]>
Commit | Line | Data |
---|---|---|
d77c3dfd FV |
1 | #!/usr/bin/env python |
2 | # -*- coding: utf-8 -*- | |
3 | ||
9e8056d5 PH |
4 | from __future__ import absolute_import |
5 | ||
4fcca4bb | 6 | import base64 |
d77c3dfd | 7 | import datetime |
ccf65f9d | 8 | import itertools |
d77c3dfd FV |
9 | import netrc |
10 | import os | |
11 | import re | |
12 | import socket | |
13 | import time | |
d77c3dfd | 14 | import email.utils |
921a1455 | 15 | import xml.etree.ElementTree |
302efc19 | 16 | import random |
17 | import math | |
6324fd1d | 18 | import operator |
d77c3dfd | 19 | |
9e8056d5 | 20 | from .utils import * |
d77c3dfd FV |
21 | |
22 | ||
23 | class InfoExtractor(object): | |
59ae15a5 | 24 | """Information Extractor class. |
d77c3dfd | 25 | |
59ae15a5 PH |
26 | Information extractors are the classes that, given a URL, extract |
27 | information about the video (or videos) the URL refers to. This | |
28 | information includes the real video URL, the video title, author and | |
cdb30764 | 29 | others. The information is stored in a dictionary which is then |
59ae15a5 PH |
30 | passed to the FileDownloader. The FileDownloader processes this |
31 | information possibly downloading the video to the file system, among | |
32 | other possible outcomes. | |
717b1f72 | 33 | |
59ae15a5 | 34 | The dictionaries must include the following fields: |
717b1f72 | 35 | |
59ae15a5 PH |
36 | id: Video identifier. |
37 | url: Final video URL. | |
59ae15a5 PH |
38 | title: Video title, unescaped. |
39 | ext: Video filename extension. | |
717b1f72 | 40 | |
59ae15a5 | 41 | The following fields are optional: |
717b1f72 | 42 | |
59ae15a5 PH |
43 | format: The video format, defaults to ext (used for --get-format) |
44 | thumbnail: Full URL to a video thumbnail image. | |
45 | description: One-line video description. | |
539679c7 PH |
46 | uploader: Full name of the video uploader. |
47 | upload_date: Video upload date (YYYYMMDD). | |
77c4beab | 48 | uploader_id: Nickname or id of the video uploader. |
6119f78c | 49 | location: Physical location of the video. |
59ae15a5 | 50 | player_url: SWF Player URL (used for rtmpdump). |
553d0974 | 51 | subtitles: The subtitle file contents. |
59ae15a5 PH |
52 | urlhandle: [internal] The urlHandle to be used to download the file, |
53 | like returned by urllib.request.urlopen | |
d77c3dfd | 54 | |
59ae15a5 | 55 | The fields should all be Unicode strings. |
9ce5d9ee | 56 | |
59ae15a5 PH |
57 | Subclasses of this one should re-define the _real_initialize() and |
58 | _real_extract() methods and define a _VALID_URL regexp. | |
59 | Probably, they should also be added to the list of extractors. | |
717b1f72 | 60 | |
59ae15a5 PH |
61 | _real_extract() must return a *list* of information dictionaries as |
62 | described above. | |
03c5b0fb | 63 | |
59ae15a5 PH |
64 | Finally, the _WORKING attribute should be set to False for broken IEs |
65 | in order to warn the users and skip the tests. | |
66 | """ | |
d77c3dfd | 67 | |
59ae15a5 PH |
68 | _ready = False |
69 | _downloader = None | |
70 | _WORKING = True | |
d77c3dfd | 71 | |
59ae15a5 PH |
72 | def __init__(self, downloader=None): |
73 | """Constructor. Receives an optional downloader.""" | |
74 | self._ready = False | |
75 | self.set_downloader(downloader) | |
d77c3dfd | 76 | |
89de9eb1 FV |
77 | @classmethod |
78 | def suitable(cls, url): | |
59ae15a5 | 79 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 | 80 | return re.match(cls._VALID_URL, url) is not None |
d77c3dfd | 81 | |
89de9eb1 FV |
82 | @classmethod |
83 | def working(cls): | |
59ae15a5 | 84 | """Getter method for _WORKING.""" |
89de9eb1 | 85 | return cls._WORKING |
03c5b0fb | 86 | |
59ae15a5 PH |
87 | def initialize(self): |
88 | """Initializes an instance (authentication, etc).""" | |
89 | if not self._ready: | |
90 | self._real_initialize() | |
91 | self._ready = True | |
d77c3dfd | 92 | |
59ae15a5 PH |
93 | def extract(self, url): |
94 | """Extracts URL information and returns it in list of dicts.""" | |
95 | self.initialize() | |
96 | return self._real_extract(url) | |
d77c3dfd | 97 | |
59ae15a5 PH |
98 | def set_downloader(self, downloader): |
99 | """Sets the downloader for this IE.""" | |
100 | self._downloader = downloader | |
d77c3dfd | 101 | |
59ae15a5 PH |
102 | def _real_initialize(self): |
103 | """Real initialization process. Redefine in subclasses.""" | |
104 | pass | |
d77c3dfd | 105 | |
59ae15a5 PH |
106 | def _real_extract(self, url): |
107 | """Real extraction process. Redefine in subclasses.""" | |
108 | pass | |
d77c3dfd | 109 | |
d0d4f277 PH |
110 | @property |
111 | def IE_NAME(self): | |
112 | return type(self).__name__[:-2] | |
d77c3dfd | 113 | |
64ce2aad PH |
114 | def _request_webpage(self, url_or_request, video_id, note=None, errnote=None): |
115 | """ Returns the response handle """ | |
d830b7c2 | 116 | if note is None: |
0d173446 JMF |
117 | self.report_download_webpage(video_id) |
118 | elif note is not False: | |
f17ce13a | 119 | self.to_screen(u'%s: %s' % (video_id, note)) |
d830b7c2 | 120 | try: |
64ce2aad | 121 | return compat_urllib_request.urlopen(url_or_request) |
d830b7c2 PH |
122 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
123 | if errnote is None: | |
124 | errnote = u'Unable to download webpage' | |
01951dda | 125 | raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2]) |
d830b7c2 | 126 | |
64ce2aad PH |
127 | def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): |
128 | """ Returns the data of the page as a string """ | |
129 | urlh = self._request_webpage(url_or_request, video_id, note, errnote) | |
e32b06e9 PH |
130 | content_type = urlh.headers.get('Content-Type', '') |
131 | m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) | |
132 | if m: | |
133 | encoding = m.group(1) | |
134 | else: | |
135 | encoding = 'utf-8' | |
64ce2aad | 136 | webpage_bytes = urlh.read() |
855703e5 PH |
137 | if self._downloader.params.get('dump_intermediate_pages', False): |
138 | try: | |
139 | url = url_or_request.get_full_url() | |
140 | except AttributeError: | |
141 | url = url_or_request | |
f17ce13a | 142 | self.to_screen(u'Dumping request to ' + url) |
855703e5 PH |
143 | dump = base64.b64encode(webpage_bytes).decode('ascii') |
144 | self._downloader.to_screen(dump) | |
e32b06e9 | 145 | return webpage_bytes.decode(encoding, 'replace') |
f17ce13a JMF |
146 | |
147 | def to_screen(self, msg): | |
148 | """Print msg to screen, prefixing it with '[ie_name]'""" | |
149 | self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg)) | |
150 | ||
41a6eb94 JMF |
151 | def report_extraction(self, id_or_name): |
152 | """Report information extraction.""" | |
153 | self.to_screen(u'%s: Extracting information' % id_or_name) | |
154 | ||
320e26a0 JMF |
155 | def report_download_webpage(self, video_id): |
156 | """Report webpage download.""" | |
157 | self.to_screen(u'%s: Downloading webpage' % video_id) | |
158 | ||
e11eb119 JMF |
159 | def report_age_confirmation(self): |
160 | """Report attempt to confirm age.""" | |
161 | self.to_screen(u'Confirming age') | |
162 | ||
8a38a194 JMF |
163 | #Methods for following #608 |
164 | #They set the correct value of the '_type' key | |
165 | def video_result(self, video_info): | |
166 | """Returns a video""" | |
167 | video_info['_type'] = 'video' | |
168 | return video_info | |
169 | def url_result(self, url, ie=None): | |
170 | """Returns a url that points to a page that should be processed""" | |
171 | #TODO: ie should be the class used for getting the info | |
172 | video_info = {'_type': 'url', | |
6de8f1af JMF |
173 | 'url': url, |
174 | 'ie_key': ie} | |
8a38a194 | 175 | return video_info |
d2c69082 | 176 | def playlist_result(self, entries, playlist_id=None, playlist_title=None): |
8a38a194 JMF |
177 | """Returns a playlist""" |
178 | video_info = {'_type': 'playlist', | |
179 | 'entries': entries} | |
d2c69082 JMF |
180 | if playlist_id: |
181 | video_info['id'] = playlist_id | |
182 | if playlist_title: | |
183 | video_info['title'] = playlist_title | |
8a38a194 | 184 | return video_info |
64ce2aad | 185 | |
d830b7c2 | 186 | |
d77c3dfd | 187 | class YoutubeIE(InfoExtractor): |
59ae15a5 PH |
188 | """Information extractor for youtube.com.""" |
189 | ||
190 | _VALID_URL = r"""^ | |
191 | ( | |
192 | (?:https?://)? # http(s):// (optional) | |
193 | (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| | |
194 | tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains | |
195 | (?:.*?\#/)? # handle anchor (#/) redirect urls | |
59ae15a5 PH |
196 | (?: # the various things that can precede the ID: |
197 | (?:(?:v|embed|e)/) # v/ or embed/ or e/ | |
198 | |(?: # or the v= param in all its forms | |
199 | (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) | |
200 | (?:\?|\#!?) # the params delimiter ? or # or #! | |
3bb61659 | 201 | (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) |
59ae15a5 PH |
202 | v= |
203 | ) | |
204 | )? # optional -> youtube.com/xxxx is OK | |
205 | )? # all until now is optional -> you can pass the naked ID | |
206 | ([0-9A-Za-z_-]+) # here is it! the YouTube video ID | |
207 | (?(1).+)? # if we found the ID, everything can follow | |
208 | $""" | |
209 | _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' | |
d3f5f9f6 | 210 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' |
59ae15a5 PH |
211 | _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' |
212 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' | |
213 | _NETRC_MACHINE = 'youtube' | |
214 | # Listed in order of quality | |
215 | _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] | |
216 | _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] | |
217 | _video_extensions = { | |
218 | '13': '3gp', | |
219 | '17': 'mp4', | |
220 | '18': 'mp4', | |
221 | '22': 'mp4', | |
222 | '37': 'mp4', | |
223 | '38': 'video', # You actually don't know if this will be MOV, AVI or whatever | |
224 | '43': 'webm', | |
225 | '44': 'webm', | |
226 | '45': 'webm', | |
227 | '46': 'webm', | |
228 | } | |
229 | _video_dimensions = { | |
230 | '5': '240x400', | |
231 | '6': '???', | |
232 | '13': '???', | |
233 | '17': '144x176', | |
234 | '18': '360x640', | |
235 | '22': '720x1280', | |
236 | '34': '360x640', | |
237 | '35': '480x854', | |
238 | '37': '1080x1920', | |
239 | '38': '3072x4096', | |
240 | '43': '360x640', | |
241 | '44': '480x854', | |
242 | '45': '720x1280', | |
243 | '46': '1080x1920', | |
cdb30764 | 244 | } |
59ae15a5 PH |
245 | IE_NAME = u'youtube' |
246 | ||
89de9eb1 FV |
247 | @classmethod |
248 | def suitable(cls, url): | |
59ae15a5 | 249 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 FV |
250 | if YoutubePlaylistIE.suitable(url): return False |
251 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None | |
59ae15a5 PH |
252 | |
253 | def report_lang(self): | |
254 | """Report attempt to set language.""" | |
f17ce13a | 255 | self.to_screen(u'Setting language') |
59ae15a5 PH |
256 | |
257 | def report_login(self): | |
258 | """Report attempt to log in.""" | |
f17ce13a | 259 | self.to_screen(u'Logging in') |
59ae15a5 | 260 | |
59ae15a5 PH |
261 | def report_video_webpage_download(self, video_id): |
262 | """Report attempt to download video webpage.""" | |
f17ce13a | 263 | self.to_screen(u'%s: Downloading video webpage' % video_id) |
59ae15a5 PH |
264 | |
265 | def report_video_info_webpage_download(self, video_id): | |
266 | """Report attempt to download video info webpage.""" | |
f17ce13a | 267 | self.to_screen(u'%s: Downloading video info webpage' % video_id) |
59ae15a5 PH |
268 | |
269 | def report_video_subtitles_download(self, video_id): | |
270 | """Report attempt to download video info webpage.""" | |
f17ce13a | 271 | self.to_screen(u'%s: Checking available subtitles' % video_id) |
59ae15a5 | 272 | |
2a4093ea | 273 | def report_video_subtitles_request(self, video_id, sub_lang, format): |
ae608b80 | 274 | """Report attempt to download video info webpage.""" |
f17ce13a | 275 | self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format)) |
2a4093ea IM |
276 | |
277 | def report_video_subtitles_available(self, video_id, sub_lang_list): | |
278 | """Report available subtitles.""" | |
279 | sub_lang = ",".join(list(sub_lang_list.keys())) | |
f17ce13a | 280 | self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang)) |
59ae15a5 PH |
281 | |
282 | def report_information_extraction(self, video_id): | |
283 | """Report attempt to extract video information.""" | |
f17ce13a | 284 | self.to_screen(u'%s: Extracting video information' % video_id) |
59ae15a5 PH |
285 | |
286 | def report_unavailable_format(self, video_id, format): | |
287 | """Report extracted video URL.""" | |
f17ce13a | 288 | self.to_screen(u'%s: Format %s not available' % (video_id, format)) |
59ae15a5 PH |
289 | |
290 | def report_rtmp_download(self): | |
291 | """Indicate the download will use the RTMP protocol.""" | |
f17ce13a | 292 | self.to_screen(u'RTMP download detected') |
59ae15a5 | 293 | |
ae608b80 | 294 | def _get_available_subtitles(self, video_id): |
056d8575 FV |
295 | self.report_video_subtitles_download(video_id) |
296 | request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) | |
297 | try: | |
553d0974 | 298 | sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8') |
056d8575 | 299 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
bc97f6d6 | 300 | return (u'unable to download video subtitles: %s' % compat_str(err), None) |
553d0974 IM |
301 | sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list) |
302 | sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list) | |
303 | if not sub_lang_list: | |
bc97f6d6 | 304 | return (u'video doesn\'t have subtitles', None) |
553d0974 | 305 | return sub_lang_list |
ae608b80 | 306 | |
2a4093ea IM |
307 | def _list_available_subtitles(self, video_id): |
308 | sub_lang_list = self._get_available_subtitles(video_id) | |
309 | self.report_video_subtitles_available(video_id, sub_lang_list) | |
310 | ||
9e62bc44 | 311 | def _request_subtitle(self, sub_lang, sub_name, video_id, format): |
6a205c88 JMF |
312 | """ |
313 | Return tuple: | |
314 | (error_message, sub_lang, sub) | |
315 | """ | |
2a4093ea | 316 | self.report_video_subtitles_request(video_id, sub_lang, format) |
fb778e66 | 317 | params = compat_urllib_parse.urlencode({ |
553d0974 IM |
318 | 'lang': sub_lang, |
319 | 'name': sub_name, | |
fb778e66 | 320 | 'v': video_id, |
ae608b80 | 321 | 'fmt': format, |
fb778e66 PH |
322 | }) |
323 | url = 'http://www.youtube.com/api/timedtext?' + params | |
056d8575 | 324 | try: |
553d0974 | 325 | sub = compat_urllib_request.urlopen(url).read().decode('utf-8') |
056d8575 | 326 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
bc97f6d6 | 327 | return (u'unable to download video subtitles: %s' % compat_str(err), None, None) |
553d0974 | 328 | if not sub: |
bc97f6d6 | 329 | return (u'Did not fetch video subtitles', None, None) |
553d0974 | 330 | return (None, sub_lang, sub) |
ae608b80 IM |
331 | |
332 | def _extract_subtitle(self, video_id): | |
0fb37564 JMF |
333 | """ |
334 | Return a list with a tuple: | |
335 | [(error_message, sub_lang, sub)] | |
336 | """ | |
553d0974 | 337 | sub_lang_list = self._get_available_subtitles(video_id) |
9e62bc44 | 338 | sub_format = self._downloader.params.get('subtitlesformat') |
0fb37564 JMF |
339 | if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles |
340 | return [(sub_lang_list[0], None, None)] | |
ae608b80 | 341 | if self._downloader.params.get('subtitleslang', False): |
553d0974 IM |
342 | sub_lang = self._downloader.params.get('subtitleslang') |
343 | elif 'en' in sub_lang_list: | |
344 | sub_lang = 'en' | |
ae608b80 | 345 | else: |
553d0974 IM |
346 | sub_lang = list(sub_lang_list.keys())[0] |
347 | if not sub_lang in sub_lang_list: | |
bc97f6d6 | 348 | return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)] |
ae608b80 | 349 | |
9e62bc44 | 350 | subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) |
553d0974 | 351 | return [subtitle] |
ae608b80 IM |
352 | |
353 | def _extract_all_subtitles(self, video_id): | |
553d0974 | 354 | sub_lang_list = self._get_available_subtitles(video_id) |
9e62bc44 | 355 | sub_format = self._downloader.params.get('subtitlesformat') |
ef767f9f JMF |
356 | if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles |
357 | return [(sub_lang_list[0], None, None)] | |
553d0974 IM |
358 | subtitles = [] |
359 | for sub_lang in sub_lang_list: | |
9e62bc44 | 360 | subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) |
553d0974 IM |
361 | subtitles.append(subtitle) |
362 | return subtitles | |
056d8575 | 363 | |
59ae15a5 PH |
364 | def _print_formats(self, formats): |
365 | print('Available formats:') | |
366 | for x in formats: | |
367 | print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))) | |
368 | ||
369 | def _real_initialize(self): | |
370 | if self._downloader is None: | |
371 | return | |
372 | ||
373 | username = None | |
374 | password = None | |
375 | downloader_params = self._downloader.params | |
376 | ||
377 | # Attempt to use provided username and password or .netrc data | |
378 | if downloader_params.get('username', None) is not None: | |
379 | username = downloader_params['username'] | |
380 | password = downloader_params['password'] | |
381 | elif downloader_params.get('usenetrc', False): | |
382 | try: | |
383 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
384 | if info is not None: | |
385 | username = info[0] | |
386 | password = info[2] | |
387 | else: | |
388 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
389 | except (IOError, netrc.NetrcParseError) as err: | |
2e5457be | 390 | self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) |
59ae15a5 PH |
391 | return |
392 | ||
393 | # Set language | |
394 | request = compat_urllib_request.Request(self._LANG_URL) | |
395 | try: | |
396 | self.report_lang() | |
397 | compat_urllib_request.urlopen(request).read() | |
398 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2e5457be | 399 | self._downloader.report_warning(u'unable to set language: %s' % compat_str(err)) |
59ae15a5 PH |
400 | return |
401 | ||
402 | # No authentication to be performed | |
403 | if username is None: | |
404 | return | |
405 | ||
d3f5f9f6 PH |
406 | request = compat_urllib_request.Request(self._LOGIN_URL) |
407 | try: | |
408 | login_page = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
409 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2e5457be | 410 | self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err)) |
d3f5f9f6 PH |
411 | return |
412 | ||
413 | galx = None | |
414 | dsh = None | |
415 | match = re.search(re.compile(r'<input.+?name="GALX".+?value="(.+?)"', re.DOTALL), login_page) | |
416 | if match: | |
417 | galx = match.group(1) | |
418 | ||
419 | match = re.search(re.compile(r'<input.+?name="dsh".+?value="(.+?)"', re.DOTALL), login_page) | |
420 | if match: | |
421 | dsh = match.group(1) | |
422 | ||
59ae15a5 | 423 | # Log in |
d3f5f9f6 PH |
424 | login_form_strs = { |
425 | u'continue': u'http://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', | |
426 | u'Email': username, | |
427 | u'GALX': galx, | |
428 | u'Passwd': password, | |
429 | u'PersistentCookie': u'yes', | |
430 | u'_utf8': u'霱', | |
431 | u'bgresponse': u'js_disabled', | |
432 | u'checkConnection': u'', | |
433 | u'checkedDomains': u'youtube', | |
434 | u'dnConn': u'', | |
435 | u'dsh': dsh, | |
436 | u'pstMsg': u'0', | |
437 | u'rmShown': u'1', | |
438 | u'secTok': u'', | |
439 | u'signIn': u'Sign in', | |
440 | u'timeStmp': u'', | |
441 | u'service': u'youtube', | |
442 | u'uilel': u'3', | |
443 | u'hl': u'en_US', | |
444 | } | |
445 | # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode | |
446 | # chokes on unicode | |
447 | login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items()) | |
448 | login_data = compat_urllib_parse.urlencode(login_form).encode('ascii') | |
449 | request = compat_urllib_request.Request(self._LOGIN_URL, login_data) | |
59ae15a5 PH |
450 | try: |
451 | self.report_login() | |
80d3177e | 452 | login_results = compat_urllib_request.urlopen(request).read().decode('utf-8') |
d3f5f9f6 | 453 | if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: |
2e5457be | 454 | self._downloader.report_warning(u'unable to log in: bad username or password') |
59ae15a5 PH |
455 | return |
456 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2e5457be | 457 | self._downloader.report_warning(u'unable to log in: %s' % compat_str(err)) |
59ae15a5 PH |
458 | return |
459 | ||
460 | # Confirm age | |
461 | age_form = { | |
462 | 'next_url': '/', | |
463 | 'action_confirm': 'Confirm', | |
464 | } | |
465 | request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form)) | |
466 | try: | |
467 | self.report_age_confirmation() | |
80d3177e | 468 | age_results = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 | 469 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 470 | self._downloader.report_error(u'unable to confirm age: %s' % compat_str(err)) |
59ae15a5 PH |
471 | return |
472 | ||
3bb61659 | 473 | def _extract_id(self, url): |
59ae15a5 PH |
474 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
475 | if mobj is None: | |
e5f30ade | 476 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
477 | return |
478 | video_id = mobj.group(2) | |
3bb61659 PH |
479 | return video_id |
480 | ||
481 | def _real_extract(self, url): | |
482 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter | |
483 | mobj = re.search(self._NEXT_URL_RE, url) | |
484 | if mobj: | |
485 | url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') | |
486 | video_id = self._extract_id(url) | |
59ae15a5 PH |
487 | |
488 | # Get video webpage | |
489 | self.report_video_webpage_download(video_id) | |
3bb61659 PH |
490 | url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id |
491 | request = compat_urllib_request.Request(url) | |
59ae15a5 PH |
492 | try: |
493 | video_webpage_bytes = compat_urllib_request.urlopen(request).read() | |
494 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 495 | self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
496 | return |
497 | ||
498 | video_webpage = video_webpage_bytes.decode('utf-8', 'ignore') | |
499 | ||
500 | # Attempt to extract SWF player URL | |
501 | mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) | |
502 | if mobj is not None: | |
503 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
504 | else: | |
505 | player_url = None | |
506 | ||
507 | # Get video info | |
508 | self.report_video_info_webpage_download(video_id) | |
509 | for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: | |
927c8c49 | 510 | video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' |
59ae15a5 | 511 | % (video_id, el_type)) |
927c8c49 PH |
512 | video_info_webpage = self._download_webpage(video_info_url, video_id, |
513 | note=False, | |
514 | errnote='unable to download video info webpage') | |
515 | video_info = compat_parse_qs(video_info_webpage) | |
516 | if 'token' in video_info: | |
517 | break | |
59ae15a5 PH |
518 | if 'token' not in video_info: |
519 | if 'reason' in video_info: | |
e5f30ade | 520 | self._downloader.report_error(u'YouTube said: %s' % video_info['reason'][0]) |
59ae15a5 | 521 | else: |
e5f30ade | 522 | self._downloader.report_error(u'"token" parameter not in video info for unknown reason') |
59ae15a5 PH |
523 | return |
524 | ||
525 | # Check for "rental" videos | |
526 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
e5f30ade | 527 | self._downloader.report_error(u'"rental" videos not supported') |
59ae15a5 PH |
528 | return |
529 | ||
530 | # Start extracting information | |
531 | self.report_information_extraction(video_id) | |
532 | ||
533 | # uploader | |
534 | if 'author' not in video_info: | |
e5f30ade | 535 | self._downloader.report_error(u'unable to extract uploader name') |
59ae15a5 PH |
536 | return |
537 | video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) | |
538 | ||
77c4beab FV |
539 | # uploader_id |
540 | video_uploader_id = None | |
26cf0408 | 541 | mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage) |
77c4beab FV |
542 | if mobj is not None: |
543 | video_uploader_id = mobj.group(1) | |
544 | else: | |
c9fa1cba | 545 | self._downloader.report_warning(u'unable to extract uploader nickname') |
77c4beab | 546 | |
59ae15a5 PH |
547 | # title |
548 | if 'title' not in video_info: | |
e5f30ade | 549 | self._downloader.report_error(u'unable to extract video title') |
59ae15a5 PH |
550 | return |
551 | video_title = compat_urllib_parse.unquote_plus(video_info['title'][0]) | |
552 | ||
553 | # thumbnail image | |
554 | if 'thumbnail_url' not in video_info: | |
c9fa1cba | 555 | self._downloader.report_warning(u'unable to extract video thumbnail') |
59ae15a5 PH |
556 | video_thumbnail = '' |
557 | else: # don't panic if we can't find it | |
558 | video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) | |
559 | ||
560 | # upload date | |
561 | upload_date = None | |
562 | mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL) | |
563 | if mobj is not None: | |
564 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) | |
bf50b038 | 565 | upload_date = unified_strdate(upload_date) |
59ae15a5 PH |
566 | |
567 | # description | |
568 | video_description = get_element_by_id("eow-description", video_webpage) | |
569 | if video_description: | |
570 | video_description = clean_html(video_description) | |
571 | else: | |
7b670a44 PH |
572 | fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage) |
573 | if fd_mobj: | |
574 | video_description = unescapeHTML(fd_mobj.group(1)) | |
575 | else: | |
576 | video_description = u'' | |
59ae15a5 | 577 | |
9e62bc44 | 578 | # subtitles |
59ae15a5 | 579 | video_subtitles = None |
ae608b80 | 580 | |
59ae15a5 | 581 | if self._downloader.params.get('writesubtitles', False): |
ae608b80 IM |
582 | video_subtitles = self._extract_subtitle(video_id) |
583 | if video_subtitles: | |
553d0974 IM |
584 | (sub_error, sub_lang, sub) = video_subtitles[0] |
585 | if sub_error: | |
bc97f6d6 | 586 | self._downloader.report_error(sub_error) |
ae608b80 IM |
587 | |
588 | if self._downloader.params.get('allsubtitles', False): | |
589 | video_subtitles = self._extract_all_subtitles(video_id) | |
590 | for video_subtitle in video_subtitles: | |
553d0974 IM |
591 | (sub_error, sub_lang, sub) = video_subtitle |
592 | if sub_error: | |
bc97f6d6 | 593 | self._downloader.report_error(sub_error) |
59ae15a5 | 594 | |
2a4093ea IM |
595 | if self._downloader.params.get('listsubtitles', False): |
596 | sub_lang_list = self._list_available_subtitles(video_id) | |
597 | return | |
59ae15a5 PH |
598 | |
599 | if 'length_seconds' not in video_info: | |
c9fa1cba | 600 | self._downloader.report_warning(u'unable to extract video duration') |
59ae15a5 PH |
601 | video_duration = '' |
602 | else: | |
603 | video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]) | |
604 | ||
605 | # token | |
606 | video_token = compat_urllib_parse.unquote_plus(video_info['token'][0]) | |
607 | ||
608 | # Decide which formats to download | |
609 | req_format = self._downloader.params.get('format', None) | |
610 | ||
611 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): | |
612 | self.report_rtmp_download() | |
613 | video_url_list = [(None, video_info['conn'][0])] | |
614 | elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: | |
615 | url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') | |
616 | url_data = [compat_parse_qs(uds) for uds in url_data_strs] | |
1a2c3c0f | 617 | url_data = [ud for ud in url_data if 'itag' in ud and 'url' in ud] |
c8c5443b | 618 | url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data) |
59ae15a5 PH |
619 | |
620 | format_limit = self._downloader.params.get('format_limit', None) | |
621 | available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats | |
622 | if format_limit is not None and format_limit in available_formats: | |
623 | format_list = available_formats[available_formats.index(format_limit):] | |
624 | else: | |
625 | format_list = available_formats | |
626 | existing_formats = [x for x in format_list if x in url_map] | |
627 | if len(existing_formats) == 0: | |
c681a039 | 628 | raise ExtractorError(u'no known formats available for video') |
59ae15a5 PH |
629 | if self._downloader.params.get('listformats', None): |
630 | self._print_formats(existing_formats) | |
631 | return | |
632 | if req_format is None or req_format == 'best': | |
633 | video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality | |
634 | elif req_format == 'worst': | |
635 | video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality | |
636 | elif req_format in ('-1', 'all'): | |
637 | video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats | |
638 | else: | |
639 | # Specific formats. We pick the first in a slash-delimeted sequence. | |
640 | # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. | |
641 | req_formats = req_format.split('/') | |
642 | video_url_list = None | |
643 | for rf in req_formats: | |
644 | if rf in url_map: | |
645 | video_url_list = [(rf, url_map[rf])] | |
646 | break | |
647 | if video_url_list is None: | |
c681a039 | 648 | raise ExtractorError(u'requested format not available') |
59ae15a5 | 649 | else: |
c681a039 | 650 | raise ExtractorError(u'no conn or url_encoded_fmt_stream_map information found in video info') |
59ae15a5 PH |
651 | |
652 | results = [] | |
653 | for format_param, video_real_url in video_url_list: | |
654 | # Extension | |
655 | video_extension = self._video_extensions.get(format_param, 'flv') | |
656 | ||
32761d86 FV |
657 | video_format = '{0} - {1}'.format(format_param if format_param else video_extension, |
658 | self._video_dimensions.get(format_param, '???')) | |
59ae15a5 PH |
659 | |
660 | results.append({ | |
661 | 'id': video_id, | |
662 | 'url': video_real_url, | |
663 | 'uploader': video_uploader, | |
77c4beab | 664 | 'uploader_id': video_uploader_id, |
59ae15a5 PH |
665 | 'upload_date': upload_date, |
666 | 'title': video_title, | |
667 | 'ext': video_extension, | |
668 | 'format': video_format, | |
669 | 'thumbnail': video_thumbnail, | |
670 | 'description': video_description, | |
671 | 'player_url': player_url, | |
672 | 'subtitles': video_subtitles, | |
673 | 'duration': video_duration | |
674 | }) | |
675 | return results | |
d77c3dfd FV |
676 | |
677 | ||
678 | class MetacafeIE(InfoExtractor): | |
59ae15a5 PH |
679 | """Information Extractor for metacafe.com.""" |
680 | ||
681 | _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' | |
682 | _DISCLAIMER = 'http://www.metacafe.com/family_filter/' | |
683 | _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' | |
684 | IE_NAME = u'metacafe' | |
685 | ||
59ae15a5 PH |
686 | def report_disclaimer(self): |
687 | """Report disclaimer retrieval.""" | |
f17ce13a | 688 | self.to_screen(u'Retrieving disclaimer') |
59ae15a5 | 689 | |
59ae15a5 PH |
690 | def _real_initialize(self): |
691 | # Retrieve disclaimer | |
692 | request = compat_urllib_request.Request(self._DISCLAIMER) | |
693 | try: | |
694 | self.report_disclaimer() | |
695 | disclaimer = compat_urllib_request.urlopen(request).read() | |
696 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 697 | self._downloader.report_error(u'unable to retrieve disclaimer: %s' % compat_str(err)) |
59ae15a5 PH |
698 | return |
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: | |
e5f30ade | 710 | self._downloader.report_error(u'unable to confirm age: %s' % compat_str(err)) |
59ae15a5 PH |
711 | return |
712 | ||
713 | def _real_extract(self, url): | |
714 | # Extract id and simplified title from URL | |
715 | mobj = re.match(self._VALID_URL, url) | |
716 | if mobj is None: | |
e5f30ade | 717 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
718 | return |
719 | ||
720 | video_id = mobj.group(1) | |
721 | ||
722 | # Check if video comes from YouTube | |
723 | mobj2 = re.match(r'^yt-(.*)$', video_id) | |
724 | if mobj2 is not None: | |
6de8f1af | 725 | return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')] |
59ae15a5 PH |
726 | |
727 | # Retrieve video webpage to extract further information | |
f7a9721e | 728 | webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id) |
59ae15a5 PH |
729 | |
730 | # Extract URL, uploader and title from webpage | |
731 | self.report_extraction(video_id) | |
732 | mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) | |
733 | if mobj is not None: | |
734 | mediaURL = compat_urllib_parse.unquote(mobj.group(1)) | |
735 | video_extension = mediaURL[-3:] | |
736 | ||
737 | # Extract gdaKey if available | |
738 | mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) | |
739 | if mobj is None: | |
740 | video_url = mediaURL | |
741 | else: | |
742 | gdaKey = mobj.group(1) | |
743 | video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) | |
744 | else: | |
745 | mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) | |
746 | if mobj is None: | |
e5f30ade | 747 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 PH |
748 | return |
749 | vardict = compat_parse_qs(mobj.group(1)) | |
750 | if 'mediaData' not in vardict: | |
e5f30ade | 751 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 | 752 | return |
f7a9721e | 753 | mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0]) |
59ae15a5 | 754 | if mobj is None: |
e5f30ade | 755 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 | 756 | return |
f7a9721e | 757 | mediaURL = mobj.group('mediaURL').replace('\\/', '/') |
59ae15a5 | 758 | video_extension = mediaURL[-3:] |
f7a9721e | 759 | video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) |
59ae15a5 PH |
760 | |
761 | mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) | |
762 | if mobj is None: | |
e5f30ade | 763 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 PH |
764 | return |
765 | video_title = mobj.group(1).decode('utf-8') | |
766 | ||
767 | mobj = re.search(r'submitter=(.*?);', webpage) | |
768 | if mobj is None: | |
e5f30ade | 769 | self._downloader.report_error(u'unable to extract uploader nickname') |
59ae15a5 PH |
770 | return |
771 | video_uploader = mobj.group(1) | |
772 | ||
773 | return [{ | |
774 | 'id': video_id.decode('utf-8'), | |
775 | 'url': video_url.decode('utf-8'), | |
776 | 'uploader': video_uploader.decode('utf-8'), | |
777 | 'upload_date': None, | |
778 | 'title': video_title, | |
779 | 'ext': video_extension.decode('utf-8'), | |
780 | }] | |
d77c3dfd FV |
781 | |
782 | ||
783 | class DailymotionIE(InfoExtractor): | |
59ae15a5 PH |
784 | """Information Extractor for Dailymotion""" |
785 | ||
786 | _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' | |
787 | IE_NAME = u'dailymotion' | |
b17c974a | 788 | _WORKING = False |
59ae15a5 | 789 | |
59ae15a5 PH |
790 | def _real_extract(self, url): |
791 | # Extract id and simplified title from URL | |
792 | mobj = re.match(self._VALID_URL, url) | |
793 | if mobj is None: | |
e5f30ade | 794 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
795 | return |
796 | ||
797 | video_id = mobj.group(1).split('_')[0].split('?')[0] | |
798 | ||
799 | video_extension = 'mp4' | |
800 | ||
801 | # Retrieve video webpage to extract further information | |
802 | request = compat_urllib_request.Request(url) | |
803 | request.add_header('Cookie', 'family_filter=off') | |
8e241d1a | 804 | webpage = self._download_webpage(request, video_id) |
59ae15a5 PH |
805 | |
806 | # Extract URL, uploader and title from webpage | |
807 | self.report_extraction(video_id) | |
808 | mobj = re.search(r'\s*var flashvars = (.*)', webpage) | |
809 | if mobj is None: | |
e5f30ade | 810 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 PH |
811 | return |
812 | flashvars = compat_urllib_parse.unquote(mobj.group(1)) | |
813 | ||
814 | for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: | |
815 | if key in flashvars: | |
816 | max_quality = key | |
f17ce13a | 817 | self.to_screen(u'Using %s' % key) |
59ae15a5 PH |
818 | break |
819 | else: | |
e5f30ade | 820 | self._downloader.report_error(u'unable to extract video URL') |
59ae15a5 PH |
821 | return |
822 | ||
823 | mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) | |
824 | if mobj is None: | |
e5f30ade | 825 | self._downloader.report_error(u'unable to extract video URL') |
59ae15a5 PH |
826 | return |
827 | ||
828 | video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/') | |
829 | ||
830 | # TODO: support choosing qualities | |
831 | ||
832 | mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage) | |
833 | if mobj is None: | |
e5f30ade | 834 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 | 835 | return |
28ca6b5a | 836 | video_title = unescapeHTML(mobj.group('title')) |
59ae15a5 PH |
837 | |
838 | video_uploader = None | |
839 | mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage) | |
840 | if mobj is None: | |
841 | # lookin for official user | |
842 | mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage) | |
843 | if mobj_official is None: | |
c9fa1cba | 844 | self._downloader.report_warning(u'unable to extract uploader nickname') |
59ae15a5 PH |
845 | else: |
846 | video_uploader = mobj_official.group(1) | |
847 | else: | |
848 | video_uploader = mobj.group(1) | |
849 | ||
850 | video_upload_date = None | |
851 | mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage) | |
852 | if mobj is not None: | |
853 | video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1) | |
854 | ||
855 | return [{ | |
28ca6b5a PH |
856 | 'id': video_id, |
857 | 'url': video_url, | |
858 | 'uploader': video_uploader, | |
59ae15a5 PH |
859 | 'upload_date': video_upload_date, |
860 | 'title': video_title, | |
28ca6b5a | 861 | 'ext': video_extension, |
59ae15a5 | 862 | }] |
d77c3dfd FV |
863 | |
864 | ||
d77c3dfd | 865 | class PhotobucketIE(InfoExtractor): |
59ae15a5 PH |
866 | """Information extractor for photobucket.com.""" |
867 | ||
868 | _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' | |
869 | IE_NAME = u'photobucket' | |
870 | ||
59ae15a5 PH |
871 | def _real_extract(self, url): |
872 | # Extract id from URL | |
873 | mobj = re.match(self._VALID_URL, url) | |
874 | if mobj is None: | |
e5f30ade | 875 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
876 | return |
877 | ||
878 | video_id = mobj.group(1) | |
879 | ||
880 | video_extension = 'flv' | |
881 | ||
882 | # Retrieve video webpage to extract further information | |
883 | request = compat_urllib_request.Request(url) | |
884 | try: | |
885 | self.report_download_webpage(video_id) | |
886 | webpage = compat_urllib_request.urlopen(request).read() | |
887 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 888 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
889 | return |
890 | ||
891 | # Extract URL, uploader, and title from webpage | |
892 | self.report_extraction(video_id) | |
893 | mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage) | |
894 | if mobj is None: | |
e5f30ade | 895 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 PH |
896 | return |
897 | mediaURL = compat_urllib_parse.unquote(mobj.group(1)) | |
898 | ||
899 | video_url = mediaURL | |
900 | ||
901 | mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) | |
902 | if mobj is None: | |
e5f30ade | 903 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 PH |
904 | return |
905 | video_title = mobj.group(1).decode('utf-8') | |
906 | ||
907 | video_uploader = mobj.group(2).decode('utf-8') | |
908 | ||
909 | return [{ | |
910 | 'id': video_id.decode('utf-8'), | |
911 | 'url': video_url.decode('utf-8'), | |
912 | 'uploader': video_uploader, | |
913 | 'upload_date': None, | |
914 | 'title': video_title, | |
915 | 'ext': video_extension.decode('utf-8'), | |
916 | }] | |
d77c3dfd FV |
917 | |
918 | ||
919 | class YahooIE(InfoExtractor): | |
59ae15a5 PH |
920 | """Information extractor for video.yahoo.com.""" |
921 | ||
93702113 | 922 | _WORKING = False |
59ae15a5 PH |
923 | # _VALID_URL matches all Yahoo! Video URLs |
924 | # _VPAGE_URL matches only the extractable '/watch/' URLs | |
925 | _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' | |
926 | _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' | |
927 | IE_NAME = u'video.yahoo' | |
928 | ||
59ae15a5 PH |
929 | def _real_extract(self, url, new_video=True): |
930 | # Extract ID from URL | |
931 | mobj = re.match(self._VALID_URL, url) | |
932 | if mobj is None: | |
e5f30ade | 933 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
934 | return |
935 | ||
936 | video_id = mobj.group(2) | |
937 | video_extension = 'flv' | |
938 | ||
939 | # Rewrite valid but non-extractable URLs as | |
940 | # extractable English language /watch/ URLs | |
941 | if re.match(self._VPAGE_URL, url) is None: | |
942 | request = compat_urllib_request.Request(url) | |
943 | try: | |
944 | webpage = compat_urllib_request.urlopen(request).read() | |
945 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 946 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
947 | return |
948 | ||
949 | mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) | |
950 | if mobj is None: | |
e5f30ade | 951 | self._downloader.report_error(u'Unable to extract id field') |
59ae15a5 PH |
952 | return |
953 | yahoo_id = mobj.group(1) | |
954 | ||
955 | mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) | |
956 | if mobj is None: | |
e5f30ade | 957 | self._downloader.report_error(u'Unable to extract vid field') |
59ae15a5 PH |
958 | return |
959 | yahoo_vid = mobj.group(1) | |
960 | ||
961 | url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) | |
962 | return self._real_extract(url, new_video=False) | |
963 | ||
964 | # Retrieve video webpage to extract further information | |
965 | request = compat_urllib_request.Request(url) | |
966 | try: | |
967 | self.report_download_webpage(video_id) | |
968 | webpage = compat_urllib_request.urlopen(request).read() | |
969 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 970 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
971 | return |
972 | ||
973 | # Extract uploader and title from webpage | |
974 | self.report_extraction(video_id) | |
975 | mobj = re.search(r'<meta name="title" content="(.*)" />', webpage) | |
976 | if mobj is None: | |
e5f30ade | 977 | self._downloader.report_error(u'unable to extract video title') |
59ae15a5 PH |
978 | return |
979 | video_title = mobj.group(1).decode('utf-8') | |
980 | ||
981 | mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage) | |
982 | if mobj is None: | |
e5f30ade | 983 | self._downloader.report_error(u'unable to extract video uploader') |
59ae15a5 PH |
984 | return |
985 | video_uploader = mobj.group(1).decode('utf-8') | |
986 | ||
987 | # Extract video thumbnail | |
988 | mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage) | |
989 | if mobj is None: | |
e5f30ade | 990 | self._downloader.report_error(u'unable to extract video thumbnail') |
59ae15a5 PH |
991 | return |
992 | video_thumbnail = mobj.group(1).decode('utf-8') | |
993 | ||
994 | # Extract video description | |
995 | mobj = re.search(r'<meta name="description" content="(.*)" />', webpage) | |
996 | if mobj is None: | |
e5f30ade | 997 | self._downloader.report_error(u'unable to extract video description') |
59ae15a5 PH |
998 | return |
999 | video_description = mobj.group(1).decode('utf-8') | |
1000 | if not video_description: | |
1001 | video_description = 'No description available.' | |
1002 | ||
1003 | # Extract video height and width | |
1004 | mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage) | |
1005 | if mobj is None: | |
e5f30ade | 1006 | self._downloader.report_error(u'unable to extract video height') |
59ae15a5 PH |
1007 | return |
1008 | yv_video_height = mobj.group(1) | |
1009 | ||
1010 | mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage) | |
1011 | if mobj is None: | |
e5f30ade | 1012 | self._downloader.report_error(u'unable to extract video width') |
59ae15a5 PH |
1013 | return |
1014 | yv_video_width = mobj.group(1) | |
1015 | ||
1016 | # Retrieve video playlist to extract media URL | |
1017 | # I'm not completely sure what all these options are, but we | |
1018 | # seem to need most of them, otherwise the server sends a 401. | |
1019 | yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents | |
1020 | yv_bitrate = '700' # according to Wikipedia this is hard-coded | |
1021 | request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + | |
1022 | '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + | |
1023 | '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') | |
1024 | try: | |
1025 | self.report_download_webpage(video_id) | |
1026 | webpage = compat_urllib_request.urlopen(request).read() | |
1027 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1028 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1029 | return |
1030 | ||
1031 | # Extract media URL from playlist XML | |
1032 | mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage) | |
1033 | if mobj is None: | |
e5f30ade | 1034 | self._downloader.report_error(u'Unable to extract media URL') |
59ae15a5 PH |
1035 | return |
1036 | video_url = compat_urllib_parse.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') | |
1037 | video_url = unescapeHTML(video_url) | |
1038 | ||
1039 | return [{ | |
1040 | 'id': video_id.decode('utf-8'), | |
1041 | 'url': video_url, | |
1042 | 'uploader': video_uploader, | |
1043 | 'upload_date': None, | |
1044 | 'title': video_title, | |
1045 | 'ext': video_extension.decode('utf-8'), | |
1046 | 'thumbnail': video_thumbnail.decode('utf-8'), | |
1047 | 'description': video_description, | |
1048 | }] | |
d77c3dfd FV |
1049 | |
1050 | ||
1051 | class VimeoIE(InfoExtractor): | |
59ae15a5 PH |
1052 | """Information extractor for vimeo.com.""" |
1053 | ||
1054 | # _VALID_URL matches Vimeo URLs | |
8edc2cf8 | 1055 | _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)' |
59ae15a5 PH |
1056 | IE_NAME = u'vimeo' |
1057 | ||
59ae15a5 PH |
1058 | def _real_extract(self, url, new_video=True): |
1059 | # Extract ID from URL | |
1060 | mobj = re.match(self._VALID_URL, url) | |
1061 | if mobj is None: | |
e5f30ade | 1062 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1063 | return |
1064 | ||
8edc2cf8 PH |
1065 | video_id = mobj.group('id') |
1066 | if not mobj.group('proto'): | |
1067 | url = 'https://' + url | |
1068 | if mobj.group('direct_link'): | |
1069 | url = 'https://vimeo.com/' + video_id | |
59ae15a5 PH |
1070 | |
1071 | # Retrieve video webpage to extract further information | |
1072 | request = compat_urllib_request.Request(url, None, std_headers) | |
1073 | try: | |
1074 | self.report_download_webpage(video_id) | |
f1171f7c PH |
1075 | webpage_bytes = compat_urllib_request.urlopen(request).read() |
1076 | webpage = webpage_bytes.decode('utf-8') | |
59ae15a5 | 1077 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 1078 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1079 | return |
1080 | ||
1081 | # Now we begin extracting as much information as we can from what we | |
1082 | # retrieved. First we extract the information common to all extractors, | |
1083 | # and latter we extract those that are Vimeo specific. | |
1084 | self.report_extraction(video_id) | |
1085 | ||
1086 | # Extract the config JSON | |
59ae15a5 | 1087 | try: |
1ca63e3a | 1088 | config = webpage.split(' = {config:')[1].split(',assets:')[0] |
59ae15a5 PH |
1089 | config = json.loads(config) |
1090 | except: | |
3820df01 JMF |
1091 | if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): |
1092 | self._downloader.report_error(u'The author has restricted the access to this video, try with the "--referer" option') | |
1093 | else: | |
1094 | self._downloader.report_error(u'unable to extract info section') | |
59ae15a5 | 1095 | return |
cdb30764 | 1096 | |
59ae15a5 PH |
1097 | # Extract title |
1098 | video_title = config["video"]["title"] | |
1099 | ||
77c4beab | 1100 | # Extract uploader and uploader_id |
59ae15a5 | 1101 | video_uploader = config["video"]["owner"]["name"] |
77c4beab | 1102 | video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] |
59ae15a5 PH |
1103 | |
1104 | # Extract video thumbnail | |
1105 | video_thumbnail = config["video"]["thumbnail"] | |
1106 | ||
1107 | # Extract video description | |
0dcfb234 | 1108 | video_description = get_element_by_attribute("itemprop", "description", webpage) |
59ae15a5 | 1109 | if video_description: video_description = clean_html(video_description) |
dc36bc94 | 1110 | else: video_description = u'' |
59ae15a5 PH |
1111 | |
1112 | # Extract upload date | |
1113 | video_upload_date = None | |
6b3aef80 | 1114 | mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage) |
59ae15a5 | 1115 | if mobj is not None: |
6b3aef80 | 1116 | video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) |
59ae15a5 PH |
1117 | |
1118 | # Vimeo specific: extract request signature and timestamp | |
1119 | sig = config['request']['signature'] | |
1120 | timestamp = config['request']['timestamp'] | |
1121 | ||
1122 | # Vimeo specific: extract video codec and quality information | |
1123 | # First consider quality, then codecs, then take everything | |
1124 | # TODO bind to format param | |
1125 | codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')] | |
1126 | files = { 'hd': [], 'sd': [], 'other': []} | |
1127 | for codec_name, codec_extension in codecs: | |
1128 | if codec_name in config["video"]["files"]: | |
1129 | if 'hd' in config["video"]["files"][codec_name]: | |
1130 | files['hd'].append((codec_name, codec_extension, 'hd')) | |
1131 | elif 'sd' in config["video"]["files"][codec_name]: | |
1132 | files['sd'].append((codec_name, codec_extension, 'sd')) | |
1133 | else: | |
1134 | files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0])) | |
1135 | ||
1136 | for quality in ('hd', 'sd', 'other'): | |
1137 | if len(files[quality]) > 0: | |
1138 | video_quality = files[quality][0][2] | |
1139 | video_codec = files[quality][0][0] | |
1140 | video_extension = files[quality][0][1] | |
f17ce13a | 1141 | self.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) |
59ae15a5 PH |
1142 | break |
1143 | else: | |
e5f30ade | 1144 | self._downloader.report_error(u'no known codec found') |
59ae15a5 PH |
1145 | return |
1146 | ||
1147 | video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ | |
1148 | %(video_id, sig, timestamp, video_quality, video_codec.upper()) | |
1149 | ||
1150 | return [{ | |
1151 | 'id': video_id, | |
1152 | 'url': video_url, | |
1153 | 'uploader': video_uploader, | |
77c4beab | 1154 | 'uploader_id': video_uploader_id, |
59ae15a5 PH |
1155 | 'upload_date': video_upload_date, |
1156 | 'title': video_title, | |
1157 | 'ext': video_extension, | |
1158 | 'thumbnail': video_thumbnail, | |
1159 | 'description': video_description, | |
1160 | }] | |
d77c3dfd FV |
1161 | |
1162 | ||
f2ad10a9 | 1163 | class ArteTvIE(InfoExtractor): |
59ae15a5 PH |
1164 | """arte.tv information extractor.""" |
1165 | ||
1166 | _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' | |
1167 | _LIVE_URL = r'index-[0-9]+\.html$' | |
1168 | ||
1169 | IE_NAME = u'arte.tv' | |
1170 | ||
59ae15a5 | 1171 | def fetch_webpage(self, url): |
59ae15a5 PH |
1172 | request = compat_urllib_request.Request(url) |
1173 | try: | |
1174 | self.report_download_webpage(url) | |
1175 | webpage = compat_urllib_request.urlopen(request).read() | |
1176 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1177 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1178 | return |
1179 | except ValueError as err: | |
e5f30ade | 1180 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1181 | return |
1182 | return webpage | |
1183 | ||
1184 | def grep_webpage(self, url, regex, regexFlags, matchTuples): | |
1185 | page = self.fetch_webpage(url) | |
1186 | mobj = re.search(regex, page, regexFlags) | |
1187 | info = {} | |
1188 | ||
1189 | if mobj is None: | |
e5f30ade | 1190 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1191 | return |
1192 | ||
1193 | for (i, key, err) in matchTuples: | |
1194 | if mobj.group(i) is None: | |
613bf669 | 1195 | self._downloader.report_error(err) |
59ae15a5 PH |
1196 | return |
1197 | else: | |
1198 | info[key] = mobj.group(i) | |
1199 | ||
1200 | return info | |
1201 | ||
1202 | def extractLiveStream(self, url): | |
1203 | video_lang = url.split('/')[-4] | |
1204 | info = self.grep_webpage( | |
1205 | url, | |
1206 | r'src="(.*?/videothek_js.*?\.js)', | |
1207 | 0, | |
1208 | [ | |
613bf669 | 1209 | (1, 'url', u'Invalid URL: %s' % url) |
59ae15a5 PH |
1210 | ] |
1211 | ) | |
1212 | http_host = url.split('/')[2] | |
1213 | next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url'))) | |
1214 | info = self.grep_webpage( | |
1215 | next_url, | |
1216 | r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' + | |
1217 | '(http://.*?\.swf).*?' + | |
1218 | '(rtmp://.*?)\'', | |
1219 | re.DOTALL, | |
1220 | [ | |
613bf669 JMF |
1221 | (1, 'path', u'could not extract video path: %s' % url), |
1222 | (2, 'player', u'could not extract video player: %s' % url), | |
1223 | (3, 'url', u'could not extract video url: %s' % url) | |
59ae15a5 PH |
1224 | ] |
1225 | ) | |
1226 | video_url = u'%s/%s' % (info.get('url'), info.get('path')) | |
1227 | ||
1228 | def extractPlus7Stream(self, url): | |
1229 | video_lang = url.split('/')[-3] | |
1230 | info = self.grep_webpage( | |
1231 | url, | |
1232 | r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', | |
1233 | 0, | |
1234 | [ | |
613bf669 | 1235 | (1, 'url', u'Invalid URL: %s' % url) |
59ae15a5 PH |
1236 | ] |
1237 | ) | |
1238 | next_url = compat_urllib_parse.unquote(info.get('url')) | |
1239 | info = self.grep_webpage( | |
1240 | next_url, | |
1241 | r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang, | |
1242 | 0, | |
1243 | [ | |
613bf669 | 1244 | (1, 'url', u'Could not find <video> tag: %s' % url) |
59ae15a5 PH |
1245 | ] |
1246 | ) | |
1247 | next_url = compat_urllib_parse.unquote(info.get('url')) | |
1248 | ||
1249 | info = self.grep_webpage( | |
1250 | next_url, | |
1251 | r'<video id="(.*?)".*?>.*?' + | |
1252 | '<name>(.*?)</name>.*?' + | |
1253 | '<dateVideo>(.*?)</dateVideo>.*?' + | |
1254 | '<url quality="hd">(.*?)</url>', | |
1255 | re.DOTALL, | |
1256 | [ | |
613bf669 JMF |
1257 | (1, 'id', u'could not extract video id: %s' % url), |
1258 | (2, 'title', u'could not extract video title: %s' % url), | |
1259 | (3, 'date', u'could not extract video date: %s' % url), | |
1260 | (4, 'url', u'could not extract video url: %s' % url) | |
59ae15a5 PH |
1261 | ] |
1262 | ) | |
1263 | ||
1264 | return { | |
1265 | 'id': info.get('id'), | |
1266 | 'url': compat_urllib_parse.unquote(info.get('url')), | |
1267 | 'uploader': u'arte.tv', | |
1268 | 'upload_date': info.get('date'), | |
93702113 | 1269 | 'title': info.get('title').decode('utf-8'), |
59ae15a5 PH |
1270 | 'ext': u'mp4', |
1271 | 'format': u'NA', | |
1272 | 'player_url': None, | |
1273 | } | |
1274 | ||
1275 | def _real_extract(self, url): | |
1276 | video_id = url.split('/')[-1] | |
1277 | self.report_extraction(video_id) | |
1278 | ||
1279 | if re.search(self._LIVE_URL, video_id) is not None: | |
1280 | self.extractLiveStream(url) | |
1281 | return | |
1282 | else: | |
1283 | info = self.extractPlus7Stream(url) | |
1284 | ||
1285 | return [info] | |
f2ad10a9 CA |
1286 | |
1287 | ||
d77c3dfd | 1288 | class GenericIE(InfoExtractor): |
59ae15a5 PH |
1289 | """Generic last-resort information extractor.""" |
1290 | ||
1291 | _VALID_URL = r'.*' | |
1292 | IE_NAME = u'generic' | |
1293 | ||
59ae15a5 PH |
1294 | def report_download_webpage(self, video_id): |
1295 | """Report webpage download.""" | |
3d342357 | 1296 | if not self._downloader.params.get('test', False): |
f17ce13a | 1297 | self._downloader.report_warning(u'Falling back on generic information extractor.') |
0d173446 | 1298 | super(GenericIE, self).report_download_webpage(video_id) |
59ae15a5 | 1299 | |
59ae15a5 PH |
1300 | def report_following_redirect(self, new_url): |
1301 | """Report information extraction.""" | |
1302 | self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url) | |
cdb30764 | 1303 | |
59ae15a5 | 1304 | def _test_redirect(self, url): |
a0d6fe7b | 1305 | """Check if it is a redirect, like url shorteners, in case return the new url.""" |
59ae15a5 PH |
1306 | class HeadRequest(compat_urllib_request.Request): |
1307 | def get_method(self): | |
1308 | return "HEAD" | |
1309 | ||
1310 | class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler): | |
1311 | """ | |
cdb30764 | 1312 | Subclass the HTTPRedirectHandler to make it use our |
59ae15a5 PH |
1313 | HeadRequest also on the redirected URL |
1314 | """ | |
cdb30764 | 1315 | def redirect_request(self, req, fp, code, msg, headers, newurl): |
59ae15a5 | 1316 | if code in (301, 302, 303, 307): |
cdb30764 | 1317 | newurl = newurl.replace(' ', '%20') |
59ae15a5 PH |
1318 | newheaders = dict((k,v) for k,v in req.headers.items() |
1319 | if k.lower() not in ("content-length", "content-type")) | |
cdb30764 | 1320 | return HeadRequest(newurl, |
59ae15a5 | 1321 | headers=newheaders, |
cdb30764 ND |
1322 | origin_req_host=req.get_origin_req_host(), |
1323 | unverifiable=True) | |
1324 | else: | |
1325 | raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp) | |
59ae15a5 PH |
1326 | |
1327 | class HTTPMethodFallback(compat_urllib_request.BaseHandler): | |
1328 | """ | |
1329 | Fallback to GET if HEAD is not allowed (405 HTTP error) | |
1330 | """ | |
cdb30764 | 1331 | def http_error_405(self, req, fp, code, msg, headers): |
59ae15a5 PH |
1332 | fp.read() |
1333 | fp.close() | |
1334 | ||
1335 | newheaders = dict((k,v) for k,v in req.headers.items() | |
1336 | if k.lower() not in ("content-length", "content-type")) | |
cdb30764 ND |
1337 | return self.parent.open(compat_urllib_request.Request(req.get_full_url(), |
1338 | headers=newheaders, | |
1339 | origin_req_host=req.get_origin_req_host(), | |
59ae15a5 PH |
1340 | unverifiable=True)) |
1341 | ||
1342 | # Build our opener | |
cdb30764 | 1343 | opener = compat_urllib_request.OpenerDirector() |
59ae15a5 PH |
1344 | for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler, |
1345 | HTTPMethodFallback, HEADRedirectHandler, | |
7c038b3c | 1346 | compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]: |
59ae15a5 PH |
1347 | opener.add_handler(handler()) |
1348 | ||
1349 | response = opener.open(HeadRequest(url)) | |
1350 | new_url = response.geturl() | |
1351 | ||
1352 | if url == new_url: | |
1353 | return False | |
1354 | ||
1355 | self.report_following_redirect(new_url) | |
a0d6fe7b | 1356 | return new_url |
59ae15a5 PH |
1357 | |
1358 | def _real_extract(self, url): | |
a0d6fe7b JMF |
1359 | new_url = self._test_redirect(url) |
1360 | if new_url: return [self.url_result(new_url)] | |
59ae15a5 PH |
1361 | |
1362 | video_id = url.split('/')[-1] | |
59ae15a5 | 1363 | try: |
3d342357 | 1364 | webpage = self._download_webpage(url, video_id) |
59ae15a5 PH |
1365 | except ValueError as err: |
1366 | # since this is the last-resort InfoExtractor, if | |
1367 | # this error is thrown, it'll be thrown here | |
e5f30ade | 1368 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1369 | return |
1370 | ||
1371 | self.report_extraction(video_id) | |
1372 | # Start with something easy: JW Player in SWFObject | |
1373 | mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) | |
1374 | if mobj is None: | |
1375 | # Broaden the search a little bit | |
1376 | mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) | |
1013186a PH |
1377 | if mobj is None: |
1378 | # Broaden the search a little bit: JWPlayer JS loader | |
1379 | mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage) | |
59ae15a5 | 1380 | if mobj is None: |
e5f30ade | 1381 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1382 | return |
1383 | ||
1384 | # It's possible that one of the regexes | |
1385 | # matched, but returned an empty group: | |
1386 | if mobj.group(1) is None: | |
e5f30ade | 1387 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
1388 | return |
1389 | ||
1390 | video_url = compat_urllib_parse.unquote(mobj.group(1)) | |
1391 | video_id = os.path.basename(video_url) | |
1392 | ||
1393 | # here's a fun little line of code for you: | |
1394 | video_extension = os.path.splitext(video_id)[1][1:] | |
1395 | video_id = os.path.splitext(video_id)[0] | |
1396 | ||
1397 | # it's tempting to parse this further, but you would | |
1398 | # have to take into account all the variations like | |
1399 | # Video Title - Site Name | |
1400 | # Site Name | Video Title | |
1401 | # Video Title - Tagline | Site Name | |
1402 | # and so on and so forth; it's just not practical | |
1403 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
1404 | if mobj is None: | |
e5f30ade | 1405 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 | 1406 | return |
f1171f7c | 1407 | video_title = mobj.group(1) |
59ae15a5 PH |
1408 | |
1409 | # video uploader is domain name | |
1410 | mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) | |
1411 | if mobj is None: | |
e5f30ade | 1412 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 | 1413 | return |
f1171f7c | 1414 | video_uploader = mobj.group(1) |
59ae15a5 PH |
1415 | |
1416 | return [{ | |
f1171f7c PH |
1417 | 'id': video_id, |
1418 | 'url': video_url, | |
59ae15a5 PH |
1419 | 'uploader': video_uploader, |
1420 | 'upload_date': None, | |
1421 | 'title': video_title, | |
f1171f7c | 1422 | 'ext': video_extension, |
59ae15a5 | 1423 | }] |
d77c3dfd FV |
1424 | |
1425 | ||
1426 | class YoutubeSearchIE(InfoExtractor): | |
59ae15a5 PH |
1427 | """Information Extractor for YouTube search queries.""" |
1428 | _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+' | |
1429 | _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' | |
1430 | _max_youtube_results = 1000 | |
1431 | IE_NAME = u'youtube:search' | |
1432 | ||
59ae15a5 PH |
1433 | def report_download_page(self, query, pagenum): |
1434 | """Report attempt to download search page with given number.""" | |
1435 | query = query.decode(preferredencoding()) | |
1436 | self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) | |
1437 | ||
1438 | def _real_extract(self, query): | |
1439 | mobj = re.match(self._VALID_URL, query) | |
1440 | if mobj is None: | |
e5f30ade | 1441 | self._downloader.report_error(u'invalid search query "%s"' % query) |
59ae15a5 PH |
1442 | return |
1443 | ||
1444 | prefix, query = query.split(':') | |
1445 | prefix = prefix[8:] | |
1446 | query = query.encode('utf-8') | |
1447 | if prefix == '': | |
8c416ad2 | 1448 | return self._get_n_results(query, 1) |
59ae15a5 | 1449 | elif prefix == 'all': |
8c416ad2 | 1450 | self._get_n_results(query, self._max_youtube_results) |
59ae15a5 PH |
1451 | else: |
1452 | try: | |
1453 | n = int(prefix) | |
1454 | if n <= 0: | |
e5f30ade | 1455 | self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query)) |
59ae15a5 PH |
1456 | return |
1457 | elif n > self._max_youtube_results: | |
2e5457be | 1458 | self._downloader.report_warning(u'ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) |
59ae15a5 | 1459 | n = self._max_youtube_results |
8c416ad2 | 1460 | return self._get_n_results(query, n) |
59ae15a5 | 1461 | except ValueError: # parsing prefix as integer fails |
8c416ad2 | 1462 | return self._get_n_results(query, 1) |
59ae15a5 | 1463 | |
8c416ad2 JMF |
1464 | def _get_n_results(self, query, n): |
1465 | """Get a specified number of results for a query""" | |
59ae15a5 PH |
1466 | |
1467 | video_ids = [] | |
1468 | pagenum = 0 | |
1469 | limit = n | |
1470 | ||
1471 | while (50 * pagenum) < limit: | |
1472 | self.report_download_page(query, pagenum+1) | |
1473 | result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1) | |
1474 | request = compat_urllib_request.Request(result_url) | |
1475 | try: | |
d1b7a243 | 1476 | data = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 | 1477 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 1478 | self._downloader.report_error(u'unable to download API page: %s' % compat_str(err)) |
59ae15a5 PH |
1479 | return |
1480 | api_response = json.loads(data)['data'] | |
1481 | ||
9e07cf29 | 1482 | if not 'items' in api_response: |
613bf669 | 1483 | self._downloader.report_error(u'[youtube] No video results') |
9e07cf29 J |
1484 | return |
1485 | ||
59ae15a5 PH |
1486 | new_ids = list(video['id'] for video in api_response['items']) |
1487 | video_ids += new_ids | |
1488 | ||
1489 | limit = min(n, api_response['totalItems']) | |
1490 | pagenum += 1 | |
1491 | ||
1492 | if len(video_ids) > n: | |
1493 | video_ids = video_ids[:n] | |
8c416ad2 JMF |
1494 | videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids] |
1495 | return videos | |
d77c3dfd FV |
1496 | |
1497 | ||
1498 | class GoogleSearchIE(InfoExtractor): | |
59ae15a5 PH |
1499 | """Information Extractor for Google Video search queries.""" |
1500 | _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+' | |
1501 | _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' | |
1502 | _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)' | |
1503 | _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"' | |
1504 | _max_google_results = 1000 | |
1505 | IE_NAME = u'video.google:search' | |
1506 | ||
59ae15a5 PH |
1507 | def report_download_page(self, query, pagenum): |
1508 | """Report attempt to download playlist page with given number.""" | |
1509 | query = query.decode(preferredencoding()) | |
f17ce13a | 1510 | self.to_screen(u'query "%s": Downloading page %s' % (query, pagenum)) |
59ae15a5 PH |
1511 | |
1512 | def _real_extract(self, query): | |
1513 | mobj = re.match(self._VALID_URL, query) | |
1514 | if mobj is None: | |
e5f30ade | 1515 | self._downloader.report_error(u'invalid search query "%s"' % query) |
59ae15a5 PH |
1516 | return |
1517 | ||
1518 | prefix, query = query.split(':') | |
1519 | prefix = prefix[8:] | |
1520 | query = query.encode('utf-8') | |
1521 | if prefix == '': | |
1522 | self._download_n_results(query, 1) | |
1523 | return | |
1524 | elif prefix == 'all': | |
1525 | self._download_n_results(query, self._max_google_results) | |
1526 | return | |
1527 | else: | |
1528 | try: | |
1529 | n = int(prefix) | |
1530 | if n <= 0: | |
e5f30ade | 1531 | self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query)) |
59ae15a5 PH |
1532 | return |
1533 | elif n > self._max_google_results: | |
2e5457be | 1534 | self._downloader.report_warning(u'gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) |
59ae15a5 PH |
1535 | n = self._max_google_results |
1536 | self._download_n_results(query, n) | |
1537 | return | |
1538 | except ValueError: # parsing prefix as integer fails | |
1539 | self._download_n_results(query, 1) | |
1540 | return | |
1541 | ||
1542 | def _download_n_results(self, query, n): | |
1543 | """Downloads a specified number of results for a query""" | |
1544 | ||
1545 | video_ids = [] | |
1546 | pagenum = 0 | |
1547 | ||
1548 | while True: | |
1549 | self.report_download_page(query, pagenum) | |
1550 | result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum*10) | |
1551 | request = compat_urllib_request.Request(result_url) | |
1552 | try: | |
1553 | page = compat_urllib_request.urlopen(request).read() | |
1554 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1555 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1556 | return |
1557 | ||
1558 | # Extract video identifiers | |
1559 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
1560 | video_id = mobj.group(1) | |
1561 | if video_id not in video_ids: | |
1562 | video_ids.append(video_id) | |
1563 | if len(video_ids) == n: | |
1564 | # Specified n videos reached | |
1565 | for id in video_ids: | |
1566 | self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id]) | |
1567 | return | |
1568 | ||
1569 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
1570 | for id in video_ids: | |
1571 | self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id]) | |
1572 | return | |
1573 | ||
1574 | pagenum = pagenum + 1 | |
d77c3dfd FV |
1575 | |
1576 | ||
1577 | class YahooSearchIE(InfoExtractor): | |
59ae15a5 | 1578 | """Information Extractor for Yahoo! Video search queries.""" |
93702113 FV |
1579 | |
1580 | _WORKING = False | |
59ae15a5 PH |
1581 | _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+' |
1582 | _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' | |
1583 | _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' | |
1584 | _MORE_PAGES_INDICATOR = r'\s*Next' | |
1585 | _max_yahoo_results = 1000 | |
1586 | IE_NAME = u'video.yahoo:search' | |
1587 | ||
59ae15a5 PH |
1588 | def report_download_page(self, query, pagenum): |
1589 | """Report attempt to download playlist page with given number.""" | |
1590 | query = query.decode(preferredencoding()) | |
f17ce13a | 1591 | self.to_screen(u'query "%s": Downloading page %s' % (query, pagenum)) |
59ae15a5 PH |
1592 | |
1593 | def _real_extract(self, query): | |
1594 | mobj = re.match(self._VALID_URL, query) | |
1595 | if mobj is None: | |
e5f30ade | 1596 | self._downloader.report_error(u'invalid search query "%s"' % query) |
59ae15a5 PH |
1597 | return |
1598 | ||
1599 | prefix, query = query.split(':') | |
1600 | prefix = prefix[8:] | |
1601 | query = query.encode('utf-8') | |
1602 | if prefix == '': | |
1603 | self._download_n_results(query, 1) | |
1604 | return | |
1605 | elif prefix == 'all': | |
1606 | self._download_n_results(query, self._max_yahoo_results) | |
1607 | return | |
1608 | else: | |
1609 | try: | |
1610 | n = int(prefix) | |
1611 | if n <= 0: | |
e5f30ade | 1612 | self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query)) |
59ae15a5 PH |
1613 | return |
1614 | elif n > self._max_yahoo_results: | |
2e5457be | 1615 | self._downloader.report_warning(u'yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) |
59ae15a5 PH |
1616 | n = self._max_yahoo_results |
1617 | self._download_n_results(query, n) | |
1618 | return | |
1619 | except ValueError: # parsing prefix as integer fails | |
1620 | self._download_n_results(query, 1) | |
1621 | return | |
1622 | ||
1623 | def _download_n_results(self, query, n): | |
1624 | """Downloads a specified number of results for a query""" | |
1625 | ||
1626 | video_ids = [] | |
1627 | already_seen = set() | |
1628 | pagenum = 1 | |
1629 | ||
1630 | while True: | |
1631 | self.report_download_page(query, pagenum) | |
1632 | result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum) | |
1633 | request = compat_urllib_request.Request(result_url) | |
1634 | try: | |
1635 | page = compat_urllib_request.urlopen(request).read() | |
1636 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1637 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1638 | return |
1639 | ||
1640 | # Extract video identifiers | |
1641 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
1642 | video_id = mobj.group(1) | |
1643 | if video_id not in already_seen: | |
1644 | video_ids.append(video_id) | |
1645 | already_seen.add(video_id) | |
1646 | if len(video_ids) == n: | |
1647 | # Specified n videos reached | |
1648 | for id in video_ids: | |
1649 | self._downloader.download(['http://video.yahoo.com/watch/%s' % id]) | |
1650 | return | |
1651 | ||
1652 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
1653 | for id in video_ids: | |
1654 | self._downloader.download(['http://video.yahoo.com/watch/%s' % id]) | |
1655 | return | |
1656 | ||
1657 | pagenum = pagenum + 1 | |
d77c3dfd FV |
1658 | |
1659 | ||
1660 | class YoutubePlaylistIE(InfoExtractor): | |
59ae15a5 PH |
1661 | """Information Extractor for YouTube playlists.""" |
1662 | ||
6324fd1d FV |
1663 | _VALID_URL = r"""(?: |
1664 | (?:https?://)? | |
1665 | (?:\w+\.)? | |
1666 | youtube\.com/ | |
1667 | (?: | |
89de9eb1 FV |
1668 | (?:course|view_play_list|my_playlists|artist|playlist|watch) |
1669 | \? (?:.*?&)*? (?:p|a|list)= | |
6324fd1d | 1670 | | p/ |
6324fd1d | 1671 | ) |
89de9eb1 FV |
1672 | ((?:PL|EC|UU)?[0-9A-Za-z-_]{10,}) |
1673 | .* | |
1674 | | | |
1675 | ((?:PL|EC|UU)[0-9A-Za-z-_]{10,}) | |
1676 | )""" | |
6324fd1d FV |
1677 | _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/playlists/%s?max-results=%i&start-index=%i&v=2&alt=json' |
1678 | _MAX_RESULTS = 50 | |
59ae15a5 PH |
1679 | IE_NAME = u'youtube:playlist' |
1680 | ||
89de9eb1 FV |
1681 | @classmethod |
1682 | def suitable(cls, url): | |
6324fd1d | 1683 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 | 1684 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None |
6324fd1d | 1685 | |
59ae15a5 PH |
1686 | def report_download_page(self, playlist_id, pagenum): |
1687 | """Report attempt to download playlist page with given number.""" | |
1688 | self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) | |
1689 | ||
1690 | def _real_extract(self, url): | |
1691 | # Extract playlist id | |
6324fd1d | 1692 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
59ae15a5 | 1693 | if mobj is None: |
e5f30ade | 1694 | self._downloader.report_error(u'invalid url: %s' % url) |
59ae15a5 PH |
1695 | return |
1696 | ||
6324fd1d | 1697 | # Download playlist videos from API |
89de9eb1 | 1698 | playlist_id = mobj.group(1) or mobj.group(2) |
6324fd1d FV |
1699 | page_num = 1 |
1700 | videos = [] | |
59ae15a5 PH |
1701 | |
1702 | while True: | |
6324fd1d FV |
1703 | self.report_download_page(playlist_id, page_num) |
1704 | ||
1705 | url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, self._MAX_RESULTS * (page_num - 1) + 1) | |
59ae15a5 | 1706 | try: |
6324fd1d | 1707 | page = compat_urllib_request.urlopen(url).read().decode('utf8') |
59ae15a5 | 1708 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 1709 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1710 | return |
1711 | ||
6324fd1d FV |
1712 | try: |
1713 | response = json.loads(page) | |
1714 | except ValueError as err: | |
e5f30ade | 1715 | self._downloader.report_error(u'Invalid JSON in API response: ' + compat_str(err)) |
6324fd1d | 1716 | return |
59ae15a5 | 1717 | |
feba604e | 1718 | if 'feed' not in response: |
e5f30ade | 1719 | self._downloader.report_error(u'Got a malformed response from YouTube API') |
89de9eb1 | 1720 | return |
aba8df23 | 1721 | playlist_title = response['feed']['title']['$t'] |
feba604e PH |
1722 | if 'entry' not in response['feed']: |
1723 | # Number of videos is a multiple of self._MAX_RESULTS | |
1724 | break | |
1725 | ||
89de9eb1 FV |
1726 | videos += [ (entry['yt$position']['$t'], entry['content']['src']) |
1727 | for entry in response['feed']['entry'] | |
1728 | if 'content' in entry ] | |
6324fd1d FV |
1729 | |
1730 | if len(response['feed']['entry']) < self._MAX_RESULTS: | |
59ae15a5 | 1731 | break |
6324fd1d | 1732 | page_num += 1 |
59ae15a5 | 1733 | |
691db5ba | 1734 | videos = [v[1] for v in sorted(videos)] |
9789a05c | 1735 | |
6de8f1af | 1736 | url_results = [self.url_result(url, 'Youtube') for url in videos] |
c7293824 | 1737 | return [self.playlist_result(url_results, playlist_id, playlist_title)] |
d77c3dfd FV |
1738 | |
1739 | ||
902b2a0a | 1740 | class YoutubeChannelIE(InfoExtractor): |
59ae15a5 PH |
1741 | """Information Extractor for YouTube channels.""" |
1742 | ||
5a8d1319 | 1743 | _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)" |
59ae15a5 | 1744 | _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en' |
5a8d1319 | 1745 | _MORE_PAGES_INDICATOR = 'yt-uix-load-more' |
1746 | _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' | |
59ae15a5 PH |
1747 | IE_NAME = u'youtube:channel' |
1748 | ||
1749 | def report_download_page(self, channel_id, pagenum): | |
1750 | """Report attempt to download channel page with given number.""" | |
1751 | self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum)) | |
1752 | ||
5a8d1319 | 1753 | def extract_videos_from_page(self, page): |
1754 | ids_in_page = [] | |
1755 | for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&?', page): | |
1756 | if mobj.group(1) not in ids_in_page: | |
1757 | ids_in_page.append(mobj.group(1)) | |
1758 | return ids_in_page | |
1759 | ||
59ae15a5 PH |
1760 | def _real_extract(self, url): |
1761 | # Extract channel id | |
1762 | mobj = re.match(self._VALID_URL, url) | |
1763 | if mobj is None: | |
e5f30ade | 1764 | self._downloader.report_error(u'invalid url: %s' % url) |
59ae15a5 PH |
1765 | return |
1766 | ||
5a8d1319 | 1767 | # Download channel page |
59ae15a5 PH |
1768 | channel_id = mobj.group(1) |
1769 | video_ids = [] | |
1770 | pagenum = 1 | |
1771 | ||
5a8d1319 | 1772 | self.report_download_page(channel_id, pagenum) |
1773 | url = self._TEMPLATE_URL % (channel_id, pagenum) | |
1774 | request = compat_urllib_request.Request(url) | |
1775 | try: | |
1776 | page = compat_urllib_request.urlopen(request).read().decode('utf8') | |
1777 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1778 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) | |
1779 | return | |
59ae15a5 | 1780 | |
5a8d1319 | 1781 | # Extract video identifiers |
1782 | ids_in_page = self.extract_videos_from_page(page) | |
1783 | video_ids.extend(ids_in_page) | |
59ae15a5 | 1784 | |
5a8d1319 | 1785 | # Download any subsequent channel pages using the json-based channel_ajax query |
1786 | if self._MORE_PAGES_INDICATOR in page: | |
1787 | while True: | |
1788 | pagenum = pagenum + 1 | |
1789 | ||
1790 | self.report_download_page(channel_id, pagenum) | |
1791 | url = self._MORE_PAGES_URL % (pagenum, channel_id) | |
1792 | request = compat_urllib_request.Request(url) | |
1793 | try: | |
1794 | page = compat_urllib_request.urlopen(request).read().decode('utf8') | |
1795 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1796 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) | |
1797 | return | |
1798 | ||
1799 | page = json.loads(page) | |
1800 | ||
1801 | ids_in_page = self.extract_videos_from_page(page['content_html']) | |
1802 | video_ids.extend(ids_in_page) | |
1803 | ||
1804 | if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']: | |
1805 | break | |
59ae15a5 | 1806 | |
9789a05c FV |
1807 | self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) |
1808 | ||
f6e6da95 | 1809 | urls = ['http://www.youtube.com/watch?v=%s' % id for id in video_ids] |
6de8f1af | 1810 | url_entries = [self.url_result(url, 'Youtube') for url in urls] |
d2c69082 | 1811 | return [self.playlist_result(url_entries, channel_id)] |
902b2a0a FV |
1812 | |
1813 | ||
d77c3dfd | 1814 | class YoutubeUserIE(InfoExtractor): |
59ae15a5 | 1815 | """Information Extractor for YouTube users.""" |
d77c3dfd | 1816 | |
59ae15a5 PH |
1817 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)' |
1818 | _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' | |
1819 | _GDATA_PAGE_SIZE = 50 | |
1820 | _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' | |
1821 | _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]' | |
1822 | IE_NAME = u'youtube:user' | |
d77c3dfd | 1823 | |
59ae15a5 PH |
1824 | def report_download_page(self, username, start_index): |
1825 | """Report attempt to download user page.""" | |
1826 | self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % | |
1827 | (username, start_index, start_index + self._GDATA_PAGE_SIZE)) | |
d77c3dfd | 1828 | |
59ae15a5 PH |
1829 | def _real_extract(self, url): |
1830 | # Extract username | |
1831 | mobj = re.match(self._VALID_URL, url) | |
1832 | if mobj is None: | |
e5f30ade | 1833 | self._downloader.report_error(u'invalid url: %s' % url) |
59ae15a5 | 1834 | return |
d77c3dfd | 1835 | |
59ae15a5 | 1836 | username = mobj.group(1) |
d77c3dfd | 1837 | |
59ae15a5 PH |
1838 | # Download video ids using YouTube Data API. Result size per |
1839 | # query is limited (currently to 50 videos) so we need to query | |
1840 | # page by page until there are no video ids - it means we got | |
1841 | # all of them. | |
d77c3dfd | 1842 | |
59ae15a5 PH |
1843 | video_ids = [] |
1844 | pagenum = 0 | |
d77c3dfd | 1845 | |
59ae15a5 PH |
1846 | while True: |
1847 | start_index = pagenum * self._GDATA_PAGE_SIZE + 1 | |
1848 | self.report_download_page(username, start_index) | |
d77c3dfd | 1849 | |
59ae15a5 | 1850 | request = compat_urllib_request.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)) |
d77c3dfd | 1851 | |
59ae15a5 | 1852 | try: |
80d3177e | 1853 | page = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 | 1854 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 1855 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 | 1856 | return |
d77c3dfd | 1857 | |
59ae15a5 PH |
1858 | # Extract video identifiers |
1859 | ids_in_page = [] | |
d77c3dfd | 1860 | |
59ae15a5 PH |
1861 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): |
1862 | if mobj.group(1) not in ids_in_page: | |
1863 | ids_in_page.append(mobj.group(1)) | |
d77c3dfd | 1864 | |
59ae15a5 | 1865 | video_ids.extend(ids_in_page) |
d77c3dfd | 1866 | |
59ae15a5 PH |
1867 | # A little optimization - if current page is not |
1868 | # "full", ie. does not contain PAGE_SIZE video ids then | |
1869 | # we can assume that this page is the last one - there | |
1870 | # are no more ids on further pages - no need to query | |
1871 | # again. | |
d77c3dfd | 1872 | |
59ae15a5 PH |
1873 | if len(ids_in_page) < self._GDATA_PAGE_SIZE: |
1874 | break | |
d77c3dfd | 1875 | |
59ae15a5 | 1876 | pagenum += 1 |
d77c3dfd | 1877 | |
597cc8a4 | 1878 | urls = ['http://www.youtube.com/watch?v=%s' % video_id for video_id in video_ids] |
6de8f1af | 1879 | url_results = [self.url_result(url, 'Youtube') for url in urls] |
d2c69082 | 1880 | return [self.playlist_result(url_results, playlist_title = username)] |
d77c3dfd FV |
1881 | |
1882 | ||
eeeb4daa | 1883 | class BlipTVUserIE(InfoExtractor): |
59ae15a5 | 1884 | """Information Extractor for blip.tv users.""" |
eeeb4daa | 1885 | |
59ae15a5 PH |
1886 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' |
1887 | _PAGE_SIZE = 12 | |
1888 | IE_NAME = u'blip.tv:user' | |
eeeb4daa | 1889 | |
59ae15a5 PH |
1890 | def report_download_page(self, username, pagenum): |
1891 | """Report attempt to download user page.""" | |
f17ce13a JMF |
1892 | self.to_screen(u'user %s: Downloading video ids from page %d' % |
1893 | (username, pagenum)) | |
eeeb4daa | 1894 | |
59ae15a5 PH |
1895 | def _real_extract(self, url): |
1896 | # Extract username | |
1897 | mobj = re.match(self._VALID_URL, url) | |
1898 | if mobj is None: | |
e5f30ade | 1899 | self._downloader.report_error(u'invalid url: %s' % url) |
59ae15a5 | 1900 | return |
eeeb4daa | 1901 | |
59ae15a5 | 1902 | username = mobj.group(1) |
eeeb4daa | 1903 | |
59ae15a5 | 1904 | page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' |
eeeb4daa | 1905 | |
59ae15a5 | 1906 | request = compat_urllib_request.Request(url) |
eeeb4daa | 1907 | |
59ae15a5 PH |
1908 | try: |
1909 | page = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
1910 | mobj = re.search(r'data-users-id="([^"]+)"', page) | |
1911 | page_base = page_base % mobj.group(1) | |
1912 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1913 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 | 1914 | return |
eeeb4daa JCGS |
1915 | |
1916 | ||
59ae15a5 PH |
1917 | # Download video ids using BlipTV Ajax calls. Result size per |
1918 | # query is limited (currently to 12 videos) so we need to query | |
1919 | # page by page until there are no video ids - it means we got | |
1920 | # all of them. | |
eeeb4daa | 1921 | |
59ae15a5 PH |
1922 | video_ids = [] |
1923 | pagenum = 1 | |
eeeb4daa | 1924 | |
59ae15a5 PH |
1925 | while True: |
1926 | self.report_download_page(username, pagenum) | |
450e7099 PH |
1927 | url = page_base + "&page=" + str(pagenum) |
1928 | request = compat_urllib_request.Request( url ) | |
59ae15a5 PH |
1929 | try: |
1930 | page = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
1931 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1932 | self._downloader.report_error(u'unable to download webpage: %s' % str(err)) |
59ae15a5 | 1933 | return |
eeeb4daa | 1934 | |
59ae15a5 PH |
1935 | # Extract video identifiers |
1936 | ids_in_page = [] | |
eeeb4daa | 1937 | |
59ae15a5 PH |
1938 | for mobj in re.finditer(r'href="/([^"]+)"', page): |
1939 | if mobj.group(1) not in ids_in_page: | |
1940 | ids_in_page.append(unescapeHTML(mobj.group(1))) | |
eeeb4daa | 1941 | |
59ae15a5 | 1942 | video_ids.extend(ids_in_page) |
eeeb4daa | 1943 | |
59ae15a5 PH |
1944 | # A little optimization - if current page is not |
1945 | # "full", ie. does not contain PAGE_SIZE video ids then | |
1946 | # we can assume that this page is the last one - there | |
1947 | # are no more ids on further pages - no need to query | |
1948 | # again. | |
eeeb4daa | 1949 | |
59ae15a5 PH |
1950 | if len(ids_in_page) < self._PAGE_SIZE: |
1951 | break | |
eeeb4daa | 1952 | |
59ae15a5 | 1953 | pagenum += 1 |
eeeb4daa | 1954 | |
f6e6da95 | 1955 | urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids] |
6de8f1af | 1956 | url_entries = [self.url_result(url, 'BlipTV') for url in urls] |
d2c69082 | 1957 | return [self.playlist_result(url_entries, playlist_title = username)] |
eeeb4daa JCGS |
1958 | |
1959 | ||
d77c3dfd | 1960 | class DepositFilesIE(InfoExtractor): |
59ae15a5 PH |
1961 | """Information extractor for depositfiles.com""" |
1962 | ||
1963 | _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' | |
59ae15a5 | 1964 | |
59ae15a5 PH |
1965 | def _real_extract(self, url): |
1966 | file_id = url.split('/')[-1] | |
1967 | # Rebuild url in english locale | |
1968 | url = 'http://depositfiles.com/en/files/' + file_id | |
1969 | ||
1970 | # Retrieve file webpage with 'Free download' button pressed | |
1971 | free_download_indication = { 'gateway_result' : '1' } | |
1972 | request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication)) | |
1973 | try: | |
1974 | self.report_download_webpage(file_id) | |
1975 | webpage = compat_urllib_request.urlopen(request).read() | |
1976 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 1977 | self._downloader.report_error(u'Unable to retrieve file webpage: %s' % compat_str(err)) |
59ae15a5 PH |
1978 | return |
1979 | ||
1980 | # Search for the real file URL | |
1981 | mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage) | |
1982 | if (mobj is None) or (mobj.group(1) is None): | |
1983 | # Try to figure out reason of the error. | |
1984 | mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL) | |
1985 | if (mobj is not None) and (mobj.group(1) is not None): | |
1986 | restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() | |
e5f30ade | 1987 | self._downloader.report_error(u'%s' % restriction_message) |
59ae15a5 | 1988 | else: |
e5f30ade | 1989 | self._downloader.report_error(u'unable to extract download URL from: %s' % url) |
59ae15a5 PH |
1990 | return |
1991 | ||
1992 | file_url = mobj.group(1) | |
1993 | file_extension = os.path.splitext(file_url)[1][1:] | |
1994 | ||
1995 | # Search for file title | |
1996 | mobj = re.search(r'<b title="(.*?)">', webpage) | |
1997 | if mobj is None: | |
e5f30ade | 1998 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 PH |
1999 | return |
2000 | file_title = mobj.group(1).decode('utf-8') | |
2001 | ||
2002 | return [{ | |
2003 | 'id': file_id.decode('utf-8'), | |
2004 | 'url': file_url.decode('utf-8'), | |
2005 | 'uploader': None, | |
2006 | 'upload_date': None, | |
2007 | 'title': file_title, | |
2008 | 'ext': file_extension.decode('utf-8'), | |
2009 | }] | |
d77c3dfd FV |
2010 | |
2011 | ||
2012 | class FacebookIE(InfoExtractor): | |
59ae15a5 PH |
2013 | """Information Extractor for Facebook""" |
2014 | ||
59ae15a5 PH |
2015 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' |
2016 | _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' | |
2017 | _NETRC_MACHINE = 'facebook' | |
59ae15a5 PH |
2018 | IE_NAME = u'facebook' |
2019 | ||
59ae15a5 PH |
2020 | def report_login(self): |
2021 | """Report attempt to log in.""" | |
f17ce13a | 2022 | self.to_screen(u'Logging in') |
59ae15a5 PH |
2023 | |
2024 | def _real_initialize(self): | |
2025 | if self._downloader is None: | |
2026 | return | |
2027 | ||
2028 | useremail = None | |
2029 | password = None | |
2030 | downloader_params = self._downloader.params | |
2031 | ||
2032 | # Attempt to use provided username and password or .netrc data | |
2033 | if downloader_params.get('username', None) is not None: | |
2034 | useremail = downloader_params['username'] | |
2035 | password = downloader_params['password'] | |
2036 | elif downloader_params.get('usenetrc', False): | |
2037 | try: | |
2038 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
2039 | if info is not None: | |
2040 | useremail = info[0] | |
2041 | password = info[2] | |
2042 | else: | |
2043 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
2044 | except (IOError, netrc.NetrcParseError) as err: | |
2e5457be | 2045 | self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) |
59ae15a5 PH |
2046 | return |
2047 | ||
2048 | if useremail is None: | |
2049 | return | |
2050 | ||
2051 | # Log in | |
2052 | login_form = { | |
2053 | 'email': useremail, | |
2054 | 'pass': password, | |
2055 | 'login': 'Log+In' | |
2056 | } | |
2057 | request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) | |
2058 | try: | |
2059 | self.report_login() | |
2060 | login_results = compat_urllib_request.urlopen(request).read() | |
2061 | if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: | |
2e5457be | 2062 | self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') |
59ae15a5 PH |
2063 | return |
2064 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2e5457be | 2065 | self._downloader.report_warning(u'unable to log in: %s' % compat_str(err)) |
59ae15a5 PH |
2066 | return |
2067 | ||
2068 | def _real_extract(self, url): | |
2069 | mobj = re.match(self._VALID_URL, url) | |
2070 | if mobj is None: | |
e5f30ade | 2071 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2072 | return |
2073 | video_id = mobj.group('ID') | |
2074 | ||
b954070d PH |
2075 | url = 'https://www.facebook.com/video/video.php?v=%s' % video_id |
2076 | webpage = self._download_webpage(url, video_id) | |
2077 | ||
32c96387 | 2078 | BEFORE = '{swf.addParam(param[0], param[1]);});\n' |
b954070d PH |
2079 | AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' |
2080 | m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) | |
2081 | if not m: | |
2082 | raise ExtractorError(u'Cannot parse data') | |
2083 | data = dict(json.loads(m.group(1))) | |
edba5137 PH |
2084 | params_raw = compat_urllib_parse.unquote(data['params']) |
2085 | params = json.loads(params_raw) | |
32c96387 PH |
2086 | video_data = params['video_data'][0] |
2087 | video_url = video_data.get('hd_src') | |
7796e8c2 | 2088 | if not video_url: |
32c96387 | 2089 | video_url = video_data['sd_src'] |
7796e8c2 PH |
2090 | if not video_url: |
2091 | raise ExtractorError(u'Cannot find video URL') | |
32c96387 PH |
2092 | video_duration = int(video_data['video_duration']) |
2093 | thumbnail = video_data['thumbnail_src'] | |
b954070d PH |
2094 | |
2095 | m = re.search('<h2 class="uiHeaderTitle">([^<]+)</h2>', webpage) | |
2096 | if not m: | |
2097 | raise ExtractorError(u'Cannot find title in webpage') | |
2098 | video_title = unescapeHTML(m.group(1)) | |
2099 | ||
2100 | info = { | |
2101 | 'id': video_id, | |
2102 | 'title': video_title, | |
2103 | 'url': video_url, | |
2104 | 'ext': 'mp4', | |
2105 | 'duration': video_duration, | |
32c96387 | 2106 | 'thumbnail': thumbnail, |
b954070d PH |
2107 | } |
2108 | return [info] | |
59ae15a5 | 2109 | |
d77c3dfd FV |
2110 | |
2111 | class BlipTVIE(InfoExtractor): | |
59ae15a5 PH |
2112 | """Information extractor for blip.tv""" |
2113 | ||
2114 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' | |
2115 | _URL_EXT = r'^.*\.([a-z0-9]+)$' | |
2116 | IE_NAME = u'blip.tv' | |
2117 | ||
59ae15a5 PH |
2118 | def report_direct_download(self, title): |
2119 | """Report information extraction.""" | |
f17ce13a | 2120 | self.to_screen(u'%s: Direct download detected' % title) |
59ae15a5 PH |
2121 | |
2122 | def _real_extract(self, url): | |
2123 | mobj = re.match(self._VALID_URL, url) | |
2124 | if mobj is None: | |
e5f30ade | 2125 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2126 | return |
2127 | ||
f7b567ff PH |
2128 | urlp = compat_urllib_parse_urlparse(url) |
2129 | if urlp.path.startswith('/play/'): | |
7f9d41a5 JCGS |
2130 | request = compat_urllib_request.Request(url) |
2131 | response = compat_urllib_request.urlopen(request) | |
2132 | redirecturl = response.geturl() | |
f7b567ff PH |
2133 | rurlp = compat_urllib_parse_urlparse(redirecturl) |
2134 | file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2] | |
2135 | url = 'http://blip.tv/a/a-' + file_id | |
2136 | return self._real_extract(url) | |
2137 | ||
7f9d41a5 | 2138 | |
59ae15a5 PH |
2139 | if '?' in url: |
2140 | cchar = '&' | |
2141 | else: | |
2142 | cchar = '?' | |
2143 | json_url = url + cchar + 'skin=json&version=2&no_wrap=1' | |
55c05398 | 2144 | request = compat_urllib_request.Request(json_url) |
3446dfb7 | 2145 | request.add_header('User-Agent', 'iTunes/10.6.1') |
59ae15a5 PH |
2146 | self.report_extraction(mobj.group(1)) |
2147 | info = None | |
2148 | try: | |
2149 | urlh = compat_urllib_request.urlopen(request) | |
2150 | if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download | |
2151 | basename = url.split('/')[-1] | |
2152 | title,ext = os.path.splitext(basename) | |
2153 | title = title.decode('UTF-8') | |
2154 | ext = ext.replace('.', '') | |
2155 | self.report_direct_download(title) | |
2156 | info = { | |
2157 | 'id': title, | |
2158 | 'url': url, | |
2159 | 'uploader': None, | |
2160 | 'upload_date': None, | |
2161 | 'title': title, | |
2162 | 'ext': ext, | |
2163 | 'urlhandle': urlh | |
2164 | } | |
2165 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
3446dfb7 | 2166 | raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) |
59ae15a5 PH |
2167 | if info is None: # Regular URL |
2168 | try: | |
55c05398 PH |
2169 | json_code_bytes = urlh.read() |
2170 | json_code = json_code_bytes.decode('utf-8') | |
59ae15a5 | 2171 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 2172 | self._downloader.report_error(u'unable to read video info webpage: %s' % compat_str(err)) |
59ae15a5 PH |
2173 | return |
2174 | ||
2175 | try: | |
2176 | json_data = json.loads(json_code) | |
2177 | if 'Post' in json_data: | |
2178 | data = json_data['Post'] | |
2179 | else: | |
2180 | data = json_data | |
2181 | ||
2182 | upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') | |
2183 | video_url = data['media']['url'] | |
2184 | umobj = re.match(self._URL_EXT, video_url) | |
2185 | if umobj is None: | |
2186 | raise ValueError('Can not determine filename extension') | |
2187 | ext = umobj.group(1) | |
2188 | ||
2189 | info = { | |
2190 | 'id': data['item_id'], | |
2191 | 'url': video_url, | |
2192 | 'uploader': data['display_name'], | |
2193 | 'upload_date': upload_date, | |
2194 | 'title': data['title'], | |
2195 | 'ext': ext, | |
2196 | 'format': data['media']['mimeType'], | |
2197 | 'thumbnail': data['thumbnailUrl'], | |
2198 | 'description': data['description'], | |
3446dfb7 PH |
2199 | 'player_url': data['embedUrl'], |
2200 | 'user_agent': 'iTunes/10.6.1', | |
59ae15a5 PH |
2201 | } |
2202 | except (ValueError,KeyError) as err: | |
e5f30ade | 2203 | self._downloader.report_error(u'unable to parse video information: %s' % repr(err)) |
59ae15a5 PH |
2204 | return |
2205 | ||
59ae15a5 | 2206 | return [info] |
d77c3dfd FV |
2207 | |
2208 | ||
2209 | class MyVideoIE(InfoExtractor): | |
59ae15a5 PH |
2210 | """Information Extractor for myvideo.de.""" |
2211 | ||
2212 | _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' | |
2213 | IE_NAME = u'myvideo' | |
2214 | ||
59ae15a5 PH |
2215 | def _real_extract(self,url): |
2216 | mobj = re.match(self._VALID_URL, url) | |
2217 | if mobj is None: | |
e5f30ade | 2218 | self._download.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2219 | return |
2220 | ||
2221 | video_id = mobj.group(1) | |
2222 | ||
2223 | # Get video webpage | |
5f955171 PH |
2224 | webpage_url = 'http://www.myvideo.de/watch/%s' % video_id |
2225 | webpage = self._download_webpage(webpage_url, video_id) | |
59ae15a5 PH |
2226 | |
2227 | self.report_extraction(video_id) | |
7decf895 | 2228 | mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/.*?\.jpg\'', |
59ae15a5 PH |
2229 | webpage) |
2230 | if mobj is None: | |
e5f30ade | 2231 | self._downloader.report_error(u'unable to extract media URL') |
59ae15a5 PH |
2232 | return |
2233 | video_url = mobj.group(1) + ('/%s.flv' % video_id) | |
2234 | ||
2235 | mobj = re.search('<title>([^<]+)</title>', webpage) | |
2236 | if mobj is None: | |
e5f30ade | 2237 | self._downloader.report_error(u'unable to extract title') |
59ae15a5 PH |
2238 | return |
2239 | ||
2240 | video_title = mobj.group(1) | |
2241 | ||
2242 | return [{ | |
2243 | 'id': video_id, | |
2244 | 'url': video_url, | |
2245 | 'uploader': None, | |
2246 | 'upload_date': None, | |
2247 | 'title': video_title, | |
2248 | 'ext': u'flv', | |
2249 | }] | |
d77c3dfd FV |
2250 | |
2251 | class ComedyCentralIE(InfoExtractor): | |
59ae15a5 PH |
2252 | """Information extractor for The Daily Show and Colbert Report """ |
2253 | ||
ca6849e6 | 2254 | # urls can be abbreviations like :thedailyshow or :colbert |
cdb30764 | 2255 | # urls for episodes like: |
ca6849e6 | 2256 | # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day |
2257 | # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news | |
cdb30764 | 2258 | # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524 |
ca6849e6 | 2259 | _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport) |
2260 | |(https?://)?(www\.)? | |
2261 | (?P<showname>thedailyshow|colbertnation)\.com/ | |
2262 | (full-episodes/(?P<episode>.*)| | |
2263 | (?P<clip> | |
2264 | (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) | |
2265 | |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))))) | |
cdb30764 | 2266 | $""" |
59ae15a5 PH |
2267 | |
2268 | _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] | |
2269 | ||
2270 | _video_extensions = { | |
2271 | '3500': 'mp4', | |
2272 | '2200': 'mp4', | |
2273 | '1700': 'mp4', | |
2274 | '1200': 'mp4', | |
2275 | '750': 'mp4', | |
2276 | '400': 'mp4', | |
2277 | } | |
2278 | _video_dimensions = { | |
2279 | '3500': '1280x720', | |
2280 | '2200': '960x540', | |
2281 | '1700': '768x432', | |
2282 | '1200': '640x360', | |
2283 | '750': '512x288', | |
2284 | '400': '384x216', | |
2285 | } | |
2286 | ||
89de9eb1 FV |
2287 | @classmethod |
2288 | def suitable(cls, url): | |
ca6849e6 | 2289 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 | 2290 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None |
ca6849e6 | 2291 | |
32635ec6 | 2292 | def report_config_download(self, episode_id, media_id): |
f17ce13a | 2293 | self.to_screen(u'%s: Downloading configuration for %s' % (episode_id, media_id)) |
59ae15a5 PH |
2294 | |
2295 | def report_index_download(self, episode_id): | |
f17ce13a | 2296 | self.to_screen(u'%s: Downloading show index' % episode_id) |
59ae15a5 | 2297 | |
59ae15a5 PH |
2298 | def _print_formats(self, formats): |
2299 | print('Available formats:') | |
2300 | for x in formats: | |
2301 | print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???'))) | |
2302 | ||
2303 | ||
2304 | def _real_extract(self, url): | |
ca6849e6 | 2305 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
59ae15a5 | 2306 | if mobj is None: |
e5f30ade | 2307 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2308 | return |
2309 | ||
2310 | if mobj.group('shortname'): | |
2311 | if mobj.group('shortname') in ('tds', 'thedailyshow'): | |
2312 | url = u'http://www.thedailyshow.com/full-episodes/' | |
2313 | else: | |
2314 | url = u'http://www.colbertnation.com/full-episodes/' | |
ca6849e6 | 2315 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
59ae15a5 PH |
2316 | assert mobj is not None |
2317 | ||
ca6849e6 | 2318 | if mobj.group('clip'): |
2319 | if mobj.group('showname') == 'thedailyshow': | |
2320 | epTitle = mobj.group('tdstitle') | |
2321 | else: | |
2322 | epTitle = mobj.group('cntitle') | |
2323 | dlNewest = False | |
59ae15a5 | 2324 | else: |
ca6849e6 | 2325 | dlNewest = not mobj.group('episode') |
2326 | if dlNewest: | |
2327 | epTitle = mobj.group('showname') | |
2328 | else: | |
2329 | epTitle = mobj.group('episode') | |
59ae15a5 PH |
2330 | |
2331 | req = compat_urllib_request.Request(url) | |
2332 | self.report_extraction(epTitle) | |
2333 | try: | |
2334 | htmlHandle = compat_urllib_request.urlopen(req) | |
2335 | html = htmlHandle.read() | |
93148102 | 2336 | webpage = html.decode('utf-8') |
59ae15a5 | 2337 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 2338 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 PH |
2339 | return |
2340 | if dlNewest: | |
2341 | url = htmlHandle.geturl() | |
ca6849e6 | 2342 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
59ae15a5 | 2343 | if mobj is None: |
e5f30ade | 2344 | self._downloader.report_error(u'Invalid redirected URL: ' + url) |
59ae15a5 PH |
2345 | return |
2346 | if mobj.group('episode') == '': | |
e5f30ade | 2347 | self._downloader.report_error(u'Redirected URL is still not specific: ' + url) |
59ae15a5 PH |
2348 | return |
2349 | epTitle = mobj.group('episode') | |
2350 | ||
93148102 | 2351 | mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage) |
59ae15a5 PH |
2352 | |
2353 | if len(mMovieParams) == 0: | |
2354 | # The Colbert Report embeds the information in a without | |
2355 | # a URL prefix; so extract the alternate reference | |
2356 | # and then add the URL prefix manually. | |
2357 | ||
93148102 | 2358 | altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage) |
59ae15a5 | 2359 | if len(altMovieParams) == 0: |
e5f30ade | 2360 | self._downloader.report_error(u'unable to find Flash URL in webpage ' + url) |
59ae15a5 PH |
2361 | return |
2362 | else: | |
2363 | mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] | |
cdb30764 | 2364 | |
59ae15a5 PH |
2365 | uri = mMovieParams[0][1] |
2366 | indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri}) | |
2367 | self.report_index_download(epTitle) | |
2368 | try: | |
2369 | indexXml = compat_urllib_request.urlopen(indexUrl).read() | |
2370 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2371 | self._downloader.report_error(u'unable to download episode index: ' + compat_str(err)) |
59ae15a5 PH |
2372 | return |
2373 | ||
2374 | results = [] | |
2375 | ||
2376 | idoc = xml.etree.ElementTree.fromstring(indexXml) | |
2377 | itemEls = idoc.findall('.//item') | |
7717ae19 | 2378 | for partNum,itemEl in enumerate(itemEls): |
59ae15a5 PH |
2379 | mediaId = itemEl.findall('./guid')[0].text |
2380 | shortMediaId = mediaId.split(':')[-1] | |
2381 | showId = mediaId.split(':')[-2].replace('.com', '') | |
2382 | officialTitle = itemEl.findall('./title')[0].text | |
bf50b038 | 2383 | officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text) |
59ae15a5 PH |
2384 | |
2385 | configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + | |
2386 | compat_urllib_parse.urlencode({'uri': mediaId})) | |
2387 | configReq = compat_urllib_request.Request(configUrl) | |
32635ec6 | 2388 | self.report_config_download(epTitle, shortMediaId) |
59ae15a5 PH |
2389 | try: |
2390 | configXml = compat_urllib_request.urlopen(configReq).read() | |
2391 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2392 | self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err)) |
59ae15a5 PH |
2393 | return |
2394 | ||
2395 | cdoc = xml.etree.ElementTree.fromstring(configXml) | |
2396 | turls = [] | |
2397 | for rendition in cdoc.findall('.//rendition'): | |
2398 | finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) | |
2399 | turls.append(finfo) | |
2400 | ||
2401 | if len(turls) == 0: | |
c9fa1cba | 2402 | self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found') |
59ae15a5 | 2403 | continue |
cdb30764 | 2404 | |
59ae15a5 PH |
2405 | if self._downloader.params.get('listformats', None): |
2406 | self._print_formats([i[0] for i in turls]) | |
2407 | return | |
2408 | ||
2409 | # For now, just pick the highest bitrate | |
32635ec6 | 2410 | format,rtmp_video_url = turls[-1] |
59ae15a5 PH |
2411 | |
2412 | # Get the format arg from the arg stream | |
2413 | req_format = self._downloader.params.get('format', None) | |
2414 | ||
2415 | # Select format if we can find one | |
2416 | for f,v in turls: | |
2417 | if f == req_format: | |
32635ec6 | 2418 | format, rtmp_video_url = f, v |
59ae15a5 PH |
2419 | break |
2420 | ||
32635ec6 PH |
2421 | m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url) |
2422 | if not m: | |
2423 | raise ExtractorError(u'Cannot transform RTMP url') | |
2424 | base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' | |
2425 | video_url = base + m.group('finalid') | |
59ae15a5 | 2426 | |
7717ae19 | 2427 | effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1) |
59ae15a5 PH |
2428 | info = { |
2429 | 'id': shortMediaId, | |
2430 | 'url': video_url, | |
2431 | 'uploader': showId, | |
2432 | 'upload_date': officialDate, | |
2433 | 'title': effTitle, | |
2434 | 'ext': 'mp4', | |
2435 | 'format': format, | |
2436 | 'thumbnail': None, | |
2437 | 'description': officialTitle, | |
59ae15a5 | 2438 | } |
59ae15a5 | 2439 | results.append(info) |
cdb30764 | 2440 | |
59ae15a5 | 2441 | return results |
d77c3dfd FV |
2442 | |
2443 | ||
2444 | class EscapistIE(InfoExtractor): | |
59ae15a5 PH |
2445 | """Information extractor for The Escapist """ |
2446 | ||
2447 | _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$' | |
2448 | IE_NAME = u'escapist' | |
2449 | ||
59ae15a5 | 2450 | def report_config_download(self, showName): |
f17ce13a | 2451 | self.to_screen(u'%s: Downloading configuration' % showName) |
59ae15a5 PH |
2452 | |
2453 | def _real_extract(self, url): | |
2454 | mobj = re.match(self._VALID_URL, url) | |
2455 | if mobj is None: | |
e5f30ade | 2456 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2457 | return |
2458 | showName = mobj.group('showname') | |
2459 | videoId = mobj.group('episode') | |
2460 | ||
2461 | self.report_extraction(showName) | |
2462 | try: | |
2463 | webPage = compat_urllib_request.urlopen(url) | |
2464 | webPageBytes = webPage.read() | |
2465 | m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type']) | |
2466 | webPage = webPageBytes.decode(m.group(1) if m else 'utf-8') | |
2467 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2468 | self._downloader.report_error(u'unable to download webpage: ' + compat_str(err)) |
59ae15a5 PH |
2469 | return |
2470 | ||
2471 | descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) | |
2472 | description = unescapeHTML(descMatch.group(1)) | |
2473 | imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) | |
2474 | imgUrl = unescapeHTML(imgMatch.group(1)) | |
2475 | playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage) | |
2476 | playerUrl = unescapeHTML(playerUrlMatch.group(1)) | |
2477 | configUrlMatch = re.search('config=(.*)$', playerUrl) | |
2478 | configUrl = compat_urllib_parse.unquote(configUrlMatch.group(1)) | |
2479 | ||
2480 | self.report_config_download(showName) | |
2481 | try: | |
93702113 FV |
2482 | configJSON = compat_urllib_request.urlopen(configUrl) |
2483 | m = re.match(r'text/html; charset="?([^"]+)"?', configJSON.headers['Content-Type']) | |
2484 | configJSON = configJSON.read().decode(m.group(1) if m else 'utf-8') | |
59ae15a5 | 2485 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 2486 | self._downloader.report_error(u'unable to download configuration: ' + compat_str(err)) |
59ae15a5 PH |
2487 | return |
2488 | ||
2489 | # Technically, it's JavaScript, not JSON | |
2490 | configJSON = configJSON.replace("'", '"') | |
2491 | ||
2492 | try: | |
2493 | config = json.loads(configJSON) | |
2494 | except (ValueError,) as err: | |
e5f30ade | 2495 | self._downloader.report_error(u'Invalid JSON in configuration file: ' + compat_str(err)) |
59ae15a5 PH |
2496 | return |
2497 | ||
2498 | playlist = config['playlist'] | |
2499 | videoUrl = playlist[1]['url'] | |
2500 | ||
2501 | info = { | |
2502 | 'id': videoId, | |
2503 | 'url': videoUrl, | |
2504 | 'uploader': showName, | |
2505 | 'upload_date': None, | |
2506 | 'title': showName, | |
47dcd621 | 2507 | 'ext': 'mp4', |
59ae15a5 PH |
2508 | 'thumbnail': imgUrl, |
2509 | 'description': description, | |
2510 | 'player_url': playerUrl, | |
2511 | } | |
2512 | ||
2513 | return [info] | |
d77c3dfd | 2514 | |
d77c3dfd | 2515 | class CollegeHumorIE(InfoExtractor): |
59ae15a5 PH |
2516 | """Information extractor for collegehumor.com""" |
2517 | ||
0eb0faa2 | 2518 | _WORKING = False |
59ae15a5 PH |
2519 | _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$' |
2520 | IE_NAME = u'collegehumor' | |
2521 | ||
799c0763 | 2522 | def report_manifest(self, video_id): |
59ae15a5 | 2523 | """Report information extraction.""" |
f17ce13a | 2524 | self.to_screen(u'%s: Downloading XML manifest' % video_id) |
59ae15a5 | 2525 | |
59ae15a5 PH |
2526 | def _real_extract(self, url): |
2527 | mobj = re.match(self._VALID_URL, url) | |
2528 | if mobj is None: | |
e5f30ade | 2529 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2530 | return |
2531 | video_id = mobj.group('videoid') | |
2532 | ||
59ae15a5 PH |
2533 | info = { |
2534 | 'id': video_id, | |
59ae15a5 PH |
2535 | 'uploader': None, |
2536 | 'upload_date': None, | |
2537 | } | |
2538 | ||
2539 | self.report_extraction(video_id) | |
799c0763 | 2540 | xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id |
59ae15a5 PH |
2541 | try: |
2542 | metaXml = compat_urllib_request.urlopen(xmlUrl).read() | |
2543 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2544 | self._downloader.report_error(u'unable to download video info XML: %s' % compat_str(err)) |
59ae15a5 PH |
2545 | return |
2546 | ||
2547 | mdoc = xml.etree.ElementTree.fromstring(metaXml) | |
2548 | try: | |
2549 | videoNode = mdoc.findall('./video')[0] | |
2550 | info['description'] = videoNode.findall('./description')[0].text | |
2551 | info['title'] = videoNode.findall('./caption')[0].text | |
59ae15a5 | 2552 | info['thumbnail'] = videoNode.findall('./thumbnail')[0].text |
799c0763 | 2553 | manifest_url = videoNode.findall('./file')[0].text |
59ae15a5 | 2554 | except IndexError: |
c9fa1cba | 2555 | self._downloader.report_error(u'Invalid metadata XML file') |
59ae15a5 PH |
2556 | return |
2557 | ||
799c0763 PH |
2558 | manifest_url += '?hdcore=2.10.3' |
2559 | self.report_manifest(video_id) | |
2560 | try: | |
2561 | manifestXml = compat_urllib_request.urlopen(manifest_url).read() | |
2562 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2563 | self._downloader.report_error(u'unable to download video info XML: %s' % compat_str(err)) |
799c0763 PH |
2564 | return |
2565 | ||
2566 | adoc = xml.etree.ElementTree.fromstring(manifestXml) | |
2567 | try: | |
2568 | media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] | |
2569 | node_id = media_node.attrib['url'] | |
2570 | video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text | |
2571 | except IndexError as err: | |
c9fa1cba | 2572 | self._downloader.report_error(u'Invalid manifest file') |
799c0763 PH |
2573 | return |
2574 | ||
2575 | url_pr = compat_urllib_parse_urlparse(manifest_url) | |
2576 | url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1' | |
2577 | ||
2578 | info['url'] = url | |
2579 | info['ext'] = 'f4f' | |
59ae15a5 | 2580 | return [info] |
d77c3dfd FV |
2581 | |
2582 | ||
2583 | class XVideosIE(InfoExtractor): | |
59ae15a5 | 2584 | """Information extractor for xvideos.com""" |
d77c3dfd | 2585 | |
59ae15a5 PH |
2586 | _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' |
2587 | IE_NAME = u'xvideos' | |
d77c3dfd | 2588 | |
59ae15a5 PH |
2589 | def _real_extract(self, url): |
2590 | mobj = re.match(self._VALID_URL, url) | |
2591 | if mobj is None: | |
e5f30ade | 2592 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 | 2593 | return |
8588a86f | 2594 | video_id = mobj.group(1) |
d77c3dfd | 2595 | |
5f955171 | 2596 | webpage = self._download_webpage(url, video_id) |
d77c3dfd | 2597 | |
59ae15a5 | 2598 | self.report_extraction(video_id) |
d77c3dfd FV |
2599 | |
2600 | ||
59ae15a5 PH |
2601 | # Extract video URL |
2602 | mobj = re.search(r'flv_url=(.+?)&', webpage) | |
2603 | if mobj is None: | |
e5f30ade | 2604 | self._downloader.report_error(u'unable to extract video url') |
59ae15a5 | 2605 | return |
8588a86f | 2606 | video_url = compat_urllib_parse.unquote(mobj.group(1)) |
d77c3dfd FV |
2607 | |
2608 | ||
59ae15a5 PH |
2609 | # Extract title |
2610 | mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage) | |
2611 | if mobj is None: | |
e5f30ade | 2612 | self._downloader.report_error(u'unable to extract video title') |
59ae15a5 | 2613 | return |
8588a86f | 2614 | video_title = mobj.group(1) |
d77c3dfd FV |
2615 | |
2616 | ||
59ae15a5 PH |
2617 | # Extract video thumbnail |
2618 | 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) | |
2619 | if mobj is None: | |
e5f30ade | 2620 | self._downloader.report_error(u'unable to extract video thumbnail') |
59ae15a5 | 2621 | return |
8588a86f | 2622 | video_thumbnail = mobj.group(0) |
d77c3dfd | 2623 | |
59ae15a5 PH |
2624 | info = { |
2625 | 'id': video_id, | |
2626 | 'url': video_url, | |
2627 | 'uploader': None, | |
2628 | 'upload_date': None, | |
2629 | 'title': video_title, | |
2630 | 'ext': 'flv', | |
2631 | 'thumbnail': video_thumbnail, | |
2632 | 'description': None, | |
2633 | } | |
d77c3dfd | 2634 | |
59ae15a5 | 2635 | return [info] |
d77c3dfd FV |
2636 | |
2637 | ||
2638 | class SoundcloudIE(InfoExtractor): | |
59ae15a5 PH |
2639 | """Information extractor for soundcloud.com |
2640 | To access the media, the uid of the song and a stream token | |
2641 | must be extracted from the page source and the script must make | |
2642 | a request to media.soundcloud.com/crossdomain.xml. Then | |
2643 | the media can be grabbed by requesting from an url composed | |
2644 | of the stream token and uid | |
2645 | """ | |
2646 | ||
2647 | _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)' | |
2648 | IE_NAME = u'soundcloud' | |
2649 | ||
8fd3afd5 | 2650 | def report_resolve(self, video_id): |
59ae15a5 | 2651 | """Report information extraction.""" |
f17ce13a | 2652 | self.to_screen(u'%s: Resolving id' % video_id) |
59ae15a5 | 2653 | |
59ae15a5 PH |
2654 | def _real_extract(self, url): |
2655 | mobj = re.match(self._VALID_URL, url) | |
2656 | if mobj is None: | |
e5f30ade | 2657 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2658 | return |
2659 | ||
2660 | # extract uploader (which is in the url) | |
15c8d833 | 2661 | uploader = mobj.group(1) |
59ae15a5 | 2662 | # extract simple title (uploader + slug of song title) |
15c8d833 | 2663 | slug_title = mobj.group(2) |
59ae15a5 PH |
2664 | simple_title = uploader + u'-' + slug_title |
2665 | ||
8fd3afd5 | 2666 | self.report_resolve('%s/%s' % (uploader, slug_title)) |
59ae15a5 | 2667 | |
8fd3afd5 PH |
2668 | url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title) |
2669 | resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28' | |
2670 | request = compat_urllib_request.Request(resolv_url) | |
59ae15a5 | 2671 | try: |
8fd3afd5 PH |
2672 | info_json_bytes = compat_urllib_request.urlopen(request).read() |
2673 | info_json = info_json_bytes.decode('utf-8') | |
59ae15a5 | 2674 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 2675 | self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
2676 | return |
2677 | ||
8fd3afd5 PH |
2678 | info = json.loads(info_json) |
2679 | video_id = info['id'] | |
59ae15a5 PH |
2680 | self.report_extraction('%s/%s' % (uploader, slug_title)) |
2681 | ||
8fd3afd5 | 2682 | streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28' |
c7214f9a | 2683 | request = compat_urllib_request.Request(streams_url) |
8fd3afd5 PH |
2684 | try: |
2685 | stream_json_bytes = compat_urllib_request.urlopen(request).read() | |
2686 | stream_json = stream_json_bytes.decode('utf-8') | |
2687 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2688 | self._downloader.report_error(u'unable to download stream definitions: %s' % compat_str(err)) |
b4cd069d | 2689 | return |
59ae15a5 | 2690 | |
8fd3afd5 | 2691 | streams = json.loads(stream_json) |
c7214f9a | 2692 | mediaURL = streams['http_mp3_128_url'] |
bf50b038 | 2693 | upload_date = unified_strdate(info['created_at']) |
59ae15a5 PH |
2694 | |
2695 | return [{ | |
c7214f9a | 2696 | 'id': info['id'], |
59ae15a5 | 2697 | 'url': mediaURL, |
c7214f9a | 2698 | 'uploader': info['user']['username'], |
bf50b038 | 2699 | 'upload_date': upload_date, |
c7214f9a | 2700 | 'title': info['title'], |
59ae15a5 | 2701 | 'ext': u'mp3', |
c7214f9a | 2702 | 'description': info['description'], |
59ae15a5 | 2703 | }] |
d77c3dfd | 2704 | |
5011cded | 2705 | class SoundcloudSetIE(InfoExtractor): |
2706 | """Information extractor for soundcloud.com sets | |
2707 | To access the media, the uid of the song and a stream token | |
2708 | must be extracted from the page source and the script must make | |
2709 | a request to media.soundcloud.com/crossdomain.xml. Then | |
2710 | the media can be grabbed by requesting from an url composed | |
2711 | of the stream token and uid | |
2712 | """ | |
2713 | ||
2714 | _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)' | |
2715 | IE_NAME = u'soundcloud' | |
2716 | ||
5011cded | 2717 | def report_resolve(self, video_id): |
2718 | """Report information extraction.""" | |
f17ce13a | 2719 | self.to_screen(u'%s: Resolving id' % video_id) |
5011cded | 2720 | |
5011cded | 2721 | def _real_extract(self, url): |
2722 | mobj = re.match(self._VALID_URL, url) | |
2723 | if mobj is None: | |
613bf669 | 2724 | self._downloader.report_error(u'invalid URL: %s' % url) |
5011cded | 2725 | return |
2726 | ||
2727 | # extract uploader (which is in the url) | |
2728 | uploader = mobj.group(1) | |
2729 | # extract simple title (uploader + slug of song title) | |
2730 | slug_title = mobj.group(2) | |
2731 | simple_title = uploader + u'-' + slug_title | |
2732 | ||
2733 | self.report_resolve('%s/sets/%s' % (uploader, slug_title)) | |
2734 | ||
2735 | url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title) | |
2736 | resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28' | |
2737 | request = compat_urllib_request.Request(resolv_url) | |
2738 | try: | |
2739 | info_json_bytes = compat_urllib_request.urlopen(request).read() | |
2740 | info_json = info_json_bytes.decode('utf-8') | |
2741 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
613bf669 | 2742 | self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err)) |
5011cded | 2743 | return |
2744 | ||
2745 | videos = [] | |
2746 | info = json.loads(info_json) | |
2747 | if 'errors' in info: | |
2748 | for err in info['errors']: | |
613bf669 | 2749 | self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err['error_message'])) |
5011cded | 2750 | return |
2751 | ||
2752 | for track in info['tracks']: | |
2753 | video_id = track['id'] | |
2754 | self.report_extraction('%s/sets/%s' % (uploader, slug_title)) | |
2755 | ||
2756 | streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28' | |
2757 | request = compat_urllib_request.Request(streams_url) | |
2758 | try: | |
2759 | stream_json_bytes = compat_urllib_request.urlopen(request).read() | |
2760 | stream_json = stream_json_bytes.decode('utf-8') | |
2761 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
613bf669 | 2762 | self._downloader.report_error(u'unable to download stream definitions: %s' % compat_str(err)) |
5011cded | 2763 | return |
2764 | ||
2765 | streams = json.loads(stream_json) | |
2766 | mediaURL = streams['http_mp3_128_url'] | |
2767 | ||
2768 | videos.append({ | |
2769 | 'id': video_id, | |
2770 | 'url': mediaURL, | |
2771 | 'uploader': track['user']['username'], | |
2772 | 'upload_date': track['created_at'], | |
2773 | 'title': track['title'], | |
2774 | 'ext': u'mp3', | |
2775 | 'description': track['description'], | |
2776 | }) | |
2777 | return videos | |
2778 | ||
d77c3dfd FV |
2779 | |
2780 | class InfoQIE(InfoExtractor): | |
59ae15a5 | 2781 | """Information extractor for infoq.com""" |
59ae15a5 | 2782 | _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' |
59ae15a5 | 2783 | |
59ae15a5 PH |
2784 | def _real_extract(self, url): |
2785 | mobj = re.match(self._VALID_URL, url) | |
2786 | if mobj is None: | |
e5f30ade | 2787 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2788 | return |
2789 | ||
4fcca4bb | 2790 | webpage = self._download_webpage(url, video_id=url) |
59ae15a5 PH |
2791 | self.report_extraction(url) |
2792 | ||
59ae15a5 | 2793 | # Extract video URL |
a3d689cf | 2794 | mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage) |
59ae15a5 | 2795 | if mobj is None: |
e5f30ade | 2796 | self._downloader.report_error(u'unable to extract video url') |
59ae15a5 | 2797 | return |
4fcca4bb PH |
2798 | real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8')) |
2799 | video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id | |
59ae15a5 PH |
2800 | |
2801 | # Extract title | |
2802 | mobj = re.search(r'contentTitle = "(.*?)";', webpage) | |
2803 | if mobj is None: | |
e5f30ade | 2804 | self._downloader.report_error(u'unable to extract video title') |
59ae15a5 | 2805 | return |
4fcca4bb | 2806 | video_title = mobj.group(1) |
59ae15a5 PH |
2807 | |
2808 | # Extract description | |
2809 | video_description = u'No description available.' | |
2810 | mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage) | |
2811 | if mobj is not None: | |
4fcca4bb | 2812 | video_description = mobj.group(1) |
59ae15a5 PH |
2813 | |
2814 | video_filename = video_url.split('/')[-1] | |
2815 | video_id, extension = video_filename.split('.') | |
2816 | ||
2817 | info = { | |
2818 | 'id': video_id, | |
2819 | 'url': video_url, | |
2820 | 'uploader': None, | |
2821 | 'upload_date': None, | |
2822 | 'title': video_title, | |
2823 | 'ext': extension, # Extension is always(?) mp4, but seems to be flv | |
2824 | 'thumbnail': None, | |
2825 | 'description': video_description, | |
2826 | } | |
2827 | ||
2828 | return [info] | |
d77c3dfd FV |
2829 | |
2830 | class MixcloudIE(InfoExtractor): | |
59ae15a5 | 2831 | """Information extractor for www.mixcloud.com""" |
93702113 FV |
2832 | |
2833 | _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/ | |
59ae15a5 PH |
2834 | _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' |
2835 | IE_NAME = u'mixcloud' | |
2836 | ||
59ae15a5 PH |
2837 | def report_download_json(self, file_id): |
2838 | """Report JSON download.""" | |
f17ce13a | 2839 | self.to_screen(u'Downloading json') |
59ae15a5 | 2840 | |
59ae15a5 PH |
2841 | def get_urls(self, jsonData, fmt, bitrate='best'): |
2842 | """Get urls from 'audio_formats' section in json""" | |
2843 | file_url = None | |
2844 | try: | |
2845 | bitrate_list = jsonData[fmt] | |
2846 | if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list: | |
2847 | bitrate = max(bitrate_list) # select highest | |
2848 | ||
2849 | url_list = jsonData[fmt][bitrate] | |
2850 | except TypeError: # we have no bitrate info. | |
2851 | url_list = jsonData[fmt] | |
2852 | return url_list | |
2853 | ||
2854 | def check_urls(self, url_list): | |
2855 | """Returns 1st active url from list""" | |
2856 | for url in url_list: | |
2857 | try: | |
2858 | compat_urllib_request.urlopen(url) | |
2859 | return url | |
2860 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2861 | url = None | |
2862 | ||
2863 | return None | |
2864 | ||
2865 | def _print_formats(self, formats): | |
2866 | print('Available formats:') | |
2867 | for fmt in formats.keys(): | |
2868 | for b in formats[fmt]: | |
2869 | try: | |
2870 | ext = formats[fmt][b][0] | |
2871 | print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])) | |
2872 | except TypeError: # we have no bitrate info | |
2873 | ext = formats[fmt][0] | |
2874 | print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])) | |
2875 | break | |
2876 | ||
2877 | def _real_extract(self, url): | |
2878 | mobj = re.match(self._VALID_URL, url) | |
2879 | if mobj is None: | |
e5f30ade | 2880 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
2881 | return |
2882 | # extract uploader & filename from url | |
2883 | uploader = mobj.group(1).decode('utf-8') | |
2884 | file_id = uploader + "-" + mobj.group(2).decode('utf-8') | |
2885 | ||
2886 | # construct API request | |
2887 | file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json' | |
2888 | # retrieve .json file with links to files | |
2889 | request = compat_urllib_request.Request(file_url) | |
2890 | try: | |
2891 | self.report_download_json(file_url) | |
2892 | jsonData = compat_urllib_request.urlopen(request).read() | |
2893 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2894 | self._downloader.report_error(u'Unable to retrieve file: %s' % compat_str(err)) |
59ae15a5 PH |
2895 | return |
2896 | ||
2897 | # parse JSON | |
2898 | json_data = json.loads(jsonData) | |
2899 | player_url = json_data['player_swf_url'] | |
2900 | formats = dict(json_data['audio_formats']) | |
2901 | ||
2902 | req_format = self._downloader.params.get('format', None) | |
2903 | bitrate = None | |
2904 | ||
2905 | if self._downloader.params.get('listformats', None): | |
2906 | self._print_formats(formats) | |
2907 | return | |
2908 | ||
2909 | if req_format is None or req_format == 'best': | |
2910 | for format_param in formats.keys(): | |
2911 | url_list = self.get_urls(formats, format_param) | |
2912 | # check urls | |
2913 | file_url = self.check_urls(url_list) | |
2914 | if file_url is not None: | |
2915 | break # got it! | |
2916 | else: | |
99b0a129 | 2917 | if req_format not in formats: |
e5f30ade | 2918 | self._downloader.report_error(u'format is not available') |
59ae15a5 PH |
2919 | return |
2920 | ||
2921 | url_list = self.get_urls(formats, req_format) | |
2922 | file_url = self.check_urls(url_list) | |
2923 | format_param = req_format | |
2924 | ||
2925 | return [{ | |
2926 | 'id': file_id.decode('utf-8'), | |
2927 | 'url': file_url.decode('utf-8'), | |
2928 | 'uploader': uploader.decode('utf-8'), | |
2929 | 'upload_date': None, | |
2930 | 'title': json_data['name'], | |
2931 | 'ext': file_url.split('.')[-1].decode('utf-8'), | |
2932 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), | |
2933 | 'thumbnail': json_data['thumbnail_url'], | |
2934 | 'description': json_data['description'], | |
2935 | 'player_url': player_url.decode('utf-8'), | |
2936 | }] | |
d77c3dfd FV |
2937 | |
2938 | class StanfordOpenClassroomIE(InfoExtractor): | |
59ae15a5 PH |
2939 | """Information extractor for Stanford's Open ClassRoom""" |
2940 | ||
2941 | _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' | |
2942 | IE_NAME = u'stanfordoc' | |
2943 | ||
59ae15a5 PH |
2944 | def _real_extract(self, url): |
2945 | mobj = re.match(self._VALID_URL, url) | |
2946 | if mobj is None: | |
f0bad2b0 | 2947 | raise ExtractorError(u'Invalid URL: %s' % url) |
59ae15a5 PH |
2948 | |
2949 | if mobj.group('course') and mobj.group('video'): # A specific video | |
2950 | course = mobj.group('course') | |
2951 | video = mobj.group('video') | |
2952 | info = { | |
2953 | 'id': course + '_' + video, | |
2954 | 'uploader': None, | |
2955 | 'upload_date': None, | |
2956 | } | |
2957 | ||
2958 | self.report_extraction(info['id']) | |
2959 | baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' | |
2960 | xmlUrl = baseUrl + video + '.xml' | |
2961 | try: | |
2962 | metaXml = compat_urllib_request.urlopen(xmlUrl).read() | |
2963 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 2964 | self._downloader.report_error(u'unable to download video info XML: %s' % compat_str(err)) |
59ae15a5 PH |
2965 | return |
2966 | mdoc = xml.etree.ElementTree.fromstring(metaXml) | |
2967 | try: | |
2968 | info['title'] = mdoc.findall('./title')[0].text | |
2969 | info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text | |
2970 | except IndexError: | |
c9fa1cba | 2971 | self._downloader.report_error(u'Invalid metadata XML file') |
59ae15a5 PH |
2972 | return |
2973 | info['ext'] = info['url'].rpartition('.')[2] | |
2974 | return [info] | |
2975 | elif mobj.group('course'): # A course page | |
2976 | course = mobj.group('course') | |
2977 | info = { | |
2978 | 'id': course, | |
2979 | 'type': 'playlist', | |
2980 | 'uploader': None, | |
2981 | 'upload_date': None, | |
2982 | } | |
2983 | ||
f0bad2b0 PH |
2984 | coursepage = self._download_webpage(url, info['id'], |
2985 | note='Downloading course info page', | |
2986 | errnote='Unable to download course info page') | |
59ae15a5 PH |
2987 | |
2988 | m = re.search('<h1>([^<]+)</h1>', coursepage) | |
2989 | if m: | |
2990 | info['title'] = unescapeHTML(m.group(1)) | |
2991 | else: | |
2992 | info['title'] = info['id'] | |
2993 | ||
2994 | m = re.search('<description>([^<]+)</description>', coursepage) | |
2995 | if m: | |
2996 | info['description'] = unescapeHTML(m.group(1)) | |
2997 | ||
2998 | links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) | |
2999 | info['list'] = [ | |
3000 | { | |
3001 | 'type': 'reference', | |
3002 | 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), | |
3003 | } | |
3004 | for vpage in links] | |
3005 | results = [] | |
3006 | for entry in info['list']: | |
3007 | assert entry['type'] == 'reference' | |
3008 | results += self.extract(entry['url']) | |
3009 | return results | |
59ae15a5 PH |
3010 | else: # Root page |
3011 | info = { | |
3012 | 'id': 'Stanford OpenClassroom', | |
3013 | 'type': 'playlist', | |
3014 | 'uploader': None, | |
3015 | 'upload_date': None, | |
3016 | } | |
3017 | ||
3018 | self.report_download_webpage(info['id']) | |
3019 | rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' | |
3020 | try: | |
3021 | rootpage = compat_urllib_request.urlopen(rootURL).read() | |
3022 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 3023 | self._downloader.report_error(u'unable to download course info page: ' + compat_str(err)) |
59ae15a5 PH |
3024 | return |
3025 | ||
3026 | info['title'] = info['id'] | |
3027 | ||
3028 | links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage)) | |
3029 | info['list'] = [ | |
3030 | { | |
3031 | 'type': 'reference', | |
3032 | 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), | |
3033 | } | |
3034 | for cpage in links] | |
3035 | ||
3036 | results = [] | |
3037 | for entry in info['list']: | |
3038 | assert entry['type'] == 'reference' | |
3039 | results += self.extract(entry['url']) | |
3040 | return results | |
d77c3dfd FV |
3041 | |
3042 | class MTVIE(InfoExtractor): | |
59ae15a5 PH |
3043 | """Information extractor for MTV.com""" |
3044 | ||
3045 | _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$' | |
3046 | IE_NAME = u'mtv' | |
3047 | ||
59ae15a5 PH |
3048 | def _real_extract(self, url): |
3049 | mobj = re.match(self._VALID_URL, url) | |
3050 | if mobj is None: | |
e5f30ade | 3051 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
3052 | return |
3053 | if not mobj.group('proto'): | |
3054 | url = 'http://' + url | |
3055 | video_id = mobj.group('videoid') | |
59ae15a5 | 3056 | |
5f955171 | 3057 | webpage = self._download_webpage(url, video_id) |
59ae15a5 PH |
3058 | |
3059 | mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage) | |
3060 | if mobj is None: | |
e5f30ade | 3061 | self._downloader.report_error(u'unable to extract song name') |
59ae15a5 PH |
3062 | return |
3063 | song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1')) | |
3064 | mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage) | |
3065 | if mobj is None: | |
e5f30ade | 3066 | self._downloader.report_error(u'unable to extract performer') |
59ae15a5 PH |
3067 | return |
3068 | performer = unescapeHTML(mobj.group(1).decode('iso-8859-1')) | |
cdb30764 | 3069 | video_title = performer + ' - ' + song_name |
59ae15a5 PH |
3070 | |
3071 | mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage) | |
3072 | if mobj is None: | |
e5f30ade | 3073 | self._downloader.report_error(u'unable to mtvn_uri') |
59ae15a5 PH |
3074 | return |
3075 | mtvn_uri = mobj.group(1) | |
3076 | ||
3077 | mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage) | |
3078 | if mobj is None: | |
e5f30ade | 3079 | self._downloader.report_error(u'unable to extract content id') |
59ae15a5 PH |
3080 | return |
3081 | content_id = mobj.group(1) | |
3082 | ||
3083 | 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 | |
3084 | self.report_extraction(video_id) | |
3085 | request = compat_urllib_request.Request(videogen_url) | |
3086 | try: | |
3087 | metadataXml = compat_urllib_request.urlopen(request).read() | |
3088 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 3089 | self._downloader.report_error(u'unable to download video metadata: %s' % compat_str(err)) |
59ae15a5 PH |
3090 | return |
3091 | ||
3092 | mdoc = xml.etree.ElementTree.fromstring(metadataXml) | |
3093 | renditions = mdoc.findall('.//rendition') | |
3094 | ||
3095 | # For now, always pick the highest quality. | |
3096 | rendition = renditions[-1] | |
3097 | ||
3098 | try: | |
3099 | _,_,ext = rendition.attrib['type'].partition('/') | |
3100 | format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate'] | |
3101 | video_url = rendition.find('./src').text | |
3102 | except KeyError: | |
613bf669 | 3103 | self._downloader.report_error('Invalid rendition field.') |
59ae15a5 PH |
3104 | return |
3105 | ||
3106 | info = { | |
3107 | 'id': video_id, | |
3108 | 'url': video_url, | |
3109 | 'uploader': performer, | |
3110 | 'upload_date': None, | |
3111 | 'title': video_title, | |
3112 | 'ext': ext, | |
3113 | 'format': format, | |
3114 | } | |
3115 | ||
3116 | return [info] | |
6de7ef9b | 3117 | |
302efc19 | 3118 | |
302efc19 | 3119 | class YoukuIE(InfoExtractor): |
59ae15a5 | 3120 | _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html' |
59ae15a5 | 3121 | |
59ae15a5 PH |
3122 | def _gen_sid(self): |
3123 | nowTime = int(time.time() * 1000) | |
3124 | random1 = random.randint(1000,1998) | |
3125 | random2 = random.randint(1000,9999) | |
3126 | ||
3127 | return "%d%d%d" %(nowTime,random1,random2) | |
3128 | ||
3129 | def _get_file_ID_mix_string(self, seed): | |
3130 | mixed = [] | |
3131 | source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890") | |
3132 | seed = float(seed) | |
3133 | for i in range(len(source)): | |
3134 | seed = (seed * 211 + 30031 ) % 65536 | |
3135 | index = math.floor(seed / 65536 * len(source) ) | |
3136 | mixed.append(source[int(index)]) | |
3137 | source.remove(source[int(index)]) | |
3138 | #return ''.join(mixed) | |
3139 | return mixed | |
3140 | ||
3141 | def _get_file_id(self, fileId, seed): | |
3142 | mixed = self._get_file_ID_mix_string(seed) | |
3143 | ids = fileId.split('*') | |
3144 | realId = [] | |
3145 | for ch in ids: | |
3146 | if ch: | |
3147 | realId.append(mixed[int(ch)]) | |
3148 | return ''.join(realId) | |
3149 | ||
3150 | def _real_extract(self, url): | |
3151 | mobj = re.match(self._VALID_URL, url) | |
3152 | if mobj is None: | |
e5f30ade | 3153 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 PH |
3154 | return |
3155 | video_id = mobj.group('ID') | |
3156 | ||
3157 | info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id | |
3158 | ||
3159 | request = compat_urllib_request.Request(info_url, None, std_headers) | |
3160 | try: | |
3161 | self.report_download_webpage(video_id) | |
3162 | jsondata = compat_urllib_request.urlopen(request).read() | |
3163 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 3164 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
3165 | return |
3166 | ||
3167 | self.report_extraction(video_id) | |
3168 | try: | |
8f6f40d9 PH |
3169 | jsonstr = jsondata.decode('utf-8') |
3170 | config = json.loads(jsonstr) | |
59ae15a5 PH |
3171 | |
3172 | video_title = config['data'][0]['title'] | |
3173 | seed = config['data'][0]['seed'] | |
3174 | ||
3175 | format = self._downloader.params.get('format', None) | |
1a2c3c0f | 3176 | supported_format = list(config['data'][0]['streamfileids'].keys()) |
59ae15a5 PH |
3177 | |
3178 | if format is None or format == 'best': | |
3179 | if 'hd2' in supported_format: | |
3180 | format = 'hd2' | |
3181 | else: | |
3182 | format = 'flv' | |
3183 | ext = u'flv' | |
3184 | elif format == 'worst': | |
3185 | format = 'mp4' | |
3186 | ext = u'mp4' | |
3187 | else: | |
3188 | format = 'flv' | |
3189 | ext = u'flv' | |
3190 | ||
3191 | ||
3192 | fileid = config['data'][0]['streamfileids'][format] | |
e2a8ff24 | 3193 | keys = [s['k'] for s in config['data'][0]['segs'][format]] |
8f6f40d9 | 3194 | except (UnicodeDecodeError, ValueError, KeyError): |
e5f30ade | 3195 | self._downloader.report_error(u'unable to extract info section') |
59ae15a5 PH |
3196 | return |
3197 | ||
3198 | files_info=[] | |
3199 | sid = self._gen_sid() | |
3200 | fileid = self._get_file_id(fileid, seed) | |
3201 | ||
3202 | #column 8,9 of fileid represent the segment number | |
3203 | #fileid[7:9] should be changed | |
3204 | for index, key in enumerate(keys): | |
3205 | ||
3206 | temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:]) | |
3207 | download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) | |
3208 | ||
3209 | info = { | |
3210 | 'id': '%s_part%02d' % (video_id, index), | |
3211 | 'url': download_url, | |
3212 | 'uploader': None, | |
3213 | 'upload_date': None, | |
3214 | 'title': video_title, | |
3215 | 'ext': ext, | |
3216 | } | |
3217 | files_info.append(info) | |
3218 | ||
3219 | return files_info | |
5dc846fa FV |
3220 | |
3221 | ||
6de7ef9b | 3222 | class XNXXIE(InfoExtractor): |
59ae15a5 PH |
3223 | """Information extractor for xnxx.com""" |
3224 | ||
caec7618 | 3225 | _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)' |
59ae15a5 PH |
3226 | IE_NAME = u'xnxx' |
3227 | VIDEO_URL_RE = r'flv_url=(.*?)&' | |
3228 | VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM' | |
3229 | VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&' | |
3230 | ||
59ae15a5 PH |
3231 | def _real_extract(self, url): |
3232 | mobj = re.match(self._VALID_URL, url) | |
3233 | if mobj is None: | |
e5f30ade | 3234 | self._downloader.report_error(u'invalid URL: %s' % url) |
59ae15a5 | 3235 | return |
bec102a8 | 3236 | video_id = mobj.group(1) |
59ae15a5 | 3237 | |
320e26a0 | 3238 | self.report_download_webpage(video_id) |
59ae15a5 PH |
3239 | |
3240 | # Get webpage content | |
3241 | try: | |
bec102a8 PH |
3242 | webpage_bytes = compat_urllib_request.urlopen(url).read() |
3243 | webpage = webpage_bytes.decode('utf-8') | |
59ae15a5 | 3244 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 3245 | self._downloader.report_error(u'unable to download video webpage: %s' % err) |
59ae15a5 PH |
3246 | return |
3247 | ||
3248 | result = re.search(self.VIDEO_URL_RE, webpage) | |
3249 | if result is None: | |
e5f30ade | 3250 | self._downloader.report_error(u'unable to extract video url') |
59ae15a5 | 3251 | return |
bec102a8 | 3252 | video_url = compat_urllib_parse.unquote(result.group(1)) |
59ae15a5 PH |
3253 | |
3254 | result = re.search(self.VIDEO_TITLE_RE, webpage) | |
3255 | if result is None: | |
e5f30ade | 3256 | self._downloader.report_error(u'unable to extract video title') |
59ae15a5 | 3257 | return |
bec102a8 | 3258 | video_title = result.group(1) |
59ae15a5 PH |
3259 | |
3260 | result = re.search(self.VIDEO_THUMB_RE, webpage) | |
3261 | if result is None: | |
e5f30ade | 3262 | self._downloader.report_error(u'unable to extract video thumbnail') |
59ae15a5 | 3263 | return |
bec102a8 | 3264 | video_thumbnail = result.group(1) |
59ae15a5 PH |
3265 | |
3266 | return [{ | |
3267 | 'id': video_id, | |
3268 | 'url': video_url, | |
3269 | 'uploader': None, | |
3270 | 'upload_date': None, | |
3271 | 'title': video_title, | |
3272 | 'ext': 'flv', | |
3273 | 'thumbnail': video_thumbnail, | |
3274 | 'description': None, | |
3275 | }] | |
fd873c69 FV |
3276 | |
3277 | ||
d443aca8 | 3278 | class GooglePlusIE(InfoExtractor): |
59ae15a5 PH |
3279 | """Information extractor for plus.google.com.""" |
3280 | ||
93702113 | 3281 | _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)' |
59ae15a5 PH |
3282 | IE_NAME = u'plus.google' |
3283 | ||
59ae15a5 PH |
3284 | def report_extract_entry(self, url): |
3285 | """Report downloading extry""" | |
f17ce13a | 3286 | self.to_screen(u'Downloading entry: %s' % url) |
59ae15a5 PH |
3287 | |
3288 | def report_date(self, upload_date): | |
3289 | """Report downloading extry""" | |
f17ce13a | 3290 | self.to_screen(u'Entry date: %s' % upload_date) |
59ae15a5 PH |
3291 | |
3292 | def report_uploader(self, uploader): | |
3293 | """Report downloading extry""" | |
f17ce13a | 3294 | self.to_screen(u'Uploader: %s' % uploader) |
59ae15a5 PH |
3295 | |
3296 | def report_title(self, video_title): | |
3297 | """Report downloading extry""" | |
f17ce13a | 3298 | self.to_screen(u'Title: %s' % video_title) |
59ae15a5 PH |
3299 | |
3300 | def report_extract_vid_page(self, video_page): | |
3301 | """Report information extraction.""" | |
f17ce13a | 3302 | self.to_screen(u'Extracting video page: %s' % video_page) |
59ae15a5 PH |
3303 | |
3304 | def _real_extract(self, url): | |
3305 | # Extract id from URL | |
3306 | mobj = re.match(self._VALID_URL, url) | |
3307 | if mobj is None: | |
e5f30ade | 3308 | self._downloader.report_error(u'Invalid URL: %s' % url) |
59ae15a5 PH |
3309 | return |
3310 | ||
3311 | post_url = mobj.group(0) | |
93702113 | 3312 | video_id = mobj.group(1) |
59ae15a5 PH |
3313 | |
3314 | video_extension = 'flv' | |
3315 | ||
3316 | # Step 1, Retrieve post webpage to extract further information | |
3317 | self.report_extract_entry(post_url) | |
3318 | request = compat_urllib_request.Request(post_url) | |
3319 | try: | |
93702113 | 3320 | webpage = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 | 3321 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 3322 | self._downloader.report_error(u'Unable to retrieve entry webpage: %s' % compat_str(err)) |
59ae15a5 PH |
3323 | return |
3324 | ||
3325 | # Extract update date | |
3326 | upload_date = None | |
3327 | pattern = 'title="Timestamp">(.*?)</a>' | |
3328 | mobj = re.search(pattern, webpage) | |
3329 | if mobj: | |
3330 | upload_date = mobj.group(1) | |
3331 | # Convert timestring to a format suitable for filename | |
3332 | upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") | |
3333 | upload_date = upload_date.strftime('%Y%m%d') | |
3334 | self.report_date(upload_date) | |
3335 | ||
3336 | # Extract uploader | |
3337 | uploader = None | |
3338 | pattern = r'rel\="author".*?>(.*?)</a>' | |
3339 | mobj = re.search(pattern, webpage) | |
3340 | if mobj: | |
3341 | uploader = mobj.group(1) | |
3342 | self.report_uploader(uploader) | |
3343 | ||
3344 | # Extract title | |
3345 | # Get the first line for title | |
3346 | video_title = u'NA' | |
3347 | pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]' | |
3348 | mobj = re.search(pattern, webpage) | |
3349 | if mobj: | |
3350 | video_title = mobj.group(1) | |
3351 | self.report_title(video_title) | |
3352 | ||
3353 | # Step 2, Stimulate clicking the image box to launch video | |
3354 | pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]' | |
3355 | mobj = re.search(pattern, webpage) | |
3356 | if mobj is None: | |
e5f30ade | 3357 | self._downloader.report_error(u'unable to extract video page URL') |
59ae15a5 PH |
3358 | |
3359 | video_page = mobj.group(1) | |
3360 | request = compat_urllib_request.Request(video_page) | |
3361 | try: | |
93702113 | 3362 | webpage = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 | 3363 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
e5f30ade | 3364 | self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err)) |
59ae15a5 PH |
3365 | return |
3366 | self.report_extract_vid_page(video_page) | |
3367 | ||
3368 | ||
3369 | # Extract video links on video page | |
3370 | """Extract video links of all sizes""" | |
3371 | pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"' | |
3372 | mobj = re.findall(pattern, webpage) | |
3373 | if len(mobj) == 0: | |
e5f30ade | 3374 | self._downloader.report_error(u'unable to extract video links') |
59ae15a5 PH |
3375 | |
3376 | # Sort in resolution | |
3377 | links = sorted(mobj) | |
3378 | ||
3379 | # Choose the lowest of the sort, i.e. highest resolution | |
3380 | video_url = links[-1] | |
3381 | # Only get the url. The resolution part in the tuple has no use anymore | |
3382 | video_url = video_url[-1] | |
3383 | # Treat escaped \u0026 style hex | |
93702113 FV |
3384 | try: |
3385 | video_url = video_url.decode("unicode_escape") | |
3386 | except AttributeError: # Python 3 | |
3387 | video_url = bytes(video_url, 'ascii').decode('unicode-escape') | |
59ae15a5 PH |
3388 | |
3389 | ||
3390 | return [{ | |
93702113 | 3391 | 'id': video_id, |
59ae15a5 | 3392 | 'url': video_url, |
93702113 FV |
3393 | 'uploader': uploader, |
3394 | 'upload_date': upload_date, | |
3395 | 'title': video_title, | |
3396 | 'ext': video_extension, | |
59ae15a5 | 3397 | }] |
4cc3d074 PH |
3398 | |
3399 | class NBAIE(InfoExtractor): | |
3400 | _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$' | |
3401 | IE_NAME = u'nba' | |
3402 | ||
4cc3d074 PH |
3403 | def _real_extract(self, url): |
3404 | mobj = re.match(self._VALID_URL, url) | |
3405 | if mobj is None: | |
e5f30ade | 3406 | self._downloader.report_error(u'invalid URL: %s' % url) |
4cc3d074 PH |
3407 | return |
3408 | ||
3409 | video_id = mobj.group(1) | |
3410 | if video_id.endswith('/index.html'): | |
3411 | video_id = video_id[:-len('/index.html')] | |
3412 | ||
5f955171 | 3413 | webpage = self._download_webpage(url, video_id) |
4cc3d074 PH |
3414 | |
3415 | video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' | |
3416 | def _findProp(rexp, default=None): | |
3417 | m = re.search(rexp, webpage) | |
3418 | if m: | |
3419 | return unescapeHTML(m.group(1)) | |
3420 | else: | |
3421 | return default | |
3422 | ||
3423 | shortened_video_id = video_id.rpartition('/')[2] | |
3424 | title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '') | |
3425 | info = { | |
3426 | 'id': shortened_video_id, | |
3427 | 'url': video_url, | |
3428 | 'ext': 'mp4', | |
3429 | 'title': title, | |
3430 | 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'), | |
3431 | 'description': _findProp(r'<div class="description">(.*?)</h1>'), | |
3432 | } | |
3433 | return [info] | |
0b40544f DV |
3434 | |
3435 | class JustinTVIE(InfoExtractor): | |
3436 | """Information extractor for justin.tv and twitch.tv""" | |
2ab1c5ed DV |
3437 | # TODO: One broadcast may be split into multiple videos. The key |
3438 | # 'broadcast_id' is the same for all parts, and 'broadcast_part' | |
3439 | # starts at 1 and increases. Can we treat all parts as one video? | |
3440 | ||
4096b609 DV |
3441 | _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/ |
3442 | ([^/]+)(?:/b/([^/]+))?/?(?:\#.*)?$""" | |
3443 | _JUSTIN_PAGE_LIMIT = 100 | |
0b40544f DV |
3444 | IE_NAME = u'justin.tv' |
3445 | ||
4096b609 DV |
3446 | def report_download_page(self, channel, offset): |
3447 | """Report attempt to download a single page of videos.""" | |
f17ce13a JMF |
3448 | self.to_screen(u'%s: Downloading video information from %d to %d' % |
3449 | (channel, offset, offset + self._JUSTIN_PAGE_LIMIT)) | |
4096b609 | 3450 | |
2ab1c5ed DV |
3451 | # Return count of items, list of *valid* items |
3452 | def _parse_page(self, url): | |
0b40544f | 3453 | try: |
2ab1c5ed | 3454 | urlh = compat_urllib_request.urlopen(url) |
0b40544f DV |
3455 | webpage_bytes = urlh.read() |
3456 | webpage = webpage_bytes.decode('utf-8', 'ignore') | |
3457 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
e5f30ade | 3458 | self._downloader.report_error(u'unable to download video info JSON: %s' % compat_str(err)) |
0b40544f | 3459 | return |
cdb30764 | 3460 | |
0b40544f | 3461 | response = json.loads(webpage) |
fa1bf9c6 | 3462 | if type(response) != list: |
3463 | error_text = response.get('error', 'unknown error') | |
e5f30ade | 3464 | self._downloader.report_error(u'Justin.tv API: %s' % error_text) |
fa1bf9c6 | 3465 | return |
0b40544f DV |
3466 | info = [] |
3467 | for clip in response: | |
3468 | video_url = clip['video_file_url'] | |
3469 | if video_url: | |
3470 | video_extension = os.path.splitext(video_url)[1][1:] | |
fa1bf9c6 | 3471 | video_date = re.sub('-', '', clip['start_time'][:10]) |
3472 | video_uploader_id = clip.get('user_id', clip.get('channel_id')) | |
97f194c1 PH |
3473 | video_id = clip['id'] |
3474 | video_title = clip.get('title', video_id) | |
0b40544f | 3475 | info.append({ |
97f194c1 | 3476 | 'id': video_id, |
0b40544f | 3477 | 'url': video_url, |
97f194c1 | 3478 | 'title': video_title, |
fa1bf9c6 | 3479 | 'uploader': clip.get('channel_name', video_uploader_id), |
3480 | 'uploader_id': video_uploader_id, | |
0b40544f DV |
3481 | 'upload_date': video_date, |
3482 | 'ext': video_extension, | |
3483 | }) | |
2ab1c5ed DV |
3484 | return (len(response), info) |
3485 | ||
3486 | def _real_extract(self, url): | |
3487 | mobj = re.match(self._VALID_URL, url) | |
3488 | if mobj is None: | |
e5f30ade | 3489 | self._downloader.report_error(u'invalid URL: %s' % url) |
2ab1c5ed | 3490 | return |
cdb30764 | 3491 | |
2ab1c5ed DV |
3492 | api = 'http://api.justin.tv' |
3493 | video_id = mobj.group(mobj.lastindex) | |
3494 | paged = False | |
3495 | if mobj.lastindex == 1: | |
3496 | paged = True | |
3497 | api += '/channel/archives/%s.json' | |
3498 | else: | |
fa1bf9c6 | 3499 | api += '/broadcast/by_archive/%s.json' |
2ab1c5ed | 3500 | api = api % (video_id,) |
cdb30764 | 3501 | |
2ab1c5ed | 3502 | self.report_extraction(video_id) |
cdb30764 | 3503 | |
2ab1c5ed DV |
3504 | info = [] |
3505 | offset = 0 | |
4096b609 DV |
3506 | limit = self._JUSTIN_PAGE_LIMIT |
3507 | while True: | |
3508 | if paged: | |
3509 | self.report_download_page(video_id, offset) | |
2ab1c5ed DV |
3510 | page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) |
3511 | page_count, page_info = self._parse_page(page_url) | |
3512 | info.extend(page_info) | |
3513 | if not paged or page_count != limit: | |
3514 | break | |
3515 | offset += limit | |
0b40544f | 3516 | return info |
21a9c6aa PH |
3517 | |
3518 | class FunnyOrDieIE(InfoExtractor): | |
3519 | _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$' | |
21a9c6aa | 3520 | |
21a9c6aa PH |
3521 | def _real_extract(self, url): |
3522 | mobj = re.match(self._VALID_URL, url) | |
3523 | if mobj is None: | |
e5f30ade | 3524 | self._downloader.report_error(u'invalid URL: %s' % url) |
21a9c6aa PH |
3525 | return |
3526 | ||
3527 | video_id = mobj.group('id') | |
5f955171 | 3528 | webpage = self._download_webpage(url, video_id) |
21a9c6aa PH |
3529 | |
3530 | m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL) | |
3531 | if not m: | |
e5f30ade | 3532 | self._downloader.report_error(u'unable to find video information') |
21a9c6aa | 3533 | video_url = unescapeHTML(m.group('url')) |
21a9c6aa | 3534 | |
7decf895 | 3535 | m = re.search(r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", webpage, flags=re.DOTALL) |
21a9c6aa | 3536 | if not m: |
bfdf4692 PH |
3537 | m = re.search(r'<title>(?P<title>[^<]+?)</title>', webpage) |
3538 | if not m: | |
613bf669 | 3539 | self._downloader.report_error(u'Cannot find video title') |
7decf895 | 3540 | title = clean_html(m.group('title')) |
21a9c6aa PH |
3541 | |
3542 | m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage) | |
3543 | if m: | |
3544 | desc = unescapeHTML(m.group('desc')) | |
3545 | else: | |
3546 | desc = None | |
3547 | ||
3548 | info = { | |
3549 | 'id': video_id, | |
3550 | 'url': video_url, | |
3551 | 'ext': 'mp4', | |
3552 | 'title': title, | |
3553 | 'description': desc, | |
3554 | } | |
3555 | return [info] | |
d0d4f277 | 3556 | |
e314ba67 | 3557 | class SteamIE(InfoExtractor): |
6324fd1d | 3558 | _VALID_URL = r"""http://store.steampowered.com/ |
4c9f7a99 | 3559 | (agecheck/)? |
e314ba67 JMF |
3560 | (?P<urltype>video|app)/ #If the page is only for videos or for a game |
3561 | (?P<gameID>\d+)/? | |
3562 | (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID | |
3563 | """ | |
4aeae91f | 3564 | |
89de9eb1 FV |
3565 | @classmethod |
3566 | def suitable(cls, url): | |
e314ba67 | 3567 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 | 3568 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None |
5f955171 | 3569 | |
e314ba67 JMF |
3570 | def _real_extract(self, url): |
3571 | m = re.match(self._VALID_URL, url, re.VERBOSE) | |
e314ba67 | 3572 | gameID = m.group('gameID') |
e11eb119 JMF |
3573 | videourl = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' % gameID |
3574 | self.report_age_confirmation() | |
5f955171 | 3575 | webpage = self._download_webpage(videourl, gameID) |
9e1cf0c2 JMF |
3576 | game_title = re.search(r'<h2 class="pageheader">(?P<game_title>.*?)</h2>', webpage).group('game_title') |
3577 | ||
3578 | urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\}," | |
e314ba67 | 3579 | mweb = re.finditer(urlRE, webpage) |
5e9d042d JMF |
3580 | namesRE = r'<span class="title">(?P<videoName>.+?)</span>' |
3581 | titles = re.finditer(namesRE, webpage) | |
60bd48b1 JMF |
3582 | thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">' |
3583 | thumbs = re.finditer(thumbsRE, webpage) | |
e314ba67 | 3584 | videos = [] |
60bd48b1 | 3585 | for vid,vtitle,thumb in zip(mweb,titles,thumbs): |
e314ba67 | 3586 | video_id = vid.group('videoID') |
5f955171 PH |
3587 | title = vtitle.group('videoName') |
3588 | video_url = vid.group('videoURL') | |
60bd48b1 | 3589 | video_thumb = thumb.group('thumbnail') |
e314ba67 | 3590 | if not video_url: |
e5f30ade | 3591 | self._downloader.report_error(u'Cannot find video url for %s' % video_id) |
e314ba67 JMF |
3592 | info = { |
3593 | 'id':video_id, | |
3594 | 'url':video_url, | |
3595 | 'ext': 'flv', | |
60bd48b1 JMF |
3596 | 'title': unescapeHTML(title), |
3597 | 'thumbnail': video_thumb | |
e314ba67 JMF |
3598 | } |
3599 | videos.append(info) | |
9e1cf0c2 | 3600 | return [self.playlist_result(videos, gameID, game_title)] |
ef0c8d5f | 3601 | |
278986ea | 3602 | class UstreamIE(InfoExtractor): |
ef0c8d5f | 3603 | _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)' |
278986ea | 3604 | IE_NAME = u'ustream' |
ef0c8d5f | 3605 | |
278986ea JMF |
3606 | def _real_extract(self, url): |
3607 | m = re.match(self._VALID_URL, url) | |
3608 | video_id = m.group('videoID') | |
3609 | video_url = u'http://tcdn.ustream.tv/video/%s' % video_id | |
d830b7c2 | 3610 | webpage = self._download_webpage(url, video_id) |
278986ea JMF |
3611 | m = re.search(r'data-title="(?P<title>.+)"',webpage) |
3612 | title = m.group('title') | |
3613 | m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage) | |
3614 | uploader = m.group('uploader') | |
3615 | info = { | |
3616 | 'id':video_id, | |
3617 | 'url':video_url, | |
3618 | 'ext': 'flv', | |
3619 | 'title': title, | |
3620 | 'uploader': uploader | |
3621 | } | |
3622 | return [info] | |
4aeae91f | 3623 | |
40634747 | 3624 | class WorldStarHipHopIE(InfoExtractor): |
64c78d50 | 3625 | _VALID_URL = r'http://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)' |
40634747 JMS |
3626 | IE_NAME = u'WorldStarHipHop' |
3627 | ||
3628 | def _real_extract(self, url): | |
40634747 JMS |
3629 | _src_url = r"""(http://hw-videos.*(?:mp4|flv))""" |
3630 | ||
3b221c54 | 3631 | webpage_src = compat_urllib_request.urlopen(url).read() |
b3bcca08 | 3632 | webpage_src = webpage_src.decode('utf-8') |
40634747 JMS |
3633 | |
3634 | mobj = re.search(_src_url, webpage_src) | |
3635 | ||
08ec0af7 JMS |
3636 | m = re.match(self._VALID_URL, url) |
3637 | video_id = m.group('id') | |
3638 | ||
40634747 JMS |
3639 | if mobj is not None: |
3640 | video_url = mobj.group() | |
3641 | if 'mp4' in video_url: | |
b3bcca08 | 3642 | ext = 'mp4' |
40634747 | 3643 | else: |
b3bcca08 | 3644 | ext = 'flv' |
40634747 | 3645 | else: |
613bf669 | 3646 | self._downloader.report_error(u'Cannot find video url for %s' % video_id) |
08ec0af7 | 3647 | return |
40634747 JMS |
3648 | |
3649 | _title = r"""<title>(.*)</title>""" | |
3650 | ||
3651 | mobj = re.search(_title, webpage_src) | |
fa41fbd3 | 3652 | |
40634747 JMS |
3653 | if mobj is not None: |
3654 | title = mobj.group(1) | |
40634747 | 3655 | else: |
b3bcca08 | 3656 | title = 'World Start Hip Hop - %s' % time.ctime() |
40634747 JMS |
3657 | |
3658 | _thumbnail = r"""rel="image_src" href="(.*)" />""" | |
40634747 JMS |
3659 | mobj = re.search(_thumbnail, webpage_src) |
3660 | ||
3661 | # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video. | |
3662 | if mobj is not None: | |
3663 | thumbnail = mobj.group(1) | |
3664 | else: | |
3665 | _title = r"""candytitles.*>(.*)</span>""" | |
3666 | mobj = re.search(_title, webpage_src) | |
3667 | if mobj is not None: | |
3668 | title = mobj.group(1) | |
3669 | thumbnail = None | |
fa41fbd3 | 3670 | |
b3bcca08 | 3671 | results = [{ |
64c78d50 | 3672 | 'id': video_id, |
b3bcca08 JMS |
3673 | 'url' : video_url, |
3674 | 'title' : title, | |
3675 | 'thumbnail' : thumbnail, | |
3676 | 'ext' : ext, | |
3677 | }] | |
40634747 JMS |
3678 | return results |
3679 | ||
ca0a0bbe PH |
3680 | class RBMARadioIE(InfoExtractor): |
3681 | _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$' | |
3682 | ||
3683 | def _real_extract(self, url): | |
3684 | m = re.match(self._VALID_URL, url) | |
3685 | video_id = m.group('videoID') | |
3686 | ||
3687 | webpage = self._download_webpage(url, video_id) | |
3688 | m = re.search(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>', webpage) | |
3689 | if not m: | |
3690 | raise ExtractorError(u'Cannot find metadata') | |
3691 | json_data = m.group(1) | |
3692 | ||
3693 | try: | |
3694 | data = json.loads(json_data) | |
3695 | except ValueError as e: | |
3696 | raise ExtractorError(u'Invalid JSON: ' + str(e)) | |
3697 | ||
3698 | video_url = data['akamai_url'] + '&cbr=256' | |
3699 | url_parts = compat_urllib_parse_urlparse(video_url) | |
3700 | video_ext = url_parts.path.rpartition('.')[2] | |
3701 | info = { | |
3702 | 'id': video_id, | |
3703 | 'url': video_url, | |
3704 | 'ext': video_ext, | |
3705 | 'title': data['title'], | |
3706 | 'description': data.get('teaser_text'), | |
3707 | 'location': data.get('country_of_origin'), | |
3708 | 'uploader': data.get('host', {}).get('name'), | |
3709 | 'uploader_id': data.get('host', {}).get('slug'), | |
187f491a | 3710 | 'thumbnail': data.get('image', {}).get('large_url_2x'), |
ca0a0bbe PH |
3711 | 'duration': data.get('duration'), |
3712 | } | |
3713 | return [info] | |
4aeae91f | 3714 | |
991ba7fa JC |
3715 | |
3716 | class YouPornIE(InfoExtractor): | |
3717 | """Information extractor for youporn.com.""" | |
991ba7fa | 3718 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)' |
6324fd1d | 3719 | |
991ba7fa JC |
3720 | def _print_formats(self, formats): |
3721 | """Print all available formats""" | |
565f7519 | 3722 | print(u'Available formats:') |
ca6710ee JC |
3723 | print(u'ext\t\tformat') |
3724 | print(u'---------------------------------') | |
991ba7fa | 3725 | for format in formats: |
ca6710ee | 3726 | print(u'%s\t\t%s' % (format['ext'], format['format'])) |
991ba7fa JC |
3727 | |
3728 | def _specific(self, req_format, formats): | |
3729 | for x in formats: | |
3730 | if(x["format"]==req_format): | |
3731 | return x | |
3732 | return None | |
3733 | ||
991ba7fa JC |
3734 | def _real_extract(self, url): |
3735 | mobj = re.match(self._VALID_URL, url) | |
3736 | if mobj is None: | |
e5f30ade | 3737 | self._downloader.report_error(u'invalid URL: %s' % url) |
991ba7fa JC |
3738 | return |
3739 | ||
ca6710ee | 3740 | video_id = mobj.group('videoid') |
991ba7fa | 3741 | |
629fcdd1 PH |
3742 | req = compat_urllib_request.Request(url) |
3743 | req.add_header('Cookie', 'age_verified=1') | |
3744 | webpage = self._download_webpage(req, video_id) | |
991ba7fa JC |
3745 | |
3746 | # Get the video title | |
e711babb | 3747 | result = re.search(r'<h1.*?>(?P<title>.*)</h1>', webpage) |
991ba7fa | 3748 | if result is None: |
e711babb | 3749 | raise ExtractorError(u'Unable to extract video title') |
ca6710ee | 3750 | video_title = result.group('title').strip() |
991ba7fa JC |
3751 | |
3752 | # Get the video date | |
e711babb | 3753 | result = re.search(r'Date:</label>(?P<date>.*) </li>', webpage) |
991ba7fa | 3754 | if result is None: |
2e5457be | 3755 | self._downloader.report_warning(u'unable to extract video date') |
629fcdd1 PH |
3756 | upload_date = None |
3757 | else: | |
bf50b038 | 3758 | upload_date = unified_strdate(result.group('date').strip()) |
991ba7fa JC |
3759 | |
3760 | # Get the video uploader | |
e711babb | 3761 | result = re.search(r'Submitted:</label>(?P<uploader>.*)</li>', webpage) |
991ba7fa | 3762 | if result is None: |
2e5457be | 3763 | self._downloader.report_warning(u'unable to extract uploader') |
629fcdd1 PH |
3764 | video_uploader = None |
3765 | else: | |
3766 | video_uploader = result.group('uploader').strip() | |
3767 | video_uploader = clean_html( video_uploader ) | |
991ba7fa JC |
3768 | |
3769 | # Get all of the formats available | |
ca6710ee JC |
3770 | DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' |
3771 | result = re.search(DOWNLOAD_LIST_RE, webpage) | |
991ba7fa | 3772 | if result is None: |
629fcdd1 | 3773 | raise ExtractorError(u'Unable to extract download list') |
ca6710ee | 3774 | download_list_html = result.group('download_list').strip() |
991ba7fa JC |
3775 | |
3776 | # Get all of the links from the page | |
ca6710ee JC |
3777 | LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">' |
3778 | links = re.findall(LINK_RE, download_list_html) | |
991ba7fa | 3779 | if(len(links) == 0): |
629fcdd1 | 3780 | raise ExtractorError(u'ERROR: no known formats available for video') |
6324fd1d | 3781 | |
f17ce13a | 3782 | self.to_screen(u'Links found: %d' % len(links)) |
991ba7fa JC |
3783 | |
3784 | formats = [] | |
3785 | for link in links: | |
3786 | ||
3787 | # A link looks like this: | |
3788 | # 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 | |
3789 | # A path looks like this: | |
3790 | # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4 | |
ca6710ee JC |
3791 | video_url = unescapeHTML( link ) |
3792 | path = compat_urllib_parse_urlparse( video_url ).path | |
991ba7fa JC |
3793 | extension = os.path.splitext( path )[1][1:] |
3794 | format = path.split('/')[4].split('_')[:2] | |
3795 | size = format[0] | |
3796 | bitrate = format[1] | |
3797 | format = "-".join( format ) | |
3798 | title = u'%s-%s-%s' % (video_title, size, bitrate) | |
3799 | ||
3800 | formats.append({ | |
3801 | 'id': video_id, | |
3802 | 'url': video_url, | |
3803 | 'uploader': video_uploader, | |
3804 | 'upload_date': upload_date, | |
3805 | 'title': title, | |
3806 | 'ext': extension, | |
3807 | 'format': format, | |
3808 | 'thumbnail': None, | |
3809 | 'description': None, | |
3810 | 'player_url': None | |
3811 | }) | |
3812 | ||
3813 | if self._downloader.params.get('listformats', None): | |
3814 | self._print_formats(formats) | |
3815 | return | |
3816 | ||
3817 | req_format = self._downloader.params.get('format', None) | |
f17ce13a | 3818 | self.to_screen(u'Format: %s' % req_format) |
991ba7fa | 3819 | |
991ba7fa JC |
3820 | if req_format is None or req_format == 'best': |
3821 | return [formats[0]] | |
3822 | elif req_format == 'worst': | |
3823 | return [formats[-1]] | |
3824 | elif req_format in ('-1', 'all'): | |
3825 | return formats | |
3826 | else: | |
3827 | format = self._specific( req_format, formats ) | |
3828 | if result is None: | |
e5f30ade | 3829 | self._downloader.report_error(u'requested format not available') |
991ba7fa JC |
3830 | return |
3831 | return [format] | |
3832 | ||
6324fd1d | 3833 | |
991ba7fa JC |
3834 | |
3835 | class PornotubeIE(InfoExtractor): | |
3836 | """Information extractor for pornotube.com.""" | |
991ba7fa | 3837 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' |
991ba7fa | 3838 | |
991ba7fa JC |
3839 | def _real_extract(self, url): |
3840 | mobj = re.match(self._VALID_URL, url) | |
3841 | if mobj is None: | |
e5f30ade | 3842 | self._downloader.report_error(u'invalid URL: %s' % url) |
991ba7fa JC |
3843 | return |
3844 | ||
ca6710ee JC |
3845 | video_id = mobj.group('videoid') |
3846 | video_title = mobj.group('title') | |
991ba7fa JC |
3847 | |
3848 | # Get webpage content | |
ca6710ee | 3849 | webpage = self._download_webpage(url, video_id) |
991ba7fa JC |
3850 | |
3851 | # Get the video URL | |
ca6710ee JC |
3852 | VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' |
3853 | result = re.search(VIDEO_URL_RE, webpage) | |
991ba7fa | 3854 | if result is None: |
e5f30ade | 3855 | self._downloader.report_error(u'unable to extract video url') |
991ba7fa | 3856 | return |
ca6710ee | 3857 | video_url = compat_urllib_parse.unquote(result.group('url')) |
991ba7fa JC |
3858 | |
3859 | #Get the uploaded date | |
ca6710ee JC |
3860 | VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' |
3861 | result = re.search(VIDEO_UPLOADED_RE, webpage) | |
991ba7fa | 3862 | if result is None: |
e5f30ade | 3863 | self._downloader.report_error(u'unable to extract video title') |
991ba7fa | 3864 | return |
bf50b038 | 3865 | upload_date = unified_strdate(result.group('date')) |
991ba7fa JC |
3866 | |
3867 | info = {'id': video_id, | |
3868 | 'url': video_url, | |
3869 | 'uploader': None, | |
3870 | 'upload_date': upload_date, | |
3871 | 'title': video_title, | |
3872 | 'ext': 'flv', | |
565f7519 | 3873 | 'format': 'flv'} |
991ba7fa JC |
3874 | |
3875 | return [info] | |
3876 | ||
991ba7fa JC |
3877 | class YouJizzIE(InfoExtractor): |
3878 | """Information extractor for youjizz.com.""" | |
ca6710ee | 3879 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$' |
991ba7fa | 3880 | |
991ba7fa | 3881 | def _real_extract(self, url): |
ca6710ee JC |
3882 | mobj = re.match(self._VALID_URL, url) |
3883 | if mobj is None: | |
e5f30ade | 3884 | self._downloader.report_error(u'invalid URL: %s' % url) |
991ba7fa | 3885 | return |
ca6710ee JC |
3886 | |
3887 | video_id = mobj.group('videoid') | |
3888 | ||
3889 | # Get webpage content | |
3890 | webpage = self._download_webpage(url, video_id) | |
991ba7fa JC |
3891 | |
3892 | # Get the video title | |
db16276b | 3893 | result = re.search(r'<title>(?P<title>.*)</title>', webpage) |
991ba7fa | 3894 | if result is None: |
db16276b | 3895 | raise ExtractorError(u'ERROR: unable to extract video title') |
ca6710ee | 3896 | video_title = result.group('title').strip() |
991ba7fa JC |
3897 | |
3898 | # Get the embed page | |
db16276b | 3899 | result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage) |
991ba7fa | 3900 | if result is None: |
db16276b | 3901 | raise ExtractorError(u'ERROR: unable to extract embed page') |
991ba7fa | 3902 | |
ca6710ee JC |
3903 | embed_page_url = result.group(0).strip() |
3904 | video_id = result.group('videoid') | |
6324fd1d | 3905 | |
ca6710ee JC |
3906 | webpage = self._download_webpage(embed_page_url, video_id) |
3907 | ||
991ba7fa | 3908 | # Get the video URL |
db16276b | 3909 | result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', webpage) |
991ba7fa | 3910 | if result is None: |
db16276b | 3911 | raise ExtractorError(u'ERROR: unable to extract video url') |
ca6710ee | 3912 | video_url = result.group('source') |
991ba7fa JC |
3913 | |
3914 | info = {'id': video_id, | |
3915 | 'url': video_url, | |
991ba7fa JC |
3916 | 'title': video_title, |
3917 | 'ext': 'flv', | |
3918 | 'format': 'flv', | |
991ba7fa JC |
3919 | 'player_url': embed_page_url} |
3920 | ||
3921 | return [info] | |
3922 | ||
ccf65f9d PH |
3923 | class EightTracksIE(InfoExtractor): |
3924 | IE_NAME = '8tracks' | |
25580f32 | 3925 | _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' |
ccf65f9d PH |
3926 | |
3927 | def _real_extract(self, url): | |
3928 | mobj = re.match(self._VALID_URL, url) | |
3929 | if mobj is None: | |
3930 | raise ExtractorError(u'Invalid URL: %s' % url) | |
3931 | playlist_id = mobj.group('id') | |
3932 | ||
3933 | webpage = self._download_webpage(url, playlist_id) | |
3934 | ||
2a9983b7 | 3935 | m = re.search(r"PAGE.mix = (.*?);\n", webpage, flags=re.DOTALL) |
ccf65f9d PH |
3936 | if not m: |
3937 | raise ExtractorError(u'Cannot find trax information') | |
3938 | json_like = m.group(1) | |
3939 | data = json.loads(json_like) | |
3940 | ||
3941 | session = str(random.randint(0, 1000000000)) | |
3942 | mix_id = data['id'] | |
3943 | track_count = data['tracks_count'] | |
3944 | first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) | |
3945 | next_url = first_url | |
3946 | res = [] | |
3947 | for i in itertools.count(): | |
3948 | api_json = self._download_webpage(next_url, playlist_id, | |
3949 | note=u'Downloading song information %s/%s' % (str(i+1), track_count), | |
3950 | errnote=u'Failed to download song information') | |
3951 | api_data = json.loads(api_json) | |
3952 | track_data = api_data[u'set']['track'] | |
3953 | info = { | |
3954 | 'id': track_data['id'], | |
3955 | 'url': track_data['track_file_stream_url'], | |
da4de959 PH |
3956 | 'title': track_data['performer'] + u' - ' + track_data['name'], |
3957 | 'raw_title': track_data['name'], | |
3958 | 'uploader_id': data['user']['login'], | |
ccf65f9d PH |
3959 | 'ext': 'm4a', |
3960 | } | |
3961 | res.append(info) | |
3962 | if api_data['set']['at_last_track']: | |
3963 | break | |
3964 | next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id']) | |
3965 | return res | |
991ba7fa | 3966 | |
da06e2da OK |
3967 | class KeekIE(InfoExtractor): |
3968 | _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)' | |
3969 | IE_NAME = u'keek' | |
3970 | ||
3971 | def _real_extract(self, url): | |
3972 | m = re.match(self._VALID_URL, url) | |
3973 | video_id = m.group('videoID') | |
3974 | video_url = u'http://cdn.keek.com/keek/video/%s' % video_id | |
3975 | thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id | |
3976 | webpage = self._download_webpage(url, video_id) | |
f4381ab8 | 3977 | m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage) |
f0877a44 | 3978 | title = unescapeHTML(m.group('title')) |
f10b2a9c FV |
3979 | m = re.search(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', webpage) |
3980 | uploader = clean_html(m.group('uploader')) | |
da06e2da | 3981 | info = { |
f10b2a9c FV |
3982 | 'id': video_id, |
3983 | 'url': video_url, | |
da06e2da OK |
3984 | 'ext': 'mp4', |
3985 | 'title': title, | |
3986 | 'thumbnail': thumbnail, | |
3987 | 'uploader': uploader | |
f0877a44 | 3988 | } |
da06e2da OK |
3989 | return [info] |
3990 | ||
3a468f2d | 3991 | class TEDIE(InfoExtractor): |
414638cd JMF |
3992 | _VALID_URL=r'''http://www.ted.com/ |
3993 | ( | |
3994 | ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist | |
3995 | | | |
3996 | ((?P<type_talk>talks)) # We have a simple talk | |
3997 | ) | |
3998 | /(?P<name>\w+) # Here goes the name and then ".html" | |
3999 | ''' | |
4000 | ||
89de9eb1 FV |
4001 | @classmethod |
4002 | def suitable(cls, url): | |
414638cd | 4003 | """Receives a URL and returns True if suitable for this IE.""" |
89de9eb1 | 4004 | return re.match(cls._VALID_URL, url, re.VERBOSE) is not None |
414638cd | 4005 | |
3a468f2d | 4006 | def _real_extract(self, url): |
414638cd JMF |
4007 | m=re.match(self._VALID_URL, url, re.VERBOSE) |
4008 | if m.group('type_talk'): | |
4009 | return [self._talk_info(url)] | |
4010 | else : | |
4011 | playlist_id=m.group('playlist_id') | |
4012 | name=m.group('name') | |
f17ce13a | 4013 | self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name)) |
e905b6f8 | 4014 | return [self._playlist_videos_info(url,name,playlist_id)] |
414638cd JMF |
4015 | |
4016 | def _talk_video_link(self,mediaSlug): | |
4017 | '''Returns the video link for that mediaSlug''' | |
4018 | return 'http://download.ted.com/talks/%s.mp4' % mediaSlug | |
4019 | ||
4020 | def _playlist_videos_info(self,url,name,playlist_id=0): | |
4021 | '''Returns the videos of the playlist''' | |
4022 | video_RE=r''' | |
4023 | <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)" | |
4024 | ([.\s]*?)data-playlist_item_id="(\d+)" | |
4025 | ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)" | |
4026 | ''' | |
c85538db | 4027 | video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>' |
414638cd JMF |
4028 | webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage') |
4029 | m_videos=re.finditer(video_RE,webpage,re.VERBOSE) | |
4030 | m_names=re.finditer(video_name_RE,webpage) | |
e905b6f8 JMF |
4031 | |
4032 | playlist_RE = r'div class="headline">(\s*?)<h1>(\s*?)<span>(?P<playlist_title>.*?)</span>' | |
4033 | m_playlist = re.search(playlist_RE, webpage) | |
4034 | playlist_title = m_playlist.group('playlist_title') | |
4035 | ||
4036 | playlist_entries = [] | |
414638cd | 4037 | for m_video, m_name in zip(m_videos,m_names): |
c85538db JMF |
4038 | video_id=m_video.group('video_id') |
4039 | talk_url='http://www.ted.com%s' % m_name.group('talk_url') | |
e905b6f8 JMF |
4040 | playlist_entries.append(self.url_result(talk_url, 'TED')) |
4041 | return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title) | |
c85538db | 4042 | |
414638cd JMF |
4043 | def _talk_info(self, url, video_id=0): |
4044 | """Return the video for the talk in the url""" | |
4045 | m=re.match(self._VALID_URL, url,re.VERBOSE) | |
4046 | videoName=m.group('name') | |
4047 | webpage=self._download_webpage(url, video_id, 'Downloading \"%s\" page' % videoName) | |
4048 | # If the url includes the language we get the title translated | |
7decf895 | 4049 | title_RE=r'<span id="altHeadline" >(?P<title>.*)</span>' |
3a468f2d JMF |
4050 | title=re.search(title_RE, webpage).group('title') |
4051 | info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?) | |
4052 | "id":(?P<videoID>[\d]+).*? | |
4053 | "mediaSlug":"(?P<mediaSlug>[\w\d]+?)"''' | |
c85538db JMF |
4054 | thumb_RE=r'</span>[\s.]*</div>[\s.]*<img src="(?P<thumbnail>.*?)"' |
4055 | thumb_match=re.search(thumb_RE,webpage) | |
3a468f2d JMF |
4056 | info_match=re.search(info_RE,webpage,re.VERBOSE) |
4057 | video_id=info_match.group('videoID') | |
4058 | mediaSlug=info_match.group('mediaSlug') | |
414638cd | 4059 | video_url=self._talk_video_link(mediaSlug) |
3a468f2d | 4060 | info = { |
414638cd JMF |
4061 | 'id': video_id, |
4062 | 'url': video_url, | |
3a468f2d | 4063 | 'ext': 'mp4', |
c85538db JMF |
4064 | 'title': title, |
4065 | 'thumbnail': thumb_match.group('thumbnail') | |
414638cd JMF |
4066 | } |
4067 | return info | |
da06e2da | 4068 | |
58994225 | 4069 | class MySpassIE(InfoExtractor): |
1ad5d872 | 4070 | _VALID_URL = r'http://www.myspass.de/.*' |
6324fd1d | 4071 | |
1ad5d872 | 4072 | def _real_extract(self, url): |
4073 | META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s' | |
58994225 | 4074 | |
1ad5d872 | 4075 | # video id is the last path element of the URL |
4076 | # usually there is a trailing slash, so also try the second but last | |
4077 | url_path = compat_urllib_parse_urlparse(url).path | |
4078 | url_parent_path, video_id = os.path.split(url_path) | |
4079 | if not video_id: | |
4080 | _, video_id = os.path.split(url_parent_path) | |
6324fd1d | 4081 | |
1ad5d872 | 4082 | # get metadata |
4083 | metadata_url = META_DATA_URL_TEMPLATE % video_id | |
4084 | metadata_text = self._download_webpage(metadata_url, video_id) | |
4085 | metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8')) | |
6324fd1d | 4086 | |
1ad5d872 | 4087 | # extract values from metadata |
4088 | url_flv_el = metadata.find('url_flv') | |
4089 | if url_flv_el is None: | |
e5f30ade | 4090 | self._downloader.report_error(u'unable to extract download url') |
1ad5d872 | 4091 | return |
4092 | video_url = url_flv_el.text | |
4093 | extension = os.path.splitext(video_url)[1][1:] | |
4094 | title_el = metadata.find('title') | |
4095 | if title_el is None: | |
e5f30ade | 4096 | self._downloader.report_error(u'unable to extract title') |
1ad5d872 | 4097 | return |
4098 | title = title_el.text | |
4099 | format_id_el = metadata.find('format_id') | |
4100 | if format_id_el is None: | |
4101 | format = ext | |
4102 | else: | |
4103 | format = format_id_el.text | |
4104 | description_el = metadata.find('description') | |
4105 | if description_el is not None: | |
4106 | description = description_el.text | |
4107 | else: | |
4108 | description = None | |
4109 | imagePreview_el = metadata.find('imagePreview') | |
4110 | if imagePreview_el is not None: | |
4111 | thumbnail = imagePreview_el.text | |
4112 | else: | |
4113 | thumbnail = None | |
4114 | info = { | |
4115 | 'id': video_id, | |
4116 | 'url': video_url, | |
4117 | 'title': title, | |
4118 | 'ext': extension, | |
4119 | 'format': format, | |
4120 | 'thumbnail': thumbnail, | |
4121 | 'description': description | |
4122 | } | |
4123 | return [info] | |
4124 | ||
e32b06e9 | 4125 | class SpiegelIE(InfoExtractor): |
1f46c152 | 4126 | _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$' |
e32b06e9 PH |
4127 | |
4128 | def _real_extract(self, url): | |
4129 | m = re.match(self._VALID_URL, url) | |
4130 | video_id = m.group('videoID') | |
4131 | ||
4132 | webpage = self._download_webpage(url, video_id) | |
4133 | m = re.search(r'<div class="spVideoTitle">(.*?)</div>', webpage) | |
4134 | if not m: | |
4135 | raise ExtractorError(u'Cannot find title') | |
4136 | video_title = unescapeHTML(m.group(1)) | |
4137 | ||
4138 | xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml' | |
4139 | xml_code = self._download_webpage(xml_url, video_id, | |
4140 | note=u'Downloading XML', errnote=u'Failed to download XML') | |
4141 | ||
4142 | idoc = xml.etree.ElementTree.fromstring(xml_code) | |
4143 | last_type = idoc[-1] | |
4144 | filename = last_type.findall('./filename')[0].text | |
4145 | duration = float(last_type.findall('./duration')[0].text) | |
4146 | ||
4147 | video_url = 'http://video2.spiegel.de/flash/' + filename | |
4148 | video_ext = filename.rpartition('.')[2] | |
4149 | info = { | |
4150 | 'id': video_id, | |
4151 | 'url': video_url, | |
4152 | 'ext': video_ext, | |
4153 | 'title': video_title, | |
4154 | 'duration': duration, | |
4155 | } | |
4156 | return [info] | |
4157 | ||
0cd35867 | 4158 | class LiveLeakIE(InfoExtractor): |
43113d92 | 4159 | |
0cd35867 | 4160 | _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)' |
43113d92 | 4161 | IE_NAME = u'liveleak' |
4162 | ||
4163 | def _real_extract(self, url): | |
4164 | mobj = re.match(self._VALID_URL, url) | |
4165 | if mobj is None: | |
613bf669 | 4166 | self._downloader.report_error(u'invalid URL: %s' % url) |
43113d92 | 4167 | return |
4168 | ||
0cd35867 | 4169 | video_id = mobj.group('video_id') |
43113d92 | 4170 | |
4171 | webpage = self._download_webpage(url, video_id) | |
4172 | ||
0cd35867 FV |
4173 | m = re.search(r'file: "(.*?)",', webpage) |
4174 | if not m: | |
4175 | self._downloader.report_error(u'unable to find video url') | |
4176 | return | |
4177 | video_url = m.group(1) | |
4178 | ||
43113d92 | 4179 | m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage) |
4180 | if not m: | |
613bf669 | 4181 | self._downloader.report_error(u'Cannot find video title') |
0cd35867 | 4182 | title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip() |
43113d92 | 4183 | |
4184 | m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage) | |
4185 | if m: | |
4186 | desc = unescapeHTML(m.group('desc')) | |
4187 | else: | |
4188 | desc = None | |
4189 | ||
0cd35867 FV |
4190 | m = re.search(r'By:.*?(\w+)</a>', webpage) |
4191 | if m: | |
4192 | uploader = clean_html(m.group(1)) | |
4193 | else: | |
4194 | uploader = None | |
43113d92 | 4195 | |
4196 | info = { | |
4197 | 'id': video_id, | |
4198 | 'url': video_url, | |
4199 | 'ext': 'mp4', | |
4200 | 'title': title, | |
0cd35867 FV |
4201 | 'description': desc, |
4202 | 'uploader': uploader | |
43113d92 | 4203 | } |
4204 | ||
4205 | return [info] | |
4206 | ||
df2dedee | 4207 | class ARDIE(InfoExtractor): |
b03d65c2 PH |
4208 | _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?' |
4209 | _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>' | |
df2dedee MW |
4210 | _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)' |
4211 | ||
4212 | def _real_extract(self, url): | |
4213 | # determine video id from url | |
4214 | m = re.match(self._VALID_URL, url) | |
b03d65c2 PH |
4215 | |
4216 | numid = re.search(r'documentId=([0-9]+)', url) | |
4217 | if numid: | |
4218 | video_id = numid.group(1) | |
4219 | else: | |
4220 | video_id = m.group('video_id') | |
df2dedee MW |
4221 | |
4222 | # determine title and media streams from webpage | |
4223 | html = self._download_webpage(url, video_id) | |
4224 | title = re.search(self._TITLE, html).group('title') | |
4225 | streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)] | |
4226 | if not streams: | |
4227 | assert '"fsk"' in html | |
4228 | self._downloader.report_error(u'this video is only available after 8:00 pm') | |
4229 | return | |
4230 | ||
4231 | # choose default media type and highest quality for now | |
b03d65c2 PH |
4232 | stream = max([s for s in streams if int(s["media_type"]) == 0], |
4233 | key=lambda s: int(s["quality"])) | |
df2dedee MW |
4234 | |
4235 | # there's two possibilities: RTMP stream or HTTP download | |
4236 | info = {'id': video_id, 'title': title, 'ext': 'mp4'} | |
4237 | if stream['rtmp_url']: | |
f17ce13a | 4238 | self.to_screen(u'RTMP download detected') |
df2dedee MW |
4239 | assert stream['video_url'].startswith('mp4:') |
4240 | info["url"] = stream["rtmp_url"] | |
4241 | info["play_path"] = stream['video_url'] | |
4242 | else: | |
4243 | assert stream["video_url"].endswith('.mp4') | |
4244 | info["url"] = stream["video_url"] | |
4245 | return [info] | |
4246 | ||
c15e0241 JMF |
4247 | class TumblrIE(InfoExtractor): |
4248 | _VALID_URL = r'http://(?P<blog_name>.*?).tumblr.com/((post)|(video))/(?P<id>\d*)/(.*?)' | |
4249 | ||
4250 | def _real_extract(self, url): | |
4251 | m_url = re.match(self._VALID_URL, url) | |
4252 | video_id = m_url.group('id') | |
4253 | blog = m_url.group('blog_name') | |
4254 | ||
4255 | url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) | |
4256 | webpage = self._download_webpage(url, video_id) | |
4257 | ||
4258 | re_video = r'src=\\x22(?P<video_url>http://%s.tumblr.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id) | |
4259 | video = re.search(re_video, webpage) | |
4260 | if video is None: | |
4261 | self.to_screen("No video founded") | |
4262 | return [] | |
4263 | video_url = video.group('video_url') | |
4264 | ext = video.group('ext') | |
4265 | ||
4266 | re_thumb = r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22' # We pick the first poster | |
4267 | thumb = re.search(re_thumb, webpage).group('thumb').replace('\\', '') | |
4268 | ||
4269 | # The only place where you can get a title, it's not complete, | |
4270 | # but searching in other places doesn't work for all videos | |
4271 | re_title = r'<title>(.*?) - (?P<title>.*?)</title>' | |
4272 | title = unescapeHTML(re.search(re_title, webpage).group('title')) | |
4273 | ||
4274 | return [{'id': video_id, | |
4275 | 'url': video_url, | |
4276 | 'title': title, | |
4277 | 'thumbnail': thumb, | |
4278 | 'ext': ext | |
4279 | }] | |
4280 | ||
e32b06e9 | 4281 | |
4aeae91f PH |
4282 | def gen_extractors(): |
4283 | """ Return a list of an instance of every supported extractor. | |
4284 | The order does matter; the first extractor matched is the one handling the URL. | |
4285 | """ | |
4286 | return [ | |
4287 | YoutubePlaylistIE(), | |
4288 | YoutubeChannelIE(), | |
4289 | YoutubeUserIE(), | |
4290 | YoutubeSearchIE(), | |
4291 | YoutubeIE(), | |
4292 | MetacafeIE(), | |
4293 | DailymotionIE(), | |
4294 | GoogleSearchIE(), | |
4295 | PhotobucketIE(), | |
4296 | YahooIE(), | |
4297 | YahooSearchIE(), | |
4298 | DepositFilesIE(), | |
4299 | FacebookIE(), | |
4300 | BlipTVUserIE(), | |
4301 | BlipTVIE(), | |
4302 | VimeoIE(), | |
4303 | MyVideoIE(), | |
4304 | ComedyCentralIE(), | |
4305 | EscapistIE(), | |
4306 | CollegeHumorIE(), | |
4307 | XVideosIE(), | |
5011cded | 4308 | SoundcloudSetIE(), |
4aeae91f PH |
4309 | SoundcloudIE(), |
4310 | InfoQIE(), | |
4311 | MixcloudIE(), | |
4312 | StanfordOpenClassroomIE(), | |
4313 | MTVIE(), | |
4314 | YoukuIE(), | |
4315 | XNXXIE(), | |
18be482a JC |
4316 | YouJizzIE(), |
4317 | PornotubeIE(), | |
4318 | YouPornIE(), | |
4aeae91f PH |
4319 | GooglePlusIE(), |
4320 | ArteTvIE(), | |
4321 | NBAIE(), | |
40634747 | 4322 | WorldStarHipHopIE(), |
4aeae91f PH |
4323 | JustinTVIE(), |
4324 | FunnyOrDieIE(), | |
4aeae91f PH |
4325 | SteamIE(), |
4326 | UstreamIE(), | |
ca0a0bbe | 4327 | RBMARadioIE(), |
ccf65f9d | 4328 | EightTracksIE(), |
da06e2da | 4329 | KeekIE(), |
3a468f2d | 4330 | TEDIE(), |
58994225 | 4331 | MySpassIE(), |
e32b06e9 | 4332 | SpiegelIE(), |
0cd35867 | 4333 | LiveLeakIE(), |
df2dedee | 4334 | ARDIE(), |
c15e0241 | 4335 | TumblrIE(), |
4aeae91f PH |
4336 | GenericIE() |
4337 | ] | |
93412126 JMF |
4338 | |
4339 | def get_info_extractor(ie_name): | |
4340 | """Returns the info extractor class with the given ie_name""" | |
4341 | return globals()[ie_name+'IE'] |