]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/crunchyroll.py
d15fd3744d5a03e383cb36d0dd9e990d061aa6cb
[youtubedl] / youtube_dl / extractor / crunchyroll.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5 import json
6 import base64
7 import zlib
8
9 from hashlib import sha1
10 from math import pow, sqrt, floor
11 from .common import InfoExtractor
12 from ..compat import (
13 compat_etree_fromstring,
14 compat_urllib_parse_urlencode,
15 compat_urllib_request,
16 compat_urlparse,
17 )
18 from ..utils import (
19 ExtractorError,
20 bytes_to_intlist,
21 intlist_to_bytes,
22 int_or_none,
23 lowercase_escape,
24 remove_end,
25 sanitized_Request,
26 unified_strdate,
27 urlencode_postdata,
28 xpath_text,
29 extract_attributes,
30 )
31 from ..aes import (
32 aes_cbc_decrypt,
33 )
34
35
36 class CrunchyrollBaseIE(InfoExtractor):
37 _LOGIN_URL = 'https://www.crunchyroll.com/login'
38 _LOGIN_FORM = 'login_form'
39 _NETRC_MACHINE = 'crunchyroll'
40
41 def _login(self):
42 (username, password) = self._get_login_info()
43 if username is None:
44 return
45
46 login_page = self._download_webpage(
47 self._LOGIN_URL, None, 'Downloading login page')
48
49 def is_logged(webpage):
50 return '<title>Redirecting' in webpage
51
52 # Already logged in
53 if is_logged(login_page):
54 return
55
56 login_form_str = self._search_regex(
57 r'(?P<form><form[^>]+?id=(["\'])%s\2[^>]*>)' % self._LOGIN_FORM,
58 login_page, 'login form', group='form')
59
60 post_url = extract_attributes(login_form_str).get('action')
61 if not post_url:
62 post_url = self._LOGIN_URL
63 elif not post_url.startswith('http'):
64 post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
65
66 login_form = self._form_hidden_inputs(self._LOGIN_FORM, login_page)
67
68 login_form.update({
69 'login_form[name]': username,
70 'login_form[password]': password,
71 })
72
73 response = self._download_webpage(
74 post_url, None, 'Logging in', 'Wrong login info',
75 data=urlencode_postdata(login_form),
76 headers={'Content-Type': 'application/x-www-form-urlencoded'})
77
78 # Successful login
79 if is_logged(response):
80 return
81
82 error = self._html_search_regex(
83 '(?s)<ul[^>]+class=["\']messages["\'][^>]*>(.+?)</ul>',
84 response, 'error message', default=None)
85 if error:
86 raise ExtractorError('Unable to login: %s' % error, expected=True)
87
88 raise ExtractorError('Unable to log in')
89
90 def _real_initialize(self):
91 self._login()
92
93 def _download_webpage(self, url_or_request, *args, **kwargs):
94 request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
95 else sanitized_Request(url_or_request))
96 # Accept-Language must be set explicitly to accept any language to avoid issues
97 # similar to https://github.com/rg3/youtube-dl/issues/6797.
98 # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
99 # should be imposed or not (from what I can see it just takes the first language
100 # ignoring the priority and requires it to correspond the IP). By the way this causes
101 # Crunchyroll to not work in georestriction cases in some browsers that don't place
102 # the locale lang first in header. However allowing any language seems to workaround the issue.
103 request.add_header('Accept-Language', '*')
104 return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
105
106 @staticmethod
107 def _add_skip_wall(url):
108 parsed_url = compat_urlparse.urlparse(url)
109 qs = compat_urlparse.parse_qs(parsed_url.query)
110 # Always force skip_wall to bypass maturity wall, namely 18+ confirmation message:
111 # > This content may be inappropriate for some people.
112 # > Are you sure you want to continue?
113 # since it's not disabled by default in crunchyroll account's settings.
114 # See https://github.com/rg3/youtube-dl/issues/7202.
115 qs['skip_wall'] = ['1']
116 return compat_urlparse.urlunparse(
117 parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
118
119
120 class CrunchyrollIE(CrunchyrollBaseIE):
121 _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
122 _TESTS = [{
123 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
124 'info_dict': {
125 'id': '645513',
126 'ext': 'mp4',
127 'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
128 'description': 'md5:2d17137920c64f2f49981a7797d275ef',
129 'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
130 'uploader': 'Yomiuri Telecasting Corporation (YTV)',
131 'upload_date': '20131013',
132 'url': 're:(?!.*&amp)',
133 },
134 'params': {
135 # rtmp
136 'skip_download': True,
137 },
138 }, {
139 'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
140 'info_dict': {
141 'id': '589804',
142 'ext': 'flv',
143 'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
144 'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
145 'thumbnail': r're:^https?://.*\.jpg$',
146 'uploader': 'Danny Choo Network',
147 'upload_date': '20120213',
148 },
149 'params': {
150 # rtmp
151 'skip_download': True,
152 },
153 'skip': 'Video gone',
154 }, {
155 'url': 'http://www.crunchyroll.com/rezero-starting-life-in-another-world-/episode-5-the-morning-of-our-promise-is-still-distant-702409',
156 'info_dict': {
157 'id': '702409',
158 'ext': 'mp4',
159 'title': 'Re:ZERO -Starting Life in Another World- Episode 5 – The Morning of Our Promise Is Still Distant',
160 'description': 'md5:97664de1ab24bbf77a9c01918cb7dca9',
161 'thumbnail': r're:^https?://.*\.jpg$',
162 'uploader': 'TV TOKYO',
163 'upload_date': '20160508',
164 },
165 'params': {
166 # m3u8 download
167 'skip_download': True,
168 },
169 }, {
170 'url': 'http://www.crunchyroll.com/konosuba-gods-blessing-on-this-wonderful-world/episode-1-give-me-deliverance-from-this-judicial-injustice-727589',
171 'info_dict': {
172 'id': '727589',
173 'ext': 'mp4',
174 'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance from this Judicial Injustice!",
175 'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
176 'thumbnail': r're:^https?://.*\.jpg$',
177 'uploader': 'Kadokawa Pictures Inc.',
178 'upload_date': '20170118',
179 'series': "KONOSUBA -God's blessing on this wonderful world!",
180 'season': "KONOSUBA -God's blessing on this wonderful world! 2",
181 'season_number': 2,
182 'episode': 'Give Me Deliverance from this Judicial Injustice!',
183 'episode_number': 1,
184 },
185 'params': {
186 # m3u8 download
187 'skip_download': True,
188 },
189 }, {
190 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
191 'only_matching': True,
192 }, {
193 # geo-restricted (US), 18+ maturity wall, non-premium available
194 'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617',
195 'only_matching': True,
196 }, {
197 # A description with double quotes
198 'url': 'http://www.crunchyroll.com/11eyes/episode-1-piros-jszaka-red-night-535080',
199 'info_dict': {
200 'id': '535080',
201 'ext': 'mp4',
202 'title': '11eyes Episode 1 – Piros éjszaka - Red Night',
203 'description': 'Kakeru and Yuka are thrown into an alternate nightmarish world they call "Red Night".',
204 'uploader': 'Marvelous AQL Inc.',
205 'upload_date': '20091021',
206 },
207 'params': {
208 # Just test metadata extraction
209 'skip_download': True,
210 },
211 }, {
212 # make sure we can extract an uploader name that's not a link
213 'url': 'http://www.crunchyroll.com/hakuoki-reimeiroku/episode-1-dawn-of-the-divine-warriors-606899',
214 'info_dict': {
215 'id': '606899',
216 'ext': 'mp4',
217 'title': 'Hakuoki Reimeiroku Episode 1 – Dawn of the Divine Warriors',
218 'description': 'Ryunosuke was left to die, but Serizawa-san asked him a simple question "Do you want to live?"',
219 'uploader': 'Geneon Entertainment',
220 'upload_date': '20120717',
221 },
222 'params': {
223 # just test metadata extraction
224 'skip_download': True,
225 },
226 }, {
227 # A video with a vastly different season name compared to the series name
228 'url': 'http://www.crunchyroll.com/nyarko-san-another-crawling-chaos/episode-1-test-590532',
229 'info_dict': {
230 'id': '590532',
231 'ext': 'mp4',
232 'title': 'Haiyoru! Nyaruani (ONA) Episode 1 – Test',
233 'description': 'Mahiro and Nyaruko talk about official certification.',
234 'uploader': 'TV TOKYO',
235 'upload_date': '20120305',
236 'series': 'Nyarko-san: Another Crawling Chaos',
237 'season': 'Haiyoru! Nyaruani (ONA)',
238 },
239 'params': {
240 # Just test metadata extraction
241 'skip_download': True,
242 },
243 }]
244
245 _FORMAT_IDS = {
246 '360': ('60', '106'),
247 '480': ('61', '106'),
248 '720': ('62', '106'),
249 '1080': ('80', '108'),
250 }
251
252 def _decrypt_subtitles(self, data, iv, id):
253 data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
254 iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
255 id = int(id)
256
257 def obfuscate_key_aux(count, modulo, start):
258 output = list(start)
259 for _ in range(count):
260 output.append(output[-1] + output[-2])
261 # cut off start values
262 output = output[2:]
263 output = list(map(lambda x: x % modulo + 33, output))
264 return output
265
266 def obfuscate_key(key):
267 num1 = int(floor(pow(2, 25) * sqrt(6.9)))
268 num2 = (num1 ^ key) << 5
269 num3 = key ^ num1
270 num4 = num3 ^ (num3 >> 3) ^ num2
271 prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2)))
272 shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
273 # Extend 160 Bit hash to 256 Bit
274 return shaHash + [0] * 12
275
276 key = obfuscate_key(id)
277
278 decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
279 return zlib.decompress(decrypted_data)
280
281 def _convert_subtitles_to_srt(self, sub_root):
282 output = ''
283
284 for i, event in enumerate(sub_root.findall('./events/event'), 1):
285 start = event.attrib['start'].replace('.', ',')
286 end = event.attrib['end'].replace('.', ',')
287 text = event.attrib['text'].replace('\\N', '\n')
288 output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
289 return output
290
291 def _convert_subtitles_to_ass(self, sub_root):
292 output = ''
293
294 def ass_bool(strvalue):
295 assvalue = '0'
296 if strvalue == '1':
297 assvalue = '-1'
298 return assvalue
299
300 output = '[Script Info]\n'
301 output += 'Title: %s\n' % sub_root.attrib['title']
302 output += 'ScriptType: v4.00+\n'
303 output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style']
304 output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x']
305 output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y']
306 output += """
307 [V4+ Styles]
308 Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
309 """
310 for style in sub_root.findall('./styles/style'):
311 output += 'Style: ' + style.attrib['name']
312 output += ',' + style.attrib['font_name']
313 output += ',' + style.attrib['font_size']
314 output += ',' + style.attrib['primary_colour']
315 output += ',' + style.attrib['secondary_colour']
316 output += ',' + style.attrib['outline_colour']
317 output += ',' + style.attrib['back_colour']
318 output += ',' + ass_bool(style.attrib['bold'])
319 output += ',' + ass_bool(style.attrib['italic'])
320 output += ',' + ass_bool(style.attrib['underline'])
321 output += ',' + ass_bool(style.attrib['strikeout'])
322 output += ',' + style.attrib['scale_x']
323 output += ',' + style.attrib['scale_y']
324 output += ',' + style.attrib['spacing']
325 output += ',' + style.attrib['angle']
326 output += ',' + style.attrib['border_style']
327 output += ',' + style.attrib['outline']
328 output += ',' + style.attrib['shadow']
329 output += ',' + style.attrib['alignment']
330 output += ',' + style.attrib['margin_l']
331 output += ',' + style.attrib['margin_r']
332 output += ',' + style.attrib['margin_v']
333 output += ',' + style.attrib['encoding']
334 output += '\n'
335
336 output += """
337 [Events]
338 Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
339 """
340 for event in sub_root.findall('./events/event'):
341 output += 'Dialogue: 0'
342 output += ',' + event.attrib['start']
343 output += ',' + event.attrib['end']
344 output += ',' + event.attrib['style']
345 output += ',' + event.attrib['name']
346 output += ',' + event.attrib['margin_l']
347 output += ',' + event.attrib['margin_r']
348 output += ',' + event.attrib['margin_v']
349 output += ',' + event.attrib['effect']
350 output += ',' + event.attrib['text']
351 output += '\n'
352
353 return output
354
355 def _extract_subtitles(self, subtitle):
356 sub_root = compat_etree_fromstring(subtitle)
357 return [{
358 'ext': 'srt',
359 'data': self._convert_subtitles_to_srt(sub_root),
360 }, {
361 'ext': 'ass',
362 'data': self._convert_subtitles_to_ass(sub_root),
363 }]
364
365 def _get_subtitles(self, video_id, webpage):
366 subtitles = {}
367 for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
368 sub_page = self._download_webpage(
369 'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,
370 video_id, note='Downloading subtitles for ' + sub_name)
371 id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False)
372 iv = self._search_regex(r'<iv>([^<]+)', sub_page, 'subtitle_iv', fatal=False)
373 data = self._search_regex(r'<data>([^<]+)', sub_page, 'subtitle_data', fatal=False)
374 if not id or not iv or not data:
375 continue
376 subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
377 lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
378 if not lang_code:
379 continue
380 subtitles[lang_code] = self._extract_subtitles(subtitle)
381 return subtitles
382
383 def _real_extract(self, url):
384 mobj = re.match(self._VALID_URL, url)
385 video_id = mobj.group('video_id')
386
387 if mobj.group('prefix') == 'm':
388 mobile_webpage = self._download_webpage(url, video_id, 'Downloading mobile webpage')
389 webpage_url = self._search_regex(r'<link rel="canonical" href="([^"]+)" />', mobile_webpage, 'webpage_url')
390 else:
391 webpage_url = 'http://www.' + mobj.group('url')
392
393 webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
394 note_m = self._html_search_regex(
395 r'<div class="showmedia-trailer-notice">(.+?)</div>',
396 webpage, 'trailer-notice', default='')
397 if note_m:
398 raise ExtractorError(note_m)
399
400 mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
401 if mobj:
402 msg = json.loads(mobj.group('msg'))
403 if msg.get('type') == 'error':
404 raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
405
406 if 'To view this, please log in to verify you are 18 or older.' in webpage:
407 self.raise_login_required()
408
409 video_title = self._html_search_regex(
410 r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
411 webpage, 'video_title')
412 video_title = re.sub(r' {2,}', ' ', video_title)
413 video_description = self._parse_json(self._html_search_regex(
414 r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id,
415 webpage, 'description', default='{}'), video_id).get('description')
416 if video_description:
417 video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
418 video_upload_date = self._html_search_regex(
419 [r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'],
420 webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
421 if video_upload_date:
422 video_upload_date = unified_strdate(video_upload_date)
423 video_uploader = self._html_search_regex(
424 # try looking for both an uploader that's a link and one that's not
425 [r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', r'<div>\s*Publisher:\s*<span>\s*(.+?)\s*</span>\s*</div>'],
426 webpage, 'video_uploader', fatal=False)
427
428 available_fmts = []
429 for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
430 attrs = extract_attributes(a)
431 href = attrs.get('href')
432 if href and '/freetrial' in href:
433 continue
434 available_fmts.append(fmt)
435 if not available_fmts:
436 for p in (r'token=["\']showmedia\.([0-9]{3,4})p"', r'showmedia\.([0-9]{3,4})p'):
437 available_fmts = re.findall(p, webpage)
438 if available_fmts:
439 break
440 video_encode_ids = []
441 formats = []
442 for fmt in available_fmts:
443 stream_quality, stream_format = self._FORMAT_IDS[fmt]
444 video_format = fmt + 'p'
445 streamdata_req = sanitized_Request(
446 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
447 % (video_id, stream_format, stream_quality),
448 compat_urllib_parse_urlencode({'current_page': url}).encode('utf-8'))
449 streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
450 streamdata = self._download_xml(
451 streamdata_req, video_id,
452 note='Downloading media info for %s' % video_format)
453 stream_info = streamdata.find('./{default}preload/stream_info')
454 video_encode_id = xpath_text(stream_info, './video_encode_id')
455 if video_encode_id in video_encode_ids:
456 continue
457 video_encode_ids.append(video_encode_id)
458
459 video_file = xpath_text(stream_info, './file')
460 if not video_file:
461 continue
462 if video_file.startswith('http'):
463 formats.extend(self._extract_m3u8_formats(
464 video_file, video_id, 'mp4', entry_protocol='m3u8_native',
465 m3u8_id='hls', fatal=False))
466 continue
467
468 video_url = xpath_text(stream_info, './host')
469 if not video_url:
470 continue
471 metadata = stream_info.find('./metadata')
472 format_info = {
473 'format': video_format,
474 'format_id': video_format,
475 'height': int_or_none(xpath_text(metadata, './height')),
476 'width': int_or_none(xpath_text(metadata, './width')),
477 }
478
479 if '.fplive.net/' in video_url:
480 video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
481 parsed_video_url = compat_urlparse.urlparse(video_url)
482 direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
483 netloc='v.lvlt.crcdn.net',
484 path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
485 if self._is_valid_url(direct_video_url, video_id, video_format):
486 format_info.update({
487 'url': direct_video_url,
488 })
489 formats.append(format_info)
490 continue
491
492 format_info.update({
493 'url': video_url,
494 'play_path': video_file,
495 'ext': 'flv',
496 })
497 formats.append(format_info)
498 self._sort_formats(formats)
499
500 metadata = self._download_xml(
501 'http://www.crunchyroll.com/xml', video_id,
502 note='Downloading media info', query={
503 'req': 'RpcApiVideoPlayer_GetMediaMetadata',
504 'media_id': video_id,
505 })
506
507 subtitles = self.extract_subtitles(video_id, webpage)
508
509 # webpage provide more accurate data than series_title from XML
510 series = self._html_search_regex(
511 r'id=["\']showmedia_about_episode_num[^>]+>\s*<a[^>]+>([^<]+)',
512 webpage, 'series', fatal=False)
513 season = xpath_text(metadata, 'series_title')
514
515 episode = xpath_text(metadata, 'episode_title')
516 episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
517
518 season_number = int_or_none(self._search_regex(
519 r'(?s)<h4[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h4>\s*<h4>\s*Season (\d+)',
520 webpage, 'season number', default=None))
521
522 return {
523 'id': video_id,
524 'title': video_title,
525 'description': video_description,
526 'thumbnail': xpath_text(metadata, 'episode_image_url'),
527 'uploader': video_uploader,
528 'upload_date': video_upload_date,
529 'series': series,
530 'season': season,
531 'season_number': season_number,
532 'episode': episode,
533 'episode_number': episode_number,
534 'subtitles': subtitles,
535 'formats': formats,
536 }
537
538
539 class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
540 IE_NAME = 'crunchyroll:playlist'
541 _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?(?:\?|$)'
542
543 _TESTS = [{
544 'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
545 'info_dict': {
546 'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
547 'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
548 },
549 'playlist_count': 13,
550 }, {
551 # geo-restricted (US), 18+ maturity wall, non-premium available
552 'url': 'http://www.crunchyroll.com/cosplay-complex-ova',
553 'info_dict': {
554 'id': 'cosplay-complex-ova',
555 'title': 'Cosplay Complex OVA'
556 },
557 'playlist_count': 3,
558 'skip': 'Georestricted',
559 }, {
560 # geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14
561 'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1',
562 'only_matching': True,
563 }]
564
565 def _real_extract(self, url):
566 show_id = self._match_id(url)
567
568 webpage = self._download_webpage(self._add_skip_wall(url), show_id)
569 title = self._html_search_regex(
570 r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
571 webpage, 'title')
572 episode_paths = re.findall(
573 r'(?s)<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"',
574 webpage)
575 entries = [
576 self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll', ep_id)
577 for ep_id, ep in episode_paths
578 ]
579 entries.reverse()
580
581 return {
582 '_type': 'playlist',
583 'id': show_id,
584 'title': title,
585 'entries': entries,
586 }