2 from __future__ import unicode_literals
8 import xml.etree.ElementTree
10 from hashlib import sha1
11 from math import pow, sqrt, floor
12 from .subtitles import SubtitlesInfoExtractor
13 from ..compat import (
15 compat_urllib_request,
28 from .common import InfoExtractor
31 class CrunchyrollIE(SubtitlesInfoExtractor):
32 _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
34 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
35 #'md5': 'b1639fd6ddfaa43788c85f6d1dddd412',
39 'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
40 'description': 'md5:2d17137920c64f2f49981a7797d275ef',
41 'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
42 'uploader': 'Yomiuri Telecasting Corporation (YTV)',
43 'upload_date': '20131013',
44 'url': 're:(?!.*&)',
48 'skip_download': True,
56 '1080': ('80', '108'),
60 (username, password) = self._get_login_info()
64 login_url = 'https://www.crunchyroll.com/?a=formhandler'
65 data = urlencode_postdata({
66 'formname': 'RpcApiUser_Login',
70 login_request = compat_urllib_request.Request(login_url, data)
71 login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
72 self._download_webpage(login_request, None, False, 'Wrong login info')
74 def _real_initialize(self):
77 def _decrypt_subtitles(self, data, iv, id):
78 data = bytes_to_intlist(data)
79 iv = bytes_to_intlist(iv)
82 def obfuscate_key_aux(count, modulo, start):
84 for _ in range(count):
85 output.append(output[-1] + output[-2])
86 # cut off start values
88 output = list(map(lambda x: x % modulo + 33, output))
91 def obfuscate_key(key):
92 num1 = int(floor(pow(2, 25) * sqrt(6.9)))
93 num2 = (num1 ^ key) << 5
95 num4 = num3 ^ (num3 >> 3) ^ num2
96 prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2)))
97 shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
98 # Extend 160 Bit hash to 256 Bit
99 return shaHash + [0] * 12
101 key = obfuscate_key(id)
106 def next_value(self):
108 self.__value = inc(self.__value)
110 decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
111 return zlib.decompress(decrypted_data)
113 def _convert_subtitles_to_srt(self, sub_root):
116 for i, event in enumerate(sub_root.findall('./events/event'), 1):
117 start = event.attrib['start'].replace('.', ',')
118 end = event.attrib['end'].replace('.', ',')
119 text = event.attrib['text'].replace('\\N', '\n')
120 output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
123 def _convert_subtitles_to_ass(self, sub_root):
126 def ass_bool(strvalue):
132 output = '[Script Info]\n'
133 output += 'Title: %s\n' % sub_root.attrib["title"]
134 output += 'ScriptType: v4.00+\n'
135 output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"]
136 output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"]
137 output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"]
138 output += """ScaledBorderAndShadow: yes
141 Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
143 for style in sub_root.findall('./styles/style'):
144 output += 'Style: ' + style.attrib["name"]
145 output += ',' + style.attrib["font_name"]
146 output += ',' + style.attrib["font_size"]
147 output += ',' + style.attrib["primary_colour"]
148 output += ',' + style.attrib["secondary_colour"]
149 output += ',' + style.attrib["outline_colour"]
150 output += ',' + style.attrib["back_colour"]
151 output += ',' + ass_bool(style.attrib["bold"])
152 output += ',' + ass_bool(style.attrib["italic"])
153 output += ',' + ass_bool(style.attrib["underline"])
154 output += ',' + ass_bool(style.attrib["strikeout"])
155 output += ',' + style.attrib["scale_x"]
156 output += ',' + style.attrib["scale_y"]
157 output += ',' + style.attrib["spacing"]
158 output += ',' + style.attrib["angle"]
159 output += ',' + style.attrib["border_style"]
160 output += ',' + style.attrib["outline"]
161 output += ',' + style.attrib["shadow"]
162 output += ',' + style.attrib["alignment"]
163 output += ',' + style.attrib["margin_l"]
164 output += ',' + style.attrib["margin_r"]
165 output += ',' + style.attrib["margin_v"]
166 output += ',' + style.attrib["encoding"]
171 Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
173 for event in sub_root.findall('./events/event'):
174 output += 'Dialogue: 0'
175 output += ',' + event.attrib["start"]
176 output += ',' + event.attrib["end"]
177 output += ',' + event.attrib["style"]
178 output += ',' + event.attrib["name"]
179 output += ',' + event.attrib["margin_l"]
180 output += ',' + event.attrib["margin_r"]
181 output += ',' + event.attrib["margin_v"]
182 output += ',' + event.attrib["effect"]
183 output += ',' + event.attrib["text"]
188 def _real_extract(self, url):
189 mobj = re.match(self._VALID_URL, url)
190 video_id = mobj.group('video_id')
192 if mobj.group('prefix') == 'm':
193 mobile_webpage = self._download_webpage(url, video_id, 'Downloading mobile webpage')
194 webpage_url = self._search_regex(r'<link rel="canonical" href="([^"]+)" />', mobile_webpage, 'webpage_url')
196 webpage_url = 'http://www.' + mobj.group('url')
198 webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage')
199 note_m = self._html_search_regex(r'<div class="showmedia-trailer-notice">(.+?)</div>', webpage, 'trailer-notice', default='')
201 raise ExtractorError(note_m)
203 mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
205 msg = json.loads(mobj.group('msg'))
206 if msg.get('type') == 'error':
207 raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
209 video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
210 video_title = re.sub(r' {2,}', ' ', video_title)
211 video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
212 if not video_description:
213 video_description = None
214 video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
215 if video_upload_date:
216 video_upload_date = unified_strdate(video_upload_date)
217 video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, 'video_uploader', fatal=False, flags=re.DOTALL)
219 playerdata_url = compat_urllib_parse.unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
220 playerdata_req = compat_urllib_request.Request(playerdata_url)
221 playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
222 playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
223 playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
225 stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id')
226 video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
229 for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage):
230 stream_quality, stream_format = self._FORMAT_IDS[fmt]
231 video_format = fmt + 'p'
232 streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')
233 # urlencode doesn't work!
234 streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality=' + stream_quality + '&media%5Fid=' + stream_id + '&video%5Fformat=' + stream_format
235 streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
236 streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
237 streamdata = self._download_xml(
238 streamdata_req, video_id,
239 note='Downloading media info for %s' % video_format)
240 video_url = streamdata.find('.//host').text
241 video_play_path = streamdata.find('.//file').text
244 'play_path': video_play_path,
246 'format': video_format,
247 'format_id': video_format,
251 sub_format = self._downloader.params.get('subtitlesformat', 'srt')
252 for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
253 sub_page = self._download_webpage(
254 'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,
255 video_id, note='Downloading subtitles for ' + sub_name)
256 id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False)
257 iv = self._search_regex(r'<iv>([^<]+)', sub_page, 'subtitle_iv', fatal=False)
258 data = self._search_regex(r'<data>([^<]+)', sub_page, 'subtitle_data', fatal=False)
259 if not id or not iv or not data:
262 iv = base64.b64decode(iv)
263 data = base64.b64decode(data)
265 subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
266 lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
269 sub_root = xml.etree.ElementTree.fromstring(subtitle)
270 if sub_format == 'ass':
271 subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root)
273 subtitles[lang_code] = self._convert_subtitles_to_srt(sub_root)
275 if self._downloader.params.get('listsubtitles', False):
276 self._list_available_subtitles(video_id, subtitles)
281 'title': video_title,
282 'description': video_description,
283 'thumbnail': video_thumbnail,
284 'uploader': video_uploader,
285 'upload_date': video_upload_date,
286 'subtitles': subtitles,
291 class CrunchyrollShowPlaylistIE(InfoExtractor):
292 IE_NAME = "crunchyroll:playlist"
293 _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\-]+))/?$'
296 'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
298 'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
299 'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
301 'playlist_count': 13,
304 def _real_extract(self, url):
305 show_id = self._match_id(url)
307 webpage = self._download_webpage(url, show_id)
308 title = self._html_search_regex(
309 r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
311 episode_paths = re.findall(
312 r'(?s)<li id="showview_videos_media_[0-9]+"[^>]+>.*?<a href="([^"]+)"',
315 self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll')
316 for ep in episode_paths