From 5f699251e9421035cc89baf0b9dc78f3b6eacb77 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 28 Nov 2017 10:55:32 +0100 Subject: [PATCH] [daisuki] add support for motto.daisuki.com(fixes #14681) --- youtube_dl/extractor/daisuki.py | 86 ++++++++++++++---------------- youtube_dl/extractor/extractors.py | 4 +- 2 files changed, 42 insertions(+), 48 deletions(-) diff --git a/youtube_dl/extractor/daisuki.py b/youtube_dl/extractor/daisuki.py index 58cc98666..5c9ac68a0 100644 --- a/youtube_dl/extractor/daisuki.py +++ b/youtube_dl/extractor/daisuki.py @@ -13,33 +13,30 @@ from ..aes import ( from ..utils import ( bytes_to_intlist, bytes_to_long, - clean_html, + extract_attributes, ExtractorError, intlist_to_bytes, - get_element_by_id, js_to_json, int_or_none, long_to_bytes, pkcs1pad, - remove_end, ) -class DaisukiIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?daisuki\.net/[^/]+/[^/]+/[^/]+/watch\.[^.]+\.(?P\d+)\.html' +class DaisukiMottoIE(InfoExtractor): + _VALID_URL = r'https?://motto\.daisuki\.net/framewatch/embed/[^/]+/(?P[0-9a-zA-Z]{3})' _TEST = { - 'url': 'http://www.daisuki.net/tw/en/anime/watch.TheIdolMasterCG.11213.html', + 'url': 'http://motto.daisuki.net/framewatch/embed/embedDRAGONBALLSUPERUniverseSurvivalsaga/V2e/760/428', 'info_dict': { - 'id': '11213', + 'id': 'V2e', 'ext': 'mp4', - 'title': '#01 Who is in the pumpkin carriage? - THE IDOLM@STER CINDERELLA GIRLS', + 'title': '#117 SHOWDOWN OF LOVE! ANDROIDS VS UNIVERSE 2!!', 'subtitles': { 'mul': [{ 'ext': 'ttml', }], }, - 'creator': 'BANDAI NAMCO Entertainment', }, 'params': { 'skip_download': True, # AES-encrypted HLS stream @@ -73,15 +70,17 @@ class DaisukiIE(InfoExtractor): n, e = self._RSA_KEY encrypted_aeskey = long_to_bytes(pow(bytes_to_long(padded_aeskey), e, n)) - init_data = self._download_json('http://www.daisuki.net/bin/bgn/init', video_id, query={ - 's': flashvars.get('s', ''), - 'c': flashvars.get('ss3_prm', ''), - 'e': url, - 'd': base64.b64encode(intlist_to_bytes(aes_cbc_encrypt( - bytes_to_intlist(json.dumps(data)), - aes_key, iv))).decode('ascii'), - 'a': base64.b64encode(encrypted_aeskey).decode('ascii'), - }, note='Downloading JSON metadata' + (' (try #%d)' % (idx + 1) if idx > 0 else '')) + init_data = self._download_json( + 'http://motto.daisuki.net/fastAPI/bgn/init/', + video_id, query={ + 's': flashvars.get('s', ''), + 'c': flashvars.get('ss3_prm', ''), + 'e': url, + 'd': base64.b64encode(intlist_to_bytes(aes_cbc_encrypt( + bytes_to_intlist(json.dumps(data)), + aes_key, iv))).decode('ascii'), + 'a': base64.b64encode(encrypted_aeskey).decode('ascii'), + }, note='Downloading JSON metadata' + (' (try #%d)' % (idx + 1) if idx > 0 else '')) if 'rtn' in init_data: encrypted_rtn = init_data['rtn'] @@ -98,14 +97,11 @@ class DaisukiIE(InfoExtractor): aes_key, iv)).decode('utf-8').rstrip('\0'), video_id) + title = rtn['title_str'] + formats = self._extract_m3u8_formats( rtn['play_url'], video_id, ext='mp4', entry_protocol='m3u8_native') - title = remove_end(self._og_search_title(webpage), ' - DAISUKI') - - creator = self._html_search_regex( - r'Creator\s*:\s*([^<]+)', webpage, 'creator', fatal=False) - subtitles = {} caption_url = rtn.get('caption_url') if caption_url: @@ -120,21 +116,18 @@ class DaisukiIE(InfoExtractor): 'title': title, 'formats': formats, 'subtitles': subtitles, - 'creator': creator, } -class DaisukiPlaylistIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)daisuki\.net/[^/]+/[^/]+/[^/]+/detail\.(?P[a-zA-Z0-9]+)\.html' +class DaisukiMottoPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://motto\.daisuki\.net/(?Pinformation)/' _TEST = { - 'url': 'http://www.daisuki.net/tw/en/anime/detail.TheIdolMasterCG.html', + 'url': 'http://motto.daisuki.net/information/', 'info_dict': { - 'id': 'TheIdolMasterCG', - 'title': 'THE IDOLM@STER CINDERELLA GIRLS', - 'description': 'md5:0f2c028a9339f7a2c7fbf839edc5c5d8', + 'title': 'DRAGON BALL SUPER', }, - 'playlist_count': 26, + 'playlist_mincount': 117, } def _real_extract(self, url): @@ -142,18 +135,19 @@ class DaisukiPlaylistIE(InfoExtractor): webpage = self._download_webpage(url, playlist_id) - episode_pattern = r'''(?sx) - ]+delay="[^"]+/(\d+)/movie\.jpg".+? - ]+class=".*?\bepisodeNumber\b.*?">(?:]+>)?([^<]+)''' - entries = [{ - '_type': 'url_transparent', - 'url': url.replace('detail', 'watch').replace('.html', '.' + movie_id + '.html'), - 'episode_id': episode_id, - 'episode_number': int_or_none(episode_id), - } for movie_id, episode_id in re.findall(episode_pattern, webpage)] - - playlist_title = remove_end( - self._og_search_title(webpage, fatal=False), ' - Anime - DAISUKI') - playlist_description = clean_html(get_element_by_id('synopsisTxt', webpage)) - - return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) + entries = [] + for li in re.findall(r'(]+?data-product_id="[a-zA-Z0-9]{3}"[^>]+>)', webpage): + attr = extract_attributes(li) + ad_id = attr.get('data-ad_id') + product_id = attr.get('data-product_id') + if ad_id and product_id: + episode_id = attr.get('data-chapter') + entries.append({ + '_type': 'url_transparent', + 'url': 'http://motto.daisuki.net/framewatch/embed/%s/%s/760/428' % (ad_id, product_id), + 'episode_id': episode_id, + 'episode_number': int_or_none(episode_id), + 'ie_key': 'DaisukiMotto', + }) + + return self.playlist_result(entries, playlist_title='DRAGON BALL SUPER') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d3104f393..6db1297f1 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -246,8 +246,8 @@ from .dailymotion import ( DailymotionCloudIE, ) from .daisuki import ( - DaisukiIE, - DaisukiPlaylistIE, + DaisukiMottoIE, + DaisukiMottoPlaylistIE, ) from .daum import ( DaumIE,