2016-10-02 04:39:18 -07:00
|
|
|
|
# coding: utf-8
|
2014-01-29 14:23:44 -08:00
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
2014-02-25 05:26:11 -08:00
|
|
|
|
import re
|
2014-02-25 05:29:16 -08:00
|
|
|
|
import json
|
2014-02-25 05:26:11 -08:00
|
|
|
|
import base64
|
|
|
|
|
import zlib
|
|
|
|
|
|
2013-11-03 18:08:17 -08:00
|
|
|
|
from hashlib import sha1
|
|
|
|
|
from math import pow, sqrt, floor
|
2015-02-15 09:21:42 -08:00
|
|
|
|
from .common import InfoExtractor
|
2014-12-13 03:24:42 -08:00
|
|
|
|
from ..compat import (
|
2015-10-25 12:04:55 -07:00
|
|
|
|
compat_etree_fromstring,
|
2016-03-25 12:46:57 -07:00
|
|
|
|
compat_urllib_parse_urlencode,
|
2013-11-03 18:08:17 -08:00
|
|
|
|
compat_urllib_request,
|
2015-08-18 10:02:57 -07:00
|
|
|
|
compat_urlparse,
|
2014-12-13 03:24:42 -08:00
|
|
|
|
)
|
|
|
|
|
from ..utils import (
|
|
|
|
|
ExtractorError,
|
2013-11-03 18:08:17 -08:00
|
|
|
|
bytes_to_intlist,
|
|
|
|
|
intlist_to_bytes,
|
2015-09-03 04:15:02 -07:00
|
|
|
|
int_or_none,
|
2015-11-07 06:02:39 -08:00
|
|
|
|
lowercase_escape,
|
2015-08-18 10:02:57 -07:00
|
|
|
|
remove_end,
|
2015-11-21 08:18:17 -08:00
|
|
|
|
sanitized_Request,
|
2013-11-03 18:08:17 -08:00
|
|
|
|
unified_strdate,
|
2014-08-29 14:32:03 -07:00
|
|
|
|
urlencode_postdata,
|
2015-09-03 04:15:02 -07:00
|
|
|
|
xpath_text,
|
2016-04-29 03:46:42 -07:00
|
|
|
|
extract_attributes,
|
2013-11-03 18:08:17 -08:00
|
|
|
|
)
|
|
|
|
|
from ..aes import (
|
|
|
|
|
aes_cbc_decrypt,
|
|
|
|
|
)
|
|
|
|
|
|
2014-02-25 05:26:11 -08:00
|
|
|
|
|
2015-09-08 01:11:20 -07:00
|
|
|
|
class CrunchyrollBaseIE(InfoExtractor):
|
2016-09-15 07:53:35 -07:00
|
|
|
|
_LOGIN_URL = 'https://www.crunchyroll.com/login'
|
|
|
|
|
_LOGIN_FORM = 'login_form'
|
2015-10-17 17:57:57 -07:00
|
|
|
|
_NETRC_MACHINE = 'crunchyroll'
|
|
|
|
|
|
|
|
|
|
def _login(self):
|
|
|
|
|
(username, password) = self._get_login_info()
|
|
|
|
|
if username is None:
|
|
|
|
|
return
|
2016-09-15 07:53:35 -07:00
|
|
|
|
|
|
|
|
|
login_page = self._download_webpage(
|
|
|
|
|
self._LOGIN_URL, None, 'Downloading login page')
|
|
|
|
|
|
2016-09-18 12:50:06 -07:00
|
|
|
|
def is_logged(webpage):
|
|
|
|
|
return '<title>Redirecting' in webpage
|
|
|
|
|
|
|
|
|
|
# Already logged in
|
|
|
|
|
if is_logged(login_page):
|
|
|
|
|
return
|
|
|
|
|
|
2016-09-15 07:53:35 -07:00
|
|
|
|
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,
|
2015-10-17 17:57:57 -07:00
|
|
|
|
})
|
2016-09-15 07:53:35 -07:00
|
|
|
|
|
|
|
|
|
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
|
2016-09-18 12:50:06 -07:00
|
|
|
|
if is_logged(response):
|
2016-09-15 07:53:35 -07:00
|
|
|
|
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')
|
2015-10-17 17:57:57 -07:00
|
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
|
|
|
|
self._login()
|
|
|
|
|
|
2016-03-17 09:55:04 -07:00
|
|
|
|
def _download_webpage(self, url_or_request, *args, **kwargs):
|
2015-09-08 01:11:20 -07:00
|
|
|
|
request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
|
2015-11-21 08:18:17 -08:00
|
|
|
|
else sanitized_Request(url_or_request))
|
2015-09-08 01:11:20 -07:00
|
|
|
|
# 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', '*')
|
2016-03-17 09:55:04 -07:00
|
|
|
|
return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
|
2015-09-08 01:11:20 -07:00
|
|
|
|
|
2015-10-17 17:57:57 -07:00
|
|
|
|
@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(
|
2016-03-25 12:46:57 -07:00
|
|
|
|
parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
|
2015-10-17 17:57:57 -07:00
|
|
|
|
|
2015-09-08 01:11:20 -07:00
|
|
|
|
|
|
|
|
|
class CrunchyrollIE(CrunchyrollBaseIE):
|
2015-07-04 17:29:36 -07:00
|
|
|
|
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
|
2014-12-21 10:58:15 -08:00
|
|
|
|
_TESTS = [{
|
2014-01-29 14:23:44 -08:00
|
|
|
|
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
|
|
|
|
|
'info_dict': {
|
2014-02-25 05:26:11 -08:00
|
|
|
|
'id': '645513',
|
|
|
|
|
'ext': 'flv',
|
2014-01-29 14:23:44 -08:00
|
|
|
|
'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
|
|
|
|
|
'description': 'md5:2d17137920c64f2f49981a7797d275ef',
|
|
|
|
|
'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
|
|
|
|
|
'uploader': 'Yomiuri Telecasting Corporation (YTV)',
|
|
|
|
|
'upload_date': '20131013',
|
2014-10-23 14:25:02 -07:00
|
|
|
|
'url': 're:(?!.*&)',
|
2013-11-03 18:08:17 -08:00
|
|
|
|
},
|
2014-01-29 14:23:44 -08:00
|
|
|
|
'params': {
|
2013-11-03 18:08:17 -08:00
|
|
|
|
# rtmp
|
2014-01-29 14:23:44 -08:00
|
|
|
|
'skip_download': True,
|
2013-11-03 18:08:17 -08:00
|
|
|
|
},
|
2015-07-04 17:29:36 -07:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '589804',
|
|
|
|
|
'ext': 'flv',
|
|
|
|
|
'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
|
2015-11-07 06:02:39 -08:00
|
|
|
|
'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
|
2017-01-02 04:08:07 -08:00
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
2015-07-04 17:29:36 -07:00
|
|
|
|
'uploader': 'Danny Choo Network',
|
|
|
|
|
'upload_date': '20120213',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
# rtmp
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2016-10-14 23:36:07 -07:00
|
|
|
|
'skip': 'Video gone',
|
2016-08-11 10:56:16 -07:00
|
|
|
|
}, {
|
|
|
|
|
'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 04:08:07 -08:00
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
2016-08-11 10:56:16 -07:00
|
|
|
|
'uploader': 'TV TOKYO',
|
|
|
|
|
'upload_date': '20160508',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
# m3u8 download
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2017-01-27 08:55:55 -08:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.crunchyroll.com/konosuba-gods-blessing-on-this-wonderful-world/episode-1-give-me-deliverance-from-this-judicial-injustice-727589',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '727589',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance from this Judicial Injustice!",
|
|
|
|
|
'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
|
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
|
|
|
|
'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,
|
|
|
|
|
},
|
2014-12-21 10:58:15 -08:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
|
|
|
|
|
'only_matching': True,
|
2015-10-17 18:06:47 -07:00
|
|
|
|
}, {
|
|
|
|
|
# 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,
|
2014-12-21 10:58:15 -08:00
|
|
|
|
}]
|
2013-11-03 18:08:17 -08:00
|
|
|
|
|
|
|
|
|
_FORMAT_IDS = {
|
2014-01-29 14:23:44 -08:00
|
|
|
|
'360': ('60', '106'),
|
|
|
|
|
'480': ('61', '106'),
|
|
|
|
|
'720': ('62', '106'),
|
|
|
|
|
'1080': ('80', '108'),
|
2013-11-03 18:08:17 -08:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
def _decrypt_subtitles(self, data, iv, id):
|
2015-05-30 01:36:45 -07:00
|
|
|
|
data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
|
|
|
|
|
iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
|
2013-11-03 18:08:17 -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)))
|
2014-01-29 14:23:44 -08:00
|
|
|
|
shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
|
2013-11-03 18:08:17 -08:00
|
|
|
|
# Extend 160 Bit hash to 256 Bit
|
|
|
|
|
return shaHash + [0] * 12
|
2014-02-25 05:26:11 -08:00
|
|
|
|
|
2013-11-03 18:08:17 -08:00
|
|
|
|
key = obfuscate_key(id)
|
2014-11-23 11:41:03 -08:00
|
|
|
|
|
2013-11-03 18:08:17 -08:00
|
|
|
|
decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
|
|
|
|
|
return zlib.decompress(decrypted_data)
|
|
|
|
|
|
2014-10-29 13:19:20 -07:00
|
|
|
|
def _convert_subtitles_to_srt(self, sub_root):
|
2014-01-29 14:23:44 -08:00
|
|
|
|
output = ''
|
2014-10-29 13:19:20 -07:00
|
|
|
|
|
|
|
|
|
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')
|
2014-01-29 14:23:44 -08:00
|
|
|
|
output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
|
2013-11-03 18:08:17 -08:00
|
|
|
|
return output
|
|
|
|
|
|
2014-10-29 13:19:20 -07:00
|
|
|
|
def _convert_subtitles_to_ass(self, sub_root):
|
2014-08-30 04:48:56 -07:00
|
|
|
|
output = ''
|
|
|
|
|
|
|
|
|
|
def ass_bool(strvalue):
|
|
|
|
|
assvalue = '0'
|
|
|
|
|
if strvalue == '1':
|
|
|
|
|
assvalue = '-1'
|
|
|
|
|
return assvalue
|
|
|
|
|
|
|
|
|
|
output = '[Script Info]\n'
|
2016-02-14 01:37:17 -08:00
|
|
|
|
output += 'Title: %s\n' % sub_root.attrib['title']
|
2014-08-30 04:48:56 -07:00
|
|
|
|
output += 'ScriptType: v4.00+\n'
|
2016-02-14 01:37:17 -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']
|
2016-03-29 10:26:24 -07:00
|
|
|
|
output += """ScaledBorderAndShadow: no
|
2014-08-30 04:48:56 -07:00
|
|
|
|
|
|
|
|
|
[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 01:37:17 -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 04:48:56 -07:00
|
|
|
|
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 01:37:17 -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 04:48:56 -07:00
|
|
|
|
output += '\n'
|
|
|
|
|
|
|
|
|
|
return output
|
|
|
|
|
|
2015-05-30 01:12:58 -07:00
|
|
|
|
def _extract_subtitles(self, subtitle):
|
2015-10-25 12:04:55 -07:00
|
|
|
|
sub_root = compat_etree_fromstring(subtitle)
|
2015-05-30 01:12:58 -07:00
|
|
|
|
return [{
|
|
|
|
|
'ext': 'srt',
|
|
|
|
|
'data': self._convert_subtitles_to_srt(sub_root),
|
|
|
|
|
}, {
|
|
|
|
|
'ext': 'ass',
|
|
|
|
|
'data': self._convert_subtitles_to_ass(sub_root),
|
|
|
|
|
}]
|
|
|
|
|
|
2015-02-15 09:21:42 -08:00
|
|
|
|
def _get_subtitles(self, video_id, webpage):
|
|
|
|
|
subtitles = {}
|
2015-10-22 07:34:11 -07:00
|
|
|
|
for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
|
2015-02-15 09:21:42 -08:00
|
|
|
|
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
|
2015-05-30 01:12:58 -07:00
|
|
|
|
subtitles[lang_code] = self._extract_subtitles(subtitle)
|
2015-02-15 09:21:42 -08:00
|
|
|
|
return subtitles
|
|
|
|
|
|
2014-11-23 11:41:03 -08:00
|
|
|
|
def _real_extract(self, url):
|
2013-11-03 18:08:17 -08:00
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
2014-01-29 14:23:44 -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')
|
2013-11-03 18:08:17 -08:00
|
|
|
|
|
2015-10-17 17:57:57 -07:00
|
|
|
|
webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
|
2015-08-26 07:47:57 -07:00
|
|
|
|
note_m = self._html_search_regex(
|
|
|
|
|
r'<div class="showmedia-trailer-notice">(.+?)</div>',
|
|
|
|
|
webpage, 'trailer-notice', default='')
|
2013-11-03 18:08:17 -08:00
|
|
|
|
if note_m:
|
|
|
|
|
raise ExtractorError(note_m)
|
|
|
|
|
|
2014-02-25 05:29:16 -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 07:47:57 -07:00
|
|
|
|
|
|
|
|
|
if 'To view this, please log in to verify you are 18 or older.' in webpage:
|
2015-08-26 08:27:57 -07:00
|
|
|
|
self.raise_login_required()
|
2014-02-25 05:29:16 -08:00
|
|
|
|
|
2015-11-07 05:25:59 -08:00
|
|
|
|
video_title = self._html_search_regex(
|
|
|
|
|
r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
|
|
|
|
|
webpage, 'video_title')
|
2014-01-29 14:23:44 -08:00
|
|
|
|
video_title = re.sub(r' {2,}', ' ', video_title)
|
2015-11-07 05:29:09 -08:00
|
|
|
|
video_description = self._html_search_regex(
|
2015-11-07 06:02:39 -08:00
|
|
|
|
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'))
|
2015-09-08 01:37:53 -07:00
|
|
|
|
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)
|
2013-11-03 18:08:17 -08:00
|
|
|
|
if video_upload_date:
|
|
|
|
|
video_upload_date = unified_strdate(video_upload_date)
|
2015-09-08 01:37:53 -07:00
|
|
|
|
video_uploader = self._html_search_regex(
|
|
|
|
|
r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage,
|
|
|
|
|
'video_uploader', fatal=False)
|
2013-11-03 18:08:17 -08:00
|
|
|
|
|
2016-04-29 03:46:42 -07:00
|
|
|
|
available_fmts = []
|
2016-04-29 06:39:27 -07:00
|
|
|
|
for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
|
2016-04-29 03:46:42 -07:00
|
|
|
|
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 06:43:53 -07:00
|
|
|
|
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
|
2016-04-28 10:42:20 -07:00
|
|
|
|
video_encode_ids = []
|
2016-04-29 03:46:42 -07:00
|
|
|
|
formats = []
|
|
|
|
|
for fmt in available_fmts:
|
2013-11-03 18:08:17 -08:00
|
|
|
|
stream_quality, stream_format = self._FORMAT_IDS[fmt]
|
2014-11-23 12:23:05 -08:00
|
|
|
|
video_format = fmt + 'p'
|
2015-11-21 08:18:17 -08:00
|
|
|
|
streamdata_req = sanitized_Request(
|
2015-07-04 17:29:36 -07:00
|
|
|
|
'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
|
2016-04-28 10:42:20 -07:00
|
|
|
|
% (video_id, stream_format, stream_quality),
|
2016-03-25 12:46:57 -07:00
|
|
|
|
compat_urllib_parse_urlencode({'current_page': url}).encode('utf-8'))
|
2014-01-29 14:23:44 -08:00
|
|
|
|
streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
2014-10-23 14:25:02 -07:00
|
|
|
|
streamdata = self._download_xml(
|
|
|
|
|
streamdata_req, video_id,
|
|
|
|
|
note='Downloading media info for %s' % video_format)
|
2015-07-04 17:29:36 -07:00
|
|
|
|
stream_info = streamdata.find('./{default}preload/stream_info')
|
2016-04-28 10:42:20 -07:00
|
|
|
|
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)
|
2016-08-11 10:56:16 -07:00
|
|
|
|
|
|
|
|
|
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
|
|
|
|
|
|
2016-01-06 21:26:14 -08:00
|
|
|
|
video_url = xpath_text(stream_info, './host')
|
2016-08-11 10:56:16 -07:00
|
|
|
|
if not video_url:
|
2016-01-06 21:26:14 -08:00
|
|
|
|
continue
|
2015-09-03 04:15:02 -07:00
|
|
|
|
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')),
|
|
|
|
|
}
|
2015-08-18 10:02:57 -07:00
|
|
|
|
|
|
|
|
|
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',
|
2016-08-11 10:56:16 -07:00
|
|
|
|
path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
|
2015-08-18 10:02:57 -07:00
|
|
|
|
if self._is_valid_url(direct_video_url, video_id, video_format):
|
2015-09-03 04:15:02 -07:00
|
|
|
|
format_info.update({
|
2015-08-18 10:02:57 -07:00
|
|
|
|
'url': direct_video_url,
|
|
|
|
|
})
|
2015-09-03 04:15:02 -07:00
|
|
|
|
formats.append(format_info)
|
2015-08-18 10:02:57 -07:00
|
|
|
|
continue
|
|
|
|
|
|
2015-09-03 04:15:02 -07:00
|
|
|
|
format_info.update({
|
2014-01-29 14:23:44 -08:00
|
|
|
|
'url': video_url,
|
2016-08-11 10:56:16 -07:00
|
|
|
|
'play_path': video_file,
|
2014-01-29 14:23:44 -08:00
|
|
|
|
'ext': 'flv',
|
2013-11-03 18:08:17 -08:00
|
|
|
|
})
|
2015-09-03 04:15:02 -07:00
|
|
|
|
formats.append(format_info)
|
2016-04-29 06:44:10 -07:00
|
|
|
|
self._sort_formats(formats)
|
2013-11-03 18:08:17 -08:00
|
|
|
|
|
2016-04-28 10:42:20 -07:00
|
|
|
|
metadata = self._download_xml(
|
|
|
|
|
'http://www.crunchyroll.com/xml', video_id,
|
|
|
|
|
note='Downloading media info', query={
|
|
|
|
|
'req': 'RpcApiVideoPlayer_GetMediaMetadata',
|
|
|
|
|
'media_id': video_id,
|
|
|
|
|
})
|
|
|
|
|
|
2015-02-15 09:21:42 -08:00
|
|
|
|
subtitles = self.extract_subtitles(video_id, webpage)
|
2014-09-25 07:57:38 -07:00
|
|
|
|
|
2017-01-27 08:55:55 -08:00
|
|
|
|
# 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))
|
|
|
|
|
|
2013-11-03 18:08:17 -08:00
|
|
|
|
return {
|
2014-11-23 12:20:46 -08:00
|
|
|
|
'id': video_id,
|
|
|
|
|
'title': video_title,
|
2014-01-29 14:23:44 -08:00
|
|
|
|
'description': video_description,
|
2016-04-28 10:42:20 -07:00
|
|
|
|
'thumbnail': xpath_text(metadata, 'episode_image_url'),
|
2014-11-23 12:20:46 -08:00
|
|
|
|
'uploader': video_uploader,
|
2014-01-29 14:23:44 -08:00
|
|
|
|
'upload_date': video_upload_date,
|
2017-01-27 08:55:55 -08:00
|
|
|
|
'series': series,
|
|
|
|
|
'season_number': season_number,
|
|
|
|
|
'episode': episode,
|
|
|
|
|
'episode_number': episode_number,
|
2014-11-23 12:20:46 -08:00
|
|
|
|
'subtitles': subtitles,
|
|
|
|
|
'formats': formats,
|
2014-02-25 11:51:51 -08:00
|
|
|
|
}
|
2014-10-19 22:47:05 -07:00
|
|
|
|
|
|
|
|
|
|
2015-09-08 01:11:20 -07:00
|
|
|
|
class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
|
2016-02-14 01:37:17 -08:00
|
|
|
|
IE_NAME = 'crunchyroll:playlist'
|
2015-10-17 17:57:57 -07:00
|
|
|
|
_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\-]+))/?(?:\?|$)'
|
2014-10-19 22:47:05 -07:00
|
|
|
|
|
|
|
|
|
_TESTS = [{
|
2014-10-26 09:28:09 -07:00
|
|
|
|
'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'
|
2014-10-19 22:47:05 -07:00
|
|
|
|
},
|
2014-10-26 09:28:09 -07:00
|
|
|
|
'playlist_count': 13,
|
2015-10-17 18:06:47 -07:00
|
|
|
|
}, {
|
|
|
|
|
# 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,
|
2014-10-19 22:47:05 -07:00
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2014-10-26 09:28:09 -07:00
|
|
|
|
show_id = self._match_id(url)
|
|
|
|
|
|
2015-10-17 17:57:57 -07:00
|
|
|
|
webpage = self._download_webpage(self._add_skip_wall(url), show_id)
|
2014-10-26 09:28:09 -07:00
|
|
|
|
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()
|
|
|
|
|
|
2014-10-19 22:47:05 -07:00
|
|
|
|
return {
|
2014-10-26 09:28:09 -07:00
|
|
|
|
'_type': 'playlist',
|
|
|
|
|
'id': show_id,
|
|
|
|
|
'title': title,
|
|
|
|
|
'entries': entries,
|
|
|
|
|
}
|