]>
Commit | Line | Data |
---|---|---|
d77c3dfd FV |
1 | #!/usr/bin/env python |
2 | # -*- coding: utf-8 -*- | |
3 | ||
9e8056d5 PH |
4 | from __future__ import absolute_import |
5 | ||
d77c3dfd | 6 | import datetime |
d77c3dfd FV |
7 | import netrc |
8 | import os | |
9 | import re | |
10 | import socket | |
11 | import time | |
d77c3dfd | 12 | import email.utils |
921a1455 | 13 | import xml.etree.ElementTree |
302efc19 | 14 | import random |
15 | import math | |
d77c3dfd | 16 | |
9e8056d5 | 17 | from .utils import * |
d77c3dfd FV |
18 | |
19 | ||
20 | class InfoExtractor(object): | |
59ae15a5 | 21 | """Information Extractor class. |
d77c3dfd | 22 | |
59ae15a5 PH |
23 | Information extractors are the classes that, given a URL, extract |
24 | information about the video (or videos) the URL refers to. This | |
25 | information includes the real video URL, the video title, author and | |
cdb30764 | 26 | others. The information is stored in a dictionary which is then |
59ae15a5 PH |
27 | passed to the FileDownloader. The FileDownloader processes this |
28 | information possibly downloading the video to the file system, among | |
29 | other possible outcomes. | |
717b1f72 | 30 | |
59ae15a5 | 31 | The dictionaries must include the following fields: |
717b1f72 | 32 | |
59ae15a5 PH |
33 | id: Video identifier. |
34 | url: Final video URL. | |
77c4beab | 35 | uploader: Full name of the video uploader, unescaped. |
59ae15a5 PH |
36 | upload_date: Video upload date (YYYYMMDD). |
37 | title: Video title, unescaped. | |
38 | ext: Video filename extension. | |
717b1f72 | 39 | |
59ae15a5 | 40 | The following fields are optional: |
717b1f72 | 41 | |
59ae15a5 PH |
42 | format: The video format, defaults to ext (used for --get-format) |
43 | thumbnail: Full URL to a video thumbnail image. | |
44 | description: One-line video description. | |
77c4beab | 45 | uploader_id: Nickname or id of the video uploader. |
59ae15a5 PH |
46 | player_url: SWF Player URL (used for rtmpdump). |
47 | subtitles: The .srt file contents. | |
48 | urlhandle: [internal] The urlHandle to be used to download the file, | |
49 | like returned by urllib.request.urlopen | |
d77c3dfd | 50 | |
59ae15a5 | 51 | The fields should all be Unicode strings. |
9ce5d9ee | 52 | |
59ae15a5 PH |
53 | Subclasses of this one should re-define the _real_initialize() and |
54 | _real_extract() methods and define a _VALID_URL regexp. | |
55 | Probably, they should also be added to the list of extractors. | |
717b1f72 | 56 | |
59ae15a5 PH |
57 | _real_extract() must return a *list* of information dictionaries as |
58 | described above. | |
03c5b0fb | 59 | |
59ae15a5 PH |
60 | Finally, the _WORKING attribute should be set to False for broken IEs |
61 | in order to warn the users and skip the tests. | |
62 | """ | |
d77c3dfd | 63 | |
59ae15a5 PH |
64 | _ready = False |
65 | _downloader = None | |
66 | _WORKING = True | |
d77c3dfd | 67 | |
59ae15a5 PH |
68 | def __init__(self, downloader=None): |
69 | """Constructor. Receives an optional downloader.""" | |
70 | self._ready = False | |
71 | self.set_downloader(downloader) | |
d77c3dfd | 72 | |
59ae15a5 PH |
73 | def suitable(self, url): |
74 | """Receives a URL and returns True if suitable for this IE.""" | |
75 | return re.match(self._VALID_URL, url) is not None | |
d77c3dfd | 76 | |
59ae15a5 PH |
77 | def working(self): |
78 | """Getter method for _WORKING.""" | |
79 | return self._WORKING | |
03c5b0fb | 80 | |
59ae15a5 PH |
81 | def initialize(self): |
82 | """Initializes an instance (authentication, etc).""" | |
83 | if not self._ready: | |
84 | self._real_initialize() | |
85 | self._ready = True | |
d77c3dfd | 86 | |
59ae15a5 PH |
87 | def extract(self, url): |
88 | """Extracts URL information and returns it in list of dicts.""" | |
89 | self.initialize() | |
90 | return self._real_extract(url) | |
d77c3dfd | 91 | |
59ae15a5 PH |
92 | def set_downloader(self, downloader): |
93 | """Sets the downloader for this IE.""" | |
94 | self._downloader = downloader | |
d77c3dfd | 95 | |
59ae15a5 PH |
96 | def _real_initialize(self): |
97 | """Real initialization process. Redefine in subclasses.""" | |
98 | pass | |
d77c3dfd | 99 | |
59ae15a5 PH |
100 | def _real_extract(self, url): |
101 | """Real extraction process. Redefine in subclasses.""" | |
102 | pass | |
d77c3dfd FV |
103 | |
104 | ||
105 | class YoutubeIE(InfoExtractor): | |
59ae15a5 PH |
106 | """Information extractor for youtube.com.""" |
107 | ||
108 | _VALID_URL = r"""^ | |
109 | ( | |
110 | (?:https?://)? # http(s):// (optional) | |
111 | (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| | |
112 | tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains | |
113 | (?:.*?\#/)? # handle anchor (#/) redirect urls | |
114 | (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs | |
115 | (?: # the various things that can precede the ID: | |
116 | (?:(?:v|embed|e)/) # v/ or embed/ or e/ | |
117 | |(?: # or the v= param in all its forms | |
118 | (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) | |
119 | (?:\?|\#!?) # the params delimiter ? or # or #! | |
120 | (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx) | |
121 | v= | |
122 | ) | |
123 | )? # optional -> youtube.com/xxxx is OK | |
124 | )? # all until now is optional -> you can pass the naked ID | |
125 | ([0-9A-Za-z_-]+) # here is it! the YouTube video ID | |
126 | (?(1).+)? # if we found the ID, everything can follow | |
127 | $""" | |
128 | _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' | |
129 | _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' | |
130 | _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' | |
131 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' | |
132 | _NETRC_MACHINE = 'youtube' | |
133 | # Listed in order of quality | |
134 | _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] | |
135 | _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] | |
136 | _video_extensions = { | |
137 | '13': '3gp', | |
138 | '17': 'mp4', | |
139 | '18': 'mp4', | |
140 | '22': 'mp4', | |
141 | '37': 'mp4', | |
142 | '38': 'video', # You actually don't know if this will be MOV, AVI or whatever | |
143 | '43': 'webm', | |
144 | '44': 'webm', | |
145 | '45': 'webm', | |
146 | '46': 'webm', | |
147 | } | |
148 | _video_dimensions = { | |
149 | '5': '240x400', | |
150 | '6': '???', | |
151 | '13': '???', | |
152 | '17': '144x176', | |
153 | '18': '360x640', | |
154 | '22': '720x1280', | |
155 | '34': '360x640', | |
156 | '35': '480x854', | |
157 | '37': '1080x1920', | |
158 | '38': '3072x4096', | |
159 | '43': '360x640', | |
160 | '44': '480x854', | |
161 | '45': '720x1280', | |
162 | '46': '1080x1920', | |
cdb30764 | 163 | } |
59ae15a5 PH |
164 | IE_NAME = u'youtube' |
165 | ||
166 | def suitable(self, url): | |
167 | """Receives a URL and returns True if suitable for this IE.""" | |
168 | return re.match(self._VALID_URL, url, re.VERBOSE) is not None | |
169 | ||
170 | def report_lang(self): | |
171 | """Report attempt to set language.""" | |
172 | self._downloader.to_screen(u'[youtube] Setting language') | |
173 | ||
174 | def report_login(self): | |
175 | """Report attempt to log in.""" | |
176 | self._downloader.to_screen(u'[youtube] Logging in') | |
177 | ||
178 | def report_age_confirmation(self): | |
179 | """Report attempt to confirm age.""" | |
180 | self._downloader.to_screen(u'[youtube] Confirming age') | |
181 | ||
182 | def report_video_webpage_download(self, video_id): | |
183 | """Report attempt to download video webpage.""" | |
184 | self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) | |
185 | ||
186 | def report_video_info_webpage_download(self, video_id): | |
187 | """Report attempt to download video info webpage.""" | |
188 | self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) | |
189 | ||
190 | def report_video_subtitles_download(self, video_id): | |
191 | """Report attempt to download video info webpage.""" | |
192 | self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id) | |
193 | ||
194 | def report_information_extraction(self, video_id): | |
195 | """Report attempt to extract video information.""" | |
196 | self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) | |
197 | ||
198 | def report_unavailable_format(self, video_id, format): | |
199 | """Report extracted video URL.""" | |
200 | self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) | |
201 | ||
202 | def report_rtmp_download(self): | |
203 | """Indicate the download will use the RTMP protocol.""" | |
204 | self._downloader.to_screen(u'[youtube] RTMP download detected') | |
205 | ||
206 | def _closed_captions_xml_to_srt(self, xml_string): | |
207 | srt = '' | |
208 | texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE) | |
209 | # TODO parse xml instead of regex | |
210 | for n, (start, dur_tag, dur, caption) in enumerate(texts): | |
211 | if not dur: dur = '4' | |
212 | start = float(start) | |
213 | end = start + float(dur) | |
214 | start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) | |
215 | end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) | |
216 | caption = unescapeHTML(caption) | |
217 | caption = unescapeHTML(caption) # double cycle, intentional | |
218 | srt += str(n+1) + '\n' | |
219 | srt += start + ' --> ' + end + '\n' | |
220 | srt += caption + '\n\n' | |
221 | return srt | |
222 | ||
056d8575 FV |
223 | def _extract_subtitles(self, video_id): |
224 | self.report_video_subtitles_download(video_id) | |
225 | request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) | |
226 | try: | |
227 | srt_list = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
228 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
229 | return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None) | |
230 | srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list) | |
231 | srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list) | |
232 | if not srt_lang_list: | |
233 | return (u'WARNING: video has no closed captions', None) | |
234 | if self._downloader.params.get('subtitleslang', False): | |
235 | srt_lang = self._downloader.params.get('subtitleslang') | |
236 | elif 'en' in srt_lang_list: | |
237 | srt_lang = 'en' | |
238 | else: | |
1a2c3c0f | 239 | srt_lang = list(srt_lang_list.keys())[0] |
056d8575 FV |
240 | if not srt_lang in srt_lang_list: |
241 | return (u'WARNING: no closed captions found in the specified language', None) | |
242 | request = compat_urllib_request.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id)) | |
243 | try: | |
244 | srt_xml = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
245 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
246 | return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None) | |
247 | if not srt_xml: | |
248 | return (u'WARNING: unable to download video subtitles', None) | |
249 | return (None, self._closed_captions_xml_to_srt(srt_xml)) | |
250 | ||
59ae15a5 PH |
251 | def _print_formats(self, formats): |
252 | print('Available formats:') | |
253 | for x in formats: | |
254 | print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))) | |
255 | ||
256 | def _real_initialize(self): | |
257 | if self._downloader is None: | |
258 | return | |
259 | ||
260 | username = None | |
261 | password = None | |
262 | downloader_params = self._downloader.params | |
263 | ||
264 | # Attempt to use provided username and password or .netrc data | |
265 | if downloader_params.get('username', None) is not None: | |
266 | username = downloader_params['username'] | |
267 | password = downloader_params['password'] | |
268 | elif downloader_params.get('usenetrc', False): | |
269 | try: | |
270 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
271 | if info is not None: | |
272 | username = info[0] | |
273 | password = info[2] | |
274 | else: | |
275 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
276 | except (IOError, netrc.NetrcParseError) as err: | |
277 | self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) | |
278 | return | |
279 | ||
280 | # Set language | |
281 | request = compat_urllib_request.Request(self._LANG_URL) | |
282 | try: | |
283 | self.report_lang() | |
284 | compat_urllib_request.urlopen(request).read() | |
285 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
286 | self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err)) | |
287 | return | |
288 | ||
289 | # No authentication to be performed | |
290 | if username is None: | |
291 | return | |
292 | ||
293 | # Log in | |
294 | login_form = { | |
295 | 'current_form': 'loginForm', | |
296 | 'next': '/', | |
297 | 'action_login': 'Log In', | |
298 | 'username': username, | |
299 | 'password': password, | |
300 | } | |
301 | request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) | |
302 | try: | |
303 | self.report_login() | |
80d3177e | 304 | login_results = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 PH |
305 | if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None: |
306 | self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') | |
307 | return | |
308 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
309 | self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err)) | |
310 | return | |
311 | ||
312 | # Confirm age | |
313 | age_form = { | |
314 | 'next_url': '/', | |
315 | 'action_confirm': 'Confirm', | |
316 | } | |
317 | request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form)) | |
318 | try: | |
319 | self.report_age_confirmation() | |
80d3177e | 320 | age_results = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 PH |
321 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
322 | self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) | |
323 | return | |
324 | ||
325 | def _real_extract(self, url): | |
326 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter | |
327 | mobj = re.search(self._NEXT_URL_RE, url) | |
328 | if mobj: | |
329 | url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') | |
330 | ||
331 | # Extract video id from URL | |
332 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) | |
333 | if mobj is None: | |
334 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
335 | return | |
336 | video_id = mobj.group(2) | |
337 | ||
338 | # Get video webpage | |
339 | self.report_video_webpage_download(video_id) | |
340 | request = compat_urllib_request.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) | |
341 | try: | |
342 | video_webpage_bytes = compat_urllib_request.urlopen(request).read() | |
343 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
344 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) | |
345 | return | |
346 | ||
347 | video_webpage = video_webpage_bytes.decode('utf-8', 'ignore') | |
348 | ||
349 | # Attempt to extract SWF player URL | |
350 | mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) | |
351 | if mobj is not None: | |
352 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
353 | else: | |
354 | player_url = None | |
355 | ||
356 | # Get video info | |
357 | self.report_video_info_webpage_download(video_id) | |
358 | for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: | |
359 | video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
360 | % (video_id, el_type)) | |
361 | request = compat_urllib_request.Request(video_info_url) | |
362 | try: | |
363 | video_info_webpage_bytes = compat_urllib_request.urlopen(request).read() | |
364 | video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore') | |
365 | video_info = compat_parse_qs(video_info_webpage) | |
366 | if 'token' in video_info: | |
367 | break | |
368 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
369 | self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) | |
370 | return | |
371 | if 'token' not in video_info: | |
372 | if 'reason' in video_info: | |
373 | self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0]) | |
374 | else: | |
375 | self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') | |
376 | return | |
377 | ||
378 | # Check for "rental" videos | |
379 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
380 | self._downloader.trouble(u'ERROR: "rental" videos not supported') | |
381 | return | |
382 | ||
383 | # Start extracting information | |
384 | self.report_information_extraction(video_id) | |
385 | ||
386 | # uploader | |
387 | if 'author' not in video_info: | |
77c4beab | 388 | self._downloader.trouble(u'ERROR: unable to extract uploader name') |
59ae15a5 PH |
389 | return |
390 | video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) | |
391 | ||
77c4beab FV |
392 | # uploader_id |
393 | video_uploader_id = None | |
394 | mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/user/([^"]+)">', video_webpage) | |
395 | if mobj is not None: | |
396 | video_uploader_id = mobj.group(1) | |
397 | else: | |
398 | self._downloader.trouble(u'WARNING: unable to extract uploader nickname') | |
399 | ||
59ae15a5 PH |
400 | # title |
401 | if 'title' not in video_info: | |
402 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
403 | return | |
404 | video_title = compat_urllib_parse.unquote_plus(video_info['title'][0]) | |
405 | ||
406 | # thumbnail image | |
407 | if 'thumbnail_url' not in video_info: | |
408 | self._downloader.trouble(u'WARNING: unable to extract video thumbnail') | |
409 | video_thumbnail = '' | |
410 | else: # don't panic if we can't find it | |
411 | video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) | |
412 | ||
413 | # upload date | |
414 | upload_date = None | |
415 | mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL) | |
416 | if mobj is not None: | |
417 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) | |
418 | format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] | |
419 | for expression in format_expressions: | |
420 | try: | |
421 | upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') | |
422 | except: | |
423 | pass | |
424 | ||
425 | # description | |
426 | video_description = get_element_by_id("eow-description", video_webpage) | |
427 | if video_description: | |
428 | video_description = clean_html(video_description) | |
429 | else: | |
430 | video_description = '' | |
431 | ||
432 | # closed captions | |
433 | video_subtitles = None | |
434 | if self._downloader.params.get('writesubtitles', False): | |
056d8575 FV |
435 | (srt_error, video_subtitles) = self._extract_subtitles(video_id) |
436 | if srt_error: | |
437 | self._downloader.trouble(srt_error) | |
59ae15a5 PH |
438 | |
439 | if 'length_seconds' not in video_info: | |
440 | self._downloader.trouble(u'WARNING: unable to extract video duration') | |
441 | video_duration = '' | |
442 | else: | |
443 | video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]) | |
444 | ||
445 | # token | |
446 | video_token = compat_urllib_parse.unquote_plus(video_info['token'][0]) | |
447 | ||
448 | # Decide which formats to download | |
449 | req_format = self._downloader.params.get('format', None) | |
450 | ||
451 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): | |
452 | self.report_rtmp_download() | |
453 | video_url_list = [(None, video_info['conn'][0])] | |
454 | elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: | |
455 | url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') | |
456 | url_data = [compat_parse_qs(uds) for uds in url_data_strs] | |
1a2c3c0f | 457 | url_data = [ud for ud in url_data if 'itag' in ud and 'url' in ud] |
59ae15a5 PH |
458 | url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data) |
459 | ||
460 | format_limit = self._downloader.params.get('format_limit', None) | |
461 | available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats | |
462 | if format_limit is not None and format_limit in available_formats: | |
463 | format_list = available_formats[available_formats.index(format_limit):] | |
464 | else: | |
465 | format_list = available_formats | |
466 | existing_formats = [x for x in format_list if x in url_map] | |
467 | if len(existing_formats) == 0: | |
468 | self._downloader.trouble(u'ERROR: no known formats available for video') | |
469 | return | |
470 | if self._downloader.params.get('listformats', None): | |
471 | self._print_formats(existing_formats) | |
472 | return | |
473 | if req_format is None or req_format == 'best': | |
474 | video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality | |
475 | elif req_format == 'worst': | |
476 | video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality | |
477 | elif req_format in ('-1', 'all'): | |
478 | video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats | |
479 | else: | |
480 | # Specific formats. We pick the first in a slash-delimeted sequence. | |
481 | # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. | |
482 | req_formats = req_format.split('/') | |
483 | video_url_list = None | |
484 | for rf in req_formats: | |
485 | if rf in url_map: | |
486 | video_url_list = [(rf, url_map[rf])] | |
487 | break | |
488 | if video_url_list is None: | |
489 | self._downloader.trouble(u'ERROR: requested format not available') | |
490 | return | |
491 | else: | |
492 | self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') | |
493 | return | |
494 | ||
495 | results = [] | |
496 | for format_param, video_real_url in video_url_list: | |
497 | # Extension | |
498 | video_extension = self._video_extensions.get(format_param, 'flv') | |
499 | ||
32761d86 FV |
500 | video_format = '{0} - {1}'.format(format_param if format_param else video_extension, |
501 | self._video_dimensions.get(format_param, '???')) | |
59ae15a5 PH |
502 | |
503 | results.append({ | |
504 | 'id': video_id, | |
505 | 'url': video_real_url, | |
506 | 'uploader': video_uploader, | |
77c4beab | 507 | 'uploader_id': video_uploader_id, |
59ae15a5 PH |
508 | 'upload_date': upload_date, |
509 | 'title': video_title, | |
510 | 'ext': video_extension, | |
511 | 'format': video_format, | |
512 | 'thumbnail': video_thumbnail, | |
513 | 'description': video_description, | |
514 | 'player_url': player_url, | |
515 | 'subtitles': video_subtitles, | |
516 | 'duration': video_duration | |
517 | }) | |
518 | return results | |
d77c3dfd FV |
519 | |
520 | ||
521 | class MetacafeIE(InfoExtractor): | |
59ae15a5 PH |
522 | """Information Extractor for metacafe.com.""" |
523 | ||
524 | _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' | |
525 | _DISCLAIMER = 'http://www.metacafe.com/family_filter/' | |
526 | _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' | |
527 | IE_NAME = u'metacafe' | |
528 | ||
529 | def __init__(self, downloader=None): | |
530 | InfoExtractor.__init__(self, downloader) | |
531 | ||
532 | def report_disclaimer(self): | |
533 | """Report disclaimer retrieval.""" | |
534 | self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') | |
535 | ||
536 | def report_age_confirmation(self): | |
537 | """Report attempt to confirm age.""" | |
538 | self._downloader.to_screen(u'[metacafe] Confirming age') | |
539 | ||
540 | def report_download_webpage(self, video_id): | |
541 | """Report webpage download.""" | |
542 | self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) | |
543 | ||
544 | def report_extraction(self, video_id): | |
545 | """Report information extraction.""" | |
546 | self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) | |
547 | ||
548 | def _real_initialize(self): | |
549 | # Retrieve disclaimer | |
550 | request = compat_urllib_request.Request(self._DISCLAIMER) | |
551 | try: | |
552 | self.report_disclaimer() | |
553 | disclaimer = compat_urllib_request.urlopen(request).read() | |
554 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
555 | self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err)) | |
556 | return | |
557 | ||
558 | # Confirm age | |
559 | disclaimer_form = { | |
560 | 'filters': '0', | |
561 | 'submit': "Continue - I'm over 18", | |
562 | } | |
563 | request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) | |
564 | try: | |
565 | self.report_age_confirmation() | |
566 | disclaimer = compat_urllib_request.urlopen(request).read() | |
567 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
568 | self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) | |
569 | return | |
570 | ||
571 | def _real_extract(self, url): | |
572 | # Extract id and simplified title from URL | |
573 | mobj = re.match(self._VALID_URL, url) | |
574 | if mobj is None: | |
575 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
576 | return | |
577 | ||
578 | video_id = mobj.group(1) | |
579 | ||
580 | # Check if video comes from YouTube | |
581 | mobj2 = re.match(r'^yt-(.*)$', video_id) | |
582 | if mobj2 is not None: | |
583 | self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)]) | |
584 | return | |
585 | ||
586 | # Retrieve video webpage to extract further information | |
587 | request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) | |
588 | try: | |
589 | self.report_download_webpage(video_id) | |
590 | webpage = compat_urllib_request.urlopen(request).read() | |
591 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
592 | self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) | |
593 | return | |
594 | ||
595 | # Extract URL, uploader and title from webpage | |
596 | self.report_extraction(video_id) | |
597 | mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) | |
598 | if mobj is not None: | |
599 | mediaURL = compat_urllib_parse.unquote(mobj.group(1)) | |
600 | video_extension = mediaURL[-3:] | |
601 | ||
602 | # Extract gdaKey if available | |
603 | mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) | |
604 | if mobj is None: | |
605 | video_url = mediaURL | |
606 | else: | |
607 | gdaKey = mobj.group(1) | |
608 | video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) | |
609 | else: | |
610 | mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) | |
611 | if mobj is None: | |
612 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
613 | return | |
614 | vardict = compat_parse_qs(mobj.group(1)) | |
615 | if 'mediaData' not in vardict: | |
616 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
617 | return | |
618 | mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) | |
619 | if mobj is None: | |
620 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
621 | return | |
622 | mediaURL = mobj.group(1).replace('\\/', '/') | |
623 | video_extension = mediaURL[-3:] | |
624 | video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) | |
625 | ||
626 | mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) | |
627 | if mobj is None: | |
628 | self._downloader.trouble(u'ERROR: unable to extract title') | |
629 | return | |
630 | video_title = mobj.group(1).decode('utf-8') | |
631 | ||
632 | mobj = re.search(r'submitter=(.*?);', webpage) | |
633 | if mobj is None: | |
634 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
635 | return | |
636 | video_uploader = mobj.group(1) | |
637 | ||
638 | return [{ | |
639 | 'id': video_id.decode('utf-8'), | |
640 | 'url': video_url.decode('utf-8'), | |
641 | 'uploader': video_uploader.decode('utf-8'), | |
642 | 'upload_date': None, | |
643 | 'title': video_title, | |
644 | 'ext': video_extension.decode('utf-8'), | |
645 | }] | |
d77c3dfd FV |
646 | |
647 | ||
648 | class DailymotionIE(InfoExtractor): | |
59ae15a5 PH |
649 | """Information Extractor for Dailymotion""" |
650 | ||
651 | _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' | |
652 | IE_NAME = u'dailymotion' | |
653 | ||
654 | def __init__(self, downloader=None): | |
655 | InfoExtractor.__init__(self, downloader) | |
656 | ||
657 | def report_download_webpage(self, video_id): | |
658 | """Report webpage download.""" | |
659 | self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) | |
660 | ||
661 | def report_extraction(self, video_id): | |
662 | """Report information extraction.""" | |
663 | self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) | |
664 | ||
665 | def _real_extract(self, url): | |
666 | # Extract id and simplified title from URL | |
667 | mobj = re.match(self._VALID_URL, url) | |
668 | if mobj is None: | |
669 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
670 | return | |
671 | ||
672 | video_id = mobj.group(1).split('_')[0].split('?')[0] | |
673 | ||
674 | video_extension = 'mp4' | |
675 | ||
676 | # Retrieve video webpage to extract further information | |
677 | request = compat_urllib_request.Request(url) | |
678 | request.add_header('Cookie', 'family_filter=off') | |
679 | try: | |
680 | self.report_download_webpage(video_id) | |
28ca6b5a PH |
681 | webpage_bytes = compat_urllib_request.urlopen(request).read() |
682 | webpage = webpage_bytes.decode('utf-8') | |
59ae15a5 PH |
683 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
684 | self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) | |
685 | return | |
686 | ||
687 | # Extract URL, uploader and title from webpage | |
688 | self.report_extraction(video_id) | |
689 | mobj = re.search(r'\s*var flashvars = (.*)', webpage) | |
690 | if mobj is None: | |
691 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
692 | return | |
693 | flashvars = compat_urllib_parse.unquote(mobj.group(1)) | |
694 | ||
695 | for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: | |
696 | if key in flashvars: | |
697 | max_quality = key | |
698 | self._downloader.to_screen(u'[dailymotion] Using %s' % key) | |
699 | break | |
700 | else: | |
701 | self._downloader.trouble(u'ERROR: unable to extract video URL') | |
702 | return | |
703 | ||
704 | mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) | |
705 | if mobj is None: | |
706 | self._downloader.trouble(u'ERROR: unable to extract video URL') | |
707 | return | |
708 | ||
709 | video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/') | |
710 | ||
711 | # TODO: support choosing qualities | |
712 | ||
713 | mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage) | |
714 | if mobj is None: | |
715 | self._downloader.trouble(u'ERROR: unable to extract title') | |
716 | return | |
28ca6b5a | 717 | video_title = unescapeHTML(mobj.group('title')) |
59ae15a5 PH |
718 | |
719 | video_uploader = None | |
720 | mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage) | |
721 | if mobj is None: | |
722 | # lookin for official user | |
723 | mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage) | |
724 | if mobj_official is None: | |
725 | self._downloader.trouble(u'WARNING: unable to extract uploader nickname') | |
726 | else: | |
727 | video_uploader = mobj_official.group(1) | |
728 | else: | |
729 | video_uploader = mobj.group(1) | |
730 | ||
731 | video_upload_date = None | |
732 | mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage) | |
733 | if mobj is not None: | |
734 | video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1) | |
735 | ||
736 | return [{ | |
28ca6b5a PH |
737 | 'id': video_id, |
738 | 'url': video_url, | |
739 | 'uploader': video_uploader, | |
59ae15a5 PH |
740 | 'upload_date': video_upload_date, |
741 | 'title': video_title, | |
28ca6b5a | 742 | 'ext': video_extension, |
59ae15a5 | 743 | }] |
d77c3dfd FV |
744 | |
745 | ||
d77c3dfd | 746 | class PhotobucketIE(InfoExtractor): |
59ae15a5 PH |
747 | """Information extractor for photobucket.com.""" |
748 | ||
749 | _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' | |
750 | IE_NAME = u'photobucket' | |
751 | ||
752 | def __init__(self, downloader=None): | |
753 | InfoExtractor.__init__(self, downloader) | |
754 | ||
755 | def report_download_webpage(self, video_id): | |
756 | """Report webpage download.""" | |
757 | self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) | |
758 | ||
759 | def report_extraction(self, video_id): | |
760 | """Report information extraction.""" | |
761 | self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) | |
762 | ||
763 | def _real_extract(self, url): | |
764 | # Extract id from URL | |
765 | mobj = re.match(self._VALID_URL, url) | |
766 | if mobj is None: | |
767 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
768 | return | |
769 | ||
770 | video_id = mobj.group(1) | |
771 | ||
772 | video_extension = 'flv' | |
773 | ||
774 | # Retrieve video webpage to extract further information | |
775 | request = compat_urllib_request.Request(url) | |
776 | try: | |
777 | self.report_download_webpage(video_id) | |
778 | webpage = compat_urllib_request.urlopen(request).read() | |
779 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
780 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) | |
781 | return | |
782 | ||
783 | # Extract URL, uploader, and title from webpage | |
784 | self.report_extraction(video_id) | |
785 | mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage) | |
786 | if mobj is None: | |
787 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
788 | return | |
789 | mediaURL = compat_urllib_parse.unquote(mobj.group(1)) | |
790 | ||
791 | video_url = mediaURL | |
792 | ||
793 | mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) | |
794 | if mobj is None: | |
795 | self._downloader.trouble(u'ERROR: unable to extract title') | |
796 | return | |
797 | video_title = mobj.group(1).decode('utf-8') | |
798 | ||
799 | video_uploader = mobj.group(2).decode('utf-8') | |
800 | ||
801 | return [{ | |
802 | 'id': video_id.decode('utf-8'), | |
803 | 'url': video_url.decode('utf-8'), | |
804 | 'uploader': video_uploader, | |
805 | 'upload_date': None, | |
806 | 'title': video_title, | |
807 | 'ext': video_extension.decode('utf-8'), | |
808 | }] | |
d77c3dfd FV |
809 | |
810 | ||
811 | class YahooIE(InfoExtractor): | |
59ae15a5 PH |
812 | """Information extractor for video.yahoo.com.""" |
813 | ||
93702113 | 814 | _WORKING = False |
59ae15a5 PH |
815 | # _VALID_URL matches all Yahoo! Video URLs |
816 | # _VPAGE_URL matches only the extractable '/watch/' URLs | |
817 | _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' | |
818 | _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' | |
819 | IE_NAME = u'video.yahoo' | |
820 | ||
821 | def __init__(self, downloader=None): | |
822 | InfoExtractor.__init__(self, downloader) | |
823 | ||
824 | def report_download_webpage(self, video_id): | |
825 | """Report webpage download.""" | |
826 | self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) | |
827 | ||
828 | def report_extraction(self, video_id): | |
829 | """Report information extraction.""" | |
830 | self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) | |
831 | ||
832 | def _real_extract(self, url, new_video=True): | |
833 | # Extract ID from URL | |
834 | mobj = re.match(self._VALID_URL, url) | |
835 | if mobj is None: | |
836 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
837 | return | |
838 | ||
839 | video_id = mobj.group(2) | |
840 | video_extension = 'flv' | |
841 | ||
842 | # Rewrite valid but non-extractable URLs as | |
843 | # extractable English language /watch/ URLs | |
844 | if re.match(self._VPAGE_URL, url) is None: | |
845 | request = compat_urllib_request.Request(url) | |
846 | try: | |
847 | webpage = compat_urllib_request.urlopen(request).read() | |
848 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
849 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) | |
850 | return | |
851 | ||
852 | mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) | |
853 | if mobj is None: | |
854 | self._downloader.trouble(u'ERROR: Unable to extract id field') | |
855 | return | |
856 | yahoo_id = mobj.group(1) | |
857 | ||
858 | mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) | |
859 | if mobj is None: | |
860 | self._downloader.trouble(u'ERROR: Unable to extract vid field') | |
861 | return | |
862 | yahoo_vid = mobj.group(1) | |
863 | ||
864 | url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) | |
865 | return self._real_extract(url, new_video=False) | |
866 | ||
867 | # Retrieve video webpage to extract further information | |
868 | request = compat_urllib_request.Request(url) | |
869 | try: | |
870 | self.report_download_webpage(video_id) | |
871 | webpage = compat_urllib_request.urlopen(request).read() | |
872 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
873 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) | |
874 | return | |
875 | ||
876 | # Extract uploader and title from webpage | |
877 | self.report_extraction(video_id) | |
878 | mobj = re.search(r'<meta name="title" content="(.*)" />', webpage) | |
879 | if mobj is None: | |
880 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
881 | return | |
882 | video_title = mobj.group(1).decode('utf-8') | |
883 | ||
884 | mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage) | |
885 | if mobj is None: | |
886 | self._downloader.trouble(u'ERROR: unable to extract video uploader') | |
887 | return | |
888 | video_uploader = mobj.group(1).decode('utf-8') | |
889 | ||
890 | # Extract video thumbnail | |
891 | mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage) | |
892 | if mobj is None: | |
893 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
894 | return | |
895 | video_thumbnail = mobj.group(1).decode('utf-8') | |
896 | ||
897 | # Extract video description | |
898 | mobj = re.search(r'<meta name="description" content="(.*)" />', webpage) | |
899 | if mobj is None: | |
900 | self._downloader.trouble(u'ERROR: unable to extract video description') | |
901 | return | |
902 | video_description = mobj.group(1).decode('utf-8') | |
903 | if not video_description: | |
904 | video_description = 'No description available.' | |
905 | ||
906 | # Extract video height and width | |
907 | mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage) | |
908 | if mobj is None: | |
909 | self._downloader.trouble(u'ERROR: unable to extract video height') | |
910 | return | |
911 | yv_video_height = mobj.group(1) | |
912 | ||
913 | mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage) | |
914 | if mobj is None: | |
915 | self._downloader.trouble(u'ERROR: unable to extract video width') | |
916 | return | |
917 | yv_video_width = mobj.group(1) | |
918 | ||
919 | # Retrieve video playlist to extract media URL | |
920 | # I'm not completely sure what all these options are, but we | |
921 | # seem to need most of them, otherwise the server sends a 401. | |
922 | yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents | |
923 | yv_bitrate = '700' # according to Wikipedia this is hard-coded | |
924 | request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + | |
925 | '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + | |
926 | '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') | |
927 | try: | |
928 | self.report_download_webpage(video_id) | |
929 | webpage = compat_urllib_request.urlopen(request).read() | |
930 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
931 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) | |
932 | return | |
933 | ||
934 | # Extract media URL from playlist XML | |
935 | mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage) | |
936 | if mobj is None: | |
937 | self._downloader.trouble(u'ERROR: Unable to extract media URL') | |
938 | return | |
939 | video_url = compat_urllib_parse.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') | |
940 | video_url = unescapeHTML(video_url) | |
941 | ||
942 | return [{ | |
943 | 'id': video_id.decode('utf-8'), | |
944 | 'url': video_url, | |
945 | 'uploader': video_uploader, | |
946 | 'upload_date': None, | |
947 | 'title': video_title, | |
948 | 'ext': video_extension.decode('utf-8'), | |
949 | 'thumbnail': video_thumbnail.decode('utf-8'), | |
950 | 'description': video_description, | |
951 | }] | |
d77c3dfd FV |
952 | |
953 | ||
954 | class VimeoIE(InfoExtractor): | |
59ae15a5 PH |
955 | """Information extractor for vimeo.com.""" |
956 | ||
957 | # _VALID_URL matches Vimeo URLs | |
958 | _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)' | |
959 | IE_NAME = u'vimeo' | |
960 | ||
961 | def __init__(self, downloader=None): | |
962 | InfoExtractor.__init__(self, downloader) | |
963 | ||
964 | def report_download_webpage(self, video_id): | |
965 | """Report webpage download.""" | |
966 | self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) | |
967 | ||
968 | def report_extraction(self, video_id): | |
969 | """Report information extraction.""" | |
970 | self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id) | |
971 | ||
972 | def _real_extract(self, url, new_video=True): | |
973 | # Extract ID from URL | |
974 | mobj = re.match(self._VALID_URL, url) | |
975 | if mobj is None: | |
976 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
977 | return | |
978 | ||
979 | video_id = mobj.group(1) | |
980 | ||
981 | # Retrieve video webpage to extract further information | |
982 | request = compat_urllib_request.Request(url, None, std_headers) | |
983 | try: | |
984 | self.report_download_webpage(video_id) | |
f1171f7c PH |
985 | webpage_bytes = compat_urllib_request.urlopen(request).read() |
986 | webpage = webpage_bytes.decode('utf-8') | |
59ae15a5 PH |
987 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
988 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) | |
989 | return | |
990 | ||
991 | # Now we begin extracting as much information as we can from what we | |
992 | # retrieved. First we extract the information common to all extractors, | |
993 | # and latter we extract those that are Vimeo specific. | |
994 | self.report_extraction(video_id) | |
995 | ||
996 | # Extract the config JSON | |
59ae15a5 | 997 | try: |
1ca63e3a | 998 | config = webpage.split(' = {config:')[1].split(',assets:')[0] |
59ae15a5 PH |
999 | config = json.loads(config) |
1000 | except: | |
1001 | self._downloader.trouble(u'ERROR: unable to extract info section') | |
1002 | return | |
cdb30764 | 1003 | |
59ae15a5 PH |
1004 | # Extract title |
1005 | video_title = config["video"]["title"] | |
1006 | ||
77c4beab | 1007 | # Extract uploader and uploader_id |
59ae15a5 | 1008 | video_uploader = config["video"]["owner"]["name"] |
77c4beab | 1009 | video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] |
59ae15a5 PH |
1010 | |
1011 | # Extract video thumbnail | |
1012 | video_thumbnail = config["video"]["thumbnail"] | |
1013 | ||
1014 | # Extract video description | |
0dcfb234 | 1015 | video_description = get_element_by_attribute("itemprop", "description", webpage) |
59ae15a5 PH |
1016 | if video_description: video_description = clean_html(video_description) |
1017 | else: video_description = '' | |
1018 | ||
1019 | # Extract upload date | |
1020 | video_upload_date = None | |
6b3aef80 | 1021 | mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage) |
59ae15a5 | 1022 | if mobj is not None: |
6b3aef80 | 1023 | video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) |
59ae15a5 PH |
1024 | |
1025 | # Vimeo specific: extract request signature and timestamp | |
1026 | sig = config['request']['signature'] | |
1027 | timestamp = config['request']['timestamp'] | |
1028 | ||
1029 | # Vimeo specific: extract video codec and quality information | |
1030 | # First consider quality, then codecs, then take everything | |
1031 | # TODO bind to format param | |
1032 | codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')] | |
1033 | files = { 'hd': [], 'sd': [], 'other': []} | |
1034 | for codec_name, codec_extension in codecs: | |
1035 | if codec_name in config["video"]["files"]: | |
1036 | if 'hd' in config["video"]["files"][codec_name]: | |
1037 | files['hd'].append((codec_name, codec_extension, 'hd')) | |
1038 | elif 'sd' in config["video"]["files"][codec_name]: | |
1039 | files['sd'].append((codec_name, codec_extension, 'sd')) | |
1040 | else: | |
1041 | files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0])) | |
1042 | ||
1043 | for quality in ('hd', 'sd', 'other'): | |
1044 | if len(files[quality]) > 0: | |
1045 | video_quality = files[quality][0][2] | |
1046 | video_codec = files[quality][0][0] | |
1047 | video_extension = files[quality][0][1] | |
1048 | self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) | |
1049 | break | |
1050 | else: | |
1051 | self._downloader.trouble(u'ERROR: no known codec found') | |
1052 | return | |
1053 | ||
1054 | video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ | |
1055 | %(video_id, sig, timestamp, video_quality, video_codec.upper()) | |
1056 | ||
1057 | return [{ | |
1058 | 'id': video_id, | |
1059 | 'url': video_url, | |
1060 | 'uploader': video_uploader, | |
77c4beab | 1061 | 'uploader_id': video_uploader_id, |
59ae15a5 PH |
1062 | 'upload_date': video_upload_date, |
1063 | 'title': video_title, | |
1064 | 'ext': video_extension, | |
1065 | 'thumbnail': video_thumbnail, | |
1066 | 'description': video_description, | |
1067 | }] | |
d77c3dfd FV |
1068 | |
1069 | ||
f2ad10a9 | 1070 | class ArteTvIE(InfoExtractor): |
59ae15a5 PH |
1071 | """arte.tv information extractor.""" |
1072 | ||
1073 | _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' | |
1074 | _LIVE_URL = r'index-[0-9]+\.html$' | |
1075 | ||
1076 | IE_NAME = u'arte.tv' | |
1077 | ||
1078 | def __init__(self, downloader=None): | |
1079 | InfoExtractor.__init__(self, downloader) | |
1080 | ||
1081 | def report_download_webpage(self, video_id): | |
1082 | """Report webpage download.""" | |
1083 | self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id) | |
1084 | ||
1085 | def report_extraction(self, video_id): | |
1086 | """Report information extraction.""" | |
1087 | self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id) | |
1088 | ||
1089 | def fetch_webpage(self, url): | |
1090 | self._downloader.increment_downloads() | |
1091 | request = compat_urllib_request.Request(url) | |
1092 | try: | |
1093 | self.report_download_webpage(url) | |
1094 | webpage = compat_urllib_request.urlopen(request).read() | |
1095 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1096 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) | |
1097 | return | |
1098 | except ValueError as err: | |
1099 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1100 | return | |
1101 | return webpage | |
1102 | ||
1103 | def grep_webpage(self, url, regex, regexFlags, matchTuples): | |
1104 | page = self.fetch_webpage(url) | |
1105 | mobj = re.search(regex, page, regexFlags) | |
1106 | info = {} | |
1107 | ||
1108 | if mobj is None: | |
1109 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1110 | return | |
1111 | ||
1112 | for (i, key, err) in matchTuples: | |
1113 | if mobj.group(i) is None: | |
1114 | self._downloader.trouble(err) | |
1115 | return | |
1116 | else: | |
1117 | info[key] = mobj.group(i) | |
1118 | ||
1119 | return info | |
1120 | ||
1121 | def extractLiveStream(self, url): | |
1122 | video_lang = url.split('/')[-4] | |
1123 | info = self.grep_webpage( | |
1124 | url, | |
1125 | r'src="(.*?/videothek_js.*?\.js)', | |
1126 | 0, | |
1127 | [ | |
1128 | (1, 'url', u'ERROR: Invalid URL: %s' % url) | |
1129 | ] | |
1130 | ) | |
1131 | http_host = url.split('/')[2] | |
1132 | next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url'))) | |
1133 | info = self.grep_webpage( | |
1134 | next_url, | |
1135 | r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' + | |
1136 | '(http://.*?\.swf).*?' + | |
1137 | '(rtmp://.*?)\'', | |
1138 | re.DOTALL, | |
1139 | [ | |
1140 | (1, 'path', u'ERROR: could not extract video path: %s' % url), | |
1141 | (2, 'player', u'ERROR: could not extract video player: %s' % url), | |
1142 | (3, 'url', u'ERROR: could not extract video url: %s' % url) | |
1143 | ] | |
1144 | ) | |
1145 | video_url = u'%s/%s' % (info.get('url'), info.get('path')) | |
1146 | ||
1147 | def extractPlus7Stream(self, url): | |
1148 | video_lang = url.split('/')[-3] | |
1149 | info = self.grep_webpage( | |
1150 | url, | |
1151 | r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', | |
1152 | 0, | |
1153 | [ | |
1154 | (1, 'url', u'ERROR: Invalid URL: %s' % url) | |
1155 | ] | |
1156 | ) | |
1157 | next_url = compat_urllib_parse.unquote(info.get('url')) | |
1158 | info = self.grep_webpage( | |
1159 | next_url, | |
1160 | r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang, | |
1161 | 0, | |
1162 | [ | |
1163 | (1, 'url', u'ERROR: Could not find <video> tag: %s' % url) | |
1164 | ] | |
1165 | ) | |
1166 | next_url = compat_urllib_parse.unquote(info.get('url')) | |
1167 | ||
1168 | info = self.grep_webpage( | |
1169 | next_url, | |
1170 | r'<video id="(.*?)".*?>.*?' + | |
1171 | '<name>(.*?)</name>.*?' + | |
1172 | '<dateVideo>(.*?)</dateVideo>.*?' + | |
1173 | '<url quality="hd">(.*?)</url>', | |
1174 | re.DOTALL, | |
1175 | [ | |
1176 | (1, 'id', u'ERROR: could not extract video id: %s' % url), | |
1177 | (2, 'title', u'ERROR: could not extract video title: %s' % url), | |
1178 | (3, 'date', u'ERROR: could not extract video date: %s' % url), | |
1179 | (4, 'url', u'ERROR: could not extract video url: %s' % url) | |
1180 | ] | |
1181 | ) | |
1182 | ||
1183 | return { | |
1184 | 'id': info.get('id'), | |
1185 | 'url': compat_urllib_parse.unquote(info.get('url')), | |
1186 | 'uploader': u'arte.tv', | |
1187 | 'upload_date': info.get('date'), | |
93702113 | 1188 | 'title': info.get('title').decode('utf-8'), |
59ae15a5 PH |
1189 | 'ext': u'mp4', |
1190 | 'format': u'NA', | |
1191 | 'player_url': None, | |
1192 | } | |
1193 | ||
1194 | def _real_extract(self, url): | |
1195 | video_id = url.split('/')[-1] | |
1196 | self.report_extraction(video_id) | |
1197 | ||
1198 | if re.search(self._LIVE_URL, video_id) is not None: | |
1199 | self.extractLiveStream(url) | |
1200 | return | |
1201 | else: | |
1202 | info = self.extractPlus7Stream(url) | |
1203 | ||
1204 | return [info] | |
f2ad10a9 CA |
1205 | |
1206 | ||
d77c3dfd | 1207 | class GenericIE(InfoExtractor): |
59ae15a5 PH |
1208 | """Generic last-resort information extractor.""" |
1209 | ||
1210 | _VALID_URL = r'.*' | |
1211 | IE_NAME = u'generic' | |
1212 | ||
1213 | def __init__(self, downloader=None): | |
1214 | InfoExtractor.__init__(self, downloader) | |
1215 | ||
1216 | def report_download_webpage(self, video_id): | |
1217 | """Report webpage download.""" | |
1218 | self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') | |
1219 | self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) | |
1220 | ||
1221 | def report_extraction(self, video_id): | |
1222 | """Report information extraction.""" | |
1223 | self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) | |
1224 | ||
1225 | def report_following_redirect(self, new_url): | |
1226 | """Report information extraction.""" | |
1227 | self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url) | |
cdb30764 | 1228 | |
59ae15a5 PH |
1229 | def _test_redirect(self, url): |
1230 | """Check if it is a redirect, like url shorteners, in case restart chain.""" | |
1231 | class HeadRequest(compat_urllib_request.Request): | |
1232 | def get_method(self): | |
1233 | return "HEAD" | |
1234 | ||
1235 | class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler): | |
1236 | """ | |
cdb30764 | 1237 | Subclass the HTTPRedirectHandler to make it use our |
59ae15a5 PH |
1238 | HeadRequest also on the redirected URL |
1239 | """ | |
cdb30764 | 1240 | def redirect_request(self, req, fp, code, msg, headers, newurl): |
59ae15a5 | 1241 | if code in (301, 302, 303, 307): |
cdb30764 | 1242 | newurl = newurl.replace(' ', '%20') |
59ae15a5 PH |
1243 | newheaders = dict((k,v) for k,v in req.headers.items() |
1244 | if k.lower() not in ("content-length", "content-type")) | |
cdb30764 | 1245 | return HeadRequest(newurl, |
59ae15a5 | 1246 | headers=newheaders, |
cdb30764 ND |
1247 | origin_req_host=req.get_origin_req_host(), |
1248 | unverifiable=True) | |
1249 | else: | |
1250 | raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp) | |
59ae15a5 PH |
1251 | |
1252 | class HTTPMethodFallback(compat_urllib_request.BaseHandler): | |
1253 | """ | |
1254 | Fallback to GET if HEAD is not allowed (405 HTTP error) | |
1255 | """ | |
cdb30764 | 1256 | def http_error_405(self, req, fp, code, msg, headers): |
59ae15a5 PH |
1257 | fp.read() |
1258 | fp.close() | |
1259 | ||
1260 | newheaders = dict((k,v) for k,v in req.headers.items() | |
1261 | if k.lower() not in ("content-length", "content-type")) | |
cdb30764 ND |
1262 | return self.parent.open(compat_urllib_request.Request(req.get_full_url(), |
1263 | headers=newheaders, | |
1264 | origin_req_host=req.get_origin_req_host(), | |
59ae15a5 PH |
1265 | unverifiable=True)) |
1266 | ||
1267 | # Build our opener | |
cdb30764 | 1268 | opener = compat_urllib_request.OpenerDirector() |
59ae15a5 PH |
1269 | for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler, |
1270 | HTTPMethodFallback, HEADRedirectHandler, | |
1271 | compat_urllib_error.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]: | |
1272 | opener.add_handler(handler()) | |
1273 | ||
1274 | response = opener.open(HeadRequest(url)) | |
1275 | new_url = response.geturl() | |
1276 | ||
1277 | if url == new_url: | |
1278 | return False | |
1279 | ||
1280 | self.report_following_redirect(new_url) | |
1281 | self._downloader.download([new_url]) | |
1282 | return True | |
1283 | ||
1284 | def _real_extract(self, url): | |
1285 | if self._test_redirect(url): return | |
1286 | ||
1287 | video_id = url.split('/')[-1] | |
1288 | request = compat_urllib_request.Request(url) | |
1289 | try: | |
1290 | self.report_download_webpage(video_id) | |
1291 | webpage = compat_urllib_request.urlopen(request).read() | |
1292 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1293 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) | |
1294 | return | |
1295 | except ValueError as err: | |
1296 | # since this is the last-resort InfoExtractor, if | |
1297 | # this error is thrown, it'll be thrown here | |
1298 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1299 | return | |
1300 | ||
1301 | self.report_extraction(video_id) | |
1302 | # Start with something easy: JW Player in SWFObject | |
1303 | mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) | |
1304 | if mobj is None: | |
1305 | # Broaden the search a little bit | |
1306 | mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) | |
1307 | if mobj is None: | |
1308 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1309 | return | |
1310 | ||
1311 | # It's possible that one of the regexes | |
1312 | # matched, but returned an empty group: | |
1313 | if mobj.group(1) is None: | |
1314 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1315 | return | |
1316 | ||
1317 | video_url = compat_urllib_parse.unquote(mobj.group(1)) | |
1318 | video_id = os.path.basename(video_url) | |
1319 | ||
1320 | # here's a fun little line of code for you: | |
1321 | video_extension = os.path.splitext(video_id)[1][1:] | |
1322 | video_id = os.path.splitext(video_id)[0] | |
1323 | ||
1324 | # it's tempting to parse this further, but you would | |
1325 | # have to take into account all the variations like | |
1326 | # Video Title - Site Name | |
1327 | # Site Name | Video Title | |
1328 | # Video Title - Tagline | Site Name | |
1329 | # and so on and so forth; it's just not practical | |
1330 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
1331 | if mobj is None: | |
1332 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1333 | return | |
f1171f7c | 1334 | video_title = mobj.group(1) |
59ae15a5 PH |
1335 | |
1336 | # video uploader is domain name | |
1337 | mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) | |
1338 | if mobj is None: | |
1339 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1340 | return | |
f1171f7c | 1341 | video_uploader = mobj.group(1) |
59ae15a5 PH |
1342 | |
1343 | return [{ | |
f1171f7c PH |
1344 | 'id': video_id, |
1345 | 'url': video_url, | |
59ae15a5 PH |
1346 | 'uploader': video_uploader, |
1347 | 'upload_date': None, | |
1348 | 'title': video_title, | |
f1171f7c | 1349 | 'ext': video_extension, |
59ae15a5 | 1350 | }] |
d77c3dfd FV |
1351 | |
1352 | ||
1353 | class YoutubeSearchIE(InfoExtractor): | |
59ae15a5 PH |
1354 | """Information Extractor for YouTube search queries.""" |
1355 | _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+' | |
1356 | _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' | |
1357 | _max_youtube_results = 1000 | |
1358 | IE_NAME = u'youtube:search' | |
1359 | ||
1360 | def __init__(self, downloader=None): | |
1361 | InfoExtractor.__init__(self, downloader) | |
1362 | ||
1363 | def report_download_page(self, query, pagenum): | |
1364 | """Report attempt to download search page with given number.""" | |
1365 | query = query.decode(preferredencoding()) | |
1366 | self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) | |
1367 | ||
1368 | def _real_extract(self, query): | |
1369 | mobj = re.match(self._VALID_URL, query) | |
1370 | if mobj is None: | |
1371 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
1372 | return | |
1373 | ||
1374 | prefix, query = query.split(':') | |
1375 | prefix = prefix[8:] | |
1376 | query = query.encode('utf-8') | |
1377 | if prefix == '': | |
1378 | self._download_n_results(query, 1) | |
1379 | return | |
1380 | elif prefix == 'all': | |
1381 | self._download_n_results(query, self._max_youtube_results) | |
1382 | return | |
1383 | else: | |
1384 | try: | |
1385 | n = int(prefix) | |
1386 | if n <= 0: | |
1387 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
1388 | return | |
1389 | elif n > self._max_youtube_results: | |
1390 | self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) | |
1391 | n = self._max_youtube_results | |
1392 | self._download_n_results(query, n) | |
1393 | return | |
1394 | except ValueError: # parsing prefix as integer fails | |
1395 | self._download_n_results(query, 1) | |
1396 | return | |
1397 | ||
1398 | def _download_n_results(self, query, n): | |
1399 | """Downloads a specified number of results for a query""" | |
1400 | ||
1401 | video_ids = [] | |
1402 | pagenum = 0 | |
1403 | limit = n | |
1404 | ||
1405 | while (50 * pagenum) < limit: | |
1406 | self.report_download_page(query, pagenum+1) | |
1407 | result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1) | |
1408 | request = compat_urllib_request.Request(result_url) | |
1409 | try: | |
1410 | data = compat_urllib_request.urlopen(request).read() | |
1411 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1412 | self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err)) | |
1413 | return | |
1414 | api_response = json.loads(data)['data'] | |
1415 | ||
1416 | new_ids = list(video['id'] for video in api_response['items']) | |
1417 | video_ids += new_ids | |
1418 | ||
1419 | limit = min(n, api_response['totalItems']) | |
1420 | pagenum += 1 | |
1421 | ||
1422 | if len(video_ids) > n: | |
1423 | video_ids = video_ids[:n] | |
1424 | for id in video_ids: | |
1425 | self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) | |
1426 | return | |
d77c3dfd FV |
1427 | |
1428 | ||
1429 | class GoogleSearchIE(InfoExtractor): | |
59ae15a5 PH |
1430 | """Information Extractor for Google Video search queries.""" |
1431 | _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+' | |
1432 | _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' | |
1433 | _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)' | |
1434 | _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"' | |
1435 | _max_google_results = 1000 | |
1436 | IE_NAME = u'video.google:search' | |
1437 | ||
1438 | def __init__(self, downloader=None): | |
1439 | InfoExtractor.__init__(self, downloader) | |
1440 | ||
1441 | def report_download_page(self, query, pagenum): | |
1442 | """Report attempt to download playlist page with given number.""" | |
1443 | query = query.decode(preferredencoding()) | |
1444 | self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) | |
1445 | ||
1446 | def _real_extract(self, query): | |
1447 | mobj = re.match(self._VALID_URL, query) | |
1448 | if mobj is None: | |
1449 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
1450 | return | |
1451 | ||
1452 | prefix, query = query.split(':') | |
1453 | prefix = prefix[8:] | |
1454 | query = query.encode('utf-8') | |
1455 | if prefix == '': | |
1456 | self._download_n_results(query, 1) | |
1457 | return | |
1458 | elif prefix == 'all': | |
1459 | self._download_n_results(query, self._max_google_results) | |
1460 | return | |
1461 | else: | |
1462 | try: | |
1463 | n = int(prefix) | |
1464 | if n <= 0: | |
1465 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
1466 | return | |
1467 | elif n > self._max_google_results: | |
1468 | self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) | |
1469 | n = self._max_google_results | |
1470 | self._download_n_results(query, n) | |
1471 | return | |
1472 | except ValueError: # parsing prefix as integer fails | |
1473 | self._download_n_results(query, 1) | |
1474 | return | |
1475 | ||
1476 | def _download_n_results(self, query, n): | |
1477 | """Downloads a specified number of results for a query""" | |
1478 | ||
1479 | video_ids = [] | |
1480 | pagenum = 0 | |
1481 | ||
1482 | while True: | |
1483 | self.report_download_page(query, pagenum) | |
1484 | result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum*10) | |
1485 | request = compat_urllib_request.Request(result_url) | |
1486 | try: | |
1487 | page = compat_urllib_request.urlopen(request).read() | |
1488 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1489 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) | |
1490 | return | |
1491 | ||
1492 | # Extract video identifiers | |
1493 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
1494 | video_id = mobj.group(1) | |
1495 | if video_id not in video_ids: | |
1496 | video_ids.append(video_id) | |
1497 | if len(video_ids) == n: | |
1498 | # Specified n videos reached | |
1499 | for id in video_ids: | |
1500 | self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id]) | |
1501 | return | |
1502 | ||
1503 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
1504 | for id in video_ids: | |
1505 | self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id]) | |
1506 | return | |
1507 | ||
1508 | pagenum = pagenum + 1 | |
d77c3dfd FV |
1509 | |
1510 | ||
1511 | class YahooSearchIE(InfoExtractor): | |
59ae15a5 | 1512 | """Information Extractor for Yahoo! Video search queries.""" |
93702113 FV |
1513 | |
1514 | _WORKING = False | |
59ae15a5 PH |
1515 | _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+' |
1516 | _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' | |
1517 | _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' | |
1518 | _MORE_PAGES_INDICATOR = r'\s*Next' | |
1519 | _max_yahoo_results = 1000 | |
1520 | IE_NAME = u'video.yahoo:search' | |
1521 | ||
1522 | def __init__(self, downloader=None): | |
1523 | InfoExtractor.__init__(self, downloader) | |
1524 | ||
1525 | def report_download_page(self, query, pagenum): | |
1526 | """Report attempt to download playlist page with given number.""" | |
1527 | query = query.decode(preferredencoding()) | |
1528 | self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) | |
1529 | ||
1530 | def _real_extract(self, query): | |
1531 | mobj = re.match(self._VALID_URL, query) | |
1532 | if mobj is None: | |
1533 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
1534 | return | |
1535 | ||
1536 | prefix, query = query.split(':') | |
1537 | prefix = prefix[8:] | |
1538 | query = query.encode('utf-8') | |
1539 | if prefix == '': | |
1540 | self._download_n_results(query, 1) | |
1541 | return | |
1542 | elif prefix == 'all': | |
1543 | self._download_n_results(query, self._max_yahoo_results) | |
1544 | return | |
1545 | else: | |
1546 | try: | |
1547 | n = int(prefix) | |
1548 | if n <= 0: | |
1549 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
1550 | return | |
1551 | elif n > self._max_yahoo_results: | |
1552 | self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) | |
1553 | n = self._max_yahoo_results | |
1554 | self._download_n_results(query, n) | |
1555 | return | |
1556 | except ValueError: # parsing prefix as integer fails | |
1557 | self._download_n_results(query, 1) | |
1558 | return | |
1559 | ||
1560 | def _download_n_results(self, query, n): | |
1561 | """Downloads a specified number of results for a query""" | |
1562 | ||
1563 | video_ids = [] | |
1564 | already_seen = set() | |
1565 | pagenum = 1 | |
1566 | ||
1567 | while True: | |
1568 | self.report_download_page(query, pagenum) | |
1569 | result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum) | |
1570 | request = compat_urllib_request.Request(result_url) | |
1571 | try: | |
1572 | page = compat_urllib_request.urlopen(request).read() | |
1573 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1574 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) | |
1575 | return | |
1576 | ||
1577 | # Extract video identifiers | |
1578 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
1579 | video_id = mobj.group(1) | |
1580 | if video_id not in already_seen: | |
1581 | video_ids.append(video_id) | |
1582 | already_seen.add(video_id) | |
1583 | if len(video_ids) == n: | |
1584 | # Specified n videos reached | |
1585 | for id in video_ids: | |
1586 | self._downloader.download(['http://video.yahoo.com/watch/%s' % id]) | |
1587 | return | |
1588 | ||
1589 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
1590 | for id in video_ids: | |
1591 | self._downloader.download(['http://video.yahoo.com/watch/%s' % id]) | |
1592 | return | |
1593 | ||
1594 | pagenum = pagenum + 1 | |
d77c3dfd FV |
1595 | |
1596 | ||
1597 | class YoutubePlaylistIE(InfoExtractor): | |
59ae15a5 PH |
1598 | """Information Extractor for YouTube playlists.""" |
1599 | ||
e387eb5a | 1600 | _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]{10,})(?:/.*?/([0-9A-Za-z_-]+))?.*' |
59ae15a5 PH |
1601 | _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' |
1602 | _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s' | |
9789a05c | 1603 | _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}" |
59ae15a5 PH |
1604 | IE_NAME = u'youtube:playlist' |
1605 | ||
1606 | def __init__(self, downloader=None): | |
1607 | InfoExtractor.__init__(self, downloader) | |
1608 | ||
1609 | def report_download_page(self, playlist_id, pagenum): | |
1610 | """Report attempt to download playlist page with given number.""" | |
1611 | self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) | |
1612 | ||
1613 | def _real_extract(self, url): | |
1614 | # Extract playlist id | |
1615 | mobj = re.match(self._VALID_URL, url) | |
1616 | if mobj is None: | |
1617 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) | |
1618 | return | |
1619 | ||
1620 | # Single video case | |
1621 | if mobj.group(3) is not None: | |
1622 | self._downloader.download([mobj.group(3)]) | |
1623 | return | |
1624 | ||
1625 | # Download playlist pages | |
1626 | # prefix is 'p' as default for playlists but there are other types that need extra care | |
1627 | playlist_prefix = mobj.group(1) | |
1628 | if playlist_prefix == 'a': | |
1629 | playlist_access = 'artist' | |
1630 | else: | |
1631 | playlist_prefix = 'p' | |
1632 | playlist_access = 'view_play_list' | |
1633 | playlist_id = mobj.group(2) | |
1634 | video_ids = [] | |
1635 | pagenum = 1 | |
1636 | ||
1637 | while True: | |
1638 | self.report_download_page(playlist_id, pagenum) | |
1639 | url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum) | |
1640 | request = compat_urllib_request.Request(url) | |
1641 | try: | |
80d3177e | 1642 | page = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 PH |
1643 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
1644 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) | |
1645 | return | |
1646 | ||
1647 | # Extract video identifiers | |
1648 | ids_in_page = [] | |
1649 | for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, page): | |
1650 | if mobj.group(1) not in ids_in_page: | |
1651 | ids_in_page.append(mobj.group(1)) | |
1652 | video_ids.extend(ids_in_page) | |
1653 | ||
9789a05c | 1654 | if self._MORE_PAGES_INDICATOR not in page: |
59ae15a5 PH |
1655 | break |
1656 | pagenum = pagenum + 1 | |
1657 | ||
9789a05c FV |
1658 | total = len(video_ids) |
1659 | ||
59ae15a5 PH |
1660 | playliststart = self._downloader.params.get('playliststart', 1) - 1 |
1661 | playlistend = self._downloader.params.get('playlistend', -1) | |
1662 | if playlistend == -1: | |
1663 | video_ids = video_ids[playliststart:] | |
1664 | else: | |
1665 | video_ids = video_ids[playliststart:playlistend] | |
1666 | ||
9789a05c FV |
1667 | if len(video_ids) == total: |
1668 | self._downloader.to_screen(u'[youtube] PL %s: Found %i videos' % (playlist_id, total)) | |
1669 | else: | |
1670 | self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(video_ids))) | |
1671 | ||
59ae15a5 PH |
1672 | for id in video_ids: |
1673 | self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) | |
1674 | return | |
d77c3dfd FV |
1675 | |
1676 | ||
902b2a0a | 1677 | class YoutubeChannelIE(InfoExtractor): |
59ae15a5 PH |
1678 | """Information Extractor for YouTube channels.""" |
1679 | ||
1680 | _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$" | |
1681 | _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en' | |
9789a05c | 1682 | _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}" |
59ae15a5 PH |
1683 | IE_NAME = u'youtube:channel' |
1684 | ||
1685 | def report_download_page(self, channel_id, pagenum): | |
1686 | """Report attempt to download channel page with given number.""" | |
1687 | self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum)) | |
1688 | ||
1689 | def _real_extract(self, url): | |
1690 | # Extract channel id | |
1691 | mobj = re.match(self._VALID_URL, url) | |
1692 | if mobj is None: | |
1693 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) | |
1694 | return | |
1695 | ||
1696 | # Download channel pages | |
1697 | channel_id = mobj.group(1) | |
1698 | video_ids = [] | |
1699 | pagenum = 1 | |
1700 | ||
1701 | while True: | |
1702 | self.report_download_page(channel_id, pagenum) | |
1703 | url = self._TEMPLATE_URL % (channel_id, pagenum) | |
1704 | request = compat_urllib_request.Request(url) | |
1705 | try: | |
9789a05c | 1706 | page = compat_urllib_request.urlopen(request).read().decode('utf8') |
59ae15a5 PH |
1707 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
1708 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) | |
1709 | return | |
1710 | ||
1711 | # Extract video identifiers | |
1712 | ids_in_page = [] | |
1713 | for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page): | |
1714 | if mobj.group(1) not in ids_in_page: | |
1715 | ids_in_page.append(mobj.group(1)) | |
1716 | video_ids.extend(ids_in_page) | |
1717 | ||
9789a05c | 1718 | if self._MORE_PAGES_INDICATOR not in page: |
59ae15a5 PH |
1719 | break |
1720 | pagenum = pagenum + 1 | |
1721 | ||
9789a05c FV |
1722 | self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) |
1723 | ||
59ae15a5 PH |
1724 | for id in video_ids: |
1725 | self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) | |
1726 | return | |
902b2a0a FV |
1727 | |
1728 | ||
d77c3dfd | 1729 | class YoutubeUserIE(InfoExtractor): |
59ae15a5 | 1730 | """Information Extractor for YouTube users.""" |
d77c3dfd | 1731 | |
59ae15a5 PH |
1732 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)' |
1733 | _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' | |
1734 | _GDATA_PAGE_SIZE = 50 | |
1735 | _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' | |
1736 | _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]' | |
1737 | IE_NAME = u'youtube:user' | |
d77c3dfd | 1738 | |
59ae15a5 PH |
1739 | def __init__(self, downloader=None): |
1740 | InfoExtractor.__init__(self, downloader) | |
d77c3dfd | 1741 | |
59ae15a5 PH |
1742 | def report_download_page(self, username, start_index): |
1743 | """Report attempt to download user page.""" | |
1744 | self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % | |
1745 | (username, start_index, start_index + self._GDATA_PAGE_SIZE)) | |
d77c3dfd | 1746 | |
59ae15a5 PH |
1747 | def _real_extract(self, url): |
1748 | # Extract username | |
1749 | mobj = re.match(self._VALID_URL, url) | |
1750 | if mobj is None: | |
1751 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) | |
1752 | return | |
d77c3dfd | 1753 | |
59ae15a5 | 1754 | username = mobj.group(1) |
d77c3dfd | 1755 | |
59ae15a5 PH |
1756 | # Download video ids using YouTube Data API. Result size per |
1757 | # query is limited (currently to 50 videos) so we need to query | |
1758 | # page by page until there are no video ids - it means we got | |
1759 | # all of them. | |
d77c3dfd | 1760 | |
59ae15a5 PH |
1761 | video_ids = [] |
1762 | pagenum = 0 | |
d77c3dfd | 1763 | |
59ae15a5 PH |
1764 | while True: |
1765 | start_index = pagenum * self._GDATA_PAGE_SIZE + 1 | |
1766 | self.report_download_page(username, start_index) | |
d77c3dfd | 1767 | |
59ae15a5 | 1768 | request = compat_urllib_request.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)) |
d77c3dfd | 1769 | |
59ae15a5 | 1770 | try: |
80d3177e | 1771 | page = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 PH |
1772 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
1773 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) | |
1774 | return | |
d77c3dfd | 1775 | |
59ae15a5 PH |
1776 | # Extract video identifiers |
1777 | ids_in_page = [] | |
d77c3dfd | 1778 | |
59ae15a5 PH |
1779 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): |
1780 | if mobj.group(1) not in ids_in_page: | |
1781 | ids_in_page.append(mobj.group(1)) | |
d77c3dfd | 1782 | |
59ae15a5 | 1783 | video_ids.extend(ids_in_page) |
d77c3dfd | 1784 | |
59ae15a5 PH |
1785 | # A little optimization - if current page is not |
1786 | # "full", ie. does not contain PAGE_SIZE video ids then | |
1787 | # we can assume that this page is the last one - there | |
1788 | # are no more ids on further pages - no need to query | |
1789 | # again. | |
d77c3dfd | 1790 | |
59ae15a5 PH |
1791 | if len(ids_in_page) < self._GDATA_PAGE_SIZE: |
1792 | break | |
d77c3dfd | 1793 | |
59ae15a5 | 1794 | pagenum += 1 |
d77c3dfd | 1795 | |
59ae15a5 PH |
1796 | all_ids_count = len(video_ids) |
1797 | playliststart = self._downloader.params.get('playliststart', 1) - 1 | |
1798 | playlistend = self._downloader.params.get('playlistend', -1) | |
d77c3dfd | 1799 | |
59ae15a5 PH |
1800 | if playlistend == -1: |
1801 | video_ids = video_ids[playliststart:] | |
1802 | else: | |
1803 | video_ids = video_ids[playliststart:playlistend] | |
d77c3dfd | 1804 | |
59ae15a5 PH |
1805 | self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" % |
1806 | (username, all_ids_count, len(video_ids))) | |
d77c3dfd | 1807 | |
59ae15a5 PH |
1808 | for video_id in video_ids: |
1809 | self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id]) | |
d77c3dfd FV |
1810 | |
1811 | ||
eeeb4daa | 1812 | class BlipTVUserIE(InfoExtractor): |
59ae15a5 | 1813 | """Information Extractor for blip.tv users.""" |
eeeb4daa | 1814 | |
59ae15a5 PH |
1815 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' |
1816 | _PAGE_SIZE = 12 | |
1817 | IE_NAME = u'blip.tv:user' | |
eeeb4daa | 1818 | |
59ae15a5 PH |
1819 | def __init__(self, downloader=None): |
1820 | InfoExtractor.__init__(self, downloader) | |
eeeb4daa | 1821 | |
59ae15a5 PH |
1822 | def report_download_page(self, username, pagenum): |
1823 | """Report attempt to download user page.""" | |
1824 | self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' % | |
1825 | (self.IE_NAME, username, pagenum)) | |
eeeb4daa | 1826 | |
59ae15a5 PH |
1827 | def _real_extract(self, url): |
1828 | # Extract username | |
1829 | mobj = re.match(self._VALID_URL, url) | |
1830 | if mobj is None: | |
1831 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) | |
1832 | return | |
eeeb4daa | 1833 | |
59ae15a5 | 1834 | username = mobj.group(1) |
eeeb4daa | 1835 | |
59ae15a5 | 1836 | page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' |
eeeb4daa | 1837 | |
59ae15a5 | 1838 | request = compat_urllib_request.Request(url) |
eeeb4daa | 1839 | |
59ae15a5 PH |
1840 | try: |
1841 | page = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
1842 | mobj = re.search(r'data-users-id="([^"]+)"', page) | |
1843 | page_base = page_base % mobj.group(1) | |
1844 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1845 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) | |
1846 | return | |
eeeb4daa JCGS |
1847 | |
1848 | ||
59ae15a5 PH |
1849 | # Download video ids using BlipTV Ajax calls. Result size per |
1850 | # query is limited (currently to 12 videos) so we need to query | |
1851 | # page by page until there are no video ids - it means we got | |
1852 | # all of them. | |
eeeb4daa | 1853 | |
59ae15a5 PH |
1854 | video_ids = [] |
1855 | pagenum = 1 | |
eeeb4daa | 1856 | |
59ae15a5 PH |
1857 | while True: |
1858 | self.report_download_page(username, pagenum) | |
eeeb4daa | 1859 | |
59ae15a5 | 1860 | request = compat_urllib_request.Request( page_base + "&page=" + str(pagenum) ) |
eeeb4daa | 1861 | |
59ae15a5 PH |
1862 | try: |
1863 | page = compat_urllib_request.urlopen(request).read().decode('utf-8') | |
1864 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1865 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
1866 | return | |
eeeb4daa | 1867 | |
59ae15a5 PH |
1868 | # Extract video identifiers |
1869 | ids_in_page = [] | |
eeeb4daa | 1870 | |
59ae15a5 PH |
1871 | for mobj in re.finditer(r'href="/([^"]+)"', page): |
1872 | if mobj.group(1) not in ids_in_page: | |
1873 | ids_in_page.append(unescapeHTML(mobj.group(1))) | |
eeeb4daa | 1874 | |
59ae15a5 | 1875 | video_ids.extend(ids_in_page) |
eeeb4daa | 1876 | |
59ae15a5 PH |
1877 | # A little optimization - if current page is not |
1878 | # "full", ie. does not contain PAGE_SIZE video ids then | |
1879 | # we can assume that this page is the last one - there | |
1880 | # are no more ids on further pages - no need to query | |
1881 | # again. | |
eeeb4daa | 1882 | |
59ae15a5 PH |
1883 | if len(ids_in_page) < self._PAGE_SIZE: |
1884 | break | |
eeeb4daa | 1885 | |
59ae15a5 | 1886 | pagenum += 1 |
eeeb4daa | 1887 | |
59ae15a5 PH |
1888 | all_ids_count = len(video_ids) |
1889 | playliststart = self._downloader.params.get('playliststart', 1) - 1 | |
1890 | playlistend = self._downloader.params.get('playlistend', -1) | |
eeeb4daa | 1891 | |
59ae15a5 PH |
1892 | if playlistend == -1: |
1893 | video_ids = video_ids[playliststart:] | |
1894 | else: | |
1895 | video_ids = video_ids[playliststart:playlistend] | |
eeeb4daa | 1896 | |
59ae15a5 PH |
1897 | self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" % |
1898 | (self.IE_NAME, username, all_ids_count, len(video_ids))) | |
eeeb4daa | 1899 | |
59ae15a5 PH |
1900 | for video_id in video_ids: |
1901 | self._downloader.download([u'http://blip.tv/'+video_id]) | |
eeeb4daa JCGS |
1902 | |
1903 | ||
d77c3dfd | 1904 | class DepositFilesIE(InfoExtractor): |
59ae15a5 PH |
1905 | """Information extractor for depositfiles.com""" |
1906 | ||
1907 | _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' | |
1908 | IE_NAME = u'DepositFiles' | |
1909 | ||
1910 | def __init__(self, downloader=None): | |
1911 | InfoExtractor.__init__(self, downloader) | |
1912 | ||
1913 | def report_download_webpage(self, file_id): | |
1914 | """Report webpage download.""" | |
1915 | self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) | |
1916 | ||
1917 | def report_extraction(self, file_id): | |
1918 | """Report information extraction.""" | |
1919 | self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) | |
1920 | ||
1921 | def _real_extract(self, url): | |
1922 | file_id = url.split('/')[-1] | |
1923 | # Rebuild url in english locale | |
1924 | url = 'http://depositfiles.com/en/files/' + file_id | |
1925 | ||
1926 | # Retrieve file webpage with 'Free download' button pressed | |
1927 | free_download_indication = { 'gateway_result' : '1' } | |
1928 | request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication)) | |
1929 | try: | |
1930 | self.report_download_webpage(file_id) | |
1931 | webpage = compat_urllib_request.urlopen(request).read() | |
1932 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1933 | self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % compat_str(err)) | |
1934 | return | |
1935 | ||
1936 | # Search for the real file URL | |
1937 | mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage) | |
1938 | if (mobj is None) or (mobj.group(1) is None): | |
1939 | # Try to figure out reason of the error. | |
1940 | mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL) | |
1941 | if (mobj is not None) and (mobj.group(1) is not None): | |
1942 | restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() | |
1943 | self._downloader.trouble(u'ERROR: %s' % restriction_message) | |
1944 | else: | |
1945 | self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url) | |
1946 | return | |
1947 | ||
1948 | file_url = mobj.group(1) | |
1949 | file_extension = os.path.splitext(file_url)[1][1:] | |
1950 | ||
1951 | # Search for file title | |
1952 | mobj = re.search(r'<b title="(.*?)">', webpage) | |
1953 | if mobj is None: | |
1954 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1955 | return | |
1956 | file_title = mobj.group(1).decode('utf-8') | |
1957 | ||
1958 | return [{ | |
1959 | 'id': file_id.decode('utf-8'), | |
1960 | 'url': file_url.decode('utf-8'), | |
1961 | 'uploader': None, | |
1962 | 'upload_date': None, | |
1963 | 'title': file_title, | |
1964 | 'ext': file_extension.decode('utf-8'), | |
1965 | }] | |
d77c3dfd FV |
1966 | |
1967 | ||
1968 | class FacebookIE(InfoExtractor): | |
59ae15a5 PH |
1969 | """Information Extractor for Facebook""" |
1970 | ||
1971 | _WORKING = False | |
1972 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' | |
1973 | _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' | |
1974 | _NETRC_MACHINE = 'facebook' | |
1975 | _available_formats = ['video', 'highqual', 'lowqual'] | |
1976 | _video_extensions = { | |
1977 | 'video': 'mp4', | |
1978 | 'highqual': 'mp4', | |
1979 | 'lowqual': 'mp4', | |
1980 | } | |
1981 | IE_NAME = u'facebook' | |
1982 | ||
1983 | def __init__(self, downloader=None): | |
1984 | InfoExtractor.__init__(self, downloader) | |
1985 | ||
1986 | def _reporter(self, message): | |
1987 | """Add header and report message.""" | |
1988 | self._downloader.to_screen(u'[facebook] %s' % message) | |
1989 | ||
1990 | def report_login(self): | |
1991 | """Report attempt to log in.""" | |
1992 | self._reporter(u'Logging in') | |
1993 | ||
1994 | def report_video_webpage_download(self, video_id): | |
1995 | """Report attempt to download video webpage.""" | |
1996 | self._reporter(u'%s: Downloading video webpage' % video_id) | |
1997 | ||
1998 | def report_information_extraction(self, video_id): | |
1999 | """Report attempt to extract video information.""" | |
2000 | self._reporter(u'%s: Extracting video information' % video_id) | |
2001 | ||
2002 | def _parse_page(self, video_webpage): | |
2003 | """Extract video information from page""" | |
2004 | # General data | |
2005 | data = {'title': r'\("video_title", "(.*?)"\)', | |
2006 | 'description': r'<div class="datawrap">(.*?)</div>', | |
2007 | 'owner': r'\("video_owner_name", "(.*?)"\)', | |
2008 | 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)', | |
2009 | } | |
2010 | video_info = {} | |
2011 | for piece in data.keys(): | |
2012 | mobj = re.search(data[piece], video_webpage) | |
2013 | if mobj is not None: | |
2014 | video_info[piece] = compat_urllib_parse.unquote_plus(mobj.group(1).decode("unicode_escape")) | |
2015 | ||
2016 | # Video urls | |
2017 | video_urls = {} | |
2018 | for fmt in self._available_formats: | |
2019 | mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage) | |
2020 | if mobj is not None: | |
2021 | # URL is in a Javascript segment inside an escaped Unicode format within | |
2022 | # the generally utf-8 page | |
2023 | video_urls[fmt] = compat_urllib_parse.unquote_plus(mobj.group(1).decode("unicode_escape")) | |
2024 | video_info['video_urls'] = video_urls | |
2025 | ||
2026 | return video_info | |
2027 | ||
2028 | def _real_initialize(self): | |
2029 | if self._downloader is None: | |
2030 | return | |
2031 | ||
2032 | useremail = None | |
2033 | password = None | |
2034 | downloader_params = self._downloader.params | |
2035 | ||
2036 | # Attempt to use provided username and password or .netrc data | |
2037 | if downloader_params.get('username', None) is not None: | |
2038 | useremail = downloader_params['username'] | |
2039 | password = downloader_params['password'] | |
2040 | elif downloader_params.get('usenetrc', False): | |
2041 | try: | |
2042 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
2043 | if info is not None: | |
2044 | useremail = info[0] | |
2045 | password = info[2] | |
2046 | else: | |
2047 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
2048 | except (IOError, netrc.NetrcParseError) as err: | |
2049 | self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) | |
2050 | return | |
2051 | ||
2052 | if useremail is None: | |
2053 | return | |
2054 | ||
2055 | # Log in | |
2056 | login_form = { | |
2057 | 'email': useremail, | |
2058 | 'pass': password, | |
2059 | 'login': 'Log+In' | |
2060 | } | |
2061 | request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) | |
2062 | try: | |
2063 | self.report_login() | |
2064 | login_results = compat_urllib_request.urlopen(request).read() | |
2065 | if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: | |
2066 | self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') | |
2067 | return | |
2068 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2069 | self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err)) | |
2070 | return | |
2071 | ||
2072 | def _real_extract(self, url): | |
2073 | mobj = re.match(self._VALID_URL, url) | |
2074 | if mobj is None: | |
2075 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2076 | return | |
2077 | video_id = mobj.group('ID') | |
2078 | ||
2079 | # Get video webpage | |
2080 | self.report_video_webpage_download(video_id) | |
2081 | request = compat_urllib_request.Request('https://www.facebook.com/video/video.php?v=%s' % video_id) | |
2082 | try: | |
2083 | page = compat_urllib_request.urlopen(request) | |
2084 | video_webpage = page.read() | |
2085 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2086 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) | |
2087 | return | |
2088 | ||
2089 | # Start extracting information | |
2090 | self.report_information_extraction(video_id) | |
2091 | ||
2092 | # Extract information | |
2093 | video_info = self._parse_page(video_webpage) | |
2094 | ||
2095 | # uploader | |
2096 | if 'owner' not in video_info: | |
2097 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
2098 | return | |
2099 | video_uploader = video_info['owner'] | |
2100 | ||
2101 | # title | |
2102 | if 'title' not in video_info: | |
2103 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
2104 | return | |
2105 | video_title = video_info['title'] | |
2106 | video_title = video_title.decode('utf-8') | |
2107 | ||
2108 | # thumbnail image | |
2109 | if 'thumbnail' not in video_info: | |
2110 | self._downloader.trouble(u'WARNING: unable to extract video thumbnail') | |
2111 | video_thumbnail = '' | |
2112 | else: | |
2113 | video_thumbnail = video_info['thumbnail'] | |
2114 | ||
2115 | # upload date | |
2116 | upload_date = None | |
2117 | if 'upload_date' in video_info: | |
2118 | upload_time = video_info['upload_date'] | |
2119 | timetuple = email.utils.parsedate_tz(upload_time) | |
2120 | if timetuple is not None: | |
2121 | try: | |
2122 | upload_date = time.strftime('%Y%m%d', timetuple[0:9]) | |
2123 | except: | |
2124 | pass | |
2125 | ||
2126 | # description | |
2127 | video_description = video_info.get('description', 'No description available.') | |
2128 | ||
2129 | url_map = video_info['video_urls'] | |
1a2c3c0f | 2130 | if len(list(url_map.keys())) > 0: |
59ae15a5 PH |
2131 | # Decide which formats to download |
2132 | req_format = self._downloader.params.get('format', None) | |
2133 | format_limit = self._downloader.params.get('format_limit', None) | |
2134 | ||
2135 | if format_limit is not None and format_limit in self._available_formats: | |
2136 | format_list = self._available_formats[self._available_formats.index(format_limit):] | |
2137 | else: | |
2138 | format_list = self._available_formats | |
2139 | existing_formats = [x for x in format_list if x in url_map] | |
2140 | if len(existing_formats) == 0: | |
2141 | self._downloader.trouble(u'ERROR: no known formats available for video') | |
2142 | return | |
2143 | if req_format is None: | |
2144 | video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality | |
2145 | elif req_format == 'worst': | |
2146 | video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality | |
2147 | elif req_format == '-1': | |
2148 | video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats | |
2149 | else: | |
2150 | # Specific format | |
2151 | if req_format not in url_map: | |
2152 | self._downloader.trouble(u'ERROR: requested format not available') | |
2153 | return | |
2154 | video_url_list = [(req_format, url_map[req_format])] # Specific format | |
2155 | ||
2156 | results = [] | |
2157 | for format_param, video_real_url in video_url_list: | |
2158 | # Extension | |
2159 | video_extension = self._video_extensions.get(format_param, 'mp4') | |
2160 | ||
2161 | results.append({ | |
2162 | 'id': video_id.decode('utf-8'), | |
2163 | 'url': video_real_url.decode('utf-8'), | |
2164 | 'uploader': video_uploader.decode('utf-8'), | |
2165 | 'upload_date': upload_date, | |
2166 | 'title': video_title, | |
2167 | 'ext': video_extension.decode('utf-8'), | |
2168 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), | |
2169 | 'thumbnail': video_thumbnail.decode('utf-8'), | |
2170 | 'description': video_description.decode('utf-8'), | |
2171 | }) | |
2172 | return results | |
d77c3dfd FV |
2173 | |
2174 | class BlipTVIE(InfoExtractor): | |
59ae15a5 PH |
2175 | """Information extractor for blip.tv""" |
2176 | ||
2177 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' | |
2178 | _URL_EXT = r'^.*\.([a-z0-9]+)$' | |
2179 | IE_NAME = u'blip.tv' | |
2180 | ||
2181 | def report_extraction(self, file_id): | |
2182 | """Report information extraction.""" | |
2183 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) | |
2184 | ||
2185 | def report_direct_download(self, title): | |
2186 | """Report information extraction.""" | |
2187 | self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title)) | |
2188 | ||
2189 | def _real_extract(self, url): | |
2190 | mobj = re.match(self._VALID_URL, url) | |
2191 | if mobj is None: | |
2192 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2193 | return | |
2194 | ||
2195 | if '?' in url: | |
2196 | cchar = '&' | |
2197 | else: | |
2198 | cchar = '?' | |
2199 | json_url = url + cchar + 'skin=json&version=2&no_wrap=1' | |
55c05398 | 2200 | request = compat_urllib_request.Request(json_url) |
59ae15a5 PH |
2201 | self.report_extraction(mobj.group(1)) |
2202 | info = None | |
2203 | try: | |
2204 | urlh = compat_urllib_request.urlopen(request) | |
2205 | if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download | |
2206 | basename = url.split('/')[-1] | |
2207 | title,ext = os.path.splitext(basename) | |
2208 | title = title.decode('UTF-8') | |
2209 | ext = ext.replace('.', '') | |
2210 | self.report_direct_download(title) | |
2211 | info = { | |
2212 | 'id': title, | |
2213 | 'url': url, | |
2214 | 'uploader': None, | |
2215 | 'upload_date': None, | |
2216 | 'title': title, | |
2217 | 'ext': ext, | |
2218 | 'urlhandle': urlh | |
2219 | } | |
2220 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2221 | self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) | |
2222 | return | |
2223 | if info is None: # Regular URL | |
2224 | try: | |
55c05398 PH |
2225 | json_code_bytes = urlh.read() |
2226 | json_code = json_code_bytes.decode('utf-8') | |
59ae15a5 PH |
2227 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
2228 | self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % compat_str(err)) | |
2229 | return | |
2230 | ||
2231 | try: | |
2232 | json_data = json.loads(json_code) | |
2233 | if 'Post' in json_data: | |
2234 | data = json_data['Post'] | |
2235 | else: | |
2236 | data = json_data | |
2237 | ||
2238 | upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') | |
2239 | video_url = data['media']['url'] | |
2240 | umobj = re.match(self._URL_EXT, video_url) | |
2241 | if umobj is None: | |
2242 | raise ValueError('Can not determine filename extension') | |
2243 | ext = umobj.group(1) | |
2244 | ||
2245 | info = { | |
2246 | 'id': data['item_id'], | |
2247 | 'url': video_url, | |
2248 | 'uploader': data['display_name'], | |
2249 | 'upload_date': upload_date, | |
2250 | 'title': data['title'], | |
2251 | 'ext': ext, | |
2252 | 'format': data['media']['mimeType'], | |
2253 | 'thumbnail': data['thumbnailUrl'], | |
2254 | 'description': data['description'], | |
2255 | 'player_url': data['embedUrl'] | |
2256 | } | |
2257 | except (ValueError,KeyError) as err: | |
2258 | self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) | |
2259 | return | |
2260 | ||
2261 | std_headers['User-Agent'] = 'iTunes/10.6.1' | |
2262 | return [info] | |
d77c3dfd FV |
2263 | |
2264 | ||
2265 | class MyVideoIE(InfoExtractor): | |
59ae15a5 PH |
2266 | """Information Extractor for myvideo.de.""" |
2267 | ||
2268 | _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' | |
2269 | IE_NAME = u'myvideo' | |
2270 | ||
2271 | def __init__(self, downloader=None): | |
2272 | InfoExtractor.__init__(self, downloader) | |
cdb30764 | 2273 | |
59ae15a5 PH |
2274 | def report_download_webpage(self, video_id): |
2275 | """Report webpage download.""" | |
2276 | self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id) | |
2277 | ||
2278 | def report_extraction(self, video_id): | |
2279 | """Report information extraction.""" | |
2280 | self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id) | |
2281 | ||
2282 | def _real_extract(self,url): | |
2283 | mobj = re.match(self._VALID_URL, url) | |
2284 | if mobj is None: | |
2285 | self._download.trouble(u'ERROR: invalid URL: %s' % url) | |
2286 | return | |
2287 | ||
2288 | video_id = mobj.group(1) | |
2289 | ||
2290 | # Get video webpage | |
2291 | request = compat_urllib_request.Request('http://www.myvideo.de/watch/%s' % video_id) | |
2292 | try: | |
2293 | self.report_download_webpage(video_id) | |
93702113 | 2294 | webpage = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 PH |
2295 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
2296 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) | |
2297 | return | |
2298 | ||
2299 | self.report_extraction(video_id) | |
2300 | mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />', | |
2301 | webpage) | |
2302 | if mobj is None: | |
2303 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
2304 | return | |
2305 | video_url = mobj.group(1) + ('/%s.flv' % video_id) | |
2306 | ||
2307 | mobj = re.search('<title>([^<]+)</title>', webpage) | |
2308 | if mobj is None: | |
2309 | self._downloader.trouble(u'ERROR: unable to extract title') | |
2310 | return | |
2311 | ||
2312 | video_title = mobj.group(1) | |
2313 | ||
2314 | return [{ | |
2315 | 'id': video_id, | |
2316 | 'url': video_url, | |
2317 | 'uploader': None, | |
2318 | 'upload_date': None, | |
2319 | 'title': video_title, | |
2320 | 'ext': u'flv', | |
2321 | }] | |
d77c3dfd FV |
2322 | |
2323 | class ComedyCentralIE(InfoExtractor): | |
59ae15a5 PH |
2324 | """Information extractor for The Daily Show and Colbert Report """ |
2325 | ||
ca6849e6 | 2326 | # urls can be abbreviations like :thedailyshow or :colbert |
cdb30764 | 2327 | # urls for episodes like: |
ca6849e6 | 2328 | # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day |
2329 | # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news | |
cdb30764 | 2330 | # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524 |
ca6849e6 | 2331 | _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport) |
2332 | |(https?://)?(www\.)? | |
2333 | (?P<showname>thedailyshow|colbertnation)\.com/ | |
2334 | (full-episodes/(?P<episode>.*)| | |
2335 | (?P<clip> | |
2336 | (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) | |
2337 | |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))))) | |
cdb30764 | 2338 | $""" |
59ae15a5 PH |
2339 | IE_NAME = u'comedycentral' |
2340 | ||
2341 | _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] | |
2342 | ||
2343 | _video_extensions = { | |
2344 | '3500': 'mp4', | |
2345 | '2200': 'mp4', | |
2346 | '1700': 'mp4', | |
2347 | '1200': 'mp4', | |
2348 | '750': 'mp4', | |
2349 | '400': 'mp4', | |
2350 | } | |
2351 | _video_dimensions = { | |
2352 | '3500': '1280x720', | |
2353 | '2200': '960x540', | |
2354 | '1700': '768x432', | |
2355 | '1200': '640x360', | |
2356 | '750': '512x288', | |
2357 | '400': '384x216', | |
2358 | } | |
2359 | ||
ca6849e6 | 2360 | def suitable(self, url): |
2361 | """Receives a URL and returns True if suitable for this IE.""" | |
2362 | return re.match(self._VALID_URL, url, re.VERBOSE) is not None | |
2363 | ||
59ae15a5 PH |
2364 | def report_extraction(self, episode_id): |
2365 | self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) | |
2366 | ||
2367 | def report_config_download(self, episode_id): | |
2368 | self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id) | |
2369 | ||
2370 | def report_index_download(self, episode_id): | |
2371 | self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) | |
2372 | ||
2373 | def report_player_url(self, episode_id): | |
2374 | self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id) | |
2375 | ||
2376 | ||
2377 | def _print_formats(self, formats): | |
2378 | print('Available formats:') | |
2379 | for x in formats: | |
2380 | print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???'))) | |
2381 | ||
2382 | ||
2383 | def _real_extract(self, url): | |
ca6849e6 | 2384 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
59ae15a5 PH |
2385 | if mobj is None: |
2386 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2387 | return | |
2388 | ||
2389 | if mobj.group('shortname'): | |
2390 | if mobj.group('shortname') in ('tds', 'thedailyshow'): | |
2391 | url = u'http://www.thedailyshow.com/full-episodes/' | |
2392 | else: | |
2393 | url = u'http://www.colbertnation.com/full-episodes/' | |
ca6849e6 | 2394 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
59ae15a5 PH |
2395 | assert mobj is not None |
2396 | ||
ca6849e6 | 2397 | if mobj.group('clip'): |
2398 | if mobj.group('showname') == 'thedailyshow': | |
2399 | epTitle = mobj.group('tdstitle') | |
2400 | else: | |
2401 | epTitle = mobj.group('cntitle') | |
2402 | dlNewest = False | |
59ae15a5 | 2403 | else: |
ca6849e6 | 2404 | dlNewest = not mobj.group('episode') |
2405 | if dlNewest: | |
2406 | epTitle = mobj.group('showname') | |
2407 | else: | |
2408 | epTitle = mobj.group('episode') | |
59ae15a5 PH |
2409 | |
2410 | req = compat_urllib_request.Request(url) | |
2411 | self.report_extraction(epTitle) | |
2412 | try: | |
2413 | htmlHandle = compat_urllib_request.urlopen(req) | |
2414 | html = htmlHandle.read() | |
2415 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2416 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) | |
2417 | return | |
2418 | if dlNewest: | |
2419 | url = htmlHandle.geturl() | |
ca6849e6 | 2420 | mobj = re.match(self._VALID_URL, url, re.VERBOSE) |
59ae15a5 PH |
2421 | if mobj is None: |
2422 | self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url) | |
2423 | return | |
2424 | if mobj.group('episode') == '': | |
2425 | self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url) | |
2426 | return | |
2427 | epTitle = mobj.group('episode') | |
2428 | ||
ca6849e6 | 2429 | mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', html) |
59ae15a5 PH |
2430 | |
2431 | if len(mMovieParams) == 0: | |
2432 | # The Colbert Report embeds the information in a without | |
2433 | # a URL prefix; so extract the alternate reference | |
2434 | # and then add the URL prefix manually. | |
2435 | ||
ca6849e6 | 2436 | altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', html) |
59ae15a5 PH |
2437 | if len(altMovieParams) == 0: |
2438 | self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) | |
2439 | return | |
2440 | else: | |
2441 | mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] | |
cdb30764 | 2442 | |
59ae15a5 PH |
2443 | playerUrl_raw = mMovieParams[0][0] |
2444 | self.report_player_url(epTitle) | |
2445 | try: | |
2446 | urlHandle = compat_urllib_request.urlopen(playerUrl_raw) | |
2447 | playerUrl = urlHandle.geturl() | |
2448 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2449 | self._downloader.trouble(u'ERROR: unable to find out player URL: ' + compat_str(err)) | |
2450 | return | |
2451 | ||
2452 | uri = mMovieParams[0][1] | |
2453 | indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri}) | |
2454 | self.report_index_download(epTitle) | |
2455 | try: | |
2456 | indexXml = compat_urllib_request.urlopen(indexUrl).read() | |
2457 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2458 | self._downloader.trouble(u'ERROR: unable to download episode index: ' + compat_str(err)) | |
2459 | return | |
2460 | ||
2461 | results = [] | |
2462 | ||
2463 | idoc = xml.etree.ElementTree.fromstring(indexXml) | |
2464 | itemEls = idoc.findall('.//item') | |
2465 | for itemEl in itemEls: | |
2466 | mediaId = itemEl.findall('./guid')[0].text | |
2467 | shortMediaId = mediaId.split(':')[-1] | |
2468 | showId = mediaId.split(':')[-2].replace('.com', '') | |
2469 | officialTitle = itemEl.findall('./title')[0].text | |
2470 | officialDate = itemEl.findall('./pubDate')[0].text | |
2471 | ||
2472 | configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + | |
2473 | compat_urllib_parse.urlencode({'uri': mediaId})) | |
2474 | configReq = compat_urllib_request.Request(configUrl) | |
2475 | self.report_config_download(epTitle) | |
2476 | try: | |
2477 | configXml = compat_urllib_request.urlopen(configReq).read() | |
2478 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2479 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) | |
2480 | return | |
2481 | ||
2482 | cdoc = xml.etree.ElementTree.fromstring(configXml) | |
2483 | turls = [] | |
2484 | for rendition in cdoc.findall('.//rendition'): | |
2485 | finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) | |
2486 | turls.append(finfo) | |
2487 | ||
2488 | if len(turls) == 0: | |
2489 | self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found') | |
2490 | continue | |
cdb30764 | 2491 | |
59ae15a5 PH |
2492 | if self._downloader.params.get('listformats', None): |
2493 | self._print_formats([i[0] for i in turls]) | |
2494 | return | |
2495 | ||
2496 | # For now, just pick the highest bitrate | |
2497 | format,video_url = turls[-1] | |
2498 | ||
2499 | # Get the format arg from the arg stream | |
2500 | req_format = self._downloader.params.get('format', None) | |
2501 | ||
2502 | # Select format if we can find one | |
2503 | for f,v in turls: | |
2504 | if f == req_format: | |
2505 | format, video_url = f, v | |
2506 | break | |
2507 | ||
2508 | # Patch to download from alternative CDN, which does not | |
2509 | # break on current RTMPDump builds | |
2510 | broken_cdn = "rtmpe://viacomccstrmfs.fplive.net/viacomccstrm/gsp.comedystor/" | |
2511 | better_cdn = "rtmpe://cp10740.edgefcs.net/ondemand/mtvnorigin/gsp.comedystor/" | |
2512 | ||
2513 | if video_url.startswith(broken_cdn): | |
2514 | video_url = video_url.replace(broken_cdn, better_cdn) | |
2515 | ||
2516 | effTitle = showId + u'-' + epTitle | |
2517 | info = { | |
2518 | 'id': shortMediaId, | |
2519 | 'url': video_url, | |
2520 | 'uploader': showId, | |
2521 | 'upload_date': officialDate, | |
2522 | 'title': effTitle, | |
2523 | 'ext': 'mp4', | |
2524 | 'format': format, | |
2525 | 'thumbnail': None, | |
2526 | 'description': officialTitle, | |
2527 | 'player_url': None #playerUrl | |
2528 | } | |
2529 | ||
2530 | results.append(info) | |
cdb30764 | 2531 | |
59ae15a5 | 2532 | return results |
d77c3dfd FV |
2533 | |
2534 | ||
2535 | class EscapistIE(InfoExtractor): | |
59ae15a5 PH |
2536 | """Information extractor for The Escapist """ |
2537 | ||
2538 | _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$' | |
2539 | IE_NAME = u'escapist' | |
2540 | ||
2541 | def report_extraction(self, showName): | |
2542 | self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName) | |
2543 | ||
2544 | def report_config_download(self, showName): | |
2545 | self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName) | |
2546 | ||
2547 | def _real_extract(self, url): | |
2548 | mobj = re.match(self._VALID_URL, url) | |
2549 | if mobj is None: | |
2550 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2551 | return | |
2552 | showName = mobj.group('showname') | |
2553 | videoId = mobj.group('episode') | |
2554 | ||
2555 | self.report_extraction(showName) | |
2556 | try: | |
2557 | webPage = compat_urllib_request.urlopen(url) | |
2558 | webPageBytes = webPage.read() | |
2559 | m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type']) | |
2560 | webPage = webPageBytes.decode(m.group(1) if m else 'utf-8') | |
2561 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2562 | self._downloader.trouble(u'ERROR: unable to download webpage: ' + compat_str(err)) | |
2563 | return | |
2564 | ||
2565 | descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) | |
2566 | description = unescapeHTML(descMatch.group(1)) | |
2567 | imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) | |
2568 | imgUrl = unescapeHTML(imgMatch.group(1)) | |
2569 | playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage) | |
2570 | playerUrl = unescapeHTML(playerUrlMatch.group(1)) | |
2571 | configUrlMatch = re.search('config=(.*)$', playerUrl) | |
2572 | configUrl = compat_urllib_parse.unquote(configUrlMatch.group(1)) | |
2573 | ||
2574 | self.report_config_download(showName) | |
2575 | try: | |
93702113 FV |
2576 | configJSON = compat_urllib_request.urlopen(configUrl) |
2577 | m = re.match(r'text/html; charset="?([^"]+)"?', configJSON.headers['Content-Type']) | |
2578 | configJSON = configJSON.read().decode(m.group(1) if m else 'utf-8') | |
59ae15a5 PH |
2579 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
2580 | self._downloader.trouble(u'ERROR: unable to download configuration: ' + compat_str(err)) | |
2581 | return | |
2582 | ||
2583 | # Technically, it's JavaScript, not JSON | |
2584 | configJSON = configJSON.replace("'", '"') | |
2585 | ||
2586 | try: | |
2587 | config = json.loads(configJSON) | |
2588 | except (ValueError,) as err: | |
2589 | self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + compat_str(err)) | |
2590 | return | |
2591 | ||
2592 | playlist = config['playlist'] | |
2593 | videoUrl = playlist[1]['url'] | |
2594 | ||
2595 | info = { | |
2596 | 'id': videoId, | |
2597 | 'url': videoUrl, | |
2598 | 'uploader': showName, | |
2599 | 'upload_date': None, | |
2600 | 'title': showName, | |
2601 | 'ext': 'flv', | |
2602 | 'thumbnail': imgUrl, | |
2603 | 'description': description, | |
2604 | 'player_url': playerUrl, | |
2605 | } | |
2606 | ||
2607 | return [info] | |
d77c3dfd FV |
2608 | |
2609 | ||
2610 | class CollegeHumorIE(InfoExtractor): | |
59ae15a5 PH |
2611 | """Information extractor for collegehumor.com""" |
2612 | ||
0eb0faa2 | 2613 | _WORKING = False |
59ae15a5 PH |
2614 | _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$' |
2615 | IE_NAME = u'collegehumor' | |
2616 | ||
799c0763 | 2617 | def report_manifest(self, video_id): |
59ae15a5 | 2618 | """Report information extraction.""" |
799c0763 | 2619 | self._downloader.to_screen(u'[%s] %s: Downloading XML manifest' % (self.IE_NAME, video_id)) |
59ae15a5 PH |
2620 | |
2621 | def report_extraction(self, video_id): | |
2622 | """Report information extraction.""" | |
2623 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
2624 | ||
2625 | def _real_extract(self, url): | |
2626 | mobj = re.match(self._VALID_URL, url) | |
2627 | if mobj is None: | |
2628 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2629 | return | |
2630 | video_id = mobj.group('videoid') | |
2631 | ||
59ae15a5 PH |
2632 | info = { |
2633 | 'id': video_id, | |
59ae15a5 PH |
2634 | 'uploader': None, |
2635 | 'upload_date': None, | |
2636 | } | |
2637 | ||
2638 | self.report_extraction(video_id) | |
799c0763 | 2639 | xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id |
59ae15a5 PH |
2640 | try: |
2641 | metaXml = compat_urllib_request.urlopen(xmlUrl).read() | |
2642 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2643 | self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err)) | |
2644 | return | |
2645 | ||
2646 | mdoc = xml.etree.ElementTree.fromstring(metaXml) | |
2647 | try: | |
2648 | videoNode = mdoc.findall('./video')[0] | |
2649 | info['description'] = videoNode.findall('./description')[0].text | |
2650 | info['title'] = videoNode.findall('./caption')[0].text | |
59ae15a5 | 2651 | info['thumbnail'] = videoNode.findall('./thumbnail')[0].text |
799c0763 | 2652 | manifest_url = videoNode.findall('./file')[0].text |
59ae15a5 PH |
2653 | except IndexError: |
2654 | self._downloader.trouble(u'\nERROR: Invalid metadata XML file') | |
2655 | return | |
2656 | ||
799c0763 PH |
2657 | manifest_url += '?hdcore=2.10.3' |
2658 | self.report_manifest(video_id) | |
2659 | try: | |
2660 | manifestXml = compat_urllib_request.urlopen(manifest_url).read() | |
2661 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2662 | self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err)) | |
2663 | return | |
2664 | ||
2665 | adoc = xml.etree.ElementTree.fromstring(manifestXml) | |
2666 | try: | |
2667 | media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] | |
2668 | node_id = media_node.attrib['url'] | |
2669 | video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text | |
2670 | except IndexError as err: | |
2671 | self._downloader.trouble(u'\nERROR: Invalid manifest file') | |
2672 | return | |
2673 | ||
2674 | url_pr = compat_urllib_parse_urlparse(manifest_url) | |
2675 | url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1' | |
2676 | ||
2677 | info['url'] = url | |
2678 | info['ext'] = 'f4f' | |
59ae15a5 | 2679 | return [info] |
d77c3dfd FV |
2680 | |
2681 | ||
2682 | class XVideosIE(InfoExtractor): | |
59ae15a5 | 2683 | """Information extractor for xvideos.com""" |
d77c3dfd | 2684 | |
59ae15a5 PH |
2685 | _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' |
2686 | IE_NAME = u'xvideos' | |
d77c3dfd | 2687 | |
59ae15a5 PH |
2688 | def report_webpage(self, video_id): |
2689 | """Report information extraction.""" | |
2690 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
d77c3dfd | 2691 | |
59ae15a5 PH |
2692 | def report_extraction(self, video_id): |
2693 | """Report information extraction.""" | |
2694 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
d77c3dfd | 2695 | |
59ae15a5 PH |
2696 | def _real_extract(self, url): |
2697 | mobj = re.match(self._VALID_URL, url) | |
2698 | if mobj is None: | |
2699 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2700 | return | |
8588a86f | 2701 | video_id = mobj.group(1) |
d77c3dfd | 2702 | |
59ae15a5 | 2703 | self.report_webpage(video_id) |
d77c3dfd | 2704 | |
59ae15a5 PH |
2705 | request = compat_urllib_request.Request(r'http://www.xvideos.com/video' + video_id) |
2706 | try: | |
8588a86f PH |
2707 | webpage_bytes = compat_urllib_request.urlopen(request).read() |
2708 | webpage = webpage_bytes.decode('utf-8', 'replace') | |
59ae15a5 PH |
2709 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
2710 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) | |
2711 | return | |
d77c3dfd | 2712 | |
59ae15a5 | 2713 | self.report_extraction(video_id) |
d77c3dfd FV |
2714 | |
2715 | ||
59ae15a5 PH |
2716 | # Extract video URL |
2717 | mobj = re.search(r'flv_url=(.+?)&', webpage) | |
2718 | if mobj is None: | |
2719 | self._downloader.trouble(u'ERROR: unable to extract video url') | |
2720 | return | |
8588a86f | 2721 | video_url = compat_urllib_parse.unquote(mobj.group(1)) |
d77c3dfd FV |
2722 | |
2723 | ||
59ae15a5 PH |
2724 | # Extract title |
2725 | mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage) | |
2726 | if mobj is None: | |
2727 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
2728 | return | |
8588a86f | 2729 | video_title = mobj.group(1) |
d77c3dfd FV |
2730 | |
2731 | ||
59ae15a5 PH |
2732 | # Extract video thumbnail |
2733 | 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) | |
2734 | if mobj is None: | |
2735 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
2736 | return | |
8588a86f | 2737 | video_thumbnail = mobj.group(0) |
d77c3dfd | 2738 | |
59ae15a5 PH |
2739 | info = { |
2740 | 'id': video_id, | |
2741 | 'url': video_url, | |
2742 | 'uploader': None, | |
2743 | 'upload_date': None, | |
2744 | 'title': video_title, | |
2745 | 'ext': 'flv', | |
2746 | 'thumbnail': video_thumbnail, | |
2747 | 'description': None, | |
2748 | } | |
d77c3dfd | 2749 | |
59ae15a5 | 2750 | return [info] |
d77c3dfd FV |
2751 | |
2752 | ||
2753 | class SoundcloudIE(InfoExtractor): | |
59ae15a5 PH |
2754 | """Information extractor for soundcloud.com |
2755 | To access the media, the uid of the song and a stream token | |
2756 | must be extracted from the page source and the script must make | |
2757 | a request to media.soundcloud.com/crossdomain.xml. Then | |
2758 | the media can be grabbed by requesting from an url composed | |
2759 | of the stream token and uid | |
2760 | """ | |
2761 | ||
2762 | _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)' | |
2763 | IE_NAME = u'soundcloud' | |
2764 | ||
2765 | def __init__(self, downloader=None): | |
2766 | InfoExtractor.__init__(self, downloader) | |
2767 | ||
8fd3afd5 | 2768 | def report_resolve(self, video_id): |
59ae15a5 | 2769 | """Report information extraction.""" |
8fd3afd5 | 2770 | self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id)) |
59ae15a5 PH |
2771 | |
2772 | def report_extraction(self, video_id): | |
2773 | """Report information extraction.""" | |
8fd3afd5 | 2774 | self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id)) |
59ae15a5 PH |
2775 | |
2776 | def _real_extract(self, url): | |
2777 | mobj = re.match(self._VALID_URL, url) | |
2778 | if mobj is None: | |
2779 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2780 | return | |
2781 | ||
2782 | # extract uploader (which is in the url) | |
15c8d833 | 2783 | uploader = mobj.group(1) |
59ae15a5 | 2784 | # extract simple title (uploader + slug of song title) |
15c8d833 | 2785 | slug_title = mobj.group(2) |
59ae15a5 PH |
2786 | simple_title = uploader + u'-' + slug_title |
2787 | ||
8fd3afd5 | 2788 | self.report_resolve('%s/%s' % (uploader, slug_title)) |
59ae15a5 | 2789 | |
8fd3afd5 PH |
2790 | url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title) |
2791 | resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28' | |
2792 | request = compat_urllib_request.Request(resolv_url) | |
59ae15a5 | 2793 | try: |
8fd3afd5 PH |
2794 | info_json_bytes = compat_urllib_request.urlopen(request).read() |
2795 | info_json = info_json_bytes.decode('utf-8') | |
59ae15a5 PH |
2796 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
2797 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) | |
2798 | return | |
2799 | ||
8fd3afd5 PH |
2800 | info = json.loads(info_json) |
2801 | video_id = info['id'] | |
59ae15a5 PH |
2802 | self.report_extraction('%s/%s' % (uploader, slug_title)) |
2803 | ||
8fd3afd5 | 2804 | streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28' |
c7214f9a | 2805 | request = compat_urllib_request.Request(streams_url) |
8fd3afd5 PH |
2806 | try: |
2807 | stream_json_bytes = compat_urllib_request.urlopen(request).read() | |
2808 | stream_json = stream_json_bytes.decode('utf-8') | |
2809 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2810 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) | |
b4cd069d | 2811 | return |
59ae15a5 | 2812 | |
8fd3afd5 | 2813 | streams = json.loads(stream_json) |
c7214f9a | 2814 | mediaURL = streams['http_mp3_128_url'] |
59ae15a5 PH |
2815 | |
2816 | return [{ | |
c7214f9a | 2817 | 'id': info['id'], |
59ae15a5 | 2818 | 'url': mediaURL, |
c7214f9a PH |
2819 | 'uploader': info['user']['username'], |
2820 | 'upload_date': info['created_at'], | |
2821 | 'title': info['title'], | |
59ae15a5 | 2822 | 'ext': u'mp3', |
c7214f9a | 2823 | 'description': info['description'], |
59ae15a5 | 2824 | }] |
d77c3dfd FV |
2825 | |
2826 | ||
2827 | class InfoQIE(InfoExtractor): | |
59ae15a5 PH |
2828 | """Information extractor for infoq.com""" |
2829 | ||
2830 | _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' | |
2831 | IE_NAME = u'infoq' | |
2832 | ||
2833 | def report_webpage(self, video_id): | |
2834 | """Report information extraction.""" | |
2835 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
2836 | ||
2837 | def report_extraction(self, video_id): | |
2838 | """Report information extraction.""" | |
2839 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
2840 | ||
2841 | def _real_extract(self, url): | |
2842 | mobj = re.match(self._VALID_URL, url) | |
2843 | if mobj is None: | |
2844 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2845 | return | |
2846 | ||
2847 | self.report_webpage(url) | |
2848 | ||
2849 | request = compat_urllib_request.Request(url) | |
2850 | try: | |
2851 | webpage = compat_urllib_request.urlopen(request).read() | |
2852 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2853 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) | |
2854 | return | |
2855 | ||
2856 | self.report_extraction(url) | |
2857 | ||
2858 | ||
2859 | # Extract video URL | |
2860 | mobj = re.search(r"jsclassref='([^']*)'", webpage) | |
2861 | if mobj is None: | |
2862 | self._downloader.trouble(u'ERROR: unable to extract video url') | |
2863 | return | |
2864 | video_url = 'rtmpe://video.infoq.com/cfx/st/' + compat_urllib_parse.unquote(mobj.group(1).decode('base64')) | |
2865 | ||
2866 | ||
2867 | # Extract title | |
2868 | mobj = re.search(r'contentTitle = "(.*?)";', webpage) | |
2869 | if mobj is None: | |
2870 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
2871 | return | |
2872 | video_title = mobj.group(1).decode('utf-8') | |
2873 | ||
2874 | # Extract description | |
2875 | video_description = u'No description available.' | |
2876 | mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage) | |
2877 | if mobj is not None: | |
2878 | video_description = mobj.group(1).decode('utf-8') | |
2879 | ||
2880 | video_filename = video_url.split('/')[-1] | |
2881 | video_id, extension = video_filename.split('.') | |
2882 | ||
2883 | info = { | |
2884 | 'id': video_id, | |
2885 | 'url': video_url, | |
2886 | 'uploader': None, | |
2887 | 'upload_date': None, | |
2888 | 'title': video_title, | |
2889 | 'ext': extension, # Extension is always(?) mp4, but seems to be flv | |
2890 | 'thumbnail': None, | |
2891 | 'description': video_description, | |
2892 | } | |
2893 | ||
2894 | return [info] | |
d77c3dfd FV |
2895 | |
2896 | class MixcloudIE(InfoExtractor): | |
59ae15a5 | 2897 | """Information extractor for www.mixcloud.com""" |
93702113 FV |
2898 | |
2899 | _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/ | |
59ae15a5 PH |
2900 | _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' |
2901 | IE_NAME = u'mixcloud' | |
2902 | ||
2903 | def __init__(self, downloader=None): | |
2904 | InfoExtractor.__init__(self, downloader) | |
2905 | ||
2906 | def report_download_json(self, file_id): | |
2907 | """Report JSON download.""" | |
2908 | self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME) | |
2909 | ||
2910 | def report_extraction(self, file_id): | |
2911 | """Report information extraction.""" | |
2912 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) | |
2913 | ||
2914 | def get_urls(self, jsonData, fmt, bitrate='best'): | |
2915 | """Get urls from 'audio_formats' section in json""" | |
2916 | file_url = None | |
2917 | try: | |
2918 | bitrate_list = jsonData[fmt] | |
2919 | if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list: | |
2920 | bitrate = max(bitrate_list) # select highest | |
2921 | ||
2922 | url_list = jsonData[fmt][bitrate] | |
2923 | except TypeError: # we have no bitrate info. | |
2924 | url_list = jsonData[fmt] | |
2925 | return url_list | |
2926 | ||
2927 | def check_urls(self, url_list): | |
2928 | """Returns 1st active url from list""" | |
2929 | for url in url_list: | |
2930 | try: | |
2931 | compat_urllib_request.urlopen(url) | |
2932 | return url | |
2933 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2934 | url = None | |
2935 | ||
2936 | return None | |
2937 | ||
2938 | def _print_formats(self, formats): | |
2939 | print('Available formats:') | |
2940 | for fmt in formats.keys(): | |
2941 | for b in formats[fmt]: | |
2942 | try: | |
2943 | ext = formats[fmt][b][0] | |
2944 | print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])) | |
2945 | except TypeError: # we have no bitrate info | |
2946 | ext = formats[fmt][0] | |
2947 | print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])) | |
2948 | break | |
2949 | ||
2950 | def _real_extract(self, url): | |
2951 | mobj = re.match(self._VALID_URL, url) | |
2952 | if mobj is None: | |
2953 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2954 | return | |
2955 | # extract uploader & filename from url | |
2956 | uploader = mobj.group(1).decode('utf-8') | |
2957 | file_id = uploader + "-" + mobj.group(2).decode('utf-8') | |
2958 | ||
2959 | # construct API request | |
2960 | file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json' | |
2961 | # retrieve .json file with links to files | |
2962 | request = compat_urllib_request.Request(file_url) | |
2963 | try: | |
2964 | self.report_download_json(file_url) | |
2965 | jsonData = compat_urllib_request.urlopen(request).read() | |
2966 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
2967 | self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % compat_str(err)) | |
2968 | return | |
2969 | ||
2970 | # parse JSON | |
2971 | json_data = json.loads(jsonData) | |
2972 | player_url = json_data['player_swf_url'] | |
2973 | formats = dict(json_data['audio_formats']) | |
2974 | ||
2975 | req_format = self._downloader.params.get('format', None) | |
2976 | bitrate = None | |
2977 | ||
2978 | if self._downloader.params.get('listformats', None): | |
2979 | self._print_formats(formats) | |
2980 | return | |
2981 | ||
2982 | if req_format is None or req_format == 'best': | |
2983 | for format_param in formats.keys(): | |
2984 | url_list = self.get_urls(formats, format_param) | |
2985 | # check urls | |
2986 | file_url = self.check_urls(url_list) | |
2987 | if file_url is not None: | |
2988 | break # got it! | |
2989 | else: | |
1a2c3c0f | 2990 | if req_format not in list(formats.keys()): |
59ae15a5 PH |
2991 | self._downloader.trouble(u'ERROR: format is not available') |
2992 | return | |
2993 | ||
2994 | url_list = self.get_urls(formats, req_format) | |
2995 | file_url = self.check_urls(url_list) | |
2996 | format_param = req_format | |
2997 | ||
2998 | return [{ | |
2999 | 'id': file_id.decode('utf-8'), | |
3000 | 'url': file_url.decode('utf-8'), | |
3001 | 'uploader': uploader.decode('utf-8'), | |
3002 | 'upload_date': None, | |
3003 | 'title': json_data['name'], | |
3004 | 'ext': file_url.split('.')[-1].decode('utf-8'), | |
3005 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), | |
3006 | 'thumbnail': json_data['thumbnail_url'], | |
3007 | 'description': json_data['description'], | |
3008 | 'player_url': player_url.decode('utf-8'), | |
3009 | }] | |
d77c3dfd FV |
3010 | |
3011 | class StanfordOpenClassroomIE(InfoExtractor): | |
59ae15a5 PH |
3012 | """Information extractor for Stanford's Open ClassRoom""" |
3013 | ||
3014 | _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' | |
3015 | IE_NAME = u'stanfordoc' | |
3016 | ||
3017 | def report_download_webpage(self, objid): | |
3018 | """Report information extraction.""" | |
3019 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid)) | |
3020 | ||
3021 | def report_extraction(self, video_id): | |
3022 | """Report information extraction.""" | |
3023 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3024 | ||
3025 | def _real_extract(self, url): | |
3026 | mobj = re.match(self._VALID_URL, url) | |
3027 | if mobj is None: | |
3028 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3029 | return | |
3030 | ||
3031 | if mobj.group('course') and mobj.group('video'): # A specific video | |
3032 | course = mobj.group('course') | |
3033 | video = mobj.group('video') | |
3034 | info = { | |
3035 | 'id': course + '_' + video, | |
3036 | 'uploader': None, | |
3037 | 'upload_date': None, | |
3038 | } | |
3039 | ||
3040 | self.report_extraction(info['id']) | |
3041 | baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' | |
3042 | xmlUrl = baseUrl + video + '.xml' | |
3043 | try: | |
3044 | metaXml = compat_urllib_request.urlopen(xmlUrl).read() | |
3045 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
3046 | self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err)) | |
3047 | return | |
3048 | mdoc = xml.etree.ElementTree.fromstring(metaXml) | |
3049 | try: | |
3050 | info['title'] = mdoc.findall('./title')[0].text | |
3051 | info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text | |
3052 | except IndexError: | |
3053 | self._downloader.trouble(u'\nERROR: Invalid metadata XML file') | |
3054 | return | |
3055 | info['ext'] = info['url'].rpartition('.')[2] | |
3056 | return [info] | |
3057 | elif mobj.group('course'): # A course page | |
3058 | course = mobj.group('course') | |
3059 | info = { | |
3060 | 'id': course, | |
3061 | 'type': 'playlist', | |
3062 | 'uploader': None, | |
3063 | 'upload_date': None, | |
3064 | } | |
3065 | ||
3066 | self.report_download_webpage(info['id']) | |
3067 | try: | |
3068 | coursepage = compat_urllib_request.urlopen(url).read() | |
3069 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
3070 | self._downloader.trouble(u'ERROR: unable to download course info page: ' + compat_str(err)) | |
3071 | return | |
3072 | ||
3073 | m = re.search('<h1>([^<]+)</h1>', coursepage) | |
3074 | if m: | |
3075 | info['title'] = unescapeHTML(m.group(1)) | |
3076 | else: | |
3077 | info['title'] = info['id'] | |
3078 | ||
3079 | m = re.search('<description>([^<]+)</description>', coursepage) | |
3080 | if m: | |
3081 | info['description'] = unescapeHTML(m.group(1)) | |
3082 | ||
3083 | links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) | |
3084 | info['list'] = [ | |
3085 | { | |
3086 | 'type': 'reference', | |
3087 | 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), | |
3088 | } | |
3089 | for vpage in links] | |
3090 | results = [] | |
3091 | for entry in info['list']: | |
3092 | assert entry['type'] == 'reference' | |
3093 | results += self.extract(entry['url']) | |
3094 | return results | |
cdb30764 | 3095 | |
59ae15a5 PH |
3096 | else: # Root page |
3097 | info = { | |
3098 | 'id': 'Stanford OpenClassroom', | |
3099 | 'type': 'playlist', | |
3100 | 'uploader': None, | |
3101 | 'upload_date': None, | |
3102 | } | |
3103 | ||
3104 | self.report_download_webpage(info['id']) | |
3105 | rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' | |
3106 | try: | |
3107 | rootpage = compat_urllib_request.urlopen(rootURL).read() | |
3108 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
3109 | self._downloader.trouble(u'ERROR: unable to download course info page: ' + compat_str(err)) | |
3110 | return | |
3111 | ||
3112 | info['title'] = info['id'] | |
3113 | ||
3114 | links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage)) | |
3115 | info['list'] = [ | |
3116 | { | |
3117 | 'type': 'reference', | |
3118 | 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), | |
3119 | } | |
3120 | for cpage in links] | |
3121 | ||
3122 | results = [] | |
3123 | for entry in info['list']: | |
3124 | assert entry['type'] == 'reference' | |
3125 | results += self.extract(entry['url']) | |
3126 | return results | |
d77c3dfd FV |
3127 | |
3128 | class MTVIE(InfoExtractor): | |
59ae15a5 PH |
3129 | """Information extractor for MTV.com""" |
3130 | ||
3131 | _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$' | |
3132 | IE_NAME = u'mtv' | |
3133 | ||
3134 | def report_webpage(self, video_id): | |
3135 | """Report information extraction.""" | |
3136 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
3137 | ||
3138 | def report_extraction(self, video_id): | |
3139 | """Report information extraction.""" | |
3140 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3141 | ||
3142 | def _real_extract(self, url): | |
3143 | mobj = re.match(self._VALID_URL, url) | |
3144 | if mobj is None: | |
3145 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3146 | return | |
3147 | if not mobj.group('proto'): | |
3148 | url = 'http://' + url | |
3149 | video_id = mobj.group('videoid') | |
3150 | self.report_webpage(video_id) | |
3151 | ||
3152 | request = compat_urllib_request.Request(url) | |
3153 | try: | |
3154 | webpage = compat_urllib_request.urlopen(request).read() | |
3155 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
3156 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) | |
3157 | return | |
3158 | ||
3159 | mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage) | |
3160 | if mobj is None: | |
3161 | self._downloader.trouble(u'ERROR: unable to extract song name') | |
3162 | return | |
3163 | song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1')) | |
3164 | mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage) | |
3165 | if mobj is None: | |
3166 | self._downloader.trouble(u'ERROR: unable to extract performer') | |
3167 | return | |
3168 | performer = unescapeHTML(mobj.group(1).decode('iso-8859-1')) | |
cdb30764 | 3169 | video_title = performer + ' - ' + song_name |
59ae15a5 PH |
3170 | |
3171 | mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage) | |
3172 | if mobj is None: | |
3173 | self._downloader.trouble(u'ERROR: unable to mtvn_uri') | |
3174 | return | |
3175 | mtvn_uri = mobj.group(1) | |
3176 | ||
3177 | mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage) | |
3178 | if mobj is None: | |
3179 | self._downloader.trouble(u'ERROR: unable to extract content id') | |
3180 | return | |
3181 | content_id = mobj.group(1) | |
3182 | ||
3183 | 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 | |
3184 | self.report_extraction(video_id) | |
3185 | request = compat_urllib_request.Request(videogen_url) | |
3186 | try: | |
3187 | metadataXml = compat_urllib_request.urlopen(request).read() | |
3188 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
3189 | self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % compat_str(err)) | |
3190 | return | |
3191 | ||
3192 | mdoc = xml.etree.ElementTree.fromstring(metadataXml) | |
3193 | renditions = mdoc.findall('.//rendition') | |
3194 | ||
3195 | # For now, always pick the highest quality. | |
3196 | rendition = renditions[-1] | |
3197 | ||
3198 | try: | |
3199 | _,_,ext = rendition.attrib['type'].partition('/') | |
3200 | format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate'] | |
3201 | video_url = rendition.find('./src').text | |
3202 | except KeyError: | |
3203 | self._downloader.trouble('Invalid rendition field.') | |
3204 | return | |
3205 | ||
3206 | info = { | |
3207 | 'id': video_id, | |
3208 | 'url': video_url, | |
3209 | 'uploader': performer, | |
3210 | 'upload_date': None, | |
3211 | 'title': video_title, | |
3212 | 'ext': ext, | |
3213 | 'format': format, | |
3214 | } | |
3215 | ||
3216 | return [info] | |
6de7ef9b | 3217 | |
302efc19 | 3218 | |
302efc19 | 3219 | class YoukuIE(InfoExtractor): |
3220 | ||
59ae15a5 PH |
3221 | _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html' |
3222 | IE_NAME = u'Youku' | |
3223 | ||
3224 | def __init__(self, downloader=None): | |
3225 | InfoExtractor.__init__(self, downloader) | |
3226 | ||
3227 | def report_download_webpage(self, file_id): | |
3228 | """Report webpage download.""" | |
3229 | self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id) | |
3230 | ||
3231 | def report_extraction(self, file_id): | |
3232 | """Report information extraction.""" | |
3233 | self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id) | |
3234 | ||
3235 | def _gen_sid(self): | |
3236 | nowTime = int(time.time() * 1000) | |
3237 | random1 = random.randint(1000,1998) | |
3238 | random2 = random.randint(1000,9999) | |
3239 | ||
3240 | return "%d%d%d" %(nowTime,random1,random2) | |
3241 | ||
3242 | def _get_file_ID_mix_string(self, seed): | |
3243 | mixed = [] | |
3244 | source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890") | |
3245 | seed = float(seed) | |
3246 | for i in range(len(source)): | |
3247 | seed = (seed * 211 + 30031 ) % 65536 | |
3248 | index = math.floor(seed / 65536 * len(source) ) | |
3249 | mixed.append(source[int(index)]) | |
3250 | source.remove(source[int(index)]) | |
3251 | #return ''.join(mixed) | |
3252 | return mixed | |
3253 | ||
3254 | def _get_file_id(self, fileId, seed): | |
3255 | mixed = self._get_file_ID_mix_string(seed) | |
3256 | ids = fileId.split('*') | |
3257 | realId = [] | |
3258 | for ch in ids: | |
3259 | if ch: | |
3260 | realId.append(mixed[int(ch)]) | |
3261 | return ''.join(realId) | |
3262 | ||
3263 | def _real_extract(self, url): | |
3264 | mobj = re.match(self._VALID_URL, url) | |
3265 | if mobj is None: | |
3266 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3267 | return | |
3268 | video_id = mobj.group('ID') | |
3269 | ||
3270 | info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id | |
3271 | ||
3272 | request = compat_urllib_request.Request(info_url, None, std_headers) | |
3273 | try: | |
3274 | self.report_download_webpage(video_id) | |
3275 | jsondata = compat_urllib_request.urlopen(request).read() | |
3276 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
3277 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) | |
3278 | return | |
3279 | ||
3280 | self.report_extraction(video_id) | |
3281 | try: | |
8f6f40d9 PH |
3282 | jsonstr = jsondata.decode('utf-8') |
3283 | config = json.loads(jsonstr) | |
59ae15a5 PH |
3284 | |
3285 | video_title = config['data'][0]['title'] | |
3286 | seed = config['data'][0]['seed'] | |
3287 | ||
3288 | format = self._downloader.params.get('format', None) | |
1a2c3c0f | 3289 | supported_format = list(config['data'][0]['streamfileids'].keys()) |
59ae15a5 PH |
3290 | |
3291 | if format is None or format == 'best': | |
3292 | if 'hd2' in supported_format: | |
3293 | format = 'hd2' | |
3294 | else: | |
3295 | format = 'flv' | |
3296 | ext = u'flv' | |
3297 | elif format == 'worst': | |
3298 | format = 'mp4' | |
3299 | ext = u'mp4' | |
3300 | else: | |
3301 | format = 'flv' | |
3302 | ext = u'flv' | |
3303 | ||
3304 | ||
3305 | fileid = config['data'][0]['streamfileids'][format] | |
e2a8ff24 | 3306 | keys = [s['k'] for s in config['data'][0]['segs'][format]] |
8f6f40d9 | 3307 | except (UnicodeDecodeError, ValueError, KeyError): |
59ae15a5 PH |
3308 | self._downloader.trouble(u'ERROR: unable to extract info section') |
3309 | return | |
3310 | ||
3311 | files_info=[] | |
3312 | sid = self._gen_sid() | |
3313 | fileid = self._get_file_id(fileid, seed) | |
3314 | ||
3315 | #column 8,9 of fileid represent the segment number | |
3316 | #fileid[7:9] should be changed | |
3317 | for index, key in enumerate(keys): | |
3318 | ||
3319 | temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:]) | |
3320 | download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) | |
3321 | ||
3322 | info = { | |
3323 | 'id': '%s_part%02d' % (video_id, index), | |
3324 | 'url': download_url, | |
3325 | 'uploader': None, | |
3326 | 'upload_date': None, | |
3327 | 'title': video_title, | |
3328 | 'ext': ext, | |
3329 | } | |
3330 | files_info.append(info) | |
3331 | ||
3332 | return files_info | |
5dc846fa FV |
3333 | |
3334 | ||
6de7ef9b | 3335 | class XNXXIE(InfoExtractor): |
59ae15a5 PH |
3336 | """Information extractor for xnxx.com""" |
3337 | ||
3338 | _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)' | |
3339 | IE_NAME = u'xnxx' | |
3340 | VIDEO_URL_RE = r'flv_url=(.*?)&' | |
3341 | VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM' | |
3342 | VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&' | |
3343 | ||
3344 | def report_webpage(self, video_id): | |
3345 | """Report information extraction""" | |
3346 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
3347 | ||
3348 | def report_extraction(self, video_id): | |
3349 | """Report information extraction""" | |
3350 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3351 | ||
3352 | def _real_extract(self, url): | |
3353 | mobj = re.match(self._VALID_URL, url) | |
3354 | if mobj is None: | |
3355 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3356 | return | |
bec102a8 | 3357 | video_id = mobj.group(1) |
59ae15a5 PH |
3358 | |
3359 | self.report_webpage(video_id) | |
3360 | ||
3361 | # Get webpage content | |
3362 | try: | |
bec102a8 PH |
3363 | webpage_bytes = compat_urllib_request.urlopen(url).read() |
3364 | webpage = webpage_bytes.decode('utf-8') | |
59ae15a5 PH |
3365 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
3366 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) | |
3367 | return | |
3368 | ||
3369 | result = re.search(self.VIDEO_URL_RE, webpage) | |
3370 | if result is None: | |
3371 | self._downloader.trouble(u'ERROR: unable to extract video url') | |
3372 | return | |
bec102a8 | 3373 | video_url = compat_urllib_parse.unquote(result.group(1)) |
59ae15a5 PH |
3374 | |
3375 | result = re.search(self.VIDEO_TITLE_RE, webpage) | |
3376 | if result is None: | |
3377 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
3378 | return | |
bec102a8 | 3379 | video_title = result.group(1) |
59ae15a5 PH |
3380 | |
3381 | result = re.search(self.VIDEO_THUMB_RE, webpage) | |
3382 | if result is None: | |
3383 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
3384 | return | |
bec102a8 | 3385 | video_thumbnail = result.group(1) |
59ae15a5 PH |
3386 | |
3387 | return [{ | |
3388 | 'id': video_id, | |
3389 | 'url': video_url, | |
3390 | 'uploader': None, | |
3391 | 'upload_date': None, | |
3392 | 'title': video_title, | |
3393 | 'ext': 'flv', | |
3394 | 'thumbnail': video_thumbnail, | |
3395 | 'description': None, | |
3396 | }] | |
fd873c69 FV |
3397 | |
3398 | ||
d443aca8 | 3399 | class GooglePlusIE(InfoExtractor): |
59ae15a5 PH |
3400 | """Information extractor for plus.google.com.""" |
3401 | ||
93702113 | 3402 | _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)' |
59ae15a5 PH |
3403 | IE_NAME = u'plus.google' |
3404 | ||
3405 | def __init__(self, downloader=None): | |
3406 | InfoExtractor.__init__(self, downloader) | |
3407 | ||
3408 | def report_extract_entry(self, url): | |
3409 | """Report downloading extry""" | |
93702113 | 3410 | self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url) |
59ae15a5 PH |
3411 | |
3412 | def report_date(self, upload_date): | |
3413 | """Report downloading extry""" | |
3414 | self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date) | |
3415 | ||
3416 | def report_uploader(self, uploader): | |
3417 | """Report downloading extry""" | |
93702113 | 3418 | self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader) |
59ae15a5 PH |
3419 | |
3420 | def report_title(self, video_title): | |
3421 | """Report downloading extry""" | |
93702113 | 3422 | self._downloader.to_screen(u'[plus.google] Title: %s' % video_title) |
59ae15a5 PH |
3423 | |
3424 | def report_extract_vid_page(self, video_page): | |
3425 | """Report information extraction.""" | |
93702113 | 3426 | self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page) |
59ae15a5 PH |
3427 | |
3428 | def _real_extract(self, url): | |
3429 | # Extract id from URL | |
3430 | mobj = re.match(self._VALID_URL, url) | |
3431 | if mobj is None: | |
3432 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
3433 | return | |
3434 | ||
3435 | post_url = mobj.group(0) | |
93702113 | 3436 | video_id = mobj.group(1) |
59ae15a5 PH |
3437 | |
3438 | video_extension = 'flv' | |
3439 | ||
3440 | # Step 1, Retrieve post webpage to extract further information | |
3441 | self.report_extract_entry(post_url) | |
3442 | request = compat_urllib_request.Request(post_url) | |
3443 | try: | |
93702113 | 3444 | webpage = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 PH |
3445 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
3446 | self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % compat_str(err)) | |
3447 | return | |
3448 | ||
3449 | # Extract update date | |
3450 | upload_date = None | |
3451 | pattern = 'title="Timestamp">(.*?)</a>' | |
3452 | mobj = re.search(pattern, webpage) | |
3453 | if mobj: | |
3454 | upload_date = mobj.group(1) | |
3455 | # Convert timestring to a format suitable for filename | |
3456 | upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") | |
3457 | upload_date = upload_date.strftime('%Y%m%d') | |
3458 | self.report_date(upload_date) | |
3459 | ||
3460 | # Extract uploader | |
3461 | uploader = None | |
3462 | pattern = r'rel\="author".*?>(.*?)</a>' | |
3463 | mobj = re.search(pattern, webpage) | |
3464 | if mobj: | |
3465 | uploader = mobj.group(1) | |
3466 | self.report_uploader(uploader) | |
3467 | ||
3468 | # Extract title | |
3469 | # Get the first line for title | |
3470 | video_title = u'NA' | |
3471 | pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]' | |
3472 | mobj = re.search(pattern, webpage) | |
3473 | if mobj: | |
3474 | video_title = mobj.group(1) | |
3475 | self.report_title(video_title) | |
3476 | ||
3477 | # Step 2, Stimulate clicking the image box to launch video | |
3478 | pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]' | |
3479 | mobj = re.search(pattern, webpage) | |
3480 | if mobj is None: | |
3481 | self._downloader.trouble(u'ERROR: unable to extract video page URL') | |
3482 | ||
3483 | video_page = mobj.group(1) | |
3484 | request = compat_urllib_request.Request(video_page) | |
3485 | try: | |
93702113 | 3486 | webpage = compat_urllib_request.urlopen(request).read().decode('utf-8') |
59ae15a5 PH |
3487 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
3488 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) | |
3489 | return | |
3490 | self.report_extract_vid_page(video_page) | |
3491 | ||
3492 | ||
3493 | # Extract video links on video page | |
3494 | """Extract video links of all sizes""" | |
3495 | pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"' | |
3496 | mobj = re.findall(pattern, webpage) | |
3497 | if len(mobj) == 0: | |
3498 | self._downloader.trouble(u'ERROR: unable to extract video links') | |
3499 | ||
3500 | # Sort in resolution | |
3501 | links = sorted(mobj) | |
3502 | ||
3503 | # Choose the lowest of the sort, i.e. highest resolution | |
3504 | video_url = links[-1] | |
3505 | # Only get the url. The resolution part in the tuple has no use anymore | |
3506 | video_url = video_url[-1] | |
3507 | # Treat escaped \u0026 style hex | |
93702113 FV |
3508 | try: |
3509 | video_url = video_url.decode("unicode_escape") | |
3510 | except AttributeError: # Python 3 | |
3511 | video_url = bytes(video_url, 'ascii').decode('unicode-escape') | |
59ae15a5 PH |
3512 | |
3513 | ||
3514 | return [{ | |
93702113 | 3515 | 'id': video_id, |
59ae15a5 | 3516 | 'url': video_url, |
93702113 FV |
3517 | 'uploader': uploader, |
3518 | 'upload_date': upload_date, | |
3519 | 'title': video_title, | |
3520 | 'ext': video_extension, | |
59ae15a5 | 3521 | }] |
4cc3d074 PH |
3522 | |
3523 | class NBAIE(InfoExtractor): | |
3524 | _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$' | |
3525 | IE_NAME = u'nba' | |
3526 | ||
3527 | def report_extraction(self, video_id): | |
3528 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3529 | ||
3530 | def _real_extract(self, url): | |
3531 | mobj = re.match(self._VALID_URL, url) | |
3532 | if mobj is None: | |
3533 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3534 | return | |
3535 | ||
3536 | video_id = mobj.group(1) | |
3537 | if video_id.endswith('/index.html'): | |
3538 | video_id = video_id[:-len('/index.html')] | |
3539 | ||
3540 | self.report_extraction(video_id) | |
3541 | try: | |
3542 | urlh = compat_urllib_request.urlopen(url) | |
3543 | webpage_bytes = urlh.read() | |
3544 | webpage = webpage_bytes.decode('utf-8', 'ignore') | |
3545 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
3546 | self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err)) | |
3547 | return | |
3548 | ||
3549 | video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' | |
3550 | def _findProp(rexp, default=None): | |
3551 | m = re.search(rexp, webpage) | |
3552 | if m: | |
3553 | return unescapeHTML(m.group(1)) | |
3554 | else: | |
3555 | return default | |
3556 | ||
3557 | shortened_video_id = video_id.rpartition('/')[2] | |
3558 | title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '') | |
3559 | info = { | |
3560 | 'id': shortened_video_id, | |
3561 | 'url': video_url, | |
3562 | 'ext': 'mp4', | |
3563 | 'title': title, | |
3564 | 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'), | |
3565 | 'description': _findProp(r'<div class="description">(.*?)</h1>'), | |
3566 | } | |
3567 | return [info] | |
0b40544f DV |
3568 | |
3569 | class JustinTVIE(InfoExtractor): | |
3570 | """Information extractor for justin.tv and twitch.tv""" | |
2ab1c5ed DV |
3571 | # TODO: One broadcast may be split into multiple videos. The key |
3572 | # 'broadcast_id' is the same for all parts, and 'broadcast_part' | |
3573 | # starts at 1 and increases. Can we treat all parts as one video? | |
3574 | ||
4096b609 DV |
3575 | _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/ |
3576 | ([^/]+)(?:/b/([^/]+))?/?(?:\#.*)?$""" | |
3577 | _JUSTIN_PAGE_LIMIT = 100 | |
0b40544f DV |
3578 | IE_NAME = u'justin.tv' |
3579 | ||
3580 | def report_extraction(self, file_id): | |
3581 | """Report information extraction.""" | |
3582 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) | |
3583 | ||
4096b609 DV |
3584 | def report_download_page(self, channel, offset): |
3585 | """Report attempt to download a single page of videos.""" | |
3586 | self._downloader.to_screen(u'[%s] %s: Downloading video information from %d to %d' % | |
3587 | (self.IE_NAME, channel, offset, offset + self._JUSTIN_PAGE_LIMIT)) | |
3588 | ||
2ab1c5ed DV |
3589 | # Return count of items, list of *valid* items |
3590 | def _parse_page(self, url): | |
0b40544f | 3591 | try: |
2ab1c5ed | 3592 | urlh = compat_urllib_request.urlopen(url) |
0b40544f DV |
3593 | webpage_bytes = urlh.read() |
3594 | webpage = webpage_bytes.decode('utf-8', 'ignore') | |
3595 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
3596 | self._downloader.trouble(u'ERROR: unable to download video info JSON: %s' % compat_str(err)) | |
3597 | return | |
cdb30764 | 3598 | |
0b40544f DV |
3599 | response = json.loads(webpage) |
3600 | info = [] | |
3601 | for clip in response: | |
3602 | video_url = clip['video_file_url'] | |
3603 | if video_url: | |
3604 | video_extension = os.path.splitext(video_url)[1][1:] | |
3605 | video_date = re.sub('-', '', clip['created_on'][:10]) | |
3606 | info.append({ | |
3607 | 'id': clip['id'], | |
3608 | 'url': video_url, | |
3609 | 'title': clip['title'], | |
4096b609 | 3610 | 'uploader': clip.get('user_id', clip.get('channel_id')), |
0b40544f DV |
3611 | 'upload_date': video_date, |
3612 | 'ext': video_extension, | |
3613 | }) | |
2ab1c5ed DV |
3614 | return (len(response), info) |
3615 | ||
3616 | def _real_extract(self, url): | |
3617 | mobj = re.match(self._VALID_URL, url) | |
3618 | if mobj is None: | |
3619 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3620 | return | |
cdb30764 | 3621 | |
2ab1c5ed DV |
3622 | api = 'http://api.justin.tv' |
3623 | video_id = mobj.group(mobj.lastindex) | |
3624 | paged = False | |
3625 | if mobj.lastindex == 1: | |
3626 | paged = True | |
3627 | api += '/channel/archives/%s.json' | |
3628 | else: | |
3629 | api += '/clip/show/%s.json' | |
3630 | api = api % (video_id,) | |
cdb30764 | 3631 | |
2ab1c5ed | 3632 | self.report_extraction(video_id) |
cdb30764 | 3633 | |
2ab1c5ed DV |
3634 | info = [] |
3635 | offset = 0 | |
4096b609 DV |
3636 | limit = self._JUSTIN_PAGE_LIMIT |
3637 | while True: | |
3638 | if paged: | |
3639 | self.report_download_page(video_id, offset) | |
2ab1c5ed DV |
3640 | page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) |
3641 | page_count, page_info = self._parse_page(page_url) | |
3642 | info.extend(page_info) | |
3643 | if not paged or page_count != limit: | |
3644 | break | |
3645 | offset += limit | |
0b40544f | 3646 | return info |
21a9c6aa PH |
3647 | |
3648 | class FunnyOrDieIE(InfoExtractor): | |
3649 | _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$' | |
3650 | IE_NAME = u'FunnyOrDie' | |
3651 | ||
3652 | def report_extraction(self, video_id): | |
3653 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3654 | ||
3655 | def _real_extract(self, url): | |
3656 | mobj = re.match(self._VALID_URL, url) | |
3657 | if mobj is None: | |
3658 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3659 | return | |
3660 | ||
3661 | video_id = mobj.group('id') | |
3662 | self.report_extraction(video_id) | |
3663 | try: | |
3664 | urlh = compat_urllib_request.urlopen(url) | |
3665 | webpage_bytes = urlh.read() | |
3666 | webpage = webpage_bytes.decode('utf-8', 'ignore') | |
3667 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
3668 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) | |
3669 | return | |
3670 | ||
3671 | m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL) | |
3672 | if not m: | |
3673 | self._downloader.trouble(u'ERROR: unable to find video information') | |
3674 | video_url = unescapeHTML(m.group('url')) | |
3675 | print(video_url) | |
3676 | ||
3677 | m = re.search(r"class='player_page_h1'>\s+<a.*?>(?P<title>.*?)</a>", webpage) | |
3678 | if not m: | |
3679 | self._downloader.trouble(u'Cannot find video title') | |
3680 | title = unescapeHTML(m.group('title')) | |
3681 | ||
3682 | m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage) | |
3683 | if m: | |
3684 | desc = unescapeHTML(m.group('desc')) | |
3685 | else: | |
3686 | desc = None | |
3687 | ||
3688 | info = { | |
3689 | 'id': video_id, | |
3690 | 'url': video_url, | |
3691 | 'ext': 'mp4', | |
3692 | 'title': title, | |
3693 | 'description': desc, | |
3694 | } | |
3695 | return [info] |