]>
Commit | Line | Data |
---|---|---|
dcdb292f | 1 | # coding: utf-8 |
38a40276 | 2 | from __future__ import unicode_literals |
3 | ||
706dfe44 | 4 | import base64 |
34440095 | 5 | import re |
1d430674 | 6 | import json |
34440095 S |
7 | import zlib |
8 | ||
c8434e83 | 9 | from hashlib import sha1 |
10 | from math import pow, sqrt, floor | |
46279958 | 11 | from .common import InfoExtractor |
54a5be4d | 12 | from .vrv import VRVIE |
1cc79574 | 13 | from ..compat import ( |
cf282071 | 14 | compat_b64decode, |
ee0ba927 | 15 | compat_etree_Element, |
36e6f62c | 16 | compat_etree_fromstring, |
6ffc3cf7 | 17 | compat_str, |
15707c7e | 18 | compat_urllib_parse_urlencode, |
c8434e83 | 19 | compat_urllib_request, |
a01da8bb | 20 | compat_urlparse, |
1cc79574 PH |
21 | ) |
22 | from ..utils import ( | |
23 | ExtractorError, | |
c8434e83 | 24 | bytes_to_intlist, |
54a5be4d RA |
25 | extract_attributes, |
26 | float_or_none, | |
706dfe44 | 27 | format_field, |
c8434e83 | 28 | intlist_to_bytes, |
725d1c58 | 29 | int_or_none, |
706dfe44 | 30 | join_nonempty, |
6d02b9a3 | 31 | lowercase_escape, |
6ffc3cf7 | 32 | merge_dicts, |
a9d4da60 | 33 | qualities, |
a01da8bb | 34 | remove_end, |
5c2266df | 35 | sanitized_Request, |
706dfe44 | 36 | traverse_obj, |
245d43ca | 37 | try_get, |
723e04d0 | 38 | urlencode_postdata, |
725d1c58 | 39 | xpath_text, |
c8434e83 | 40 | ) |
41 | from ..aes import ( | |
42 | aes_cbc_decrypt, | |
c8434e83 | 43 | ) |
44 | ||
34440095 | 45 | |
46279958 | 46 | class CrunchyrollBaseIE(InfoExtractor): |
eb5b1fc0 S |
47 | _LOGIN_URL = 'https://www.crunchyroll.com/login' |
48 | _LOGIN_FORM = 'login_form' | |
80f48920 S |
49 | _NETRC_MACHINE = 'crunchyroll' |
50 | ||
05dee6c5 RA |
51 | def _call_rpc_api(self, method, video_id, note=None, data=None): |
52 | data = data or {} | |
53 | data['req'] = 'RpcApi' + method | |
54 | data = compat_urllib_parse_urlencode(data).encode('utf-8') | |
55 | return self._download_xml( | |
d98cb62e | 56 | 'https://www.crunchyroll.com/xml/', |
05dee6c5 RA |
57 | video_id, note, fatal=False, data=data, headers={ |
58 | 'Content-Type': 'application/x-www-form-urlencoded', | |
59 | }) | |
60 | ||
80f48920 | 61 | def _login(self): |
68217024 | 62 | username, password = self._get_login_info() |
80f48920 S |
63 | if username is None: |
64 | return | |
eb5b1fc0 S |
65 | |
66 | login_page = self._download_webpage( | |
67 | self._LOGIN_URL, None, 'Downloading login page') | |
68 | ||
70b4cf9b | 69 | def is_logged(webpage): |
a8f83f0c | 70 | return 'href="/logout"' in webpage |
70b4cf9b S |
71 | |
72 | # Already logged in | |
73 | if is_logged(login_page): | |
74 | return | |
75 | ||
eb5b1fc0 S |
76 | login_form_str = self._search_regex( |
77 | r'(?P<form><form[^>]+?id=(["\'])%s\2[^>]*>)' % self._LOGIN_FORM, | |
78 | login_page, 'login form', group='form') | |
79 | ||
80 | post_url = extract_attributes(login_form_str).get('action') | |
81 | if not post_url: | |
82 | post_url = self._LOGIN_URL | |
83 | elif not post_url.startswith('http'): | |
84 | post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url) | |
85 | ||
86 | login_form = self._form_hidden_inputs(self._LOGIN_FORM, login_page) | |
87 | ||
88 | login_form.update({ | |
89 | 'login_form[name]': username, | |
90 | 'login_form[password]': password, | |
80f48920 | 91 | }) |
eb5b1fc0 S |
92 | |
93 | response = self._download_webpage( | |
94 | post_url, None, 'Logging in', 'Wrong login info', | |
95 | data=urlencode_postdata(login_form), | |
96 | headers={'Content-Type': 'application/x-www-form-urlencoded'}) | |
97 | ||
98 | # Successful login | |
70b4cf9b | 99 | if is_logged(response): |
eb5b1fc0 S |
100 | return |
101 | ||
102 | error = self._html_search_regex( | |
103 | '(?s)<ul[^>]+class=["\']messages["\'][^>]*>(.+?)</ul>', | |
104 | response, 'error message', default=None) | |
105 | if error: | |
106 | raise ExtractorError('Unable to login: %s' % error, expected=True) | |
107 | ||
108 | raise ExtractorError('Unable to log in') | |
80f48920 S |
109 | |
110 | def _real_initialize(self): | |
111 | self._login() | |
112 | ||
80f48920 S |
113 | @staticmethod |
114 | def _add_skip_wall(url): | |
115 | parsed_url = compat_urlparse.urlparse(url) | |
116 | qs = compat_urlparse.parse_qs(parsed_url.query) | |
117 | # Always force skip_wall to bypass maturity wall, namely 18+ confirmation message: | |
118 | # > This content may be inappropriate for some people. | |
119 | # > Are you sure you want to continue? | |
120 | # since it's not disabled by default in crunchyroll account's settings. | |
067aa17e | 121 | # See https://github.com/ytdl-org/youtube-dl/issues/7202. |
80f48920 S |
122 | qs['skip_wall'] = ['1'] |
123 | return compat_urlparse.urlunparse( | |
15707c7e | 124 | parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True))) |
80f48920 | 125 | |
12810c9c | 126 | |
46279958 RA |
127 | class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): |
128 | IE_NAME = 'crunchyroll' | |
d3d8d818 | 129 | _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|(?:[^/]*/){1,2}[^/?&]*?)(?P<id>[0-9]+))(?:[/?&]|$)' |
a8896c5a | 130 | _TESTS = [{ |
38a40276 | 131 | 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', |
38a40276 | 132 | 'info_dict': { |
34440095 | 133 | 'id': '645513', |
b5869560 | 134 | 'ext': 'mp4', |
38a40276 | 135 | 'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!', |
136 | 'description': 'md5:2d17137920c64f2f49981a7797d275ef', | |
54a5be4d | 137 | 'thumbnail': r're:^https?://.*\.jpg$', |
38a40276 | 138 | 'uploader': 'Yomiuri Telecasting Corporation (YTV)', |
139 | 'upload_date': '20131013', | |
b1edd7a4 | 140 | 'url': 're:(?!.*&)', |
c8434e83 | 141 | }, |
38a40276 | 142 | 'params': { |
c8434e83 | 143 | # rtmp |
38a40276 | 144 | 'skip_download': True, |
c8434e83 | 145 | }, |
6ffc3cf7 | 146 | 'skip': 'Video gone', |
ede21449 S |
147 | }, { |
148 | 'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1', | |
149 | 'info_dict': { | |
150 | 'id': '589804', | |
151 | 'ext': 'flv', | |
152 | 'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11', | |
6d02b9a3 | 153 | 'description': 'md5:2fbc01f90b87e8e9137296f37b461c12', |
ec85ded8 | 154 | 'thumbnail': r're:^https?://.*\.jpg$', |
ede21449 S |
155 | 'uploader': 'Danny Choo Network', |
156 | 'upload_date': '20120213', | |
157 | }, | |
158 | 'params': { | |
159 | # rtmp | |
160 | 'skip_download': True, | |
161 | }, | |
77c5b98d | 162 | 'skip': 'Video gone', |
990d533e S |
163 | }, { |
164 | 'url': 'http://www.crunchyroll.com/rezero-starting-life-in-another-world-/episode-5-the-morning-of-our-promise-is-still-distant-702409', | |
165 | 'info_dict': { | |
166 | 'id': '702409', | |
167 | 'ext': 'mp4', | |
6ffc3cf7 S |
168 | 'title': compat_str, |
169 | 'description': compat_str, | |
ec85ded8 | 170 | 'thumbnail': r're:^https?://.*\.jpg$', |
6ffc3cf7 S |
171 | 'uploader': 'Re:Zero Partners', |
172 | 'timestamp': 1462098900, | |
173 | 'upload_date': '20160501', | |
990d533e S |
174 | }, |
175 | 'params': { | |
176 | # m3u8 download | |
177 | 'skip_download': True, | |
178 | }, | |
e0b6e50c S |
179 | }, { |
180 | 'url': 'http://www.crunchyroll.com/konosuba-gods-blessing-on-this-wonderful-world/episode-1-give-me-deliverance-from-this-judicial-injustice-727589', | |
181 | 'info_dict': { | |
182 | 'id': '727589', | |
183 | 'ext': 'mp4', | |
6ffc3cf7 S |
184 | 'title': compat_str, |
185 | 'description': compat_str, | |
e0b6e50c S |
186 | 'thumbnail': r're:^https?://.*\.jpg$', |
187 | 'uploader': 'Kadokawa Pictures Inc.', | |
6ffc3cf7 S |
188 | 'timestamp': 1484130900, |
189 | 'upload_date': '20170111', | |
190 | 'series': compat_str, | |
8c996232 | 191 | 'season': "KONOSUBA -God's blessing on this wonderful world! 2", |
e0b6e50c | 192 | 'season_number': 2, |
b9f9f361 | 193 | 'episode': 'Give Me Deliverance From This Judicial Injustice!', |
e0b6e50c S |
194 | 'episode_number': 1, |
195 | }, | |
196 | 'params': { | |
197 | # m3u8 download | |
198 | 'skip_download': True, | |
199 | }, | |
a8896c5a S |
200 | }, { |
201 | 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697', | |
202 | 'only_matching': True, | |
49941c4e S |
203 | }, { |
204 | # geo-restricted (US), 18+ maturity wall, non-premium available | |
205 | 'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617', | |
206 | 'only_matching': True, | |
b5869560 YCH |
207 | }, { |
208 | # A description with double quotes | |
209 | 'url': 'http://www.crunchyroll.com/11eyes/episode-1-piros-jszaka-red-night-535080', | |
210 | 'info_dict': { | |
211 | 'id': '535080', | |
212 | 'ext': 'mp4', | |
6ffc3cf7 S |
213 | 'title': compat_str, |
214 | 'description': compat_str, | |
b5869560 | 215 | 'uploader': 'Marvelous AQL Inc.', |
6ffc3cf7 S |
216 | 'timestamp': 1255512600, |
217 | 'upload_date': '20091014', | |
b5869560 YCH |
218 | }, |
219 | 'params': { | |
220 | # Just test metadata extraction | |
221 | 'skip_download': True, | |
222 | }, | |
7fd46552 | 223 | }, { |
224 | # make sure we can extract an uploader name that's not a link | |
225 | 'url': 'http://www.crunchyroll.com/hakuoki-reimeiroku/episode-1-dawn-of-the-divine-warriors-606899', | |
226 | 'info_dict': { | |
227 | 'id': '606899', | |
228 | 'ext': 'mp4', | |
229 | 'title': 'Hakuoki Reimeiroku Episode 1 – Dawn of the Divine Warriors', | |
230 | 'description': 'Ryunosuke was left to die, but Serizawa-san asked him a simple question "Do you want to live?"', | |
231 | 'uploader': 'Geneon Entertainment', | |
232 | 'upload_date': '20120717', | |
233 | }, | |
234 | 'params': { | |
235 | # just test metadata extraction | |
236 | 'skip_download': True, | |
237 | }, | |
6ffc3cf7 | 238 | 'skip': 'Video gone', |
8c996232 S |
239 | }, { |
240 | # A video with a vastly different season name compared to the series name | |
241 | 'url': 'http://www.crunchyroll.com/nyarko-san-another-crawling-chaos/episode-1-test-590532', | |
242 | 'info_dict': { | |
243 | 'id': '590532', | |
244 | 'ext': 'mp4', | |
6ffc3cf7 S |
245 | 'title': compat_str, |
246 | 'description': compat_str, | |
8c996232 | 247 | 'uploader': 'TV TOKYO', |
6ffc3cf7 | 248 | 'timestamp': 1330956000, |
8c996232 S |
249 | 'upload_date': '20120305', |
250 | 'series': 'Nyarko-san: Another Crawling Chaos', | |
251 | 'season': 'Haiyoru! Nyaruani (ONA)', | |
252 | }, | |
253 | 'params': { | |
254 | # Just test metadata extraction | |
255 | 'skip_download': True, | |
256 | }, | |
b2286f8f | 257 | }, { |
258 | 'url': 'http://www.crunchyroll.com/media-723735', | |
259 | 'only_matching': True, | |
6510a3aa S |
260 | }, { |
261 | 'url': 'https://www.crunchyroll.com/en-gb/mob-psycho-100/episode-2-urban-legends-encountering-rumors-780921', | |
262 | 'only_matching': True, | |
a8896c5a | 263 | }] |
c8434e83 | 264 | |
265 | _FORMAT_IDS = { | |
38a40276 | 266 | '360': ('60', '106'), |
267 | '480': ('61', '106'), | |
268 | '720': ('62', '106'), | |
269 | '1080': ('80', '108'), | |
c8434e83 | 270 | } |
271 | ||
d415957d S |
272 | def _download_webpage(self, url_or_request, *args, **kwargs): |
273 | request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request) | |
274 | else sanitized_Request(url_or_request)) | |
275 | # Accept-Language must be set explicitly to accept any language to avoid issues | |
276 | # similar to https://github.com/ytdl-org/youtube-dl/issues/6797. | |
277 | # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction | |
278 | # should be imposed or not (from what I can see it just takes the first language | |
279 | # ignoring the priority and requires it to correspond the IP). By the way this causes | |
280 | # Crunchyroll to not work in georestriction cases in some browsers that don't place | |
281 | # the locale lang first in header. However allowing any language seems to workaround the issue. | |
282 | request.add_header('Accept-Language', '*') | |
283 | return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs) | |
284 | ||
c8434e83 | 285 | def _decrypt_subtitles(self, data, iv, id): |
cf282071 S |
286 | data = bytes_to_intlist(compat_b64decode(data)) |
287 | iv = bytes_to_intlist(compat_b64decode(iv)) | |
c8434e83 | 288 | id = int(id) |
289 | ||
290 | def obfuscate_key_aux(count, modulo, start): | |
291 | output = list(start) | |
292 | for _ in range(count): | |
293 | output.append(output[-1] + output[-2]) | |
294 | # cut off start values | |
295 | output = output[2:] | |
296 | output = list(map(lambda x: x % modulo + 33, output)) | |
297 | return output | |
298 | ||
299 | def obfuscate_key(key): | |
300 | num1 = int(floor(pow(2, 25) * sqrt(6.9))) | |
301 | num2 = (num1 ^ key) << 5 | |
302 | num3 = key ^ num1 | |
303 | num4 = num3 ^ (num3 >> 3) ^ num2 | |
304 | prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2))) | |
38a40276 | 305 | shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest()) |
c8434e83 | 306 | # Extend 160 Bit hash to 256 Bit |
307 | return shaHash + [0] * 12 | |
34440095 | 308 | |
c8434e83 | 309 | key = obfuscate_key(id) |
5f6a1245 | 310 | |
c8434e83 | 311 | decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv)) |
312 | return zlib.decompress(decrypted_data) | |
313 | ||
d65d6286 | 314 | def _convert_subtitles_to_srt(self, sub_root): |
38a40276 | 315 | output = '' |
d65d6286 JMF |
316 | |
317 | for i, event in enumerate(sub_root.findall('./events/event'), 1): | |
318 | start = event.attrib['start'].replace('.', ',') | |
319 | end = event.attrib['end'].replace('.', ',') | |
320 | text = event.attrib['text'].replace('\\N', '\n') | |
38a40276 | 321 | output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text) |
c8434e83 | 322 | return output |
323 | ||
d65d6286 | 324 | def _convert_subtitles_to_ass(self, sub_root): |
78272a07 A |
325 | output = '' |
326 | ||
327 | def ass_bool(strvalue): | |
328 | assvalue = '0' | |
329 | if strvalue == '1': | |
330 | assvalue = '-1' | |
331 | return assvalue | |
332 | ||
78272a07 | 333 | output = '[Script Info]\n' |
611c1dd9 | 334 | output += 'Title: %s\n' % sub_root.attrib['title'] |
78272a07 | 335 | output += 'ScriptType: v4.00+\n' |
611c1dd9 S |
336 | output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style'] |
337 | output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x'] | |
338 | output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y'] | |
2b2d5d31 | 339 | output += """ |
78272a07 A |
340 | [V4+ Styles] |
341 | Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding | |
342 | """ | |
343 | for style in sub_root.findall('./styles/style'): | |
611c1dd9 S |
344 | output += 'Style: ' + style.attrib['name'] |
345 | output += ',' + style.attrib['font_name'] | |
346 | output += ',' + style.attrib['font_size'] | |
347 | output += ',' + style.attrib['primary_colour'] | |
348 | output += ',' + style.attrib['secondary_colour'] | |
349 | output += ',' + style.attrib['outline_colour'] | |
350 | output += ',' + style.attrib['back_colour'] | |
351 | output += ',' + ass_bool(style.attrib['bold']) | |
352 | output += ',' + ass_bool(style.attrib['italic']) | |
353 | output += ',' + ass_bool(style.attrib['underline']) | |
354 | output += ',' + ass_bool(style.attrib['strikeout']) | |
355 | output += ',' + style.attrib['scale_x'] | |
356 | output += ',' + style.attrib['scale_y'] | |
357 | output += ',' + style.attrib['spacing'] | |
358 | output += ',' + style.attrib['angle'] | |
359 | output += ',' + style.attrib['border_style'] | |
360 | output += ',' + style.attrib['outline'] | |
361 | output += ',' + style.attrib['shadow'] | |
362 | output += ',' + style.attrib['alignment'] | |
363 | output += ',' + style.attrib['margin_l'] | |
364 | output += ',' + style.attrib['margin_r'] | |
365 | output += ',' + style.attrib['margin_v'] | |
366 | output += ',' + style.attrib['encoding'] | |
78272a07 A |
367 | output += '\n' |
368 | ||
369 | output += """ | |
370 | [Events] | |
371 | Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text | |
372 | """ | |
373 | for event in sub_root.findall('./events/event'): | |
374 | output += 'Dialogue: 0' | |
611c1dd9 S |
375 | output += ',' + event.attrib['start'] |
376 | output += ',' + event.attrib['end'] | |
377 | output += ',' + event.attrib['style'] | |
378 | output += ',' + event.attrib['name'] | |
379 | output += ',' + event.attrib['margin_l'] | |
380 | output += ',' + event.attrib['margin_r'] | |
381 | output += ',' + event.attrib['margin_v'] | |
382 | output += ',' + event.attrib['effect'] | |
383 | output += ',' + event.attrib['text'] | |
78272a07 A |
384 | output += '\n' |
385 | ||
386 | return output | |
387 | ||
0385d642 | 388 | def _extract_subtitles(self, subtitle): |
36e6f62c | 389 | sub_root = compat_etree_fromstring(subtitle) |
0385d642 S |
390 | return [{ |
391 | 'ext': 'srt', | |
392 | 'data': self._convert_subtitles_to_srt(sub_root), | |
393 | }, { | |
394 | 'ext': 'ass', | |
395 | 'data': self._convert_subtitles_to_ass(sub_root), | |
396 | }] | |
397 | ||
b5857f62 JMF |
398 | def _get_subtitles(self, video_id, webpage): |
399 | subtitles = {} | |
76907875 | 400 | for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage): |
05dee6c5 RA |
401 | sub_doc = self._call_rpc_api( |
402 | 'Subtitle_GetXml', video_id, | |
403 | 'Downloading subtitles for ' + sub_name, data={ | |
404 | 'subtitle_script_id': sub_id, | |
405 | }) | |
ee0ba927 | 406 | if not isinstance(sub_doc, compat_etree_Element): |
b5857f62 | 407 | continue |
05dee6c5 RA |
408 | sid = sub_doc.get('id') |
409 | iv = xpath_text(sub_doc, 'iv', 'subtitle iv') | |
410 | data = xpath_text(sub_doc, 'data', 'subtitle data') | |
411 | if not sid or not iv or not data: | |
412 | continue | |
413 | subtitle = self._decrypt_subtitles(data, iv, sid).decode('utf-8') | |
b5857f62 JMF |
414 | lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False) |
415 | if not lang_code: | |
416 | continue | |
0385d642 | 417 | subtitles[lang_code] = self._extract_subtitles(subtitle) |
b5857f62 JMF |
418 | return subtitles |
419 | ||
5f6a1245 | 420 | def _real_extract(self, url): |
5ad28e7f | 421 | mobj = self._match_valid_url(url) |
d3d8d818 | 422 | video_id = mobj.group('id') |
38a40276 | 423 | |
424 | if mobj.group('prefix') == 'm': | |
425 | mobile_webpage = self._download_webpage(url, video_id, 'Downloading mobile webpage') | |
426 | webpage_url = self._search_regex(r'<link rel="canonical" href="([^"]+)" />', mobile_webpage, 'webpage_url') | |
427 | else: | |
428 | webpage_url = 'http://www.' + mobj.group('url') | |
c8434e83 | 429 | |
ca77b92f RA |
430 | webpage = self._download_webpage( |
431 | self._add_skip_wall(webpage_url), video_id, | |
432 | headers=self.geo_verification_headers()) | |
2f72e83b S |
433 | note_m = self._html_search_regex( |
434 | r'<div class="showmedia-trailer-notice">(.+?)</div>', | |
435 | webpage, 'trailer-notice', default='') | |
c8434e83 | 436 | if note_m: |
a7191c6f | 437 | raise ExtractorError(note_m, expected=True) |
c8434e83 | 438 | |
1d430674 S |
439 | mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage) |
440 | if mobj: | |
441 | msg = json.loads(mobj.group('msg')) | |
442 | if msg.get('type') == 'error': | |
443 | raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True) | |
2f72e83b S |
444 | |
445 | if 'To view this, please log in to verify you are 18 or older.' in webpage: | |
39affb5a | 446 | self.raise_login_required() |
1d430674 | 447 | |
54a5be4d RA |
448 | media = self._parse_json(self._search_regex( |
449 | r'vilos\.config\.media\s*=\s*({.+?});', | |
450 | webpage, 'vilos media', default='{}'), video_id) | |
451 | media_metadata = media.get('metadata') or {} | |
452 | ||
1084563e S |
453 | language = self._search_regex( |
454 | r'(?:vilos\.config\.player\.language|LOCALE)\s*=\s*(["\'])(?P<lang>(?:(?!\1).)+)\1', | |
455 | webpage, 'language', default=None, group='lang') | |
456 | ||
5214f1e3 | 457 | video_title = self._html_search_regex( |
6ffc3cf7 S |
458 | (r'(?s)<h1[^>]*>((?:(?!<h1).)*?<(?:span[^>]+itemprop=["\']title["\']|meta[^>]+itemprop=["\']position["\'])[^>]*>(?:(?!<h1).)+?)</h1>', |
459 | r'<title>(.+?),\s+-\s+.+? Crunchyroll'), | |
460 | webpage, 'video_title', default=None) | |
461 | if not video_title: | |
462 | video_title = re.sub(r'^Watch\s+', '', self._og_search_description(webpage)) | |
38a40276 | 463 | video_title = re.sub(r' {2,}', ' ', video_title) |
54a5be4d | 464 | video_description = (self._parse_json(self._html_search_regex( |
b5869560 | 465 | r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id, |
54a5be4d | 466 | webpage, 'description', default='{}'), video_id) or media_metadata).get('description') |
245d43ca | 467 | |
468 | thumbnails = [] | |
469 | thumbnail_url = (self._parse_json(self._html_search_regex( | |
470 | r'<script type="application\/ld\+json">\n\s*(.+?)<\/script>', | |
471 | webpage, 'thumbnail_url', default='{}'), video_id)).get('image') | |
472 | if thumbnail_url: | |
473 | thumbnails.append({ | |
474 | 'url': thumbnail_url, | |
475 | 'width': 1920, | |
476 | 'height': 1080 | |
477 | }) | |
478 | ||
6d02b9a3 S |
479 | if video_description: |
480 | video_description = lowercase_escape(video_description.replace(r'\r\n', '\n')) | |
47004d95 | 481 | video_uploader = self._html_search_regex( |
7fd46552 | 482 | # try looking for both an uploader that's a link and one that's not |
483 | [r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', r'<div>\s*Publisher:\s*<span>\s*(.+?)\s*</span>\s*</div>'], | |
6ffc3cf7 | 484 | webpage, 'video_uploader', default=False) |
c8434e83 | 485 | |
a9d4da60 | 486 | requested_languages = self._configuration_arg('language') |
487 | requested_hardsubs = [('' if val == 'none' else val) for val in self._configuration_arg('hardsub')] | |
488 | language_preference = qualities((requested_languages or [language or ''])[::-1]) | |
489 | hardsub_preference = qualities((requested_hardsubs or ['', language or ''])[::-1]) | |
490 | ||
065216d9 | 491 | formats = [] |
54a5be4d | 492 | for stream in media.get('streams', []): |
a9d4da60 | 493 | audio_lang = stream.get('audio_lang') or '' |
494 | hardsub_lang = stream.get('hardsub_lang') or '' | |
495 | if (requested_languages and audio_lang.lower() not in requested_languages | |
496 | or requested_hardsubs and hardsub_lang.lower() not in requested_hardsubs): | |
497 | continue | |
1084563e | 498 | vrv_formats = self._extract_vrv_formats( |
54a5be4d | 499 | stream.get('url'), video_id, stream.get('format'), |
1084563e S |
500 | audio_lang, hardsub_lang) |
501 | for f in vrv_formats: | |
a9d4da60 | 502 | f['language_preference'] = language_preference(audio_lang) |
503 | f['quality'] = hardsub_preference(hardsub_lang) | |
1084563e | 504 | formats.extend(vrv_formats) |
54a5be4d RA |
505 | if not formats: |
506 | available_fmts = [] | |
507 | for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage): | |
508 | attrs = extract_attributes(a) | |
509 | href = attrs.get('href') | |
510 | if href and '/freetrial' in href: | |
511 | continue | |
512 | available_fmts.append(fmt) | |
513 | if not available_fmts: | |
514 | for p in (r'token=["\']showmedia\.([0-9]{3,4})p"', r'showmedia\.([0-9]{3,4})p'): | |
515 | available_fmts = re.findall(p, webpage) | |
516 | if available_fmts: | |
517 | break | |
518 | if not available_fmts: | |
519 | available_fmts = self._FORMAT_IDS.keys() | |
520 | video_encode_ids = [] | |
521 | ||
522 | for fmt in available_fmts: | |
523 | stream_quality, stream_format = self._FORMAT_IDS[fmt] | |
524 | video_format = fmt + 'p' | |
525 | stream_infos = [] | |
526 | streamdata = self._call_rpc_api( | |
527 | 'VideoPlayer_GetStandardConfig', video_id, | |
528 | 'Downloading media info for %s' % video_format, data={ | |
529 | 'media_id': video_id, | |
530 | 'video_format': stream_format, | |
531 | 'video_quality': stream_quality, | |
532 | 'current_page': url, | |
533 | }) | |
ee0ba927 | 534 | if isinstance(streamdata, compat_etree_Element): |
54a5be4d RA |
535 | stream_info = streamdata.find('./{default}preload/stream_info') |
536 | if stream_info is not None: | |
537 | stream_infos.append(stream_info) | |
538 | stream_info = self._call_rpc_api( | |
539 | 'VideoEncode_GetStreamInfo', video_id, | |
540 | 'Downloading stream info for %s' % video_format, data={ | |
541 | 'media_id': video_id, | |
542 | 'video_format': stream_format, | |
543 | 'video_encode_quality': stream_quality, | |
544 | }) | |
ee0ba927 | 545 | if isinstance(stream_info, compat_etree_Element): |
05dee6c5 | 546 | stream_infos.append(stream_info) |
54a5be4d RA |
547 | for stream_info in stream_infos: |
548 | video_encode_id = xpath_text(stream_info, './video_encode_id') | |
549 | if video_encode_id in video_encode_ids: | |
550 | continue | |
551 | video_encode_ids.append(video_encode_id) | |
c8434e83 | 552 | |
54a5be4d RA |
553 | video_file = xpath_text(stream_info, './file') |
554 | if not video_file: | |
555 | continue | |
556 | if video_file.startswith('http'): | |
557 | formats.extend(self._extract_m3u8_formats( | |
558 | video_file, video_id, 'mp4', entry_protocol='m3u8_native', | |
559 | m3u8_id='hls', fatal=False)) | |
05dee6c5 RA |
560 | continue |
561 | ||
54a5be4d RA |
562 | video_url = xpath_text(stream_info, './host') |
563 | if not video_url: | |
564 | continue | |
565 | metadata = stream_info.find('./metadata') | |
566 | format_info = { | |
567 | 'format': video_format, | |
568 | 'height': int_or_none(xpath_text(metadata, './height')), | |
569 | 'width': int_or_none(xpath_text(metadata, './width')), | |
570 | } | |
571 | ||
572 | if '.fplive.net/' in video_url: | |
573 | video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip()) | |
574 | parsed_video_url = compat_urlparse.urlparse(video_url) | |
575 | direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace( | |
576 | netloc='v.lvlt.crcdn.net', | |
577 | path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1]))) | |
578 | if self._is_valid_url(direct_video_url, video_id, video_format): | |
579 | format_info.update({ | |
580 | 'format_id': 'http-' + video_format, | |
581 | 'url': direct_video_url, | |
582 | }) | |
583 | formats.append(format_info) | |
584 | continue | |
585 | ||
586 | format_info.update({ | |
587 | 'format_id': 'rtmp-' + video_format, | |
588 | 'url': video_url, | |
589 | 'play_path': video_file, | |
590 | 'ext': 'flv', | |
591 | }) | |
592 | formats.append(format_info) | |
54f37eea | 593 | self._sort_formats(formats) |
05dee6c5 RA |
594 | |
595 | metadata = self._call_rpc_api( | |
596 | 'VideoPlayer_GetMediaMetadata', video_id, | |
597 | note='Downloading media info', data={ | |
e757fb3d | 598 | 'media_id': video_id, |
599 | }) | |
600 | ||
54a5be4d RA |
601 | subtitles = {} |
602 | for subtitle in media.get('subtitles', []): | |
603 | subtitle_url = subtitle.get('url') | |
604 | if not subtitle_url: | |
605 | continue | |
606 | subtitles.setdefault(subtitle.get('language', 'enUS'), []).append({ | |
607 | 'url': subtitle_url, | |
608 | 'ext': subtitle.get('format', 'ass'), | |
609 | }) | |
610 | if not subtitles: | |
611 | subtitles = self.extract_subtitles(video_id, webpage) | |
11b3ce85 | 612 | |
e0b6e50c S |
613 | # webpage provide more accurate data than series_title from XML |
614 | series = self._html_search_regex( | |
7abed4e0 | 615 | r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d', |
8c996232 | 616 | webpage, 'series', fatal=False) |
e0b6e50c | 617 | |
245d43ca | 618 | season = episode = episode_number = duration = None |
08c7d3da | 619 | |
ee0ba927 | 620 | if isinstance(metadata, compat_etree_Element): |
08c7d3da S |
621 | season = xpath_text(metadata, 'series_title') |
622 | episode = xpath_text(metadata, 'episode_title') | |
623 | episode_number = int_or_none(xpath_text(metadata, 'episode_number')) | |
624 | duration = float_or_none(media_metadata.get('duration'), 1000) | |
08c7d3da S |
625 | |
626 | if not episode: | |
627 | episode = media_metadata.get('title') | |
628 | if not episode_number: | |
629 | episode_number = int_or_none(media_metadata.get('episode_number')) | |
245d43ca | 630 | thumbnail_url = try_get(media, lambda x: x['thumbnail']['url']) |
631 | if thumbnail_url: | |
632 | thumbnails.append({ | |
633 | 'url': thumbnail_url, | |
634 | 'width': 640, | |
635 | 'height': 360 | |
636 | }) | |
e0b6e50c S |
637 | |
638 | season_number = int_or_none(self._search_regex( | |
7abed4e0 | 639 | r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)', |
e0b6e50c S |
640 | webpage, 'season number', default=None)) |
641 | ||
6ffc3cf7 S |
642 | info = self._search_json_ld(webpage, video_id, default={}) |
643 | ||
644 | return merge_dicts({ | |
8bcc8756 JW |
645 | 'id': video_id, |
646 | 'title': video_title, | |
38a40276 | 647 | 'description': video_description, |
08c7d3da | 648 | 'duration': duration, |
245d43ca | 649 | 'thumbnails': thumbnails, |
8bcc8756 | 650 | 'uploader': video_uploader, |
e0b6e50c | 651 | 'series': series, |
8c996232 | 652 | 'season': season, |
e0b6e50c S |
653 | 'season_number': season_number, |
654 | 'episode': episode, | |
655 | 'episode_number': episode_number, | |
8bcc8756 JW |
656 | 'subtitles': subtitles, |
657 | 'formats': formats, | |
6ffc3cf7 | 658 | }, info) |
8230018c GS |
659 | |
660 | ||
12810c9c | 661 | class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): |
611c1dd9 | 662 | IE_NAME = 'crunchyroll:playlist' |
dd078970 | 663 | _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:\w{1,2}/)?(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login|media-\d+))(?P<id>[\w\-]+))/?(?:\?|$)' |
8230018c GS |
664 | |
665 | _TESTS = [{ | |
d9488f69 | 666 | 'url': 'https://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', |
09e5d6a6 PH |
667 | 'info_dict': { |
668 | 'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', | |
669 | 'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi' | |
8230018c | 670 | }, |
09e5d6a6 | 671 | 'playlist_count': 13, |
49941c4e S |
672 | }, { |
673 | # geo-restricted (US), 18+ maturity wall, non-premium available | |
674 | 'url': 'http://www.crunchyroll.com/cosplay-complex-ova', | |
675 | 'info_dict': { | |
676 | 'id': 'cosplay-complex-ova', | |
677 | 'title': 'Cosplay Complex OVA' | |
678 | }, | |
679 | 'playlist_count': 3, | |
680 | 'skip': 'Georestricted', | |
681 | }, { | |
682 | # geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14 | |
683 | 'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1', | |
684 | 'only_matching': True, | |
dd078970 | 685 | }, { |
686 | 'url': 'http://www.crunchyroll.com/fr/ladies-versus-butlers', | |
687 | 'only_matching': True, | |
8230018c GS |
688 | }] |
689 | ||
8230018c | 690 | def _real_extract(self, url): |
09e5d6a6 PH |
691 | show_id = self._match_id(url) |
692 | ||
ca77b92f | 693 | webpage = self._download_webpage( |
d9488f69 | 694 | # https:// gives a 403, but http:// does not |
695 | self._add_skip_wall(url).replace('https://', 'http://'), show_id, | |
ca77b92f | 696 | headers=self.geo_verification_headers()) |
4681441d S |
697 | title = self._html_search_meta('name', webpage, default=None) |
698 | ||
ec3f6640 | 699 | episode_re = r'<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"' |
700 | season_re = r'<a [^>]+season-dropdown[^>]+>([^<]+)' | |
701 | paths = re.findall(f'(?s){episode_re}|{season_re}', webpage) | |
702 | ||
703 | entries, current_season = [], None | |
704 | for ep_id, ep, season in paths: | |
705 | if season: | |
706 | current_season = season | |
707 | continue | |
708 | entries.append(self.url_result( | |
709 | f'http://www.crunchyroll.com{ep}', CrunchyrollIE.ie_key(), ep_id, season=current_season)) | |
09e5d6a6 | 710 | |
8230018c | 711 | return { |
09e5d6a6 PH |
712 | '_type': 'playlist', |
713 | 'id': show_id, | |
714 | 'title': title, | |
ec3f6640 | 715 | 'entries': reversed(entries), |
09e5d6a6 | 716 | } |
dd078970 | 717 | |
718 | ||
719 | class CrunchyrollBetaIE(CrunchyrollBaseIE): | |
720 | IE_NAME = 'crunchyroll:beta' | |
721 | _VALID_URL = r'https?://beta\.crunchyroll\.com/(?P<lang>(?:\w{1,2}/)?)watch/(?P<internal_id>\w+)/(?P<id>[\w\-]+)/?(?:\?|$)' | |
722 | _TESTS = [{ | |
723 | 'url': 'https://beta.crunchyroll.com/watch/GY2P1Q98Y/to-the-future', | |
724 | 'info_dict': { | |
725 | 'id': '696363', | |
726 | 'ext': 'mp4', | |
727 | 'timestamp': 1459610100, | |
728 | 'description': 'md5:a022fbec4fbb023d43631032c91ed64b', | |
729 | 'uploader': 'Toei Animation', | |
730 | 'title': 'World Trigger Episode 73 – To the Future', | |
731 | 'upload_date': '20160402', | |
732 | }, | |
733 | 'params': {'skip_download': 'm3u8'}, | |
734 | 'expected_warnings': ['Unable to download XML'] | |
735 | }] | |
736 | ||
737 | def _real_extract(self, url): | |
738 | lang, internal_id, display_id = self._match_valid_url(url).group('lang', 'internal_id', 'id') | |
739 | webpage = self._download_webpage(url, display_id) | |
706dfe44 JH |
740 | initial_state = self._parse_json( |
741 | self._search_regex(r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'initial state'), | |
742 | display_id) | |
743 | episode_data = initial_state['content']['byId'][internal_id] | |
744 | if not self._get_cookies(url).get('etp_rt'): | |
745 | video_id = episode_data['external_id'].split('.')[1] | |
746 | series_id = episode_data['episode_metadata']['series_slug_title'] | |
747 | return self.url_result(f'https://www.crunchyroll.com/{lang}{series_id}/{display_id}-{video_id}', | |
748 | CrunchyrollIE.ie_key(), video_id) | |
749 | ||
750 | app_config = self._parse_json( | |
751 | self._search_regex(r'__APP_CONFIG__\s*=\s*({.+?})\s*;', webpage, 'app config'), | |
752 | display_id) | |
753 | client_id = app_config['cxApiParams']['accountAuthClientId'] | |
754 | api_domain = app_config['cxApiParams']['apiDomain'] | |
755 | basic_token = str(base64.b64encode(('%s:' % client_id).encode('ascii')), 'ascii') | |
756 | auth_response = self._download_json( | |
757 | f'{api_domain}/auth/v1/token', display_id, | |
758 | note='Authenticating with cookie', | |
759 | headers={ | |
760 | 'Authorization': 'Basic ' + basic_token | |
761 | }, data='grant_type=etp_rt_cookie'.encode('ascii')) | |
762 | policy_response = self._download_json( | |
763 | f'{api_domain}/index/v2', display_id, | |
764 | note='Retrieving signed policy', | |
765 | headers={ | |
766 | 'Authorization': auth_response['token_type'] + ' ' + auth_response['access_token'] | |
767 | }) | |
768 | bucket = policy_response['cms']['bucket'] | |
769 | params = { | |
770 | 'Policy': policy_response['cms']['policy'], | |
771 | 'Signature': policy_response['cms']['signature'], | |
772 | 'Key-Pair-Id': policy_response['cms']['key_pair_id'] | |
773 | } | |
774 | locale = traverse_obj(initial_state, ('localization', 'locale')) | |
775 | if locale: | |
776 | params['locale'] = locale | |
777 | episode_response = self._download_json( | |
778 | f'{api_domain}/cms/v2{bucket}/episodes/{internal_id}', display_id, | |
779 | note='Retrieving episode metadata', | |
780 | query=params) | |
781 | if episode_response.get('is_premium_only') and not episode_response.get('playback'): | |
782 | raise ExtractorError('This video is for premium members only.', expected=True) | |
783 | stream_response = self._download_json( | |
784 | episode_response['playback'], display_id, | |
785 | note='Retrieving stream info') | |
786 | ||
787 | thumbnails = [] | |
788 | for thumbnails_data in traverse_obj(episode_response, ('images', 'thumbnail')): | |
789 | for thumbnail_data in thumbnails_data: | |
790 | thumbnails.append({ | |
791 | 'url': thumbnail_data.get('source'), | |
792 | 'width': thumbnail_data.get('width'), | |
793 | 'height': thumbnail_data.get('height'), | |
794 | }) | |
795 | subtitles = {} | |
796 | for lang, subtitle_data in stream_response.get('subtitles').items(): | |
797 | subtitles[lang] = [{ | |
798 | 'url': subtitle_data.get('url'), | |
799 | 'ext': subtitle_data.get('format') | |
800 | }] | |
801 | ||
802 | requested_hardsubs = [('' if val == 'none' else val) for val in (self._configuration_arg('hardsub') or ['none'])] | |
803 | hardsub_preference = qualities(requested_hardsubs[::-1]) | |
804 | requested_formats = self._configuration_arg('format') or ['adaptive_hls'] | |
805 | ||
806 | formats = [] | |
807 | for stream_type, streams in stream_response.get('streams', {}).items(): | |
808 | if stream_type not in requested_formats: | |
809 | continue | |
810 | for stream in streams.values(): | |
811 | hardsub_lang = stream.get('hardsub_locale') or '' | |
812 | if hardsub_lang.lower() not in requested_hardsubs: | |
813 | continue | |
814 | format_id = join_nonempty( | |
815 | stream_type, | |
816 | format_field(stream, 'hardsub_locale', 'hardsub-%s')) | |
817 | if not stream.get('url'): | |
818 | continue | |
819 | if stream_type.split('_')[-1] == 'hls': | |
820 | adaptive_formats = self._extract_m3u8_formats( | |
821 | stream['url'], display_id, 'mp4', m3u8_id=format_id, | |
822 | note='Downloading %s information' % format_id, | |
823 | fatal=False) | |
824 | elif stream_type.split('_')[-1] == 'dash': | |
825 | adaptive_formats = self._extract_mpd_formats( | |
826 | stream['url'], display_id, mpd_id=format_id, | |
827 | note='Downloading %s information' % format_id, | |
828 | fatal=False) | |
829 | for f in adaptive_formats: | |
830 | if f.get('acodec') != 'none': | |
831 | f['language'] = stream_response.get('audio_locale') | |
832 | f['quality'] = hardsub_preference(hardsub_lang.lower()) | |
833 | formats.extend(adaptive_formats) | |
834 | self._sort_formats(formats) | |
835 | ||
836 | return { | |
837 | 'id': internal_id, | |
838 | 'title': '%s Episode %s – %s' % (episode_response.get('season_title'), episode_response.get('episode'), episode_response.get('title')), | |
839 | 'description': episode_response.get('description').replace(r'\r\n', '\n'), | |
840 | 'duration': float_or_none(episode_response.get('duration_ms'), 1000), | |
841 | 'thumbnails': thumbnails, | |
842 | 'series': episode_response.get('series_title'), | |
843 | 'series_id': episode_response.get('series_id'), | |
844 | 'season': episode_response.get('season_title'), | |
845 | 'season_id': episode_response.get('season_id'), | |
846 | 'season_number': episode_response.get('season_number'), | |
847 | 'episode': episode_response.get('title'), | |
848 | 'episode_number': episode_response.get('sequence_number'), | |
849 | 'subtitles': subtitles, | |
850 | 'formats': formats | |
851 | } | |
dd078970 | 852 | |
853 | ||
854 | class CrunchyrollBetaShowIE(CrunchyrollBaseIE): | |
855 | IE_NAME = 'crunchyroll:playlist:beta' | |
856 | _VALID_URL = r'https?://beta\.crunchyroll\.com/(?P<lang>(?:\w{1,2}/)?)series/\w+/(?P<id>[\w\-]+)/?(?:\?|$)' | |
857 | _TESTS = [{ | |
858 | 'url': 'https://beta.crunchyroll.com/series/GY19NQ2QR/Girl-Friend-BETA', | |
859 | 'info_dict': { | |
860 | 'id': 'girl-friend-beta', | |
861 | 'title': 'Girl Friend BETA', | |
862 | }, | |
863 | 'playlist_mincount': 10, | |
864 | }, { | |
865 | 'url': 'https://beta.crunchyroll.com/it/series/GY19NQ2QR/Girl-Friend-BETA', | |
866 | 'only_matching': True, | |
867 | }] | |
868 | ||
869 | def _real_extract(self, url): | |
870 | lang, series_id = self._match_valid_url(url).group('lang', 'id') | |
871 | return self.url_result(f'https://www.crunchyroll.com/{lang}{series_id.lower()}', | |
872 | CrunchyrollShowPlaylistIE.ie_key(), series_id) |