aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/crunchyroll.py
blob: f811c7f33e4b56d59217565500bd47633b6dfc06 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
# coding: utf-8
from __future__ import unicode_literals

import re
import json
import base64
import zlib

from hashlib import sha1
from math import pow, sqrt, floor
from .common import InfoExtractor
from ..compat import (
    compat_etree_fromstring,
    compat_urllib_parse_urlencode,
    compat_urllib_request,
    compat_urlparse,
)
from ..utils import (
    ExtractorError,
    bytes_to_intlist,
    intlist_to_bytes,
    int_or_none,
    lowercase_escape,
    remove_end,
    sanitized_Request,
    unified_strdate,
    urlencode_postdata,
    xpath_text,
    extract_attributes,
)
from ..aes import (
    aes_cbc_decrypt,
)


class CrunchyrollBaseIE(InfoExtractor):
    _LOGIN_URL = 'https://www.crunchyroll.com/login'
    _LOGIN_FORM = 'login_form'
    _NETRC_MACHINE = 'crunchyroll'

    def _login(self):
        (username, password) = self._get_login_info()
        if username is None:
            return

        login_page = self._download_webpage(
            self._LOGIN_URL, None, 'Downloading login page')

        def is_logged(webpage):
            return '<title>Redirecting' in webpage

        # Already logged in
        if is_logged(login_page):
            return

        login_form_str = self._search_regex(
            r'(?P<form><form[^>]+?id=(["\'])%s\2[^>]*>)' % self._LOGIN_FORM,
            login_page, 'login form', group='form')

        post_url = extract_attributes(login_form_str).get('action')
        if not post_url:
            post_url = self._LOGIN_URL
        elif not post_url.startswith('http'):
            post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)

        login_form = self._form_hidden_inputs(self._LOGIN_FORM, login_page)

        login_form.update({
            'login_form[name]': username,
            'login_form[password]': password,
        })

        response = self._download_webpage(
            post_url, None, 'Logging in', 'Wrong login info',
            data=urlencode_postdata(login_form),
            headers={'Content-Type': 'application/x-www-form-urlencoded'})

        # Successful login
        if is_logged(response):
            return

        error = self._html_search_regex(
            '(?s)<ul[^>]+class=["\']messages["\'][^>]*>(.+?)</ul>',
            response, 'error message', default=None)
        if error:
            raise ExtractorError('Unable to login: %s' % error, expected=True)

        raise ExtractorError('Unable to log in')

    def _real_initialize(self):
        self._login()

    def _download_webpage(self, url_or_request, *args, **kwargs):
        request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
                   else sanitized_Request(url_or_request))
        # Accept-Language must be set explicitly to accept any language to avoid issues
        # similar to https://github.com/rg3/youtube-dl/issues/6797.
        # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
        # should be imposed or not (from what I can see it just takes the first language
        # ignoring the priority and requires it to correspond the IP). By the way this causes
        # Crunchyroll to not work in georestriction cases in some browsers that don't place
        # the locale lang first in header. However allowing any language seems to workaround the issue.
        request.add_header('Accept-Language', '*')
        return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)

    @staticmethod
    def _add_skip_wall(url):
        parsed_url = compat_urlparse.urlparse(url)
        qs = compat_urlparse.parse_qs(parsed_url.query)
        # Always force skip_wall to bypass maturity wall, namely 18+ confirmation message:
        # > This content may be inappropriate for some people.
        # > Are you sure you want to continue?
        # since it's not disabled by default in crunchyroll account's settings.
        # See https://github.com/rg3/youtube-dl/issues/7202.
        qs['skip_wall'] = ['1']
        return compat_urlparse.urlunparse(
            parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))


class CrunchyrollIE(CrunchyrollBaseIE):
    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
    _TESTS = [{
        'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
        'info_dict': {
            'id': '645513',
            'ext': 'flv',
            'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
            'description': 'md5:2d17137920c64f2f49981a7797d275ef',
            'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
            'uploader': 'Yomiuri Telecasting Corporation (YTV)',
            'upload_date': '20131013',
            'url': 're:(?!.*&amp)',
        },
        'params': {
            # rtmp
            'skip_download': True,
        },
    }, {
        'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
        'info_dict': {
            'id': '589804',
            'ext': 'flv',
            'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
            'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
            'thumbnail': r're:^https?://.*\.jpg$',
            'uploader': 'Danny Choo Network',
            'upload_date': '20120213',
        },
        'params': {
            # rtmp
            'skip_download': True,
        },
        'skip': 'Video gone',
    }, {
        'url': 'http://www.crunchyroll.com/rezero-starting-life-in-another-world-/episode-5-the-morning-of-our-promise-is-still-distant-702409',
        'info_dict': {
            'id': '702409',
            'ext': 'mp4',
            'title': 'Re:ZERO -Starting Life in Another World- Episode 5 – The Morning of Our Promise Is Still Distant',
            'description': 'md5:97664de1ab24bbf77a9c01918cb7dca9',
            'thumbnail': r're:^https?://.*\.jpg$',
            'uploader': 'TV TOKYO',
            'upload_date': '20160508',
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }, {
        'url': 'http://www.crunchyroll.com/konosuba-gods-blessing-on-this-wonderful-world/episode-1-give-me-deliverance-from-this-judicial-injustice-727589',
        'info_dict': {
            'id': '727589',
            'ext': 'mp4',
            'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance from this Judicial Injustice!",
            'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
            'thumbnail': r're:^https?://.*\.jpg$',
            'uploader': 'Kadokawa Pictures Inc.',
            'upload_date': '20170118',
            'series': "KONOSUBA -God's blessing on this wonderful world!",
            'season_number': 2,
            'episode': 'Give Me Deliverance from this Judicial Injustice!',
            'episode_number': 1,
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }, {
        'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
        'only_matching': True,
    }, {
        # geo-restricted (US), 18+ maturity wall, non-premium available
        'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617',
        'only_matching': True,
    }]

    _FORMAT_IDS = {
        '360': ('60', '106'),
        '480': ('61', '106'),
        '720': ('62', '106'),
        '1080': ('80', '108'),
    }

    def _decrypt_subtitles(self, data, iv, id):
        data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
        iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
        id = int(id)

        def obfuscate_key_aux(count, modulo, start):
            output = list(start)
            for _ in range(count):
                output.append(output[-1] + output[-2])
            # cut off start values
            output = output[2:]
            output = list(map(lambda x: x % modulo + 33, output))
            return output

        def obfuscate_key(key):
            num1 = int(floor(pow(2, 25) * sqrt(6.9)))
            num2 = (num1 ^ key) << 5
            num3 = key ^ num1
            num4 = num3 ^ (num3 >> 3) ^ num2
            prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2)))
            shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
            # Extend 160 Bit hash to 256 Bit
            return shaHash + [0] * 12

        key = obfuscate_key(id)

        decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
        return zlib.decompress(decrypted_data)

    def _convert_subtitles_to_srt(self, sub_root):
        output = ''

        for i, event in enumerate(sub_root.findall('./events/event'), 1):
            start = event.attrib['start'].replace('.', ',')
            end = event.attrib['end'].replace('.', ',')
            text = event.attrib['text'].replace('\\N', '\n')
            output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
        return output

    def _convert_subtitles_to_ass(self, sub_root):
        output = ''

        def ass_bool(strvalue):
            assvalue = '0'
            if strvalue == '1':
                assvalue = '-1'
            return assvalue

        output = '[Script Info]\n'
        output += 'Title: %s\n' % sub_root.attrib['title']
        output += 'ScriptType: v4.00+\n'
        output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style']
        output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x']
        output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y']
        output += """ScaledBorderAndShadow: no

[V4+ Styles]
Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
"""
        for style in sub_root.findall('./styles/style'):
            output += 'Style: ' + style.attrib['name']
            output += ',' + style.attrib['font_name']
            output += ',' + style.attrib['font_size']
            output += ',' + style.attrib['primary_colour']
            output += ',' + style.attrib['secondary_colour']
            output += ',' + style.attrib['outline_colour']
            output += ',' + style.attrib['back_colour']
            output += ',' + ass_bool(style.attrib['bold'])
            output += ',' + ass_bool(style.attrib['italic'])
            output += ',' + ass_bool(style.attrib['underline'])
            output += ',' + ass_bool(style.attrib['strikeout'])
            output += ',' + style.attrib['scale_x']
            output += ',' + style.attrib['scale_y']
            output += ',' + style.attrib['spacing']
            output += ',' + style.attrib['angle']
            output += ',' + style.attrib['border_style']
            output += ',' + style.attrib['outline']
            output += ',' + style.attrib['shadow']
            output += ',' + style.attrib['alignment']
            output += ',' + style.attrib['margin_l']
            output += ',' + style.attrib['margin_r']
            output += ',' + style.attrib['margin_v']
            output += ',' + style.attrib['encoding']
            output += '\n'

        output += """
[Events]
Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
"""
        for event in sub_root.findall('./events/event'):
            output += 'Dialogue: 0'
            output += ',' + event.attrib['start']
            output += ',' + event.attrib['end']
            output += ',' + event.attrib['style']
            output += ',' + event.attrib['name']
            output += ',' + event.attrib['margin_l']
            output += ',' + event.attrib['margin_r']
            output += ',' + event.attrib['margin_v']
            output += ',' + event.attrib['effect']
            output += ',' + event.attrib['text']
            output += '\n'

        return output

    def _extract_subtitles(self, subtitle):
        sub_root = compat_etree_fromstring(subtitle)
        return [{
            'ext': 'srt',
            'data': self._convert_subtitles_to_srt(sub_root),
        }, {
            'ext': 'ass',
            'data': self._convert_subtitles_to_ass(sub_root),
        }]

    def _get_subtitles(self, video_id, webpage):
        subtitles = {}
        for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
            sub_page = self._download_webpage(
                'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,
                video_id, note='Downloading subtitles for ' + sub_name)
            id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False)
            iv = self._search_regex(r'<iv>([^<]+)', sub_page, 'subtitle_iv', fatal=False)
            data = self._search_regex(r'<data>([^<]+)', sub_page, 'subtitle_data', fatal=False)
            if not id or not iv or not data:
                continue
            subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
            lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
            if not lang_code:
                continue
            subtitles[lang_code] = self._extract_subtitles(subtitle)
        return subtitles

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('video_id')

        if mobj.group('prefix') == 'm':
            mobile_webpage = self._download_webpage(url, video_id, 'Downloading mobile webpage')
            webpage_url = self._search_regex(r'<link rel="canonical" href="([^"]+)" />', mobile_webpage, 'webpage_url')
        else:
            webpage_url = 'http://www.' + mobj.group('url')

        webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
        note_m = self._html_search_regex(
            r'<div class="showmedia-trailer-notice">(.+?)</div>',
            webpage, 'trailer-notice', default='')
        if note_m:
            raise ExtractorError(note_m)

        mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
        if mobj:
            msg = json.loads(mobj.group('msg'))
            if msg.get('type') == 'error':
                raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)

        if 'To view this, please log in to verify you are 18 or older.' in webpage:
            self.raise_login_required()

        video_title = self._html_search_regex(
            r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
            webpage, 'video_title')
        video_title = re.sub(r' {2,}', ' ', video_title)
        video_description = self._html_search_regex(
            r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id,
            webpage, 'description', default=None)
        if video_description:
            video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
        video_upload_date = self._html_search_regex(
            [r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'],
            webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
        if video_upload_date:
            video_upload_date = unified_strdate(video_upload_date)
        video_uploader = self._html_search_regex(
            r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage,
            'video_uploader', fatal=False)

        available_fmts = []
        for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
            attrs = extract_attributes(a)
            href = attrs.get('href')
            if href and '/freetrial' in href:
                continue
            available_fmts.append(fmt)
        if not available_fmts:
            for p in (r'token=["\']showmedia\.([0-9]{3,4})p"', r'showmedia\.([0-9]{3,4})p'):
                available_fmts = re.findall(p, webpage)
                if available_fmts:
                    break
        video_encode_ids = []
        formats = []
        for fmt in available_fmts:
            stream_quality, stream_format = self._FORMAT_IDS[fmt]
            video_format = fmt + 'p'
            streamdata_req = sanitized_Request(
                'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
                % (video_id, stream_format, stream_quality),
                compat_urllib_parse_urlencode({'current_page': url}).encode('utf-8'))
            streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
            streamdata = self._download_xml(
                streamdata_req, video_id,
                note='Downloading media info for %s' % video_format)
            stream_info = streamdata.find('./{default}preload/stream_info')
            video_encode_id = xpath_text(stream_info, './video_encode_id')
            if video_encode_id in video_encode_ids:
                continue
            video_encode_ids.append(video_encode_id)

            video_file = xpath_text(stream_info, './file')
            if not video_file:
                continue
            if video_file.startswith('http'):
                formats.extend(self._extract_m3u8_formats(
                    video_file, video_id, 'mp4', entry_protocol='m3u8_native',
                    m3u8_id='hls', fatal=False))
                continue

            video_url = xpath_text(stream_info, './host')
            if not video_url:
                continue
            metadata = stream_info.find('./metadata')
            format_info = {
                'format': video_format,
                'format_id': video_format,
                'height': int_or_none(xpath_text(metadata, './height')),
                'width': int_or_none(xpath_text(metadata, './width')),
            }

            if '.fplive.net/' in video_url:
                video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
                parsed_video_url = compat_urlparse.urlparse(video_url)
                direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
                    netloc='v.lvlt.crcdn.net',
                    path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
                if self._is_valid_url(direct_video_url, video_id, video_format):
                    format_info.update({
                        'url': direct_video_url,
                    })
                    formats.append(format_info)
                    continue

            format_info.update({
                'url': video_url,
                'play_path': video_file,
                'ext': 'flv',
            })
            formats.append(format_info)
        self._sort_formats(formats)

        metadata = self._download_xml(
            'http://www.crunchyroll.com/xml', video_id,
            note='Downloading media info', query={
                'req': 'RpcApiVideoPlayer_GetMediaMetadata',
                'media_id': video_id,
            })

        subtitles = self.extract_subtitles(video_id, webpage)

        # webpage provide more accurate data than series_title from XML
        series = self._html_search_regex(
            r'id=["\']showmedia_about_episode_num[^>]+>\s*<a[^>]+>([^<]+)',
            webpage, 'series', default=xpath_text(metadata, 'series_title'))

        episode = xpath_text(metadata, 'episode_title')
        episode_number = int_or_none(xpath_text(metadata, 'episode_number'))

        season_number = int_or_none(self._search_regex(
            r'(?s)<h4[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h4>\s*<h4>\s*Season (\d+)',
            webpage, 'season number', default=None))

        return {
            'id': video_id,
            'title': video_title,
            'description': video_description,
            'thumbnail': xpath_text(metadata, 'episode_image_url'),
            'uploader': video_uploader,
            'upload_date': video_upload_date,
            'series': series,
            'season_number': season_number,
            'episode': episode,
            'episode_number': episode_number,
            'subtitles': subtitles,
            'formats': formats,
        }


class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
    IE_NAME = 'crunchyroll:playlist'
    _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\-]+))/?(?:\?|$)'

    _TESTS = [{
        'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
        'info_dict': {
            'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
            'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
        },
        'playlist_count': 13,
    }, {
        # geo-restricted (US), 18+ maturity wall, non-premium available
        'url': 'http://www.crunchyroll.com/cosplay-complex-ova',
        'info_dict': {
            'id': 'cosplay-complex-ova',
            'title': 'Cosplay Complex OVA'
        },
        'playlist_count': 3,
        'skip': 'Georestricted',
    }, {
        # geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14
        'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        show_id = self._match_id(url)

        webpage = self._download_webpage(self._add_skip_wall(url), show_id)
        title = self._html_search_regex(
            r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
            webpage, 'title')
        episode_paths = re.findall(
            r'(?s)<li id="showview_videos_media_[0-9]+"[^>]+>.*?<a href="([^"]+)"',
            webpage)
        entries = [
            self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll')
            for ep in episode_paths
        ]
        entries.reverse()

        return {
            '_type': 'playlist',
            'id': show_id,
            'title': title,
            'entries': entries,
        }