2016-10-02 19:39:18 +08:00
|
|
|
|
# coding: utf-8
|
2014-01-30 06:23:44 +08:00
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
2014-02-25 21:26:11 +08:00
|
|
|
|
import re
|
2014-02-25 21:29:16 +08:00
|
|
|
|
import json
|
2014-02-25 21:26:11 +08:00
|
|
|
|
import zlib
|
|
|
|
|
|
2013-11-04 10:08:17 +08:00
|
|
|
|
from hashlib import sha1
|
|
|
|
|
from math import pow, sqrt, floor
|
2015-02-16 01:21:42 +08:00
|
|
|
|
from .common import InfoExtractor
|
2014-12-13 19:24:42 +08:00
|
|
|
|
from ..compat import (
|
2018-01-23 23:23:12 +08:00
|
|
|
|
compat_b64decode,
|
2015-10-26 03:04:55 +08:00
|
|
|
|
compat_etree_fromstring,
|
2016-03-26 03:46:57 +08:00
|
|
|
|
compat_urllib_parse_urlencode,
|
2013-11-04 10:08:17 +08:00
|
|
|
|
compat_urllib_request,
|
2015-08-19 01:02:57 +08:00
|
|
|
|
compat_urlparse,
|
2014-12-13 19:24:42 +08:00
|
|
|
|
)
|
|
|
|
|
from ..utils import (
|
|
|
|
|
ExtractorError,
|
2013-11-04 10:08:17 +08:00
|
|
|
|
bytes_to_intlist,
|
|
|
|
|
intlist_to_bytes,
|
2015-09-03 19:15:02 +08:00
|
|
|
|
int_or_none,
|
2015-11-07 22:02:39 +08:00
|
|
|
|
lowercase_escape,
|
2015-08-19 01:02:57 +08:00
|
|
|
|
remove_end,
|
2015-11-22 00:18:17 +08:00
|
|
|
|
sanitized_Request,
|
2013-11-04 10:08:17 +08:00
|
|
|
|
unified_strdate,
|
2014-08-30 05:32:03 +08:00
|
|
|
|
urlencode_postdata,
|
2015-09-03 19:15:02 +08:00
|
|
|
|
xpath_text,
|
2016-04-29 18:46:42 +08:00
|
|
|
|
extract_attributes,
|
2013-11-04 10:08:17 +08:00
|
|
|
|
)
|
|
|
|
|
from ..aes import (
|
|
|
|
|
aes_cbc_decrypt,
|
|
|
|
|
)
|
|
|
|
|
|
2014-02-25 21:26:11 +08:00
|
|
|
|
|
2015-09-08 16:11:20 +08:00
|
|
|
|
class CrunchyrollBaseIE(InfoExtractor):
|
2016-09-15 22:53:35 +08:00
|
|
|
|
_LOGIN_URL = 'https://www.crunchyroll.com/login'
|
|
|
|
|
_LOGIN_FORM = 'login_form'
|
2015-10-18 08:57:57 +08:00
|
|
|
|
_NETRC_MACHINE = 'crunchyroll'
|
|
|
|
|
|
2017-11-14 02:15:16 +08:00
|
|
|
|
def _call_rpc_api(self, method, video_id, note=None, data=None):
|
|
|
|
|
data = data or {}
|
|
|
|
|
data['req'] = 'RpcApi' + method
|
|
|
|
|
data = compat_urllib_parse_urlencode(data).encode('utf-8')
|
|
|
|
|
return self._download_xml(
|
|
|
|
|
'http://www.crunchyroll.com/xml/',
|
|
|
|
|
video_id, note, fatal=False, data=data, headers={
|
|
|
|
|
'Content-Type': 'application/x-www-form-urlencoded',
|
|
|
|
|
})
|
|
|
|
|
|
2015-10-18 08:57:57 +08:00
|
|
|
|
def _login(self):
|
2018-05-26 23:12:44 +08:00
|
|
|
|
username, password = self._get_login_info()
|
2015-10-18 08:57:57 +08:00
|
|
|
|
if username is None:
|
|
|
|
|
return
|
2016-09-15 22:53:35 +08:00
|
|
|
|
|
2017-11-09 03:30:05 +08:00
|
|
|
|
self._download_webpage(
|
|
|
|
|
'https://www.crunchyroll.com/?a=formhandler',
|
|
|
|
|
None, 'Logging in', 'Wrong login info',
|
|
|
|
|
data=urlencode_postdata({
|
|
|
|
|
'formname': 'RpcApiUser_Login',
|
|
|
|
|
'next_url': 'https://www.crunchyroll.com/acct/membership',
|
|
|
|
|
'name': username,
|
|
|
|
|
'password': password,
|
|
|
|
|
}))
|
|
|
|
|
|
|
|
|
|
'''
|
2016-09-15 22:53:35 +08:00
|
|
|
|
login_page = self._download_webpage(
|
|
|
|
|
self._LOGIN_URL, None, 'Downloading login page')
|
|
|
|
|
|
2016-09-19 03:50:06 +08:00
|
|
|
|
def is_logged(webpage):
|
|
|
|
|
return '<title>Redirecting' in webpage
|
|
|
|
|
|
|
|
|
|
# Already logged in
|
|
|
|
|
if is_logged(login_page):
|
|
|
|
|
return
|
|
|
|
|
|
2016-09-15 22:53:35 +08:00
|
|
|
|
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,
|
2015-10-18 08:57:57 +08:00
|
|
|
|
})
|
2016-09-15 22:53:35 +08:00
|
|
|
|
|
|
|
|
|
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
|
2016-09-19 03:50:06 +08:00
|
|
|
|
if is_logged(response):
|
2016-09-15 22:53:35 +08:00
|
|
|
|
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')
|
2017-11-09 03:30:05 +08:00
|
|
|
|
'''
|
2015-10-18 08:57:57 +08:00
|
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
|
|
|
|
self._login()
|
|
|
|
|
|
2016-03-18 00:55:04 +08:00
|
|
|
|
def _download_webpage(self, url_or_request, *args, **kwargs):
|
2015-09-08 16:11:20 +08:00
|
|
|
|
request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
|
2015-11-22 00:18:17 +08:00
|
|
|
|
else sanitized_Request(url_or_request))
|
2015-09-08 16:11:20 +08:00
|
|
|
|
# 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', '*')
|
2016-03-18 00:55:04 +08:00
|
|
|
|
return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
|
2015-09-08 16:11:20 +08:00
|
|
|
|
|
2015-10-18 08:57:57 +08:00
|
|
|
|
@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(
|
2016-03-26 03:46:57 +08:00
|
|
|
|
parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
|
2015-10-18 08:57:57 +08:00
|
|
|
|
|
2015-09-08 16:11:20 +08:00
|
|
|
|
|
|
|
|
|
class CrunchyrollIE(CrunchyrollBaseIE):
|
2015-07-05 08:29:36 +08:00
|
|
|
|
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
|
2014-12-22 02:58:15 +08:00
|
|
|
|
_TESTS = [{
|
2014-01-30 06:23:44 +08:00
|
|
|
|
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
|
|
|
|
|
'info_dict': {
|
2014-02-25 21:26:11 +08:00
|
|
|
|
'id': '645513',
|
2017-02-23 00:08:45 +08:00
|
|
|
|
'ext': 'mp4',
|
2014-01-30 06:23:44 +08:00
|
|
|
|
'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
|
|
|
|
|
'description': 'md5:2d17137920c64f2f49981a7797d275ef',
|
|
|
|
|
'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
|
|
|
|
|
'uploader': 'Yomiuri Telecasting Corporation (YTV)',
|
|
|
|
|
'upload_date': '20131013',
|
2014-10-24 05:25:02 +08:00
|
|
|
|
'url': 're:(?!.*&)',
|
2013-11-04 10:08:17 +08:00
|
|
|
|
},
|
2014-01-30 06:23:44 +08:00
|
|
|
|
'params': {
|
2013-11-04 10:08:17 +08:00
|
|
|
|
# rtmp
|
2014-01-30 06:23:44 +08:00
|
|
|
|
'skip_download': True,
|
2013-11-04 10:08:17 +08:00
|
|
|
|
},
|
2015-07-05 08:29:36 +08:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '589804',
|
|
|
|
|
'ext': 'flv',
|
|
|
|
|
'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
|
2015-11-07 22:02:39 +08:00
|
|
|
|
'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
|
2017-01-02 20:08:07 +08:00
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
2015-07-05 08:29:36 +08:00
|
|
|
|
'uploader': 'Danny Choo Network',
|
|
|
|
|
'upload_date': '20120213',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
# rtmp
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2016-10-15 14:36:07 +08:00
|
|
|
|
'skip': 'Video gone',
|
2016-08-12 01:56:16 +08:00
|
|
|
|
}, {
|
|
|
|
|
'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',
|
2017-01-02 20:08:07 +08:00
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
2016-08-12 01:56:16 +08:00
|
|
|
|
'uploader': 'TV TOKYO',
|
|
|
|
|
'upload_date': '20160508',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
# m3u8 download
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2017-01-28 00:55:55 +08:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.crunchyroll.com/konosuba-gods-blessing-on-this-wonderful-world/episode-1-give-me-deliverance-from-this-judicial-injustice-727589',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '727589',
|
|
|
|
|
'ext': 'mp4',
|
2017-05-02 01:56:51 +08:00
|
|
|
|
'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance From This Judicial Injustice!",
|
2017-01-28 00:55:55 +08:00
|
|
|
|
'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
|
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
|
|
|
|
'uploader': 'Kadokawa Pictures Inc.',
|
|
|
|
|
'upload_date': '20170118',
|
|
|
|
|
'series': "KONOSUBA -God's blessing on this wonderful world!",
|
2017-03-12 12:18:10 +08:00
|
|
|
|
'season': "KONOSUBA -God's blessing on this wonderful world! 2",
|
2017-01-28 00:55:55 +08:00
|
|
|
|
'season_number': 2,
|
2017-05-02 01:56:51 +08:00
|
|
|
|
'episode': 'Give Me Deliverance From This Judicial Injustice!',
|
2017-01-28 00:55:55 +08:00
|
|
|
|
'episode_number': 1,
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
# m3u8 download
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2014-12-22 02:58:15 +08:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
|
|
|
|
|
'only_matching': True,
|
2015-10-18 09:06:47 +08:00
|
|
|
|
}, {
|
|
|
|
|
# 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,
|
2017-02-23 00:08:45 +08:00
|
|
|
|
}, {
|
|
|
|
|
# A description with double quotes
|
|
|
|
|
'url': 'http://www.crunchyroll.com/11eyes/episode-1-piros-jszaka-red-night-535080',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '535080',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': '11eyes Episode 1 – Piros éjszaka - Red Night',
|
|
|
|
|
'description': 'Kakeru and Yuka are thrown into an alternate nightmarish world they call "Red Night".',
|
|
|
|
|
'uploader': 'Marvelous AQL Inc.',
|
|
|
|
|
'upload_date': '20091021',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
# Just test metadata extraction
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2017-02-26 19:08:10 +08:00
|
|
|
|
}, {
|
|
|
|
|
# make sure we can extract an uploader name that's not a link
|
|
|
|
|
'url': 'http://www.crunchyroll.com/hakuoki-reimeiroku/episode-1-dawn-of-the-divine-warriors-606899',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '606899',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Hakuoki Reimeiroku Episode 1 – Dawn of the Divine Warriors',
|
|
|
|
|
'description': 'Ryunosuke was left to die, but Serizawa-san asked him a simple question "Do you want to live?"',
|
|
|
|
|
'uploader': 'Geneon Entertainment',
|
|
|
|
|
'upload_date': '20120717',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
# just test metadata extraction
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2017-03-12 12:18:10 +08:00
|
|
|
|
}, {
|
|
|
|
|
# A video with a vastly different season name compared to the series name
|
|
|
|
|
'url': 'http://www.crunchyroll.com/nyarko-san-another-crawling-chaos/episode-1-test-590532',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '590532',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Haiyoru! Nyaruani (ONA) Episode 1 – Test',
|
|
|
|
|
'description': 'Mahiro and Nyaruko talk about official certification.',
|
|
|
|
|
'uploader': 'TV TOKYO',
|
|
|
|
|
'upload_date': '20120305',
|
|
|
|
|
'series': 'Nyarko-san: Another Crawling Chaos',
|
|
|
|
|
'season': 'Haiyoru! Nyaruani (ONA)',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
# Just test metadata extraction
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2014-12-22 02:58:15 +08:00
|
|
|
|
}]
|
2013-11-04 10:08:17 +08:00
|
|
|
|
|
|
|
|
|
_FORMAT_IDS = {
|
2014-01-30 06:23:44 +08:00
|
|
|
|
'360': ('60', '106'),
|
|
|
|
|
'480': ('61', '106'),
|
|
|
|
|
'720': ('62', '106'),
|
|
|
|
|
'1080': ('80', '108'),
|
2013-11-04 10:08:17 +08:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
def _decrypt_subtitles(self, data, iv, id):
|
2018-01-23 23:23:12 +08:00
|
|
|
|
data = bytes_to_intlist(compat_b64decode(data))
|
|
|
|
|
iv = bytes_to_intlist(compat_b64decode(iv))
|
2013-11-04 10:08:17 +08:00
|
|
|
|
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)))
|
2014-01-30 06:23:44 +08:00
|
|
|
|
shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
|
2013-11-04 10:08:17 +08:00
|
|
|
|
# Extend 160 Bit hash to 256 Bit
|
|
|
|
|
return shaHash + [0] * 12
|
2014-02-25 21:26:11 +08:00
|
|
|
|
|
2013-11-04 10:08:17 +08:00
|
|
|
|
key = obfuscate_key(id)
|
2014-11-24 03:41:03 +08:00
|
|
|
|
|
2013-11-04 10:08:17 +08:00
|
|
|
|
decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
|
|
|
|
|
return zlib.decompress(decrypted_data)
|
|
|
|
|
|
2014-10-30 04:19:20 +08:00
|
|
|
|
def _convert_subtitles_to_srt(self, sub_root):
|
2014-01-30 06:23:44 +08:00
|
|
|
|
output = ''
|
2014-10-30 04:19:20 +08:00
|
|
|
|
|
|
|
|
|
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')
|
2014-01-30 06:23:44 +08:00
|
|
|
|
output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
|
2013-11-04 10:08:17 +08:00
|
|
|
|
return output
|
|
|
|
|
|
2014-10-30 04:19:20 +08:00
|
|
|
|
def _convert_subtitles_to_ass(self, sub_root):
|
2014-08-30 19:48:56 +08:00
|
|
|
|
output = ''
|
|
|
|
|
|
|
|
|
|
def ass_bool(strvalue):
|
|
|
|
|
assvalue = '0'
|
|
|
|
|
if strvalue == '1':
|
|
|
|
|
assvalue = '-1'
|
|
|
|
|
return assvalue
|
|
|
|
|
|
|
|
|
|
output = '[Script Info]\n'
|
2016-02-14 17:37:17 +08:00
|
|
|
|
output += 'Title: %s\n' % sub_root.attrib['title']
|
2014-08-30 19:48:56 +08:00
|
|
|
|
output += 'ScriptType: v4.00+\n'
|
2016-02-14 17:37:17 +08:00
|
|
|
|
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']
|
2017-02-01 16:39:32 +08:00
|
|
|
|
output += """
|
2014-08-30 19:48:56 +08:00
|
|
|
|
[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'):
|
2016-02-14 17:37:17 +08:00
|
|
|
|
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']
|
2014-08-30 19:48:56 +08:00
|
|
|
|
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'
|
2016-02-14 17:37:17 +08:00
|
|
|
|
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']
|
2014-08-30 19:48:56 +08:00
|
|
|
|
output += '\n'
|
|
|
|
|
|
|
|
|
|
return output
|
|
|
|
|
|
2015-05-30 16:12:58 +08:00
|
|
|
|
def _extract_subtitles(self, subtitle):
|
2015-10-26 03:04:55 +08:00
|
|
|
|
sub_root = compat_etree_fromstring(subtitle)
|
2015-05-30 16:12:58 +08:00
|
|
|
|
return [{
|
|
|
|
|
'ext': 'srt',
|
|
|
|
|
'data': self._convert_subtitles_to_srt(sub_root),
|
|
|
|
|
}, {
|
|
|
|
|
'ext': 'ass',
|
|
|
|
|
'data': self._convert_subtitles_to_ass(sub_root),
|
|
|
|
|
}]
|
|
|
|
|
|
2015-02-16 01:21:42 +08:00
|
|
|
|
def _get_subtitles(self, video_id, webpage):
|
|
|
|
|
subtitles = {}
|
2015-10-22 22:34:11 +08:00
|
|
|
|
for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
|
2017-11-14 02:15:16 +08:00
|
|
|
|
sub_doc = self._call_rpc_api(
|
|
|
|
|
'Subtitle_GetXml', video_id,
|
|
|
|
|
'Downloading subtitles for ' + sub_name, data={
|
|
|
|
|
'subtitle_script_id': sub_id,
|
|
|
|
|
})
|
2017-12-17 16:14:52 +08:00
|
|
|
|
if sub_doc is None:
|
2015-02-16 01:21:42 +08:00
|
|
|
|
continue
|
2017-11-14 02:15:16 +08:00
|
|
|
|
sid = sub_doc.get('id')
|
|
|
|
|
iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
|
|
|
|
|
data = xpath_text(sub_doc, 'data', 'subtitle data')
|
|
|
|
|
if not sid or not iv or not data:
|
|
|
|
|
continue
|
|
|
|
|
subtitle = self._decrypt_subtitles(data, iv, sid).decode('utf-8')
|
2015-02-16 01:21:42 +08:00
|
|
|
|
lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
|
|
|
|
|
if not lang_code:
|
|
|
|
|
continue
|
2015-05-30 16:12:58 +08:00
|
|
|
|
subtitles[lang_code] = self._extract_subtitles(subtitle)
|
2015-02-16 01:21:42 +08:00
|
|
|
|
return subtitles
|
|
|
|
|
|
2014-11-24 03:41:03 +08:00
|
|
|
|
def _real_extract(self, url):
|
2013-11-04 10:08:17 +08:00
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
2014-01-30 06:23:44 +08:00
|
|
|
|
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')
|
2013-11-04 10:08:17 +08:00
|
|
|
|
|
2017-04-01 16:33:23 +08:00
|
|
|
|
webpage = self._download_webpage(
|
|
|
|
|
self._add_skip_wall(webpage_url), video_id,
|
|
|
|
|
headers=self.geo_verification_headers())
|
2015-08-26 22:47:57 +08:00
|
|
|
|
note_m = self._html_search_regex(
|
|
|
|
|
r'<div class="showmedia-trailer-notice">(.+?)</div>',
|
|
|
|
|
webpage, 'trailer-notice', default='')
|
2013-11-04 10:08:17 +08:00
|
|
|
|
if note_m:
|
|
|
|
|
raise ExtractorError(note_m)
|
|
|
|
|
|
2014-02-25 21:29:16 +08:00
|
|
|
|
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)
|
2015-08-26 22:47:57 +08:00
|
|
|
|
|
|
|
|
|
if 'To view this, please log in to verify you are 18 or older.' in webpage:
|
2015-08-26 23:27:57 +08:00
|
|
|
|
self.raise_login_required()
|
2014-02-25 21:29:16 +08:00
|
|
|
|
|
2015-11-07 21:25:59 +08:00
|
|
|
|
video_title = self._html_search_regex(
|
|
|
|
|
r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
|
|
|
|
|
webpage, 'video_title')
|
2014-01-30 06:23:44 +08:00
|
|
|
|
video_title = re.sub(r' {2,}', ' ', video_title)
|
2017-02-23 00:08:45 +08:00
|
|
|
|
video_description = self._parse_json(self._html_search_regex(
|
|
|
|
|
r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id,
|
|
|
|
|
webpage, 'description', default='{}'), video_id).get('description')
|
2015-11-07 22:02:39 +08:00
|
|
|
|
if video_description:
|
|
|
|
|
video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
|
2015-09-08 16:37:53 +08:00
|
|
|
|
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)
|
2013-11-04 10:08:17 +08:00
|
|
|
|
if video_upload_date:
|
|
|
|
|
video_upload_date = unified_strdate(video_upload_date)
|
2015-09-08 16:37:53 +08:00
|
|
|
|
video_uploader = self._html_search_regex(
|
2017-02-26 19:08:10 +08:00
|
|
|
|
# try looking for both an uploader that's a link and one that's not
|
|
|
|
|
[r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', r'<div>\s*Publisher:\s*<span>\s*(.+?)\s*</span>\s*</div>'],
|
|
|
|
|
webpage, 'video_uploader', fatal=False)
|
2013-11-04 10:08:17 +08:00
|
|
|
|
|
2016-04-29 18:46:42 +08:00
|
|
|
|
available_fmts = []
|
2016-04-29 21:39:27 +08:00
|
|
|
|
for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
|
2016-04-29 18:46:42 +08:00
|
|
|
|
attrs = extract_attributes(a)
|
|
|
|
|
href = attrs.get('href')
|
|
|
|
|
if href and '/freetrial' in href:
|
|
|
|
|
continue
|
|
|
|
|
available_fmts.append(fmt)
|
|
|
|
|
if not available_fmts:
|
2016-04-29 21:43:53 +08:00
|
|
|
|
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
|
2016-04-29 01:42:20 +08:00
|
|
|
|
video_encode_ids = []
|
2016-04-29 18:46:42 +08:00
|
|
|
|
formats = []
|
|
|
|
|
for fmt in available_fmts:
|
2013-11-04 10:08:17 +08:00
|
|
|
|
stream_quality, stream_format = self._FORMAT_IDS[fmt]
|
2014-11-24 04:23:05 +08:00
|
|
|
|
video_format = fmt + 'p'
|
2017-11-14 02:15:16 +08:00
|
|
|
|
stream_infos = []
|
|
|
|
|
streamdata = self._call_rpc_api(
|
|
|
|
|
'VideoPlayer_GetStandardConfig', video_id,
|
|
|
|
|
'Downloading media info for %s' % video_format, data={
|
|
|
|
|
'media_id': video_id,
|
|
|
|
|
'video_format': stream_format,
|
|
|
|
|
'video_quality': stream_quality,
|
|
|
|
|
'current_page': url,
|
|
|
|
|
})
|
2017-12-17 16:14:52 +08:00
|
|
|
|
if streamdata is not None:
|
2017-11-14 02:15:16 +08:00
|
|
|
|
stream_info = streamdata.find('./{default}preload/stream_info')
|
2017-12-17 16:14:52 +08:00
|
|
|
|
if stream_info is not None:
|
2017-11-14 02:15:16 +08:00
|
|
|
|
stream_infos.append(stream_info)
|
|
|
|
|
stream_info = self._call_rpc_api(
|
|
|
|
|
'VideoEncode_GetStreamInfo', video_id,
|
|
|
|
|
'Downloading stream info for %s' % video_format, data={
|
|
|
|
|
'media_id': video_id,
|
|
|
|
|
'video_format': stream_format,
|
|
|
|
|
'video_encode_quality': stream_quality,
|
|
|
|
|
})
|
2017-12-17 16:14:52 +08:00
|
|
|
|
if stream_info is not None:
|
2017-11-14 02:15:16 +08:00
|
|
|
|
stream_infos.append(stream_info)
|
|
|
|
|
for stream_info in stream_infos:
|
|
|
|
|
video_encode_id = xpath_text(stream_info, './video_encode_id')
|
|
|
|
|
if video_encode_id in video_encode_ids:
|
2015-08-19 01:02:57 +08:00
|
|
|
|
continue
|
2017-11-14 02:15:16 +08:00
|
|
|
|
video_encode_ids.append(video_encode_id)
|
2015-08-19 01:02:57 +08:00
|
|
|
|
|
2017-11-14 02:15:16 +08:00
|
|
|
|
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
|
2013-11-04 10:08:17 +08:00
|
|
|
|
|
2017-11-14 02:15:16 +08:00
|
|
|
|
video_url = xpath_text(stream_info, './host')
|
|
|
|
|
if not video_url:
|
|
|
|
|
continue
|
|
|
|
|
metadata = stream_info.find('./metadata')
|
|
|
|
|
format_info = {
|
|
|
|
|
'format': 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({
|
|
|
|
|
'format_id': 'http-' + video_format,
|
|
|
|
|
'url': direct_video_url,
|
|
|
|
|
})
|
|
|
|
|
formats.append(format_info)
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
format_info.update({
|
|
|
|
|
'format_id': 'rtmp-' + video_format,
|
|
|
|
|
'url': video_url,
|
|
|
|
|
'play_path': video_file,
|
|
|
|
|
'ext': 'flv',
|
|
|
|
|
})
|
|
|
|
|
formats.append(format_info)
|
|
|
|
|
self._sort_formats(formats, ('height', 'width', 'tbr', 'fps'))
|
|
|
|
|
|
|
|
|
|
metadata = self._call_rpc_api(
|
|
|
|
|
'VideoPlayer_GetMediaMetadata', video_id,
|
|
|
|
|
note='Downloading media info', data={
|
2016-04-29 01:42:20 +08:00
|
|
|
|
'media_id': video_id,
|
|
|
|
|
})
|
|
|
|
|
|
2015-02-16 01:21:42 +08:00
|
|
|
|
subtitles = self.extract_subtitles(video_id, webpage)
|
2014-09-25 22:57:38 +08:00
|
|
|
|
|
2017-01-28 00:55:55 +08:00
|
|
|
|
# webpage provide more accurate data than series_title from XML
|
|
|
|
|
series = self._html_search_regex(
|
2017-07-16 13:40:45 +08:00
|
|
|
|
r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d',
|
2017-03-12 12:18:10 +08:00
|
|
|
|
webpage, 'series', fatal=False)
|
|
|
|
|
season = xpath_text(metadata, 'series_title')
|
2017-01-28 00:55:55 +08:00
|
|
|
|
|
|
|
|
|
episode = xpath_text(metadata, 'episode_title')
|
|
|
|
|
episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
|
|
|
|
|
|
|
|
|
|
season_number = int_or_none(self._search_regex(
|
2017-07-16 13:40:45 +08:00
|
|
|
|
r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)',
|
2017-01-28 00:55:55 +08:00
|
|
|
|
webpage, 'season number', default=None))
|
|
|
|
|
|
2013-11-04 10:08:17 +08:00
|
|
|
|
return {
|
2014-11-24 04:20:46 +08:00
|
|
|
|
'id': video_id,
|
|
|
|
|
'title': video_title,
|
2014-01-30 06:23:44 +08:00
|
|
|
|
'description': video_description,
|
2016-04-29 01:42:20 +08:00
|
|
|
|
'thumbnail': xpath_text(metadata, 'episode_image_url'),
|
2014-11-24 04:20:46 +08:00
|
|
|
|
'uploader': video_uploader,
|
2014-01-30 06:23:44 +08:00
|
|
|
|
'upload_date': video_upload_date,
|
2017-01-28 00:55:55 +08:00
|
|
|
|
'series': series,
|
2017-03-12 12:18:10 +08:00
|
|
|
|
'season': season,
|
2017-01-28 00:55:55 +08:00
|
|
|
|
'season_number': season_number,
|
|
|
|
|
'episode': episode,
|
|
|
|
|
'episode_number': episode_number,
|
2014-11-24 04:20:46 +08:00
|
|
|
|
'subtitles': subtitles,
|
|
|
|
|
'formats': formats,
|
2014-02-26 03:51:51 +08:00
|
|
|
|
}
|
2014-10-20 13:47:05 +08:00
|
|
|
|
|
|
|
|
|
|
2015-09-08 16:11:20 +08:00
|
|
|
|
class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
|
2016-02-14 17:37:17 +08:00
|
|
|
|
IE_NAME = 'crunchyroll:playlist'
|
2015-10-18 08:57:57 +08:00
|
|
|
|
_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\-]+))/?(?:\?|$)'
|
2014-10-20 13:47:05 +08:00
|
|
|
|
|
|
|
|
|
_TESTS = [{
|
2014-10-27 00:28:09 +08:00
|
|
|
|
'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'
|
2014-10-20 13:47:05 +08:00
|
|
|
|
},
|
2014-10-27 00:28:09 +08:00
|
|
|
|
'playlist_count': 13,
|
2015-10-18 09:06:47 +08:00
|
|
|
|
}, {
|
|
|
|
|
# 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,
|
2014-10-20 13:47:05 +08:00
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2014-10-27 00:28:09 +08:00
|
|
|
|
show_id = self._match_id(url)
|
|
|
|
|
|
2017-04-01 16:33:23 +08:00
|
|
|
|
webpage = self._download_webpage(
|
|
|
|
|
self._add_skip_wall(url), show_id,
|
|
|
|
|
headers=self.geo_verification_headers())
|
2014-10-27 00:28:09 +08:00
|
|
|
|
title = self._html_search_regex(
|
|
|
|
|
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
|
|
|
|
|
webpage, 'title')
|
|
|
|
|
episode_paths = re.findall(
|
2017-02-23 18:54:43 +08:00
|
|
|
|
r'(?s)<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"',
|
2014-10-27 00:28:09 +08:00
|
|
|
|
webpage)
|
|
|
|
|
entries = [
|
2017-02-23 18:54:43 +08:00
|
|
|
|
self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll', ep_id)
|
|
|
|
|
for ep_id, ep in episode_paths
|
2014-10-27 00:28:09 +08:00
|
|
|
|
]
|
|
|
|
|
entries.reverse()
|
|
|
|
|
|
2014-10-20 13:47:05 +08:00
|
|
|
|
return {
|
2014-10-27 00:28:09 +08:00
|
|
|
|
'_type': 'playlist',
|
|
|
|
|
'id': show_id,
|
|
|
|
|
'title': title,
|
|
|
|
|
'entries': entries,
|
|
|
|
|
}
|