X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/ca4d08063804fb264eb0ae9cc57894198f66e1fb..6d835d4d6903cf5e18ad01844736929e06d16004:/youtube_dl/extractor/crunchyroll.py?ds=sidebyside diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 2b66bdd..cc612d0 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -1,8 +1,15 @@ # encoding: utf-8 -import re, base64, zlib +from __future__ import unicode_literals + +import re +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 .subtitles import SubtitlesInfoExtractor from ..utils import ( ExtractorError, compat_urllib_parse, @@ -11,38 +18,63 @@ from ..utils import ( intlist_to_bytes, unified_strdate, clean_html, + urlencode_postdata, ) from ..aes import ( aes_cbc_decrypt, inc, ) +from .common import InfoExtractor -class CrunchyrollIE(InfoExtractor): - _VALID_URL = r'(?:https?://)?(?:www\.)?(?Pcrunchyroll\.com/[^/]*/[^/?&]*?(?P[0-9]+))(?:[/?&]|$)' - _TESTS = [{ - u'url': u'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', - u'file': u'645513.flv', - #u'md5': u'b1639fd6ddfaa43788c85f6d1dddd412', - u'info_dict': { - u'title': u'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!', - u'description': u'md5:2d17137920c64f2f49981a7797d275ef', - u'thumbnail': u'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg', - u'uploader': u'Yomiuri Telecasting Corporation (YTV)', - u'upload_date': u'20131013', + +class CrunchyrollIE(SubtitlesInfoExtractor): + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P[0-9]+))(?:[/?&]|$)' + _TEST = { + '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', + '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', + 'url': 're:(?!.*&)', }, - u'params': { + 'params': { # rtmp - u'skip_download': True, + 'skip_download': True, }, - }] + } _FORMAT_IDS = { - u'360': (u'60', u'106'), - u'480': (u'61', u'106'), - u'720': (u'62', u'106'), - u'1080': (u'80', u'108'), + '360': ('60', '106'), + '480': ('61', '106'), + '720': ('62', '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) @@ -63,10 +95,10 @@ class CrunchyrollIE(InfoExtractor): num3 = key ^ num1 num4 = num3 ^ (num3 >> 3) ^ num2 prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2))) - shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode(u'ascii')).digest()) + shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest()) # Extend 160 Bit hash to 256 Bit return shaHash + [0] * 12 - + key = obfuscate_key(id) class Counter: __value = iv @@ -77,95 +109,217 @@ class CrunchyrollIE(InfoExtractor): decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv)) return zlib.decompress(decrypted_data) - def _convert_subtitles_to_srt(self, subtitles): - i=1 - output = u'' - for start, end, text in re.findall(r']*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles): - start = start.replace(u'.', u',') - end = end.replace(u'.', u',') - text = clean_html(text) - text = text.replace(u'\\N', u'\n') - if not text: - continue - output += u'%d\n%s --> %s\n%s\n\n' % (i, start, end, text) - i+=1 + def _convert_subtitles_to_srt(self, sub_root): + output = '' + + 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 _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 _real_extract(self,url): mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('video_id') - webpage_url = u'http://www.' + mobj.group('url') - video_id = mobj.group(u'video_id') - webpage = self._download_webpage(webpage_url, video_id) - note_m = self._html_search_regex(r'
(.+?)
', webpage, u'trailer-notice', default=u'') + if mobj.group('prefix') == 'm': + mobile_webpage = self._download_webpage(url, video_id, 'Downloading mobile webpage') + webpage_url = self._search_regex(r'', mobile_webpage, 'webpage_url') + else: + webpage_url = 'http://www.' + mobj.group('url') + + webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage') + note_m = self._html_search_regex(r'
(.+?)
', webpage, 'trailer-notice', default='') if note_m: raise ExtractorError(note_m) - video_title = self._html_search_regex(r']*>(.+?)', webpage, u'video_title', flags=re.DOTALL) - video_title = re.sub(r' {2,}', u' ', video_title) - video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, u'video_description', default=u'') + mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P{.+?})\]\)', 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) + + video_title = self._html_search_regex(r']*>(.+?)', webpage, 'video_title', flags=re.DOTALL) + video_title = re.sub(r' {2,}', ' ', video_title) + video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='') if not video_description: video_description = None - video_upload_date = self._html_search_regex(r'
Availability for free users:(.+?)
', webpage, u'video_upload_date', fatal=False, flags=re.DOTALL) + video_upload_date = self._html_search_regex(r'
Availability for free users:(.+?)
', webpage, 'video_upload_date', fatal=False, flags=re.DOTALL) if video_upload_date: video_upload_date = unified_strdate(video_upload_date) - video_uploader = self._html_search_regex(r'
\s*Publisher:(.+?)
', webpage, u'video_uploader', fatal=False, flags=re.DOTALL) + video_uploader = self._html_search_regex(r'
\s*Publisher:(.+?)
', webpage, 'video_uploader', fatal=False, flags=re.DOTALL) - playerdata_url = compat_urllib_parse.unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, u'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({u'current_page': webpage_url}) - playerdata_req.add_header(u'Content-Type', u'application/x-www-form-urlencoded') - playerdata = self._download_webpage(playerdata_req, video_id, note=u'Downloading media info') - - stream_id = self._search_regex(r'([^<]+)', playerdata, u'stream_id') - video_thumbnail = self._search_regex(r'([^<]+)', playerdata, u'thumbnail', fatal=False) + playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url}) + playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') + playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info') + + stream_id = self._search_regex(r'([^<]+)', playerdata, 'stream_id') + video_thumbnail = self._search_regex(r'([^<]+)', playerdata, 'thumbnail', fatal=False) formats = [] for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage): stream_quality, stream_format = self._FORMAT_IDS[fmt] - video_format = fmt+u'p' - streamdata_req = compat_urllib_request.Request(u'http://www.crunchyroll.com/xml/') + video_format = fmt+'p' + streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/') # urlencode doesn't work! - streamdata_req.data = u'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+u'&media%5Fid='+stream_id+u'&video%5Fformat='+stream_format - streamdata_req.add_header(u'Content-Type', u'application/x-www-form-urlencoded') - streamdata_req.add_header(u'Content-Length', str(len(streamdata_req.data))) - streamdata = self._download_webpage(streamdata_req, video_id, note=u'Downloading media info for '+video_format) - video_url = self._search_regex(r'([^<]+)', streamdata, u'video_url') - video_play_path = self._search_regex(r'([^<]+)', streamdata, u'video_play_path') + streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format + 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_xml( + streamdata_req, video_id, + note='Downloading media info for %s' % video_format) + video_url = streamdata.find('.//host').text + video_play_path = streamdata.find('.//file').text formats.append({ - u'url': video_url, - u'play_path': video_play_path, - u'ext': 'flv', - u'format': video_format, - u'format_id': video_format, + 'url': video_url, + 'play_path': video_play_path, + 'ext': 'flv', + 'format': video_format, + 'format_id': video_format, }) subtitles = {} + sub_format = self._downloader.params.get('subtitlesformat', 'srt') for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): - sub_page = self._download_webpage(u'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\ - video_id, note=u'Downloading subtitles for '+sub_name) - id = self._search_regex(r'id=\'([0-9]+)', sub_page, u'subtitle_id', fatal=False) - iv = self._search_regex(r'([^<]+)', sub_page, u'subtitle_iv', fatal=False) - data = self._search_regex(r'([^<]+)', sub_page, u'subtitle_data', fatal=False) + 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'([^<]+)', sub_page, 'subtitle_iv', fatal=False) + data = self._search_regex(r'([^<]+)', 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(u'utf-8') - lang_code = self._search_regex(r'lang_code=\'([^\']+)', subtitle, u'subtitle_lang_code', fatal=False) + 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) + sub_root = xml.etree.ElementTree.fromstring(subtitle) + if not sub_root: + subtitles[lang_code] = '' + if sub_format == 'ass': + subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root) + else: + subtitles[lang_code] = self._convert_subtitles_to_srt(sub_root) + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + + return { + 'id': video_id, + 'title': video_title, + 'description': video_description, + 'thumbnail': video_thumbnail, + 'uploader': video_uploader, + 'upload_date': video_upload_date, + 'subtitles': subtitles, + 'formats': formats, + } + + +class CrunchyrollShowPlaylistIE(InfoExtractor): + IE_NAME = "crunchyroll:playlist" + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P[\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)]*>\s*(.*?)', + webpage, 'title') + episode_paths = re.findall( + r'(?s)
  • ]+>.*?