']['$t'], entry['content']['src']) | |
1571 | for entry in response['feed']['entry'] | |
1572 | if 'content' in entry ] | |
1573 | ||
1574 | if len(response['feed']['entry']) < self._MAX_RESULTS: | |
1575 | break | |
1576 | page_num += 1 | |
1577 | ||
1578 | videos = [v[1] for v in sorted(videos)] | |
1579 | ||
1580 | url_results = [self.url_result(url, 'Youtube') for url in videos] | |
1581 | return [self.playlist_result(url_results, playlist_id, playlist_title)] | |
1582 | ||
1583 | ||
1584 | class YoutubeChannelIE(InfoExtractor): | |
1585 | """Information Extractor for YouTube channels.""" | |
1586 | ||
1587 | _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)" | |
1588 | _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en' | |
1589 | _MORE_PAGES_INDICATOR = 'yt-uix-load-more' | |
1590 | _MORE_PAGES_URL = 'http://www.youtube.com/channel_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s' | |
1591 | IE_NAME = u'youtube:channel' | |
1592 | ||
1593 | def extract_videos_from_page(self, page): | |
1594 | ids_in_page = [] | |
1595 | for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&?', page): | |
1596 | if mobj.group(1) not in ids_in_page: | |
1597 | ids_in_page.append(mobj.group(1)) | |
1598 | return ids_in_page | |
1599 | ||
1600 | def _real_extract(self, url): | |
1601 | # Extract channel id | |
1602 | mobj = re.match(self._VALID_URL, url) | |
1603 | if mobj is None: | |
1604 | raise ExtractorError(u'Invalid URL: %s' % url) | |
1605 | ||
1606 | # Download channel page | |
1607 | channel_id = mobj.group(1) | |
1608 | video_ids = [] | |
1609 | pagenum = 1 | |
1610 | ||
1611 | url = self._TEMPLATE_URL % (channel_id, pagenum) | |
1612 | page = self._download_webpage(url, channel_id, | |
1613 | u'Downloading page #%s' % pagenum) | |
1614 | ||
1615 | # Extract video identifiers | |
1616 | ids_in_page = self.extract_videos_from_page(page) | |
1617 | video_ids.extend(ids_in_page) | |
1618 | ||
1619 | # Download any subsequent channel pages using the json-based channel_ajax query | |
1620 | if self._MORE_PAGES_INDICATOR in page: | |
1621 | while True: | |
1622 | pagenum = pagenum + 1 | |
1623 | ||
1624 | url = self._MORE_PAGES_URL % (pagenum, channel_id) | |
1625 | page = self._download_webpage(url, channel_id, | |
1626 | u'Downloading page #%s' % pagenum) | |
1627 | ||
1628 | page = json.loads(page) | |
1629 | ||
1630 | ids_in_page = self.extract_videos_from_page(page['content_html']) | |
1631 | video_ids.extend(ids_in_page) | |
1632 | ||
1633 | if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']: | |
1634 | break | |
1635 | ||
1636 | self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) | |
1637 | ||
1638 | urls = ['http://www.youtube.com/watch?v=%s' % id for id in video_ids] | |
1639 | url_entries = [self.url_result(url, 'Youtube') for url in urls] | |
1640 | return [self.playlist_result(url_entries, channel_id)] | |
1641 | ||
1642 | ||
1643 | class YoutubeUserIE(InfoExtractor): | |
1644 | """Information Extractor for YouTube users.""" | |
1645 | ||
1646 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)' | |
1647 | _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' | |
1648 | _GDATA_PAGE_SIZE = 50 | |
1649 | _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' | |
1650 | _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]' | |
1651 | IE_NAME = u'youtube:user' | |
1652 | ||
1653 | def _real_extract(self, url): | |
1654 | # Extract username | |
1655 | mobj = re.match(self._VALID_URL, url) | |
1656 | if mobj is None: | |
1657 | raise ExtractorError(u'Invalid URL: %s' % url) | |
1658 | ||
1659 | username = mobj.group(1) | |
1660 | ||
1661 | # Download video ids using YouTube Data API. Result size per | |
1662 | # query is limited (currently to 50 videos) so we need to query | |
1663 | # page by page until there are no video ids - it means we got | |
1664 | # all of them. | |
1665 | ||
1666 | video_ids = [] | |
1667 | pagenum = 0 | |
1668 | ||
1669 | while True: | |
1670 | start_index = pagenum * self._GDATA_PAGE_SIZE + 1 | |
1671 | ||
1672 | gdata_url = self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index) | |
1673 | page = self._download_webpage(gdata_url, username, | |
1674 | u'Downloading video ids from %d to %d' % (start_index, start_index + self._GDATA_PAGE_SIZE)) | |
1675 | ||
1676 | # Extract video identifiers | |
1677 | ids_in_page = [] | |
1678 | ||
1679 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
1680 | if mobj.group(1) not in ids_in_page: | |
1681 | ids_in_page.append(mobj.group(1)) | |
1682 | ||
1683 | video_ids.extend(ids_in_page) | |
1684 | ||
1685 | # A little optimization - if current page is not | |
1686 | # "full", ie. does not contain PAGE_SIZE video ids then | |
1687 | # we can assume that this page is the last one - there | |
1688 | # are no more ids on further pages - no need to query | |
1689 | # again. | |
1690 | ||
1691 | if len(ids_in_page) < self._GDATA_PAGE_SIZE: | |
1692 | break | |
1693 | ||
1694 | pagenum += 1 | |
1695 | ||
1696 | urls = ['http://www.youtube.com/watch?v=%s' % video_id for video_id in video_ids] | |
1697 | url_results = [self.url_result(url, 'Youtube') for url in urls] | |
1698 | return [self.playlist_result(url_results, playlist_title = username)] | |
1699 | ||
1700 | ||
1701 | class BlipTVUserIE(InfoExtractor): | |
1702 | """Information Extractor for blip.tv users.""" | |
1703 | ||
1704 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' | |
1705 | _PAGE_SIZE = 12 | |
1706 | IE_NAME = u'blip.tv:user' | |
1707 | ||
1708 | def _real_extract(self, url): | |
1709 | # Extract username | |
1710 | mobj = re.match(self._VALID_URL, url) | |
1711 | if mobj is None: | |
1712 | raise ExtractorError(u'Invalid URL: %s' % url) | |
1713 | ||
1714 | username = mobj.group(1) | |
1715 | ||
1716 | page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' | |
1717 | ||
1718 | page = self._download_webpage(url, username, u'Downloading user page') | |
1719 | mobj = re.search(r'data-users-id="([^"]+)"', page) | |
1720 | page_base = page_base % mobj.group(1) | |
1721 | ||
1722 | ||
1723 | # Download video ids using BlipTV Ajax calls. Result size per | |
1724 | # query is limited (currently to 12 videos) so we need to query | |
1725 | # page by page until there are no video ids - it means we got | |
1726 | # all of them. | |
1727 | ||
1728 | video_ids = [] | |
1729 | pagenum = 1 | |
1730 | ||
1731 | while True: | |
1732 | url = page_base + "&page=" + str(pagenum) | |
1733 | page = self._download_webpage(url, username, | |
1734 | u'Downloading video ids from page %d' % pagenum) | |
1735 | ||
1736 | # Extract video identifiers | |
1737 | ids_in_page = [] | |
1738 | ||
1739 | for mobj in re.finditer(r'href="/([^"]+)"', page): | |
1740 | if mobj.group(1) not in ids_in_page: | |
1741 | ids_in_page.append(unescapeHTML(mobj.group(1))) | |
1742 | ||
1743 | video_ids.extend(ids_in_page) | |
1744 | ||
1745 | # A little optimization - if current page is not | |
1746 | # "full", ie. does not contain PAGE_SIZE video ids then | |
1747 | # we can assume that this page is the last one - there | |
1748 | # are no more ids on further pages - no need to query | |
1749 | # again. | |
1750 | ||
1751 | if len(ids_in_page) < self._PAGE_SIZE: | |
1752 | break | |
1753 | ||
1754 | pagenum += 1 | |
1755 | ||
1756 | urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids] | |
1757 | url_entries = [self.url_result(url, 'BlipTV') for url in urls] | |
1758 | return [self.playlist_result(url_entries, playlist_title = username)] | |
1759 | ||
1760 | ||
1761 | class DepositFilesIE(InfoExtractor): | |
1762 | """Information extractor for depositfiles.com""" | |
1763 | ||
1764 | _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' | |
1765 | ||
1766 | def _real_extract(self, url): | |
1767 | file_id = url.split('/')[-1] | |
1768 | # Rebuild url in english locale | |
1769 | url = 'http://depositfiles.com/en/files/' + file_id | |
1770 | ||
1771 | # Retrieve file webpage with 'Free download' button pressed | |
1772 | free_download_indication = { 'gateway_result' : '1' } | |
1773 | request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication)) | |
1774 | try: | |
1775 | self.report_download_webpage(file_id) | |
1776 | webpage = compat_urllib_request.urlopen(request).read() | |
1777 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1778 | raise ExtractorError(u'Unable to retrieve file webpage: %s' % compat_str(err)) | |
1779 | ||
1780 | # Search for the real file URL | |
1781 | mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage) | |
1782 | if (mobj is None) or (mobj.group(1) is None): | |
1783 | # Try to figure out reason of the error. | |
1784 | mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL) | |
1785 | if (mobj is not None) and (mobj.group(1) is not None): | |
1786 | restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() | |
1787 | raise ExtractorError(u'%s' % restriction_message) | |
1788 | else: | |
1789 | raise ExtractorError(u'Unable to extract download URL from: %s' % url) | |
1790 | ||
1791 | file_url = mobj.group(1) | |
1792 | file_extension = os.path.splitext(file_url)[1][1:] | |
1793 | ||
1794 | # Search for file title | |
1795 | mobj = re.search(r'<b title="(.*?)">', webpage) | |
1796 | if mobj is None: | |
1797 | raise ExtractorError(u'Unable to extract title') | |
1798 | file_title = mobj.group(1).decode('utf-8') | |
1799 | ||
1800 | return [{ | |
1801 | 'id': file_id.decode('utf-8'), | |
1802 | 'url': file_url.decode('utf-8'), | |
1803 | 'uploader': None, | |
1804 | 'upload_date': None, | |
1805 | 'title': file_title, | |
1806 | 'ext': file_extension.decode('utf-8'), | |
1807 | }] | |
1808 | ||
1809 | ||
1810 | class FacebookIE(InfoExtractor): | |
1811 | """Information Extractor for Facebook""" | |
1812 | ||
1813 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' | |
1814 | _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' | |
1815 | _NETRC_MACHINE = 'facebook' | |
1816 | IE_NAME = u'facebook' | |
1817 | ||
1818 | def report_login(self): | |
1819 | """Report attempt to log in.""" | |
1820 | self.to_screen(u'Logging in') | |
1821 | ||
1822 | def _real_initialize(self): | |
1823 | if self._downloader is None: | |
1824 | return | |
1825 | ||
1826 | useremail = None | |
1827 | password = None | |
1828 | downloader_params = self._downloader.params | |
1829 | ||
1830 | # Attempt to use provided username and password or .netrc data | |
1831 | if downloader_params.get('username', None) is not None: | |
1832 | useremail = downloader_params['username'] | |
1833 | password = downloader_params['password'] | |
1834 | elif downloader_params.get('usenetrc', False): | |
1835 | try: | |
1836 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
1837 | if info is not None: | |
1838 | useremail = info[0] | |
1839 | password = info[2] | |
1840 | else: | |
1841 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
1842 | except (IOError, netrc.NetrcParseError) as err: | |
1843 | self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) | |
1844 | return | |
1845 | ||
1846 | if useremail is None: | |
1847 | return | |
1848 | ||
1849 | # Log in | |
1850 | login_form = { | |
1851 | 'email': useremail, | |
1852 | 'pass': password, | |
1853 | 'login': 'Log+In' | |
1854 | } | |
1855 | request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) | |
1856 | try: | |
1857 | self.report_login() | |
1858 | login_results = compat_urllib_request.urlopen(request).read() | |
1859 | if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: | |
1860 | self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') | |
1861 | return | |
1862 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1863 | self._downloader.report_warning(u'unable to log in: %s' % compat_str(err)) | |
1864 | return | |
1865 | ||
1866 | def _real_extract(self, url): | |
1867 | mobj = re.match(self._VALID_URL, url) | |
1868 | if mobj is None: | |
1869 | raise ExtractorError(u'Invalid URL: %s' % url) | |
1870 | video_id = mobj.group('ID') | |
1871 | ||
1872 | url = 'https://www.facebook.com/video/video.php?v=%s' % video_id | |
1873 | webpage = self._download_webpage(url, video_id) | |
1874 | ||
1875 | BEFORE = '{swf.addParam(param[0], param[1]);});\n' | |
1876 | AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' | |
1877 | m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) | |
1878 | if not m: | |
1879 | raise ExtractorError(u'Cannot parse data') | |
1880 | data = dict(json.loads(m.group(1))) | |
1881 | params_raw = compat_urllib_parse.unquote(data['params']) | |
1882 | params = json.loads(params_raw) | |
1883 | video_data = params['video_data'][0] | |
1884 | video_url = video_data.get('hd_src') | |
1885 | if not video_url: | |
1886 | video_url = video_data['sd_src'] | |
1887 | if not video_url: | |
1888 | raise ExtractorError(u'Cannot find video URL') | |
1889 | video_duration = int(video_data['video_duration']) | |
1890 | thumbnail = video_data['thumbnail_src'] | |
1891 | ||
1892 | m = re.search('<h2 class="uiHeaderTitle">([^<]+)</h2>', webpage) | |
1893 | if not m: | |
1894 | raise ExtractorError(u'Cannot find title in webpage') | |
1895 | video_title = unescapeHTML(m.group(1)) | |
1896 | ||
1897 | info = { | |
1898 | 'id': video_id, | |
1899 | 'title': video_title, | |
1900 | 'url': video_url, | |
1901 | 'ext': 'mp4', | |
1902 | 'duration': video_duration, | |
1903 | 'thumbnail': thumbnail, | |
1904 | } | |
1905 | return [info] | |
1906 | ||
1907 | ||
1908 | class BlipTVIE(InfoExtractor): | |
1909 | """Information extractor for blip.tv""" | |
1910 | ||
1911 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' | |
1912 | _URL_EXT = r'^.*\.([a-z0-9]+)$' | |
1913 | IE_NAME = u'blip.tv' | |
1914 | ||
1915 | def report_direct_download(self, title): | |
1916 | """Report information extraction.""" | |
1917 | self.to_screen(u'%s: Direct download detected' % title) | |
1918 | ||
1919 | def _real_extract(self, url): | |
1920 | mobj = re.match(self._VALID_URL, url) | |
1921 | if mobj is None: | |
1922 | raise ExtractorError(u'Invalid URL: %s' % url) | |
1923 | ||
1924 | urlp = compat_urllib_parse_urlparse(url) | |
1925 | if urlp.path.startswith('/play/'): | |
1926 | request = compat_urllib_request.Request(url) | |
1927 | response = compat_urllib_request.urlopen(request) | |
1928 | redirecturl = response.geturl() | |
1929 | rurlp = compat_urllib_parse_urlparse(redirecturl) | |
1930 | file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2] | |
1931 | url = 'http://blip.tv/a/a-' + file_id | |
1932 | return self._real_extract(url) | |
1933 | ||
1934 | ||
1935 | if '?' in url: | |
1936 | cchar = '&' | |
1937 | else: | |
1938 | cchar = '?' | |
1939 | json_url = url + cchar + 'skin=json&version=2&no_wrap=1' | |
1940 | request = compat_urllib_request.Request(json_url) | |
1941 | request.add_header('User-Agent', 'iTunes/10.6.1') | |
1942 | self.report_extraction(mobj.group(1)) | |
1943 | info = None | |
1944 | try: | |
1945 | urlh = compat_urllib_request.urlopen(request) | |
1946 | if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download | |
1947 | basename = url.split('/')[-1] | |
1948 | title,ext = os.path.splitext(basename) | |
1949 | title = title.decode('UTF-8') | |
1950 | ext = ext.replace('.', '') | |
1951 | self.report_direct_download(title) | |
1952 | info = { | |
1953 | 'id': title, | |
1954 | 'url': url, | |
1955 | 'uploader': None, | |
1956 | 'upload_date': None, | |
1957 | 'title': title, | |
1958 | 'ext': ext, | |
1959 | 'urlhandle': urlh | |
1960 | } | |
1961 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1962 | raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) | |
1963 | if info is None: # Regular URL | |
1964 | try: | |
1965 | json_code_bytes = urlh.read() | |
1966 | json_code = json_code_bytes.decode('utf-8') | |
1967 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1968 | raise ExtractorError(u'Unable to read video info webpage: %s' % compat_str(err)) | |
1969 | ||
1970 | try: | |
1971 | json_data = json.loads(json_code) | |
1972 | if 'Post' in json_data: | |
1973 | data = json_data['Post'] | |
1974 | else: | |
1975 | data = json_data | |
1976 | ||
1977 | upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') | |
1978 | video_url = data['media']['url'] | |
1979 | umobj = re.match(self._URL_EXT, video_url) | |
1980 | if umobj is None: | |
1981 | raise ValueError('Can not determine filename extension') | |
1982 | ext = umobj.group(1) | |
1983 | ||
1984 | info = { | |
1985 | 'id': data['item_id'], | |
1986 | 'url': video_url, | |
1987 | 'uploader': data['display_name'], | |
1988 | 'upload_date': upload_date, | |
1989 | 'title': data['title'], | |
1990 | 'ext': ext, | |
1991 | 'format': data['media']['mimeType'], | |
1992 | 'thumbnail': data['thumbnailUrl'], | |
1993 | 'description': data['description'], | |
1994 | 'player_url': data['embedUrl'], | |
1995 | 'user_agent': 'iTunes/10.6.1', | |
1996 | } | |
1997 | except (ValueError,KeyError) as err: | |
1998 | raise ExtractorError(u'Unable to parse video information: %s' % repr(err)) | |
1999 | ||
2000 | return [info] | |
2001 | ||
2002 | ||
2003 | class MyVideoIE(InfoExtractor): | |
2004 | """Information Extractor for myvideo.de.""" | |
2005 | ||
2006 | _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' | |
2007 | IE_NAME = u'myvideo' | |
2008 | ||
2009 | def _real_extract(self,url): | |
2010 | mobj = re.match(self._VALID_URL, url) | |
2011 | if mobj is None: | |
2012 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2013 | ||
2014 | video_id = mobj.group(1) | |
2015 | ||
2016 | # Get video webpage | |
2017 | webpage_url = 'http://www.myvideo.de/watch/%s' % video_id | |
2018 | webpage = self._download_webpage(webpage_url, video_id) | |
2019 | ||
2020 | self.report_extraction(video_id) | |
2021 | mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/.*?\.jpg\'', | |
2022 | webpage) | |
2023 | if mobj is None: | |
2024 | raise ExtractorError(u'Unable to extract media URL') | |
2025 | video_url = mobj.group(1) + ('/%s.flv' % video_id) | |
2026 | ||
2027 | mobj = re.search('<title>([^<]+)</title>', webpage) | |
2028 | if mobj is None: | |
2029 | raise ExtractorError(u'Unable to extract title') | |
2030 | ||
2031 | video_title = mobj.group(1) | |
2032 | ||
2033 | return [{ | |
2034 | 'id': video_id, | |
2035 | 'url': video_url, | |
2036 | 'uploader': None, | |
2037 | 'upload_date': None, | |
2038 | 'title': video_title, | |
2039 | 'ext': u'flv', | |
2040 | }] | |
2041 | ||
2042 | class ComedyCentralIE(InfoExtractor): | |
2043 | """Information extractor for The Daily Show and Colbert Report """ | |
2044 | ||
2045 | # urls can be abbreviations like :thedailyshow or :colbert | |
2046 | # urls for episodes like: | |
2047 | # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day | |
2048 | # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news | |
2049 | # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524 | |
2050 | _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport) | |
2051 | |(https?://)?(www\.)? | |
2052 | (?P<showname>thedailyshow|colbertnation)\.com/ | |
2053 | (full-episodes/(?P<episode>.*)| | |
2054 | (?P<clip> | |
2055 | (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) | |
2056 | |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))))) | |
2057 | $""" | |
2058 | ||
2059 | _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] | |
2060 | ||
2061 | _video_extensions = { | |
2062 | '3500': 'mp4', | |
2063 | '2200': 'mp4', | |
2064 | '1700': 'mp4', | |
2065 | '1200': 'mp4', | |
2066 | '750': 'mp4', | |
2067 | '400': 'mp4', | |
2068 | } | |
2069 | _video_dimensions = { | |
2070 | '3500': '1280x720', | |
2071 | '2200': '960x540', | |
2072 | '1700': '768x432', | |
2073 | '1200': '640x360', | |
2074 | '750': '512x288', | |
2075 | '400': '384x216', | |
2076 | } | |
2077 | ||
2078 | @classmethod | |
2079 | def suitable(cls, url): | |
2080 | """Receives a URL and returns True if suitable for this IE.""" | |
2081 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None | |
2082 | ||
2083 | def _print_formats(self, formats): | |
2084 | print('Available formats:') | |
2085 | for x in formats: | |
2086 | print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???'))) | |
2087 | ||
2088 | ||
2089 | def _real_extract(self, url): | |
2090 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) | |
2091 | if mobj is None: | |
2092 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2093 | ||
2094 | if mobj.group('shortname'): | |
2095 | if mobj.group('shortname') in ('tds', 'thedailyshow'): | |
2096 | url = u'http://www.thedailyshow.com/full-episodes/' | |
2097 | else: | |
2098 | url = u'http://www.colbertnation.com/full-episodes/' | |
2099 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) | |
2100 | assert mobj is not None | |
2101 | ||
2102 | if mobj.group('clip'): | |
2103 | if mobj.group('showname') == 'thedailyshow': | |
2104 | epTitle = mobj.group('tdstitle') | |
2105 | else: | |
2106 | epTitle = mobj.group('cntitle') | |
2107 | dlNewest = False | |
2108 | else: | |
2109 | dlNewest = not mobj.group('episode') | |
2110 | if dlNewest: | |
2111 | epTitle = mobj.group('showname') | |
2112 | else: | |
2113 | epTitle = mobj.group('episode') | |
2114 | ||
2115 | self.report_extraction(epTitle) | |
2116 | webpage,htmlHandle = self._download_webpage_handle(url, epTitle) | |
2117 | if dlNewest: | |
2118 | url = htmlHandle.geturl() | |
2119 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) | |
2120 | if mobj is None: | |
2121 | raise ExtractorError(u'Invalid redirected URL: ' + url) | |
2122 | if mobj.group('episode') == '': | |
2123 | raise ExtractorError(u'Redirected URL is still not specific: ' + url) | |
2124 | epTitle = mobj.group('episode') | |
2125 | ||
2126 | mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage) | |
2127 | ||
2128 | if len(mMovieParams) == 0: | |
2129 | # The Colbert Report embeds the information in a without | |
2130 | # a URL prefix; so extract the alternate reference | |
2131 | # and then add the URL prefix manually. | |
2132 | ||
2133 | altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage) | |
2134 | if len(altMovieParams) == 0: | |
2135 | raise ExtractorError(u'unable to find Flash URL in webpage ' + url) | |
2136 | else: | |
2137 | mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] | |
2138 | ||
2139 | uri = mMovieParams[0][1] | |
2140 | indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri}) | |
2141 | indexXml = self._download_webpage(indexUrl, epTitle, | |
2142 | u'Downloading show index', | |
2143 | u'unable to download episode index') | |
2144 | ||
2145 | results = [] | |
2146 | ||
2147 | idoc = xml.etree.ElementTree.fromstring(indexXml) | |
2148 | itemEls = idoc.findall('.//item') | |
2149 | for partNum,itemEl in enumerate(itemEls): | |
2150 | mediaId = itemEl.findall('./guid')[0].text | |
2151 | shortMediaId = mediaId.split(':')[-1] | |
2152 | showId = mediaId.split(':')[-2].replace('.com', '') | |
2153 | officialTitle = itemEl.findall('./title')[0].text | |
2154 | officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text) | |
2155 | ||
2156 | configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + | |
2157 | compat_urllib_parse.urlencode({'uri': mediaId})) | |
2158 | configXml = self._download_webpage(configUrl, epTitle, | |
2159 | u'Downloading configuration for %s' % shortMediaId) | |
2160 | ||
2161 | cdoc = xml.etree.ElementTree.fromstring(configXml) | |
2162 | turls = [] | |
2163 | for rendition in cdoc.findall('.//rendition'): | |
2164 | finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) | |
2165 | turls.append(finfo) | |
2166 | ||
2167 | if len(turls) == 0: | |
2168 | self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found') | |
2169 | continue | |
2170 | ||
2171 | if self._downloader.params.get('listformats', None): | |
2172 | self._print_formats([i[0] for i in turls]) | |
2173 | return | |
2174 | ||
2175 | # For now, just pick the highest bitrate | |
2176 | format,rtmp_video_url = turls[-1] | |
2177 | ||
2178 | # Get the format arg from the arg stream | |
2179 | req_format = self._downloader.params.get('format', None) | |
2180 | ||
2181 | # Select format if we can find one | |
2182 | for f,v in turls: | |
2183 | if f == req_format: | |
2184 | format, rtmp_video_url = f, v | |
2185 | break | |
2186 | ||
2187 | m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url) | |
2188 | if not m: | |
2189 | raise ExtractorError(u'Cannot transform RTMP url') | |
2190 | base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' | |
2191 | video_url = base + m.group('finalid') | |
2192 | ||
2193 | effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1) | |
2194 | info = { | |
2195 | 'id': shortMediaId, | |
2196 | 'url': video_url, | |
2197 | 'uploader': showId, | |
2198 | 'upload_date': officialDate, | |
2199 | 'title': effTitle, | |
2200 | 'ext': 'mp4', | |
2201 | 'format': format, | |
2202 | 'thumbnail': None, | |
2203 | 'description': officialTitle, | |
2204 | } | |
2205 | results.append(info) | |
2206 | ||
2207 | return results | |
2208 | ||
2209 | ||
2210 | class EscapistIE(InfoExtractor): | |
2211 | """Information extractor for The Escapist """ | |
2212 | ||
2213 | _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$' | |
2214 | IE_NAME = u'escapist' | |
2215 | ||
2216 | def _real_extract(self, url): | |
2217 | mobj = re.match(self._VALID_URL, url) | |
2218 | if mobj is None: | |
2219 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2220 | showName = mobj.group('showname') | |
2221 | videoId = mobj.group('episode') | |
2222 | ||
2223 | self.report_extraction(showName) | |
2224 | webPage = self._download_webpage(url, showName) | |
2225 | ||
2226 | descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) | |
2227 | description = unescapeHTML(descMatch.group(1)) | |
2228 | imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) | |
2229 | imgUrl = unescapeHTML(imgMatch.group(1)) | |
2230 | playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage) | |
2231 | playerUrl = unescapeHTML(playerUrlMatch.group(1)) | |
2232 | configUrlMatch = re.search('config=(.*)$', playerUrl) | |
2233 | configUrl = compat_urllib_parse.unquote(configUrlMatch.group(1)) | |
2234 | ||
2235 | configJSON = self._download_webpage(configUrl, showName, | |
2236 | u'Downloading configuration', | |
2237 | u'unable to download configuration') | |
2238 | ||
2239 | # Technically, it's JavaScript, not JSON | |
2240 | configJSON = configJSON.replace("'", '"') | |
2241 | ||
2242 | try: | |
2243 | config = json.loads(configJSON) | |
2244 | except (ValueError,) as err: | |
2245 | raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err)) | |
2246 | ||
2247 | playlist = config['playlist'] | |
2248 | videoUrl = playlist[1]['url'] | |
2249 | ||
2250 | info = { | |
2251 | 'id': videoId, | |
2252 | 'url': videoUrl, | |
2253 | 'uploader': showName, | |
2254 | 'upload_date': None, | |
2255 | 'title': showName, | |
2256 | 'ext': 'mp4', | |
2257 | 'thumbnail': imgUrl, | |
2258 | 'description': description, | |
2259 | 'player_url': playerUrl, | |
2260 | } | |
2261 | ||
2262 | return [info] | |
2263 | ||
2264 | class CollegeHumorIE(InfoExtractor): | |
2265 | """Information extractor for collegehumor.com""" | |
2266 | ||
2267 | _WORKING = False | |
2268 | _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$' | |
2269 | IE_NAME = u'collegehumor' | |
2270 | ||
2271 | def report_manifest(self, video_id): | |
2272 | """Report information extraction.""" | |
2273 | self.to_screen(u'%s: Downloading XML manifest' % video_id) | |
2274 | ||
2275 | def _real_extract(self, url): | |
2276 | mobj = re.match(self._VALID_URL, url) | |
2277 | if mobj is None: | |
2278 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2279 | video_id = mobj.group('videoid') | |
2280 | ||
2281 | info = { | |
2282 | 'id': video_id, | |
2283 | 'uploader': None, | |
2284 | 'upload_date': None, | |
2285 | } | |
2286 | ||
2287 | self.report_extraction(video_id) | |
2288 | xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id | |
2289 | try: | |
2290 | metaXml = compat_urllib_request.urlopen(xmlUrl).read() | |
2291 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2292 | raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err)) | |
2293 | ||
2294 | mdoc = xml.etree.ElementTree.fromstring(metaXml) | |
2295 | try: | |
2296 | videoNode = mdoc.findall('./video')[0] | |
2297 | info['description'] = videoNode.findall('./description')[0].text | |
2298 | info['title'] = videoNode.findall('./caption')[0].text | |
2299 | info['thumbnail'] = videoNode.findall('./thumbnail')[0].text | |
2300 | manifest_url = videoNode.findall('./file')[0].text | |
2301 | except IndexError: | |
2302 | raise ExtractorError(u'Invalid metadata XML file') | |
2303 | ||
2304 | manifest_url += '?hdcore=2.10.3' | |
2305 | self.report_manifest(video_id) | |
2306 | try: | |
2307 | manifestXml = compat_urllib_request.urlopen(manifest_url).read() | |
2308 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2309 | raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err)) | |
2310 | ||
2311 | adoc = xml.etree.ElementTree.fromstring(manifestXml) | |
2312 | try: | |
2313 | media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] | |
2314 | node_id = media_node.attrib['url'] | |
2315 | video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text | |
2316 | except IndexError as err: | |
2317 | raise ExtractorError(u'Invalid manifest file') | |
2318 | ||
2319 | url_pr = compat_urllib_parse_urlparse(manifest_url) | |
2320 | url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1' | |
2321 | ||
2322 | info['url'] = url | |
2323 | info['ext'] = 'f4f' | |
2324 | return [info] | |
2325 | ||
2326 | ||
2327 | class XVideosIE(InfoExtractor): | |
2328 | """Information extractor for xvideos.com""" | |
2329 | ||
2330 | _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' | |
2331 | IE_NAME = u'xvideos' | |
2332 | ||
2333 | def _real_extract(self, url): | |
2334 | mobj = re.match(self._VALID_URL, url) | |
2335 | if mobj is None: | |
2336 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2337 | video_id = mobj.group(1) | |
2338 | ||
2339 | webpage = self._download_webpage(url, video_id) | |
2340 | ||
2341 | self.report_extraction(video_id) | |
2342 | ||
2343 | ||
2344 | # Extract video URL | |
2345 | mobj = re.search(r'flv_url=(.+?)&', webpage) | |
2346 | if mobj is None: | |
2347 | raise ExtractorError(u'Unable to extract video url') | |
2348 | video_url = compat_urllib_parse.unquote(mobj.group(1)) | |
2349 | ||
2350 | ||
2351 | # Extract title | |
2352 | mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage) | |
2353 | if mobj is None: | |
2354 | raise ExtractorError(u'Unable to extract video title') | |
2355 | video_title = mobj.group(1) | |
2356 | ||
2357 | ||
2358 | # Extract video thumbnail | |
2359 | 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) | |
2360 | if mobj is None: | |
2361 | raise ExtractorError(u'Unable to extract video thumbnail') | |
2362 | video_thumbnail = mobj.group(0) | |
2363 | ||
2364 | info = { | |
2365 | 'id': video_id, | |
2366 | 'url': video_url, | |
2367 | 'uploader': None, | |
2368 | 'upload_date': None, | |
2369 | 'title': video_title, | |
2370 | 'ext': 'flv', | |
2371 | 'thumbnail': video_thumbnail, | |
2372 | 'description': None, | |
2373 | } | |
2374 | ||
2375 | return [info] | |
2376 | ||
2377 | ||
2378 | class SoundcloudIE(InfoExtractor): | |
2379 | """Information extractor for soundcloud.com | |
2380 | To access the media, the uid of the song and a stream token | |
2381 | must be extracted from the page source and the script must make | |
2382 | a request to media.soundcloud.com/crossdomain.xml. Then | |
2383 | the media can be grabbed by requesting from an url composed | |
2384 | of the stream token and uid | |
2385 | """ | |
2386 | ||
2387 | _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)' | |
2388 | IE_NAME = u'soundcloud' | |
2389 | ||
2390 | def report_resolve(self, video_id): | |
2391 | """Report information extraction.""" | |
2392 | self.to_screen(u'%s: Resolving id' % video_id) | |
2393 | ||
2394 | def _real_extract(self, url): | |
2395 | mobj = re.match(self._VALID_URL, url) | |
2396 | if mobj is None: | |
2397 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2398 | ||
2399 | # extract uploader (which is in the url) | |
2400 | uploader = mobj.group(1) | |
2401 | # extract simple title (uploader + slug of song title) | |
2402 | slug_title = mobj.group(2) | |
2403 | simple_title = uploader + u'-' + slug_title | |
2404 | full_title = '%s/%s' % (uploader, slug_title) | |
2405 | ||
2406 | self.report_resolve(full_title) | |
2407 | ||
2408 | url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title) | |
2409 | resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28' | |
2410 | info_json = self._download_webpage(resolv_url, full_title, u'Downloading info JSON') | |
2411 | ||
2412 | info = json.loads(info_json) | |
2413 | video_id = info['id'] | |
2414 | self.report_extraction(full_title) | |
2415 | ||
2416 | streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28' | |
2417 | stream_json = self._download_webpage(streams_url, full_title, | |
2418 | u'Downloading stream definitions', | |
2419 | u'unable to download stream definitions') | |
2420 | ||
2421 | streams = json.loads(stream_json) | |
2422 | mediaURL = streams['http_mp3_128_url'] | |
2423 | upload_date = unified_strdate(info['created_at']) | |
2424 | ||
2425 | return [{ | |
2426 | 'id': info['id'], | |
2427 | 'url': mediaURL, | |
2428 | 'uploader': info['user']['username'], | |
2429 | 'upload_date': upload_date, | |
2430 | 'title': info['title'], | |
2431 | 'ext': u'mp3', | |
2432 | 'description': info['description'], | |
2433 | }] | |
2434 | ||
2435 | class SoundcloudSetIE(InfoExtractor): | |
2436 | """Information extractor for soundcloud.com sets | |
2437 | To access the media, the uid of the song and a stream token | |
2438 | must be extracted from the page source and the script must make | |
2439 | a request to media.soundcloud.com/crossdomain.xml. Then | |
2440 | the media can be grabbed by requesting from an url composed | |
2441 | of the stream token and uid | |
2442 | """ | |
2443 | ||
2444 | _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)' | |
2445 | IE_NAME = u'soundcloud:set' | |
2446 | ||
2447 | def report_resolve(self, video_id): | |
2448 | """Report information extraction.""" | |
2449 | self.to_screen(u'%s: Resolving id' % video_id) | |
2450 | ||
2451 | def _real_extract(self, url): | |
2452 | mobj = re.match(self._VALID_URL, url) | |
2453 | if mobj is None: | |
2454 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2455 | ||
2456 | # extract uploader (which is in the url) | |
2457 | uploader = mobj.group(1) | |
2458 | # extract simple title (uploader + slug of song title) | |
2459 | slug_title = mobj.group(2) | |
2460 | simple_title = uploader + u'-' + slug_title | |
2461 | full_title = '%s/sets/%s' % (uploader, slug_title) | |
2462 | ||
2463 | self.report_resolve(full_title) | |
2464 | ||
2465 | url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title) | |
2466 | resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28' | |
2467 | info_json = self._download_webpage(resolv_url, full_title) | |
2468 | ||
2469 | videos = [] | |
2470 | info = json.loads(info_json) | |
2471 | if 'errors' in info: | |
2472 | for err in info['errors']: | |
2473 | self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err['error_message'])) | |
2474 | return | |
2475 | ||
2476 | self.report_extraction(full_title) | |
2477 | for track in info['tracks']: | |
2478 | video_id = track['id'] | |
2479 | ||
2480 | streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28' | |
2481 | stream_json = self._download_webpage(streams_url, video_id, u'Downloading track info JSON') | |
2482 | ||
2483 | self.report_extraction(video_id) | |
2484 | streams = json.loads(stream_json) | |
2485 | mediaURL = streams['http_mp3_128_url'] | |
2486 | ||
2487 | videos.append({ | |
2488 | 'id': video_id, | |
2489 | 'url': mediaURL, | |
2490 | 'uploader': track['user']['username'], | |
2491 | 'upload_date': unified_strdate(track['created_at']), | |
2492 | 'title': track['title'], | |
2493 | 'ext': u'mp3', | |
2494 | 'description': track['description'], | |
2495 | }) | |
2496 | return videos | |
2497 | ||
2498 | ||
2499 | class InfoQIE(InfoExtractor): | |
2500 | """Information extractor for infoq.com""" | |
2501 | _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' | |
2502 | ||
2503 | def _real_extract(self, url): | |
2504 | mobj = re.match(self._VALID_URL, url) | |
2505 | if mobj is None: | |
2506 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2507 | ||
2508 | webpage = self._download_webpage(url, video_id=url) | |
2509 | self.report_extraction(url) | |
2510 | ||
2511 | # Extract video URL | |
2512 | mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage) | |
2513 | if mobj is None: | |
2514 | raise ExtractorError(u'Unable to extract video url') | |
2515 | real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8')) | |
2516 | video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id | |
2517 | ||
2518 | # Extract title | |
2519 | mobj = re.search(r'contentTitle = "(.*?)";', webpage) | |
2520 | if mobj is None: | |
2521 | raise ExtractorError(u'Unable to extract video title') | |
2522 | video_title = mobj.group(1) | |
2523 | ||
2524 | # Extract description | |
2525 | video_description = u'No description available.' | |
2526 | mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage) | |
2527 | if mobj is not None: | |
2528 | video_description = mobj.group(1) | |
2529 | ||
2530 | video_filename = video_url.split('/')[-1] | |
2531 | video_id, extension = video_filename.split('.') | |
2532 | ||
2533 | info = { | |
2534 | 'id': video_id, | |
2535 | 'url': video_url, | |
2536 | 'uploader': None, | |
2537 | 'upload_date': None, | |
2538 | 'title': video_title, | |
2539 | 'ext': extension, # Extension is always(?) mp4, but seems to be flv | |
2540 | 'thumbnail': None, | |
2541 | 'description': video_description, | |
2542 | } | |
2543 | ||
2544 | return [info] | |
2545 | ||
2546 | class MixcloudIE(InfoExtractor): | |
2547 | """Information extractor for www.mixcloud.com""" | |
2548 | ||
2549 | _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/ | |
2550 | _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' | |
2551 | IE_NAME = u'mixcloud' | |
2552 | ||
2553 | def report_download_json(self, file_id): | |
2554 | """Report JSON download.""" | |
2555 | self.to_screen(u'Downloading json') | |
2556 | ||
2557 | def get_urls(self, jsonData, fmt, bitrate='best'): | |
2558 | """Get urls from 'audio_formats' section in json""" | |
2559 | file_url = None | |
2560 | try: | |
2561 | bitrate_list = jsonData[fmt] | |
2562 | if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list: | |
2563 | bitrate = max(bitrate_list) # select highest | |
2564 | ||
2565 | url_list = jsonData[fmt][bitrate] | |
2566 | except TypeError: # we have no bitrate info. | |
2567 | url_list = jsonData[fmt] | |
2568 | return url_list | |
2569 | ||
2570 | def check_urls(self, url_list): | |
2571 | """Returns 1st active url from list""" | |
2572 | for url in url_list: | |
2573 | try: | |
2574 | compat_urllib_request.urlopen(url) | |
2575 | return url | |
2576 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2577 | url = None | |
2578 | ||
2579 | return None | |
2580 | ||
2581 | def _print_formats(self, formats): | |
2582 | print('Available formats:') | |
2583 | for fmt in formats.keys(): | |
2584 | for b in formats[fmt]: | |
2585 | try: | |
2586 | ext = formats[fmt][b][0] | |
2587 | print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])) | |
2588 | except TypeError: # we have no bitrate info | |
2589 | ext = formats[fmt][0] | |
2590 | print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])) | |
2591 | break | |
2592 | ||
2593 | def _real_extract(self, url): | |
2594 | mobj = re.match(self._VALID_URL, url) | |
2595 | if mobj is None: | |
2596 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2597 | # extract uploader & filename from url | |
2598 | uploader = mobj.group(1).decode('utf-8') | |
2599 | file_id = uploader + "-" + mobj.group(2).decode('utf-8') | |
2600 | ||
2601 | # construct API request | |
2602 | file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json' | |
2603 | # retrieve .json file with links to files | |
2604 | request = compat_urllib_request.Request(file_url) | |
2605 | try: | |
2606 | self.report_download_json(file_url) | |
2607 | jsonData = compat_urllib_request.urlopen(request).read() | |
2608 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2609 | raise ExtractorError(u'Unable to retrieve file: %s' % compat_str(err)) | |
2610 | ||
2611 | # parse JSON | |
2612 | json_data = json.loads(jsonData) | |
2613 | player_url = json_data['player_swf_url'] | |
2614 | formats = dict(json_data['audio_formats']) | |
2615 | ||
2616 | req_format = self._downloader.params.get('format', None) | |
2617 | bitrate = None | |
2618 | ||
2619 | if self._downloader.params.get('listformats', None): | |
2620 | self._print_formats(formats) | |
2621 | return | |
2622 | ||
2623 | if req_format is None or req_format == 'best': | |
2624 | for format_param in formats.keys(): | |
2625 | url_list = self.get_urls(formats, format_param) | |
2626 | # check urls | |
2627 | file_url = self.check_urls(url_list) | |
2628 | if file_url is not None: | |
2629 | break # got it! | |
2630 | else: | |
2631 | if req_format not in formats: | |
2632 | raise ExtractorError(u'Format is not available') | |
2633 | ||
2634 | url_list = self.get_urls(formats, req_format) | |
2635 | file_url = self.check_urls(url_list) | |
2636 | format_param = req_format | |
2637 | ||
2638 | return [{ | |
2639 | 'id': file_id.decode('utf-8'), | |
2640 | 'url': file_url.decode('utf-8'), | |
2641 | 'uploader': uploader.decode('utf-8'), | |
2642 | 'upload_date': None, | |
2643 | 'title': json_data['name'], | |
2644 | 'ext': file_url.split('.')[-1].decode('utf-8'), | |
2645 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), | |
2646 | 'thumbnail': json_data['thumbnail_url'], | |
2647 | 'description': json_data['description'], | |
2648 | 'player_url': player_url.decode('utf-8'), | |
2649 | }] | |
2650 | ||
2651 | class StanfordOpenClassroomIE(InfoExtractor): | |
2652 | """Information extractor for Stanford's Open ClassRoom""" | |
2653 | ||
2654 | _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' | |
2655 | IE_NAME = u'stanfordoc' | |
2656 | ||
2657 | def _real_extract(self, url): | |
2658 | mobj = re.match(self._VALID_URL, url) | |
2659 | if mobj is None: | |
2660 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2661 | ||
2662 | if mobj.group('course') and mobj.group('video'): # A specific video | |
2663 | course = mobj.group('course') | |
2664 | video = mobj.group('video') | |
2665 | info = { | |
2666 | 'id': course + '_' + video, | |
2667 | 'uploader': None, | |
2668 | 'upload_date': None, | |
2669 | } | |
2670 | ||
2671 | self.report_extraction(info['id']) | |
2672 | baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' | |
2673 | xmlUrl = baseUrl + video + '.xml' | |
2674 | try: | |
2675 | metaXml = compat_urllib_request.urlopen(xmlUrl).read() | |
2676 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2677 | raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err)) | |
2678 | mdoc = xml.etree.ElementTree.fromstring(metaXml) | |
2679 | try: | |
2680 | info['title'] = mdoc.findall('./title')[0].text | |
2681 | info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text | |
2682 | except IndexError: | |
2683 | raise ExtractorError(u'Invalid metadata XML file') | |
2684 | info['ext'] = info['url'].rpartition('.')[2] | |
2685 | return [info] | |
2686 | elif mobj.group('course'): # A course page | |
2687 | course = mobj.group('course') | |
2688 | info = { | |
2689 | 'id': course, | |
2690 | 'type': 'playlist', | |
2691 | 'uploader': None, | |
2692 | 'upload_date': None, | |
2693 | } | |
2694 | ||
2695 | coursepage = self._download_webpage(url, info['id'], | |
2696 | note='Downloading course info page', | |
2697 | errnote='Unable to download course info page') | |
2698 | ||
2699 | m = re.search('<h1>([^<]+)</h1>', coursepage) | |
2700 | if m: | |
2701 | info['title'] = unescapeHTML(m.group(1)) | |
2702 | else: | |
2703 | info['title'] = info['id'] | |
2704 | ||
2705 | m = re.search('<description>([^<]+)</description>', coursepage) | |
2706 | if m: | |
2707 | info['description'] = unescapeHTML(m.group(1)) | |
2708 | ||
2709 | links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) | |
2710 | info['list'] = [ | |
2711 | { | |
2712 | 'type': 'reference', | |
2713 | 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), | |
2714 | } | |
2715 | for vpage in links] | |
2716 | results = [] | |
2717 | for entry in info['list']: | |
2718 | assert entry['type'] == 'reference' | |
2719 | results += self.extract(entry['url']) | |
2720 | return results | |
2721 | else: # Root page | |
2722 | info = { | |
2723 | 'id': 'Stanford OpenClassroom', | |
2724 | 'type': 'playlist', | |
2725 | 'uploader': None, | |
2726 | 'upload_date': None, | |
2727 | } | |
2728 | ||
2729 | self.report_download_webpage(info['id']) | |
2730 | rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' | |
2731 | try: | |
2732 | rootpage = compat_urllib_request.urlopen(rootURL).read() | |
2733 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2734 | raise ExtractorError(u'Unable to download course info page: ' + compat_str(err)) | |
2735 | ||
2736 | info['title'] = info['id'] | |
2737 | ||
2738 | links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage)) | |
2739 | info['list'] = [ | |
2740 | { | |
2741 | 'type': 'reference', | |
2742 | 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), | |
2743 | } | |
2744 | for cpage in links] | |
2745 | ||
2746 | results = [] | |
2747 | for entry in info['list']: | |
2748 | assert entry['type'] == 'reference' | |
2749 | results += self.extract(entry['url']) | |
2750 | return results | |
2751 | ||
2752 | class MTVIE(InfoExtractor): | |
2753 | """Information extractor for MTV.com""" | |
2754 | ||
2755 | _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$' | |
2756 | IE_NAME = u'mtv' | |
2757 | ||
2758 | def _real_extract(self, url): | |
2759 | mobj = re.match(self._VALID_URL, url) | |
2760 | if mobj is None: | |
2761 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2762 | if not mobj.group('proto'): | |
2763 | url = 'http://' + url | |
2764 | video_id = mobj.group('videoid') | |
2765 | ||
2766 | webpage = self._download_webpage(url, video_id) | |
2767 | ||
2768 | mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage) | |
2769 | if mobj is None: | |
2770 | raise ExtractorError(u'Unable to extract song name') | |
2771 | song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1')) | |
2772 | mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage) | |
2773 | if mobj is None: | |
2774 | raise ExtractorError(u'Unable to extract performer') | |
2775 | performer = unescapeHTML(mobj.group(1).decode('iso-8859-1')) | |
2776 | video_title = performer + ' - ' + song_name | |
2777 | ||
2778 | mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage) | |
2779 | if mobj is None: | |
2780 | raise ExtractorError(u'Unable to mtvn_uri') | |
2781 | mtvn_uri = mobj.group(1) | |
2782 | ||
2783 | mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage) | |
2784 | if mobj is None: | |
2785 | raise ExtractorError(u'Unable to extract content id') | |
2786 | content_id = mobj.group(1) | |
2787 | ||
2788 | 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 | |
2789 | self.report_extraction(video_id) | |
2790 | request = compat_urllib_request.Request(videogen_url) | |
2791 | try: | |
2792 | metadataXml = compat_urllib_request.urlopen(request).read() | |
2793 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2794 | raise ExtractorError(u'Unable to download video metadata: %s' % compat_str(err)) | |
2795 | ||
2796 | mdoc = xml.etree.ElementTree.fromstring(metadataXml) | |
2797 | renditions = mdoc.findall('.//rendition') | |
2798 | ||
2799 | # For now, always pick the highest quality. | |
2800 | rendition = renditions[-1] | |
2801 | ||
2802 | try: | |
2803 | _,_,ext = rendition.attrib['type'].partition('/') | |
2804 | format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate'] | |
2805 | video_url = rendition.find('./src').text | |
2806 | except KeyError: | |
2807 | raise ExtractorError('Invalid rendition field.') | |
2808 | ||
2809 | info = { | |
2810 | 'id': video_id, | |
2811 | 'url': video_url, | |
2812 | 'uploader': performer, | |
2813 | 'upload_date': None, | |
2814 | 'title': video_title, | |
2815 | 'ext': ext, | |
2816 | 'format': format, | |
2817 | } | |
2818 | ||
2819 | return [info] | |
2820 | ||
2821 | ||
2822 | class YoukuIE(InfoExtractor): | |
2823 | _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html' | |
2824 | ||
2825 | def _gen_sid(self): | |
2826 | nowTime = int(time.time() * 1000) | |
2827 | random1 = random.randint(1000,1998) | |
2828 | random2 = random.randint(1000,9999) | |
2829 | ||
2830 | return "%d%d%d" %(nowTime,random1,random2) | |
2831 | ||
2832 | def _get_file_ID_mix_string(self, seed): | |
2833 | mixed = [] | |
2834 | source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890") | |
2835 | seed = float(seed) | |
2836 | for i in range(len(source)): | |
2837 | seed = (seed * 211 + 30031 ) % 65536 | |
2838 | index = math.floor(seed / 65536 * len(source) ) | |
2839 | mixed.append(source[int(index)]) | |
2840 | source.remove(source[int(index)]) | |
2841 | #return ''.join(mixed) | |
2842 | return mixed | |
2843 | ||
2844 | def _get_file_id(self, fileId, seed): | |
2845 | mixed = self._get_file_ID_mix_string(seed) | |
2846 | ids = fileId.split('*') | |
2847 | realId = [] | |
2848 | for ch in ids: | |
2849 | if ch: | |
2850 | realId.append(mixed[int(ch)]) | |
2851 | return ''.join(realId) | |
2852 | ||
2853 | def _real_extract(self, url): | |
2854 | mobj = re.match(self._VALID_URL, url) | |
2855 | if mobj is None: | |
2856 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2857 | video_id = mobj.group('ID') | |
2858 | ||
2859 | info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id | |
2860 | ||
2861 | jsondata = self._download_webpage(info_url, video_id) | |
2862 | ||
2863 | self.report_extraction(video_id) | |
2864 | try: | |
2865 | config = json.loads(jsondata) | |
2866 | ||
2867 | video_title = config['data'][0]['title'] | |
2868 | seed = config['data'][0]['seed'] | |
2869 | ||
2870 | format = self._downloader.params.get('format', None) | |
2871 | supported_format = list(config['data'][0]['streamfileids'].keys()) | |
2872 | ||
2873 | if format is None or format == 'best': | |
2874 | if 'hd2' in supported_format: | |
2875 | format = 'hd2' | |
2876 | else: | |
2877 | format = 'flv' | |
2878 | ext = u'flv' | |
2879 | elif format == 'worst': | |
2880 | format = 'mp4' | |
2881 | ext = u'mp4' | |
2882 | else: | |
2883 | format = 'flv' | |
2884 | ext = u'flv' | |
2885 | ||
2886 | ||
2887 | fileid = config['data'][0]['streamfileids'][format] | |
2888 | keys = [s['k'] for s in config['data'][0]['segs'][format]] | |
2889 | except (UnicodeDecodeError, ValueError, KeyError): | |
2890 | raise ExtractorError(u'Unable to extract info section') | |
2891 | ||
2892 | files_info=[] | |
2893 | sid = self._gen_sid() | |
2894 | fileid = self._get_file_id(fileid, seed) | |
2895 | ||
2896 | #column 8,9 of fileid represent the segment number | |
2897 | #fileid[7:9] should be changed | |
2898 | for index, key in enumerate(keys): | |
2899 | ||
2900 | temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:]) | |
2901 | download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) | |
2902 | ||
2903 | info = { | |
2904 | 'id': '%s_part%02d' % (video_id, index), | |
2905 | 'url': download_url, | |
2906 | 'uploader': None, | |
2907 | 'upload_date': None, | |
2908 | 'title': video_title, | |
2909 | 'ext': ext, | |
2910 | } | |
2911 | files_info.append(info) | |
2912 | ||
2913 | return files_info | |
2914 | ||
2915 | ||
2916 | class XNXXIE(InfoExtractor): | |
2917 | """Information extractor for xnxx.com""" | |
2918 | ||
2919 | _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)' | |
2920 | IE_NAME = u'xnxx' | |
2921 | VIDEO_URL_RE = r'flv_url=(.*?)&' | |
2922 | VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM' | |
2923 | VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&' | |
2924 | ||
2925 | def _real_extract(self, url): | |
2926 | mobj = re.match(self._VALID_URL, url) | |
2927 | if mobj is None: | |
2928 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2929 | video_id = mobj.group(1) | |
2930 | ||
2931 | # Get webpage content | |
2932 | webpage = self._download_webpage(url, video_id) | |
2933 | ||
2934 | result = re.search(self.VIDEO_URL_RE, webpage) | |
2935 | if result is None: | |
2936 | raise ExtractorError(u'Unable to extract video url') | |
2937 | video_url = compat_urllib_parse.unquote(result.group(1)) | |
2938 | ||
2939 | result = re.search(self.VIDEO_TITLE_RE, webpage) | |
2940 | if result is None: | |
2941 | raise ExtractorError(u'Unable to extract video title') | |
2942 | video_title = result.group(1) | |
2943 | ||
2944 | result = re.search(self.VIDEO_THUMB_RE, webpage) | |
2945 | if result is None: | |
2946 | raise ExtractorError(u'Unable to extract video thumbnail') | |
2947 | video_thumbnail = result.group(1) | |
2948 | ||
2949 | return [{ | |
2950 | 'id': video_id, | |
2951 | 'url': video_url, | |
2952 | 'uploader': None, | |
2953 | 'upload_date': None, | |
2954 | 'title': video_title, | |
2955 | 'ext': 'flv', | |
2956 | 'thumbnail': video_thumbnail, | |
2957 | 'description': None, | |
2958 | }] | |
2959 | ||
2960 | ||
2961 | class GooglePlusIE(InfoExtractor): | |
2962 | """Information extractor for plus.google.com.""" | |
2963 | ||
2964 | _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)' | |
2965 | IE_NAME = u'plus.google' | |
2966 | ||
2967 | def report_extract_entry(self, url): | |
2968 | """Report downloading extry""" | |
2969 | self.to_screen(u'Downloading entry: %s' % url) | |
2970 | ||
2971 | def report_date(self, upload_date): | |
2972 | """Report downloading extry""" | |
2973 | self.to_screen(u'Entry date: %s' % upload_date) | |
2974 | ||
2975 | def report_uploader(self, uploader): | |
2976 | """Report downloading extry""" | |
2977 | self.to_screen(u'Uploader: %s' % uploader) | |
2978 | ||
2979 | def report_title(self, video_title): | |
2980 | """Report downloading extry""" | |
2981 | self.to_screen(u'Title: %s' % video_title) | |
2982 | ||
2983 | def report_extract_vid_page(self, video_page): | |
2984 | """Report information extraction.""" | |
2985 | self.to_screen(u'Extracting video page: %s' % video_page) | |
2986 | ||
2987 | def _real_extract(self, url): | |
2988 | # Extract id from URL | |
2989 | mobj = re.match(self._VALID_URL, url) | |
2990 | if mobj is None: | |
2991 | raise ExtractorError(u'Invalid URL: %s' % url) | |
2992 | ||
2993 | post_url = mobj.group(0) | |
2994 | video_id = mobj.group(1) | |
2995 | ||
2996 | video_extension = 'flv' | |
2997 | ||
2998 | # Step 1, Retrieve post webpage to extract further information | |
2999 | self.report_extract_entry(post_url) | |
3000 | webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage') | |
3001 | ||
3002 | # Extract update date | |
3003 | upload_date = None | |
3004 | pattern = 'title="Timestamp">(.*?)</a>' | |
3005 | mobj = re.search(pattern, webpage) | |
3006 | if mobj: | |
3007 | upload_date = mobj.group(1) | |
3008 | # Convert timestring to a format suitable for filename | |
3009 | upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") | |
3010 | upload_date = upload_date.strftime('%Y%m%d') | |
3011 | self.report_date(upload_date) | |
3012 | ||
3013 | # Extract uploader | |
3014 | uploader = None | |
3015 | pattern = r'rel\="author".*?>(.*?)</a>' | |
3016 | mobj = re.search(pattern, webpage) | |
3017 | if mobj: | |
3018 | uploader = mobj.group(1) | |
3019 | self.report_uploader(uploader) | |
3020 | ||
3021 | # Extract title | |
3022 | # Get the first line for title | |
3023 | video_title = u'NA' | |
3024 | pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]' | |
3025 | mobj = re.search(pattern, webpage) | |
3026 | if mobj: | |
3027 | video_title = mobj.group(1) | |
3028 | self.report_title(video_title) | |
3029 | ||
3030 | # Step 2, Stimulate clicking the image box to launch video | |
3031 | pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]' | |
3032 | mobj = re.search(pattern, webpage) | |
3033 | if mobj is None: | |
3034 | raise ExtractorError(u'Unable to extract video page URL') | |
3035 | ||
3036 | video_page = mobj.group(1) | |
3037 | webpage = self._download_webpage(video_page, video_id, u'Downloading video page') | |
3038 | self.report_extract_vid_page(video_page) | |
3039 | ||
3040 | ||
3041 | # Extract video links on video page | |
3042 | """Extract video links of all sizes""" | |
3043 | pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"' | |
3044 | mobj = re.findall(pattern, webpage) | |
3045 | if len(mobj) == 0: | |
3046 | raise ExtractorError(u'Unable to extract video links') | |
3047 | ||
3048 | # Sort in resolution | |
3049 | links = sorted(mobj) | |
3050 | ||
3051 | # Choose the lowest of the sort, i.e. highest resolution | |
3052 | video_url = links[-1] | |
3053 | # Only get the url. The resolution part in the tuple has no use anymore | |
3054 | video_url = video_url[-1] | |
3055 | # Treat escaped \u0026 style hex | |
3056 | try: | |
3057 | video_url = video_url.decode("unicode_escape") | |
3058 | except AttributeError: # Python 3 | |
3059 | video_url = bytes(video_url, 'ascii').decode('unicode-escape') | |
3060 | ||
3061 | ||
3062 | return [{ | |
3063 | 'id': video_id, | |
3064 | 'url': video_url, | |
3065 | 'uploader': uploader, | |
3066 | 'upload_date': upload_date, | |
3067 | 'title': video_title, | |
3068 | 'ext': video_extension, | |
3069 | }] | |
3070 | ||
3071 | class NBAIE(InfoExtractor): | |
3072 | _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$' | |
3073 | IE_NAME = u'nba' | |
3074 | ||
3075 | def _real_extract(self, url): | |
3076 | mobj = re.match(self._VALID_URL, url) | |
3077 | if mobj is None: | |
3078 | raise ExtractorError(u'Invalid URL: %s' % url) | |
3079 | ||
3080 | video_id = mobj.group(1) | |
3081 | if video_id.endswith('/index.html'): | |
3082 | video_id = video_id[:-len('/index.html')] | |
3083 | ||
3084 | webpage = self._download_webpage(url, video_id) | |
3085 | ||
3086 | video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' | |
3087 | def _findProp(rexp, default=None): | |
3088 | m = re.search(rexp, webpage) | |
3089 | if m: | |
3090 | return unescapeHTML(m.group(1)) | |
3091 | else: | |
3092 | return default | |
3093 | ||
3094 | shortened_video_id = video_id.rpartition('/')[2] | |
3095 | title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '') | |
3096 | info = { | |
3097 | 'id': shortened_video_id, | |
3098 | 'url': video_url, | |
3099 | 'ext': 'mp4', | |
3100 | 'title': title, | |
3101 | 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'), | |
3102 | 'description': _findProp(r'<div class="description">(.*?)</h1>'), | |
3103 | } | |
3104 | return [info] | |
3105 | ||
3106 | class JustinTVIE(InfoExtractor): | |
3107 | """Information extractor for justin.tv and twitch.tv""" | |
3108 | # TODO: One broadcast may be split into multiple videos. The key | |
3109 | # 'broadcast_id' is the same for all parts, and 'broadcast_part' | |
3110 | # starts at 1 and increases. Can we treat all parts as one video? | |
3111 | ||
3112 | _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/ | |
3113 | (?: | |
3114 | (?P<channelid>[^/]+)| | |
3115 | (?:(?:[^/]+)/b/(?P<videoid>[^/]+))| | |
3116 | (?:(?:[^/]+)/c/(?P<chapterid>[^/]+)) | |
3117 | ) | |
3118 | /?(?:\#.*)?$ | |
3119 | """ | |
3120 | _JUSTIN_PAGE_LIMIT = 100 | |
3121 | IE_NAME = u'justin.tv' | |
3122 | ||
3123 | def report_download_page(self, channel, offset): | |
3124 | """Report attempt to download a single page of videos.""" | |
3125 | self.to_screen(u'%s: Downloading video information from %d to %d' % | |
3126 | (channel, offset, offset + self._JUSTIN_PAGE_LIMIT)) | |
3127 | ||
3128 | # Return count of items, list of *valid* items | |
3129 | def _parse_page(self, url, video_id): | |
3130 | webpage = self._download_webpage(url, video_id, | |
3131 | u'Downloading video info JSON', | |
3132 | u'unable to download video info JSON') | |
3133 | ||
3134 | response = json.loads(webpage) | |
3135 | if type(response) != list: | |
3136 | error_text = response.get('error', 'unknown error') | |
3137 | raise ExtractorError(u'Justin.tv API: %s' % error_text) | |
3138 | info = [] | |
3139 | for clip in response: | |
3140 | video_url = clip['video_file_url'] | |
3141 | if video_url: | |
3142 | video_extension = os.path.splitext(video_url)[1][1:] | |
3143 | video_date = re.sub('-', '', clip['start_time'][:10]) | |
3144 | video_uploader_id = clip.get('user_id', clip.get('channel_id')) | |
3145 | video_id = clip['id'] | |
3146 | video_title = clip.get('title', video_id) | |
3147 | info.append({ | |
3148 | 'id': video_id, | |
3149 | 'url': video_url, | |
3150 | 'title': video_title, | |
3151 | 'uploader': clip.get('channel_name', video_uploader_id), | |
3152 | 'uploader_id': video_uploader_id, | |
3153 | 'upload_date': video_date, | |
3154 | 'ext': video_extension, | |
3155 | }) | |
3156 | return (len(response), info) | |
3157 | ||
3158 | def _real_extract(self, url): | |
3159 | mobj = re.match(self._VALID_URL, url) | |
3160 | if mobj is None: | |
3161 | raise ExtractorError(u'invalid URL: %s' % url) | |
3162 | ||
3163 | api_base = 'http://api.justin.tv' | |
3164 | paged = False | |
3165 | if mobj.group('channelid'): | |
3166 | paged = True | |
3167 | video_id = mobj.group('channelid') | |
3168 | api = api_base + '/channel/archives/%s.json' % video_id | |
3169 | elif mobj.group('chapterid'): | |
3170 | chapter_id = mobj.group('chapterid') | |
3171 | ||
3172 | webpage = self._download_webpage(url, chapter_id) | |
3173 | m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage) | |
3174 | if not m: | |
3175 | raise ExtractorError(u'Cannot find archive of a chapter') | |
3176 | archive_id = m.group(1) | |
3177 | ||
3178 | api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id | |
3179 | chapter_info_xml = self._download_webpage(api, chapter_id, | |
3180 | note=u'Downloading chapter information', | |
3181 | errnote=u'Chapter information download failed') | |
3182 | doc = xml.etree.ElementTree.fromstring(chapter_info_xml) | |
3183 | for a in doc.findall('.//archive'): | |
3184 | if archive_id == a.find('./id').text: | |
3185 | break | |
3186 | else: | |
3187 | raise ExtractorError(u'Could not find chapter in chapter information') | |
3188 | ||
3189 | video_url = a.find('./video_file_url').text | |
3190 | video_ext = video_url.rpartition('.')[2] or u'flv' | |
3191 | ||
3192 | chapter_api_url = u'https://api.twitch.tv/kraken/videos/c' + chapter_id | |
3193 | chapter_info_json = self._download_webpage(chapter_api_url, u'c' + chapter_id, | |
3194 | note='Downloading chapter metadata', | |
3195 | errnote='Download of chapter metadata failed') | |
3196 | chapter_info = json.loads(chapter_info_json) | |
3197 | ||
3198 | bracket_start = int(doc.find('.//bracket_start').text) | |
3199 | bracket_end = int(doc.find('.//bracket_end').text) | |
3200 | ||
3201 | # TODO determine start (and probably fix up file) | |
3202 | # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457 | |
3203 | #video_url += u'?start=' + TODO:start_timestamp | |
3204 | # bracket_start is 13290, but we want 51670615 | |
3205 | self._downloader.report_warning(u'Chapter detected, but we can just download the whole file. ' | |
3206 | u'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end))) | |
3207 | ||
3208 | info = { | |
3209 | 'id': u'c' + chapter_id, | |
3210 | 'url': video_url, | |
3211 | 'ext': video_ext, | |
3212 | 'title': chapter_info['title'], | |
3213 | 'thumbnail': chapter_info['preview'], | |
3214 | 'description': chapter_info['description'], | |
3215 | 'uploader': chapter_info['channel']['display_name'], | |
3216 | 'uploader_id': chapter_info['channel']['name'], | |
3217 | } | |
3218 | return [info] | |
3219 | else: | |
3220 | video_id = mobj.group('videoid') | |
3221 | api = api_base + '/broadcast/by_archive/%s.json' % video_id | |
3222 | ||
3223 | self.report_extraction(video_id) | |
3224 | ||
3225 | info = [] | |
3226 | offset = 0 | |
3227 | limit = self._JUSTIN_PAGE_LIMIT | |
3228 | while True: | |
3229 | if paged: | |
3230 | self.report_download_page(video_id, offset) | |
3231 | page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) | |
3232 | page_count, page_info = self._parse_page(page_url, video_id) | |
3233 | info.extend(page_info) | |
3234 | if not paged or page_count != limit: | |
3235 | break | |
3236 | offset += limit | |
3237 | return info | |
3238 | ||
3239 | class FunnyOrDieIE(InfoExtractor): | |
3240 | _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$' | |
3241 | ||
3242 | def _real_extract(self, url): | |
3243 | mobj = re.match(self._VALID_URL, url) | |
3244 | if mobj is None: | |
3245 | raise ExtractorError(u'invalid URL: %s' % url) | |
3246 | ||
3247 | video_id = mobj.group('id') | |
3248 | webpage = self._download_webpage(url, video_id) | |
3249 | ||
3250 | m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL) | |
3251 | if not m: | |
3252 | raise ExtractorError(u'Unable to find video information') | |
3253 | video_url = unescapeHTML(m.group('url')) | |
3254 | ||
3255 | m = re.search(r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", webpage, flags=re.DOTALL) | |
3256 | if not m: | |
3257 | m = re.search(r'<title>(?P<title>[^<]+?)</title>', webpage) | |
3258 | if not m: | |
3259 | raise ExtractorError(u'Cannot find video title') | |
3260 | title = clean_html(m.group('title')) | |
3261 | ||
3262 | m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage) | |
3263 | if m: | |
3264 | desc = unescapeHTML(m.group('desc')) | |
3265 | else: | |
3266 | desc = None | |
3267 | ||
3268 | info = { | |
3269 | 'id': video_id, | |
3270 | 'url': video_url, | |
3271 | 'ext': 'mp4', | |
3272 | 'title': title, | |
3273 | 'description': desc, | |
3274 | } | |
3275 | return [info] | |
3276 | ||
3277 | class SteamIE(InfoExtractor): | |
3278 | _VALID_URL = r"""http://store\.steampowered\.com/ | |
3279 | (agecheck/)? | |
3280 | (?P<urltype>video|app)/ #If the page is only for videos or for a game | |
3281 | (?P<gameID>\d+)/? | |
3282 | (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID | |
3283 | """ | |
3284 | ||
3285 | @classmethod | |
3286 | def suitable(cls, url): | |
3287 | """Receives a URL and returns True if suitable for this IE.""" | |
3288 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None | |
3289 | ||
3290 | def _real_extract(self, url): | |
3291 | m = re.match(self._VALID_URL, url, re.VERBOSE) | |
3292 | gameID = m.group('gameID') | |
3293 | videourl = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' % gameID | |
3294 | self.report_age_confirmation() | |
3295 | webpage = self._download_webpage(videourl, gameID) | |
3296 | game_title = re.search(r'<h2 class="pageheader">(?P<game_title>.*?)</h2>', webpage).group('game_title') | |
3297 | ||
3298 | urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\}," | |
3299 | mweb = re.finditer(urlRE, webpage) | |
3300 | namesRE = r'<span class="title">(?P<videoName>.+?)</span>' | |
3301 | titles = re.finditer(namesRE, webpage) | |
3302 | thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">' | |
3303 | thumbs = re.finditer(thumbsRE, webpage) | |
3304 | videos = [] | |
3305 | for vid,vtitle,thumb in zip(mweb,titles,thumbs): | |
3306 | video_id = vid.group('videoID') | |
3307 | title = vtitle.group('videoName') | |
3308 | video_url = vid.group('videoURL') | |
3309 | video_thumb = thumb.group('thumbnail') | |
3310 | if not video_url: | |
3311 | raise ExtractorError(u'Cannot find video url for %s' % video_id) | |
3312 | info = { | |
3313 | 'id':video_id, | |
3314 | 'url':video_url, | |
3315 | 'ext': 'flv', | |
3316 | 'title': unescapeHTML(title), | |
3317 | 'thumbnail': video_thumb | |
3318 | } | |
3319 | videos.append(info) | |
3320 | return [self.playlist_result(videos, gameID, game_title)] | |
3321 | ||
3322 | class UstreamIE(InfoExtractor): | |
3323 | _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)' | |
3324 | IE_NAME = u'ustream' | |
3325 | ||
3326 | def _real_extract(self, url): | |
3327 | m = re.match(self._VALID_URL, url) | |
3328 | video_id = m.group('videoID') | |
3329 | video_url = u'http://tcdn.ustream.tv/video/%s' % video_id | |
3330 | webpage = self._download_webpage(url, video_id) | |
3331 | m = re.search(r'data-title="(?P<title>.+)"',webpage) | |
3332 | title = m.group('title') | |
3333 | m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage) | |
3334 | uploader = m.group('uploader') | |
3335 | info = { | |
3336 | 'id':video_id, | |
3337 | 'url':video_url, | |
3338 | 'ext': 'flv', | |
3339 | 'title': title, | |
3340 | 'uploader': uploader | |
3341 | } | |
3342 | return [info] | |
3343 | ||
3344 | class WorldStarHipHopIE(InfoExtractor): | |
3345 | _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)' | |
3346 | IE_NAME = u'WorldStarHipHop' | |
3347 | ||
3348 | def _real_extract(self, url): | |
3349 | _src_url = r'so\.addVariable\("file","(.*?)"\)' | |
3350 | ||
3351 | m = re.match(self._VALID_URL, url) | |
3352 | video_id = m.group('id') | |
3353 | ||
3354 | webpage_src = self._download_webpage(url, video_id) | |
3355 | ||
3356 | mobj = re.search(_src_url, webpage_src) | |
3357 | ||
3358 | if mobj is not None: | |
3359 | video_url = mobj.group(1) | |
3360 | if 'mp4' in video_url: | |
3361 | ext = 'mp4' | |
3362 | else: | |
3363 | ext = 'flv' | |
3364 | else: | |
3365 | raise ExtractorError(u'Cannot find video url for %s' % video_id) | |
3366 | ||
3367 | mobj = re.search(r"<title>(.*)</title>", webpage_src) | |
3368 | ||
3369 | if mobj is None: | |
3370 | raise ExtractorError(u'Cannot determine title') | |
3371 | title = mobj.group(1) | |
3372 | ||
3373 | mobj = re.search(r'rel="image_src" href="(.*)" />', webpage_src) | |
3374 | # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video. | |
3375 | if mobj is not None: | |
3376 | thumbnail = mobj.group(1) | |
3377 | else: | |
3378 | _title = r"""candytitles.*>(.*)</span>""" | |
3379 | mobj = re.search(_title, webpage_src) | |
3380 | if mobj is not None: | |
3381 | title = mobj.group(1) | |
3382 | thumbnail = None | |
3383 | ||
3384 | results = [{ | |
3385 | 'id': video_id, | |
3386 | 'url' : video_url, | |
3387 | 'title' : title, | |
3388 | 'thumbnail' : thumbnail, | |
3389 | 'ext' : ext, | |
3390 | }] | |
3391 | return results | |
3392 | ||
3393 | class RBMARadioIE(InfoExtractor): | |
3394 | _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$' | |
3395 | ||
3396 | def _real_extract(self, url): | |
3397 | m = re.match(self._VALID_URL, url) | |
3398 | video_id = m.group('videoID') | |
3399 | ||
3400 | webpage = self._download_webpage(url, video_id) | |
3401 | m = re.search(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>', webpage) | |
3402 | if not m: | |
3403 | raise ExtractorError(u'Cannot find metadata') | |
3404 | json_data = m.group(1) | |
3405 | ||
3406 | try: | |
3407 | data = json.loads(json_data) | |
3408 | except ValueError as e: | |
3409 | raise ExtractorError(u'Invalid JSON: ' + str(e)) | |
3410 | ||
3411 | video_url = data['akamai_url'] + '&cbr=256' | |
3412 | url_parts = compat_urllib_parse_urlparse(video_url) | |
3413 | video_ext = url_parts.path.rpartition('.')[2] | |
3414 | info = { | |
3415 | 'id': video_id, | |
3416 | 'url': video_url, | |
3417 | 'ext': video_ext, | |
3418 | 'title': data['title'], | |
3419 | 'description': data.get('teaser_text'), | |
3420 | 'location': data.get('country_of_origin'), | |
3421 | 'uploader': data.get('host', {}).get('name'), | |
3422 | 'uploader_id': data.get('host', {}).get('slug'), | |
3423 | 'thumbnail': data.get('image', {}).get('large_url_2x'), | |
3424 | 'duration': data.get('duration'), | |
3425 | } | |
3426 | return [info] | |
3427 | ||
3428 | ||
3429 | class YouPornIE(InfoExtractor): | |
3430 | """Information extractor for youporn.com.""" | |
3431 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)' | |
3432 | ||
3433 | def _print_formats(self, formats): | |
3434 | """Print all available formats""" | |
3435 | print(u'Available formats:') | |
3436 | print(u'ext\t\tformat') | |
3437 | print(u'---------------------------------') | |
3438 | for format in formats: | |
3439 | print(u'%s\t\t%s' % (format['ext'], format['format'])) | |
3440 | ||
3441 | def _specific(self, req_format, formats): | |
3442 | for x in formats: | |
3443 | if(x["format"]==req_format): | |
3444 | return x | |
3445 | return None | |
3446 | ||
3447 | def _real_extract(self, url): | |
3448 | mobj = re.match(self._VALID_URL, url) | |
3449 | if mobj is None: | |
3450 | raise ExtractorError(u'Invalid URL: %s' % url) | |
3451 | ||
3452 | video_id = mobj.group('videoid') | |
3453 | ||
3454 | req = compat_urllib_request.Request(url) | |
3455 | req.add_header('Cookie', 'age_verified=1') | |
3456 | webpage = self._download_webpage(req, video_id) | |
3457 | ||
3458 | # Get the video title | |
3459 | result = re.search(r'<h1.*?>(?P<title>.*)</h1>', webpage) | |
3460 | if result is None: | |
3461 | raise ExtractorError(u'Unable to extract video title') | |
3462 | video_title = result.group('title').strip() | |
3463 | ||
3464 | # Get the video date | |
3465 | result = re.search(r'Date:</label>(?P<date>.*) </li>', webpage) | |
3466 | if result is None: | |
3467 | self._downloader.report_warning(u'unable to extract video date') | |
3468 | upload_date = None | |
3469 | else: | |
3470 | upload_date = unified_strdate(result.group('date').strip()) | |
3471 | ||
3472 | # Get the video uploader | |
3473 | result = re.search(r'Submitted:</label>(?P<uploader>.*)</li>', webpage) | |
3474 | if result is None: | |
3475 | self._downloader.report_warning(u'unable to extract uploader') | |
3476 | video_uploader = None | |
3477 | else: | |
3478 | video_uploader = result.group('uploader').strip() | |
3479 | video_uploader = clean_html( video_uploader ) | |
3480 | ||
3481 | # Get all of the formats available | |
3482 | DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' | |
3483 | result = re.search(DOWNLOAD_LIST_RE, webpage) | |
3484 | if result is None: | |
3485 | raise ExtractorError(u'Unable to extract download list') | |
3486 | download_list_html = result.group('download_list').strip() | |
3487 | ||
3488 | # Get all of the links from the page | |
3489 | LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">' | |
3490 | links = re.findall(LINK_RE, download_list_html) | |
3491 | if(len(links) == 0): | |
3492 | raise ExtractorError(u'ERROR: no known formats available for video') | |
3493 | ||
3494 | self.to_screen(u'Links found: %d' % len(links)) | |
3495 | ||
3496 | formats = [] | |
3497 | for link in links: | |
3498 | ||
3499 | # A link looks like this: | |
3500 | # 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 | |
3501 | # A path looks like this: | |
3502 | # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4 | |
3503 | video_url = unescapeHTML( link ) | |
3504 | path = compat_urllib_parse_urlparse( video_url ).path | |
3505 | extension = os.path.splitext( path )[1][1:] | |
3506 | format = path.split('/')[4].split('_')[:2] | |
3507 | size = format[0] | |
3508 | bitrate = format[1] | |
3509 | format = "-".join( format ) | |
3510 | title = u'%s-%s-%s' % (video_title, size, bitrate) | |
3511 | ||
3512 | formats.append({ | |
3513 | 'id': video_id, | |
3514 | 'url': video_url, | |
3515 | 'uploader': video_uploader, | |
3516 | 'upload_date': upload_date, | |
3517 | 'title': title, | |
3518 | 'ext': extension, | |
3519 | 'format': format, | |
3520 | 'thumbnail': None, | |
3521 | 'description': None, | |
3522 | 'player_url': None | |
3523 | }) | |
3524 | ||
3525 | if self._downloader.params.get('listformats', None): | |
3526 | self._print_formats(formats) | |
3527 | return | |
3528 | ||
3529 | req_format = self._downloader.params.get('format', None) | |
3530 | self.to_screen(u'Format: %s' % req_format) | |
3531 | ||
3532 | if req_format is None or req_format == 'best': | |
3533 | return [formats[0]] | |
3534 | elif req_format == 'worst': | |
3535 | return [formats[-1]] | |
3536 | elif req_format in ('-1', 'all'): | |
3537 | return formats | |
3538 | else: | |
3539 | format = self._specific( req_format, formats ) | |
3540 | if result is None: | |
3541 | raise ExtractorError(u'Requested format not available') | |
3542 | return [format] | |
3543 | ||
3544 | ||
3545 | ||
3546 | class PornotubeIE(InfoExtractor): | |
3547 | """Information extractor for pornotube.com.""" | |
3548 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' | |
3549 | ||
3550 | def _real_extract(self, url): | |
3551 | mobj = re.match(self._VALID_URL, url) | |
3552 | if mobj is None: | |
3553 | raise ExtractorError(u'Invalid URL: %s' % url) | |
3554 | ||
3555 | video_id = mobj.group('videoid') | |
3556 | video_title = mobj.group('title') | |
3557 | ||
3558 | # Get webpage content | |
3559 | webpage = self._download_webpage(url, video_id) | |
3560 | ||
3561 | # Get the video URL | |
3562 | VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' | |
3563 | result = re.search(VIDEO_URL_RE, webpage) | |
3564 | if result is None: | |
3565 | raise ExtractorError(u'Unable to extract video url') | |
3566 | video_url = compat_urllib_parse.unquote(result.group('url')) | |
3567 | ||
3568 | #Get the uploaded date | |
3569 | VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' | |
3570 | result = re.search(VIDEO_UPLOADED_RE, webpage) | |
3571 | if result is None: | |
3572 | raise ExtractorError(u'Unable to extract video title') | |
3573 | upload_date = unified_strdate(result.group('date')) | |
3574 | ||
3575 | info = {'id': video_id, | |
3576 | 'url': video_url, | |
3577 | 'uploader': None, | |
3578 | 'upload_date': upload_date, | |
3579 | 'title': video_title, | |
3580 | 'ext': 'flv', | |
3581 | 'format': 'flv'} | |
3582 | ||
3583 | return [info] | |
3584 | ||
3585 | class YouJizzIE(InfoExtractor): | |
3586 | """Information extractor for youjizz.com.""" | |
3587 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$' | |
3588 | ||
3589 | def _real_extract(self, url): | |
3590 | mobj = re.match(self._VALID_URL, url) | |
3591 | if mobj is None: | |
3592 | raise ExtractorError(u'Invalid URL: %s' % url) | |
3593 | ||
3594 | video_id = mobj.group('videoid') | |
3595 | ||
3596 | # Get webpage content | |
3597 | webpage = self._download_webpage(url, video_id) | |
3598 | ||
3599 | # Get the video title | |
3600 | result = re.search(r'<title>(?P<title>.*)</title>', webpage) | |
3601 | if result is None: | |
3602 | raise ExtractorError(u'ERROR: unable to extract video title') | |
3603 | video_title = result.group('title').strip() | |
3604 | ||
3605 | # Get the embed page | |
3606 | result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage) | |
3607 | if result is None: | |
3608 | raise ExtractorError(u'ERROR: unable to extract embed page') | |
3609 | ||
3610 | embed_page_url = result.group(0).strip() | |
3611 | video_id = result.group('videoid') | |
3612 | ||
3613 | webpage = self._download_webpage(embed_page_url, video_id) | |
3614 | ||
3615 | # Get the video URL | |
3616 | result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', webpage) | |
3617 | if result is None: | |
3618 | raise ExtractorError(u'ERROR: unable to extract video url') | |
3619 | video_url = result.group('source') | |
3620 | ||
3621 | info = {'id': video_id, | |
3622 | 'url': video_url, | |
3623 | 'title': video_title, | |
3624 | 'ext': 'flv', | |
3625 | 'format': 'flv', | |
3626 | 'player_url': embed_page_url} | |
3627 | ||
3628 | return [info] | |
3629 | ||
3630 | class EightTracksIE(InfoExtractor): | |
3631 | IE_NAME = '8tracks' | |
3632 | _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' | |
3633 | ||
3634 | def _real_extract(self, url): | |
3635 | mobj = re.match(self._VALID_URL, url) | |
3636 | if mobj is None: | |
3637 | raise ExtractorError(u'Invalid URL: %s' % url) | |
3638 | playlist_id = mobj.group('id') | |
3639 | ||
3640 | webpage = self._download_webpage(url, playlist_id) | |
3641 | ||
3642 | m = re.search(r"PAGE.mix = (.*?);\n", webpage, flags=re.DOTALL) | |
3643 | if not m: | |
3644 | raise ExtractorError(u'Cannot find trax information') | |
3645 | json_like = m.group(1) | |
3646 | data = json.loads(json_like) | |
3647 | ||
3648 | session = str(random.randint(0, 1000000000)) | |
3649 | mix_id = data['id'] | |
3650 | track_count = data['tracks_count'] | |
3651 | first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) | |
3652 | next_url = first_url | |
3653 | res = [] | |
3654 | for i in itertools.count(): | |
3655 | api_json = self._download_webpage(next_url, playlist_id, | |
3656 | note=u'Downloading song information %s/%s' % (str(i+1), track_count), | |
3657 | errnote=u'Failed to download song information') | |
3658 | api_data = json.loads(api_json) | |
3659 | track_data = api_data[u'set']['track'] | |
3660 | info = { | |
3661 | 'id': track_data['id'], | |
3662 | 'url': track_data['track_file_stream_url'], | |
3663 | 'title': track_data['performer'] + u' - ' + track_data['name'], | |
3664 | 'raw_title': track_data['name'], | |
3665 | 'uploader_id': data['user']['login'], | |
3666 | 'ext': 'm4a', | |
3667 | } | |
3668 | res.append(info) | |
3669 | if api_data['set']['at_last_track']: | |
3670 | break | |
3671 | next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id']) | |
3672 | return res | |
3673 | ||
3674 | class KeekIE(InfoExtractor): | |
3675 | _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)' | |
3676 | IE_NAME = u'keek' | |
3677 | ||
3678 | def _real_extract(self, url): | |
3679 | m = re.match(self._VALID_URL, url) | |
3680 | video_id = m.group('videoID') | |
3681 | video_url = u'http://cdn.keek.com/keek/video/%s' % video_id | |
3682 | thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id | |
3683 | webpage = self._download_webpage(url, video_id) | |
3684 | m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage) | |
3685 | title = unescapeHTML(m.group('title')) | |
3686 | m = re.search(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', webpage) | |
3687 | uploader = clean_html(m.group('uploader')) | |
3688 | info = { | |
3689 | 'id': video_id, | |
3690 | 'url': video_url, | |
3691 | 'ext': 'mp4', | |
3692 | 'title': title, | |
3693 | 'thumbnail': thumbnail, | |
3694 | 'uploader': uploader | |
3695 | } | |
3696 | return [info] | |
3697 | ||
3698 | class TEDIE(InfoExtractor): | |
3699 | _VALID_URL=r'''http://www\.ted\.com/ | |
3700 | ( | |
3701 | ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist | |
3702 | | | |
3703 | ((?P<type_talk>talks)) # We have a simple talk | |
3704 | ) | |
3705 | (/lang/(.*?))? # The url may contain the language | |
3706 | /(?P<name>\w+) # Here goes the name and then ".html" | |
3707 | ''' | |
3708 | ||
3709 | @classmethod | |
3710 | def suitable(cls, url): | |
3711 | """Receives a URL and returns True if suitable for this IE.""" | |
3712 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None | |
3713 | ||
3714 | def _real_extract(self, url): | |
3715 | m=re.match(self._VALID_URL, url, re.VERBOSE) | |
3716 | if m.group('type_talk'): | |
3717 | return [self._talk_info(url)] | |
3718 | else : | |
3719 | playlist_id=m.group('playlist_id') | |
3720 | name=m.group('name') | |
3721 | self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name)) | |
3722 | return [self._playlist_videos_info(url,name,playlist_id)] | |
3723 | ||
3724 | def _talk_video_link(self,mediaSlug): | |
3725 | '''Returns the video link for that mediaSlug''' | |
3726 | return 'http://download.ted.com/talks/%s.mp4' % mediaSlug | |
3727 | ||
3728 | def _playlist_videos_info(self,url,name,playlist_id=0): | |
3729 | '''Returns the videos of the playlist''' | |
3730 | video_RE=r''' | |
3731 | <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)" | |
3732 | ([.\s]*?)data-playlist_item_id="(\d+)" | |
3733 | ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)" | |
3734 | ''' | |
3735 | video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>' | |
3736 | webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage') | |
3737 | m_videos=re.finditer(video_RE,webpage,re.VERBOSE) | |
3738 | m_names=re.finditer(video_name_RE,webpage) | |
3739 | ||
3740 | playlist_RE = r'div class="headline">(\s*?)<h1>(\s*?)<span>(?P<playlist_title>.*?)</span>' | |
3741 | m_playlist = re.search(playlist_RE, webpage) | |
3742 | playlist_title = m_playlist.group('playlist_title') | |
3743 | ||
3744 | playlist_entries = [] | |
3745 | for m_video, m_name in zip(m_videos,m_names): | |
3746 | video_id=m_video.group('video_id') | |
3747 | talk_url='http://www.ted.com%s' % m_name.group('talk_url') | |
3748 | playlist_entries.append(self.url_result(talk_url, 'TED')) | |
3749 | return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title) | |
3750 | ||
3751 | def _talk_info(self, url, video_id=0): | |
3752 | """Return the video for the talk in the url""" | |
3753 | m=re.match(self._VALID_URL, url,re.VERBOSE) | |
3754 | videoName=m.group('name') | |
3755 | webpage=self._download_webpage(url, video_id, 'Downloading \"%s\" page' % videoName) | |
3756 | # If the url includes the language we get the title translated | |
3757 | title_RE=r'<span id="altHeadline" >(?P<title>.*)</span>' | |
3758 | title=re.search(title_RE, webpage).group('title') | |
3759 | info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?) | |
3760 | "id":(?P<videoID>[\d]+).*? | |
3761 | "mediaSlug":"(?P<mediaSlug>[\w\d]+?)"''' | |
3762 | thumb_RE=r'</span>[\s.]*</div>[\s.]*<img src="(?P<thumbnail>.*?)"' | |
3763 | thumb_match=re.search(thumb_RE,webpage) | |
3764 | info_match=re.search(info_RE,webpage,re.VERBOSE) | |
3765 | video_id=info_match.group('videoID') | |
3766 | mediaSlug=info_match.group('mediaSlug') | |
3767 | video_url=self._talk_video_link(mediaSlug) | |
3768 | info = { | |
3769 | 'id': video_id, | |
3770 | 'url': video_url, | |
3771 | 'ext': 'mp4', | |
3772 | 'title': title, | |
3773 | 'thumbnail': thumb_match.group('thumbnail') | |
3774 | } | |
3775 | return info | |
3776 | ||
3777 | class MySpassIE(InfoExtractor): | |
3778 | _VALID_URL = r'http://www.myspass.de/.*' | |
3779 | ||
3780 | def _real_extract(self, url): | |
3781 | META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s' | |
3782 | ||
3783 | # video id is the last path element of the URL | |
3784 | # usually there is a trailing slash, so also try the second but last | |
3785 | url_path = compat_urllib_parse_urlparse(url).path | |
3786 | url_parent_path, video_id = os.path.split(url_path) | |
3787 | if not video_id: | |
3788 | _, video_id = os.path.split(url_parent_path) | |
3789 | ||
3790 | # get metadata | |
3791 | metadata_url = META_DATA_URL_TEMPLATE % video_id | |
3792 | metadata_text = self._download_webpage(metadata_url, video_id) | |
3793 | metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8')) | |
3794 | ||
3795 | # extract values from metadata | |
3796 | url_flv_el = metadata.find('url_flv') | |
3797 | if url_flv_el is None: | |
3798 | raise ExtractorError(u'Unable to extract download url') | |
3799 | video_url = url_flv_el.text | |
3800 | extension = os.path.splitext(video_url)[1][1:] | |
3801 | title_el = metadata.find('title') | |
3802 | if title_el is None: | |
3803 | raise ExtractorError(u'Unable to extract title') | |
3804 | title = title_el.text | |
3805 | format_id_el = metadata.find('format_id') | |
3806 | if format_id_el is None: | |
3807 | format = ext | |
3808 | else: | |
3809 | format = format_id_el.text | |
3810 | description_el = metadata.find('description') | |
3811 | if description_el is not None: | |
3812 | description = description_el.text | |
3813 | else: | |
3814 | description = None | |
3815 | imagePreview_el = metadata.find('imagePreview') | |
3816 | if imagePreview_el is not None: | |
3817 | thumbnail = imagePreview_el.text | |
3818 | else: | |
3819 | thumbnail = None | |
3820 | info = { | |
3821 | 'id': video_id, | |
3822 | 'url': video_url, | |
3823 | 'title': title, | |
3824 | 'ext': extension, | |
3825 | 'format': format, | |
3826 | 'thumbnail': thumbnail, | |
3827 | 'description': description | |
3828 | } | |
3829 | return [info] | |
3830 | ||
3831 | class SpiegelIE(InfoExtractor): | |
3832 | _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$' | |
3833 | ||
3834 | def _real_extract(self, url): | |
3835 | m = re.match(self._VALID_URL, url) | |
3836 | video_id = m.group('videoID') | |
3837 | ||
3838 | webpage = self._download_webpage(url, video_id) | |
3839 | m = re.search(r'<div class="spVideoTitle">(.*?)</div>', webpage) | |
3840 | if not m: | |
3841 | raise ExtractorError(u'Cannot find title') | |
3842 | video_title = unescapeHTML(m.group(1)) | |
3843 | ||
3844 | xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml' | |
3845 | xml_code = self._download_webpage(xml_url, video_id, | |
3846 | note=u'Downloading XML', errnote=u'Failed to download XML') | |
3847 | ||
3848 | idoc = xml.etree.ElementTree.fromstring(xml_code) | |
3849 | last_type = idoc[-1] | |
3850 | filename = last_type.findall('./filename')[0].text | |
3851 | duration = float(last_type.findall('./duration')[0].text) | |
3852 | ||
3853 | video_url = 'http://video2.spiegel.de/flash/' + filename | |
3854 | video_ext = filename.rpartition('.')[2] | |
3855 | info = { | |
3856 | 'id': video_id, | |
3857 | 'url': video_url, | |
3858 | 'ext': video_ext, | |
3859 | 'title': video_title, | |
3860 | 'duration': duration, | |
3861 | } | |
3862 | return [info] | |
3863 | ||
3864 | class LiveLeakIE(InfoExtractor): | |
3865 | ||
3866 | _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)' | |
3867 | IE_NAME = u'liveleak' | |
3868 | ||
3869 | def _real_extract(self, url): | |
3870 | mobj = re.match(self._VALID_URL, url) | |
3871 | if mobj is None: | |
3872 | raise ExtractorError(u'Invalid URL: %s' % url) | |
3873 | ||
3874 | video_id = mobj.group('video_id') | |
3875 | ||
3876 | webpage = self._download_webpage(url, video_id) | |
3877 | ||
3878 | m = re.search(r'file: "(.*?)",', webpage) | |
3879 | if not m: | |
3880 | raise ExtractorError(u'Unable to find video url') | |
3881 | video_url = m.group(1) | |
3882 | ||
3883 | m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage) | |
3884 | if not m: | |
3885 | raise ExtractorError(u'Cannot find video title') | |
3886 | title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip() | |
3887 | ||
3888 | m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage) | |
3889 | if m: | |
3890 | desc = unescapeHTML(m.group('desc')) | |
3891 | else: | |
3892 | desc = None | |
3893 | ||
3894 | m = re.search(r'By:.*?(\w+)</a>', webpage) | |
3895 | if m: | |
3896 | uploader = clean_html(m.group(1)) | |
3897 | else: | |
3898 | uploader = None | |
3899 | ||
3900 | info = { | |
3901 | 'id': video_id, | |
3902 | 'url': video_url, | |
3903 | 'ext': 'mp4', | |
3904 | 'title': title, | |
3905 | 'description': desc, | |
3906 | 'uploader': uploader | |
3907 | } | |
3908 | ||
3909 | return [info] | |
3910 | ||
3911 | class ARDIE(InfoExtractor): | |
3912 | _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?' | |
3913 | _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>' | |
3914 | _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)' | |
3915 | ||
3916 | def _real_extract(self, url): | |
3917 | # determine video id from url | |
3918 | m = re.match(self._VALID_URL, url) | |
3919 | ||
3920 | numid = re.search(r'documentId=([0-9]+)', url) | |
3921 | if numid: | |
3922 | video_id = numid.group(1) | |
3923 | else: | |
3924 | video_id = m.group('video_id') | |
3925 | ||
3926 | # determine title and media streams from webpage | |
3927 | html = self._download_webpage(url, video_id) | |
3928 | title = re.search(self._TITLE, html).group('title') | |
3929 | streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)] | |
3930 | if not streams: | |
3931 | assert '"fsk"' in html | |
3932 | raise ExtractorError(u'This video is only available after 8:00 pm') | |
3933 | ||
3934 | # choose default media type and highest quality for now | |
3935 | stream = max([s for s in streams if int(s["media_type"]) == 0], | |
3936 | key=lambda s: int(s["quality"])) | |
3937 | ||
3938 | # there's two possibilities: RTMP stream or HTTP download | |
3939 | info = {'id': video_id, 'title': title, 'ext': 'mp4'} | |
3940 | if stream['rtmp_url']: | |
3941 | self.to_screen(u'RTMP download detected') | |
3942 | assert stream['video_url'].startswith('mp4:') | |
3943 | info["url"] = stream["rtmp_url"] | |
3944 | info["play_path"] = stream['video_url'] | |
3945 | else: | |
3946 | assert stream["video_url"].endswith('.mp4') | |
3947 | info["url"] = stream["video_url"] | |
3948 | return [info] | |
3949 | ||
3950 | class TumblrIE(InfoExtractor): | |
3951 | _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)' | |
3952 | ||
3953 | def _real_extract(self, url): | |
3954 | m_url = re.match(self._VALID_URL, url) | |
3955 | video_id = m_url.group('id') | |
3956 | blog = m_url.group('blog_name') | |
3957 | ||
3958 | url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) | |
3959 | webpage = self._download_webpage(url, video_id) | |
3960 | ||
3961 | re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id) | |
3962 | video = re.search(re_video, webpage) | |
3963 | if video is None: | |
3964 | self.to_screen("No video founded") | |
3965 | return [] | |
3966 | video_url = video.group('video_url') | |
3967 | ext = video.group('ext') | |
3968 | ||
3969 | re_thumb = r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22' # We pick the first poster | |
3970 | thumb = re.search(re_thumb, webpage).group('thumb').replace('\\', '') | |
3971 | ||
3972 | # The only place where you can get a title, it's not complete, | |
3973 | # but searching in other places doesn't work for all videos | |
3974 | re_title = r'<title>(?P<title>.*?)</title>' | |
3975 | title = unescapeHTML(re.search(re_title, webpage, re.DOTALL).group('title')) | |
3976 | ||
3977 | return [{'id': video_id, | |
3978 | 'url': video_url, | |
3979 | 'title': title, | |
3980 | 'thumbnail': thumb, | |
3981 | 'ext': ext | |
3982 | }] | |
3983 | ||
3984 | class BandcampIE(InfoExtractor): | |
3985 | _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)' | |
3986 | ||
3987 | def _real_extract(self, url): | |
3988 | mobj = re.match(self._VALID_URL, url) | |
3989 | title = mobj.group('title') | |
3990 | webpage = self._download_webpage(url, title) | |
3991 | # We get the link to the free download page | |
3992 | m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage) | |
3993 | if m_download is None: | |
3994 | raise ExtractorError(u'No free songs founded') | |
3995 | ||
3996 | download_link = m_download.group(1) | |
3997 | id = re.search(r'var TralbumData = {(.*?)id: (?P<id>\d*?)$', | |
3998 | webpage, re.MULTILINE|re.DOTALL).group('id') | |
3999 | ||
4000 | download_webpage = self._download_webpage(download_link, id, | |
4001 | 'Downloading free downloads page') | |
4002 | # We get the dictionary of the track from some javascrip code | |
4003 | info = re.search(r'items: (.*?),$', | |
4004 | download_webpage, re.MULTILINE).group(1) | |
4005 | info = json.loads(info)[0] | |
4006 | # We pick mp3-320 for now, until format selection can be easily implemented. | |
4007 | mp3_info = info[u'downloads'][u'mp3-320'] | |
4008 | # If we try to use this url it says the link has expired | |
4009 | initial_url = mp3_info[u'url'] | |
4010 | re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$' | |
4011 | m_url = re.match(re_url, initial_url) | |
4012 | #We build the url we will use to get the final track url | |
4013 | # This url is build in Bandcamp in the script download_bunde_*.js | |
4014 | request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), id, m_url.group('ts')) | |
4015 | final_url_webpage = self._download_webpage(request_url, id, 'Requesting download url') | |
4016 | # If we could correctly generate the .rand field the url would be | |
4017 | #in the "download_url" key | |
4018 | final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1) | |
4019 | ||
4020 | track_info = {'id':id, | |
4021 | 'title' : info[u'title'], | |
4022 | 'ext' : 'mp3', | |
4023 | 'url' : final_url, | |
4024 | 'thumbnail' : info[u'thumb_url'], | |
4025 | 'uploader' : info[u'artist'] | |
4026 | } | |
4027 | ||
4028 | return [track_info] | |
4029 | ||
4030 | class RedTubeIE(InfoExtractor): | |
4031 | """Information Extractor for redtube""" | |
4032 | _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)' | |
4033 | ||
4034 | def _real_extract(self,url): | |
4035 | mobj = re.match(self._VALID_URL, url) | |
4036 | if mobj is None: | |
4037 | raise ExtractorError(u'Invalid URL: %s' % url) | |
4038 | ||
4039 | video_id = mobj.group('id') | |
4040 | video_extension = 'mp4' | |
4041 | webpage = self._download_webpage(url, video_id) | |
4042 | self.report_extraction(video_id) | |
4043 | mobj = re.search(r'<source src="'+'(.+)'+'" type="video/mp4">',webpage) | |
4044 | ||
4045 | if mobj is None: | |
4046 | raise ExtractorError(u'Unable to extract media URL') | |
4047 | ||
4048 | video_url = mobj.group(1) | |
4049 | mobj = re.search('<h1 class="videoTitle slidePanelMovable">(.+)</h1>',webpage) | |
4050 | if mobj is None: | |
4051 | raise ExtractorError(u'Unable to extract title') | |
4052 | video_title = mobj.group(1) | |
4053 | ||
4054 | return [{ | |
4055 | 'id': video_id, | |
4056 | 'url': video_url, | |
4057 | 'ext': video_extension, | |
4058 | 'title': video_title, | |
4059 | }] | |
4060 | ||
4061 | class InaIE(InfoExtractor): | |
4062 | """Information Extractor for Ina.fr""" | |
4063 | _VALID_URL = r'(?:http://)?(?:www.)?ina\.fr/video/(?P<id>I[0-9]+)/.*' | |
4064 | ||
4065 | def _real_extract(self,url): | |
4066 | mobj = re.match(self._VALID_URL, url) | |
4067 | ||
4068 | video_id = mobj.group('id') | |
4069 | mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id | |
4070 | video_extension = 'mp4' | |
4071 | webpage = self._download_webpage(mrss_url, video_id) | |
4072 | ||
4073 | mobj = re.search(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)', webpage) | |
4074 | if mobj is None: | |
4075 | raise ExtractorError(u'Unable to extract media URL') | |
4076 | video_url = mobj.group(1) | |
4077 | ||
4078 | mobj = re.search(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>', webpage) | |
4079 | if mobj is None: | |
4080 | raise ExtractorError(u'Unable to extract title') | |
4081 | video_title = mobj.group(1) | |
4082 | ||
4083 | return [{ | |
4084 | 'id': video_id, | |
4085 | 'url': video_url, | |
4086 | 'ext': video_extension, | |
4087 | 'title': video_title, | |
4088 | }] | |
4089 | ||
4090 | def gen_extractors(): | |
4091 | """ Return a list of an instance of every supported extractor. | |
4092 | The order does matter; the first extractor matched is the one handling the URL. | |
4093 | """ | |
4094 | return [ | |
4095 | YoutubePlaylistIE(), | |
4096 | YoutubeChannelIE(), | |
4097 | YoutubeUserIE(), | |
4098 | YoutubeSearchIE(), | |
4099 | YoutubeIE(), | |
4100 | MetacafeIE(), | |
4101 | DailymotionIE(), | |
4102 | GoogleSearchIE(), | |
4103 | PhotobucketIE(), | |
4104 | YahooIE(), | |
4105 | YahooSearchIE(), | |
4106 | DepositFilesIE(), | |
4107 | FacebookIE(), | |
4108 | BlipTVUserIE(), | |
4109 | BlipTVIE(), | |
4110 | VimeoIE(), | |
4111 | MyVideoIE(), | |
4112 | ComedyCentralIE(), | |
4113 | EscapistIE(), | |
4114 | CollegeHumorIE(), | |
4115 | XVideosIE(), | |
4116 | SoundcloudSetIE(), | |
4117 | SoundcloudIE(), | |
4118 | InfoQIE(), | |
4119 | MixcloudIE(), | |
4120 | StanfordOpenClassroomIE(), | |
4121 | MTVIE(), | |
4122 | YoukuIE(), | |
4123 | XNXXIE(), | |
4124 | YouJizzIE(), | |
4125 | PornotubeIE(), | |
4126 | YouPornIE(), | |
4127 | GooglePlusIE(), | |
4128 | ArteTvIE(), | |
4129 | NBAIE(), | |
4130 | WorldStarHipHopIE(), | |
4131 | JustinTVIE(), | |
4132 | FunnyOrDieIE(), | |
4133 | SteamIE(), | |
4134 | UstreamIE(), | |
4135 | RBMARadioIE(), | |
4136 | EightTracksIE(), | |
4137 | KeekIE(), | |
4138 | TEDIE(), | |
4139 | MySpassIE(), | |
4140 | SpiegelIE(), | |
4141 | LiveLeakIE(), | |
4142 | ARDIE(), | |
4143 | TumblrIE(), | |
4144 | BandcampIE(), | |
4145 | RedTubeIE(), | |
4146 | InaIE(), | |
4147 | GenericIE() | |
4148 | ] | |
4149 | ||
4150 | def get_info_extractor(ie_name): | |
4151 | """Returns the info extractor class with the given ie_name""" | |
4152 | return globals()[ie_name+'IE'] |