import json
import base64
import zlib
+import xml.etree.ElementTree
from hashlib import sha1
from math import pow, sqrt, floor
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
+from ..compat import (
compat_urllib_parse,
+ compat_urllib_parse_unquote,
compat_urllib_request,
+)
+from ..utils import (
+ ExtractorError,
bytes_to_intlist,
intlist_to_bytes,
unified_strdate,
- clean_html,
+ urlencode_postdata,
)
from ..aes import (
aes_cbc_decrypt,
- inc,
)
class CrunchyrollIE(InfoExtractor):
- _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
- _TEST = {
+ _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+ _NETRC_MACHINE = 'crunchyroll'
+ _TESTS = [{
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
- #'md5': 'b1639fd6ddfaa43788c85f6d1dddd412',
'info_dict': {
'id': '645513',
'ext': 'flv',
'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
'uploader': 'Yomiuri Telecasting Corporation (YTV)',
'upload_date': '20131013',
+ 'url': 're:(?!.*&)',
},
'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:fe2743efedb49d279552926d0bd0cd9e',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'uploader': 'Danny Choo Network',
+ 'upload_date': '20120213',
+ },
+ 'params': {
+ # rtmp
+ 'skip_download': True,
+ },
+
+ }, {
+ 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
+ 'only_matching': True,
+ }]
_FORMAT_IDS = {
'360': ('60', '106'),
'1080': ('80', '108'),
}
+ def _login(self):
+ (username, password) = self._get_login_info()
+ if username is None:
+ return
+ self.report_login()
+ login_url = 'https://www.crunchyroll.com/?a=formhandler'
+ data = urlencode_postdata({
+ 'formname': 'RpcApiUser_Login',
+ 'name': username,
+ 'password': password,
+ })
+ login_request = compat_urllib_request.Request(login_url, data)
+ login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+ self._download_webpage(login_request, None, False, 'Wrong login info')
+
+ def _real_initialize(self):
+ self._login()
+
def _decrypt_subtitles(self, data, iv, id):
- data = bytes_to_intlist(data)
- iv = bytes_to_intlist(iv)
+ 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):
return shaHash + [0] * 12
key = obfuscate_key(id)
- class Counter:
- __value = iv
- def next_value(self):
- temp = self.__value
- self.__value = inc(self.__value)
- return temp
+
decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
return zlib.decompress(decrypted_data)
- def _convert_subtitles_to_srt(self, subtitles):
+ def _convert_subtitles_to_srt(self, sub_root):
output = ''
- for i, (start, end, text) in enumerate(re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles), 1):
- start = start.replace('.', ',')
- end = end.replace('.', ',')
- text = clean_html(text)
- text = text.replace('\\N', '\n')
- if not text:
- continue
+
+ 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 _real_extract(self,url):
+ 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: yes
+
+[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 = xml.etree.ElementTree.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'\?ssid=([0-9]+)" title="([^"]+)', 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')
video_upload_date = unified_strdate(video_upload_date)
video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, 'video_uploader', fatal=False, flags=re.DOTALL)
- playerdata_url = compat_urllib_parse.unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
+ playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
playerdata_req = compat_urllib_request.Request(playerdata_url)
playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
formats = []
- for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage):
+ for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
stream_quality, stream_format = self._FORMAT_IDS[fmt]
- video_format = fmt+'p'
- streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')
- # urlencode doesn't work!
- streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format
+ video_format = fmt + 'p'
+ streamdata_req = compat_urllib_request.Request(
+ 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
+ % (stream_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_req.add_header('Content-Length', str(len(streamdata_req.data)))
- streamdata = self._download_webpage(streamdata_req, video_id, note='Downloading media info for '+video_format)
- video_url = self._search_regex(r'<host>([^<]+)', streamdata, 'video_url')
- video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, 'video_play_path')
+ 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_url = stream_info.find('./host').text
+ video_play_path = stream_info.find('./file').text
formats.append({
'url': video_url,
- 'play_path': video_play_path,
+ 'play_path': video_play_path,
'ext': 'flv',
'format': video_format,
'format_id': video_format,
})
- subtitles = {}
- for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', 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
- id = int(id)
- iv = base64.b64decode(iv)
- data = base64.b64decode(data)
-
- 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._convert_subtitles_to_srt(subtitle)
+ subtitles = self.extract_subtitles(video_id, webpage)
return {
- 'id': video_id,
- 'title': video_title,
+ 'id': video_id,
+ 'title': video_title,
'description': video_description,
- 'thumbnail': video_thumbnail,
- 'uploader': video_uploader,
+ 'thumbnail': video_thumbnail,
+ 'uploader': video_uploader,
'upload_date': video_upload_date,
- 'subtitles': subtitles,
- 'formats': formats,
+ 'subtitles': subtitles,
+ 'formats': formats,
+ }
+
+
+class CrunchyrollShowPlaylistIE(InfoExtractor):
+ 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,
+ }]
+
+ def _real_extract(self, url):
+ show_id = self._match_id(url)
+
+ webpage = self._download_webpage(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,
}
Rapsys Git / youtubedl / blobdiff