From 9cb00d7cd897de487583219074b80e323a185dfa Mon Sep 17 00:00:00 2001 From: skybt Date: Sun, 18 Aug 2019 23:04:19 +0200 Subject: [PATCH 1/2] [ADN] Use PhantomJS to get the subtitle encryption key (closes #12724) --- youtube_dl/extractor/adn.py | 257 +++++++++++++++++++++++++++++++++++- 1 file changed, 253 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/adn.py b/youtube_dl/extractor/adn.py index c95ad2173..1529e355d 100644 --- a/youtube_dl/extractor/adn.py +++ b/youtube_dl/extractor/adn.py @@ -6,14 +6,24 @@ import binascii import json import os import random +import subprocess +import tempfile +import re from .common import InfoExtractor from ..aes import aes_cbc_decrypt from ..compat import ( compat_b64decode, compat_ord, + compat_kwargs, + compat_urlparse, ) from ..utils import ( + check_executable, + get_exe_version, + is_outdated_version, + encodeArgument, + std_headers, bytes_to_intlist, bytes_to_long, ExtractorError, @@ -26,6 +36,219 @@ from ..utils import ( ) +def cookie_to_dict(cookie): + cookie_dict = { + 'name': cookie.name, + 'value': cookie.value, + } + if cookie.port_specified: + cookie_dict['port'] = cookie.port + if cookie.domain_specified: + cookie_dict['domain'] = cookie.domain + if cookie.path_specified: + cookie_dict['path'] = cookie.path + if cookie.expires is not None: + cookie_dict['expires'] = cookie.expires + if cookie.secure is not None: + cookie_dict['secure'] = cookie.secure + if cookie.discard is not None: + cookie_dict['discard'] = cookie.discard + try: + if (cookie.has_nonstandard_attr('httpOnly') + or cookie.has_nonstandard_attr('httponly') + or cookie.has_nonstandard_attr('HttpOnly')): + cookie_dict['httponly'] = True + except TypeError: + pass + return cookie_dict + + +def cookie_jar_to_list(cookie_jar): + return [cookie_to_dict(cookie) for cookie in cookie_jar] + + +class PhantomJSwrapper(object): + """PhantomJS wrapper class + This class is experimental. + """ + + _TEMPLATE = r''' + phantom.onError = function(msg, trace) {{ + var msgStack = ['PHANTOM ERROR: ' + msg]; + if(trace && trace.length) {{ + msgStack.push('TRACE:'); + trace.forEach(function(t) {{ + msgStack.push(' -> ' + (t.file || t.sourceURL) + ': ' + t.line + + (t.function ? ' (in function ' + t.function +')' : '')); + }}); + }} + console.error(msgStack.join('\n')); + phantom.exit(1); + }}; + var page = require('webpage').create(); + var fs = require('fs'); + var read = {{ mode: 'r', charset: 'utf-8' }}; + var write = {{ mode: 'w', charset: 'utf-8' }}; + JSON.parse(fs.read("{cookies}", read)).forEach(function(x) {{ + phantom.addCookie(x); + }}); + page.settings.resourceTimeout = {timeout}; + page.settings.userAgent = "{ua}"; + page.onLoadStarted = function() {{ + page.evaluate(function() {{ + delete window._phantom; + delete window.callPhantom; + }}); + }}; + var saveAndExit = function() {{ + fs.write("{html}", page.content, write); + fs.write("{cookies}", JSON.stringify(phantom.cookies), write); + phantom.exit(); + }}; + page.onLoadFinished = function(status) {{ + if(page.url === "") {{ + page.setContent(fs.read("{html}", read), "{url}"); + }} + else {{ + {jscode} + }} + }}; + page.open(""); + ''' + + _TMP_FILE_NAMES = ['script', 'html', 'cookies'] + + @staticmethod + def _version(): + return get_exe_version('phantomjs', version_re=r'([0-9.]+)') + + def __init__(self, extractor, required_version=None, timeout=10000): + self._TMP_FILES = {} + + self.exe = check_executable('phantomjs', ['-v']) + if not self.exe: + raise ExtractorError('PhantomJS executable not found in PATH, ' + 'download it from http://phantomjs.org', + expected=True) + + self.extractor = extractor + + if required_version: + version = self._version() + if is_outdated_version(version, required_version): + self.extractor._downloader.report_warning( + 'Your copy of PhantomJS is outdated, update it to version ' + '%s or newer if you encounter any errors.' % required_version) + + self.options = { + 'timeout': timeout, + } + for name in self._TMP_FILE_NAMES: + tmp = tempfile.NamedTemporaryFile(delete=False) + tmp.close() + self._TMP_FILES[name] = tmp + + def __del__(self): + for name in self._TMP_FILE_NAMES: + try: + os.remove(self._TMP_FILES[name].name) + except (IOError, OSError, KeyError): + pass + + def _save_cookies(self, url): + cookies = cookie_jar_to_list(self.extractor._downloader.cookiejar) + for cookie in cookies: + if 'path' not in cookie: + cookie['path'] = '/' + if 'domain' not in cookie: + cookie['domain'] = compat_urlparse.urlparse(url).netloc + with open(self._TMP_FILES['cookies'].name, 'wb') as f: + f.write(json.dumps(cookies).encode('utf-8')) + + def _load_cookies(self): + with open(self._TMP_FILES['cookies'].name, 'rb') as f: + cookies = json.loads(f.read().decode('utf-8')) + for cookie in cookies: + if cookie['httponly'] is True: + cookie['rest'] = {'httpOnly': None} + if 'expiry' in cookie: + cookie['expire_time'] = cookie['expiry'] + self.extractor._set_cookie(**compat_kwargs(cookie)) + + def get(self, url, html=None, video_id=None, note=None, note2='Executing JS on webpage', headers={}, jscode='saveAndExit();'): + """ + Downloads webpage (if needed) and executes JS + Params: + url: website url + html: optional, html code of website + video_id: video id + note: optional, displayed when downloading webpage + note2: optional, displayed when executing JS + headers: custom http headers + jscode: code to be executed when page is loaded + Returns tuple with: + * downloaded website (after JS execution) + * anything you print with `console.log` (but not inside `page.execute`!) + In most cases you don't need to add any `jscode`. + It is executed in `page.onLoadFinished`. + `saveAndExit();` is mandatory, use it instead of `phantom.exit()` + It is possible to wait for some element on the webpage, for example: + var check = function() { + var elementFound = page.evaluate(function() { + return document.querySelector('#b.done') !== null; + }); + if(elementFound) + saveAndExit(); + else + window.setTimeout(check, 500); + } + page.evaluate(function(){ + document.querySelector('#a').click(); + }); + check(); + """ + if 'saveAndExit();' not in jscode: + raise ExtractorError('`saveAndExit();` not found in `jscode`') + if not html: + html = self.extractor._download_webpage(url, video_id, note=note, headers=headers) + with open(self._TMP_FILES['html'].name, 'wb') as f: + f.write(html.encode('utf-8')) + + self._save_cookies(url) + + replaces = self.options + replaces['url'] = url + user_agent = headers.get('User-Agent') or std_headers['User-Agent'] + replaces['ua'] = user_agent.replace('"', '\\"') + replaces['jscode'] = jscode + + for x in self._TMP_FILE_NAMES: + replaces[x] = self._TMP_FILES[x].name.replace('\\', '\\\\').replace('"', '\\"') + + with open(self._TMP_FILES['script'].name, 'wb') as f: + f.write(self._TEMPLATE.format(**replaces).encode('utf-8')) + + if video_id is None: + self.extractor.to_screen('%s' % (note2,)) + else: + self.extractor.to_screen('%s: %s' % (video_id, note2)) + + p = subprocess.Popen([ + self.exe, '--ssl-protocol=any', + self._TMP_FILES['script'].name + ], stdout=subprocess.PIPE, stderr=subprocess.PIPE) + out, err = p.communicate() + if p.returncode != 0: + raise ExtractorError( + 'Executing JS failed\n:' + encodeArgument(err)) + with open(self._TMP_FILES['html'].name, 'rb') as f: + html = f.read().decode('utf-8') + + self._load_cookies() + + return (html, encodeArgument(out)) + + class ADNIE(InfoExtractor): IE_DESC = 'Anime Digital Network' _VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P\d+)' @@ -54,7 +277,7 @@ class ADNIE(InfoExtractor): def _ass_subtitles_timecode(seconds): return '%01d:%02d:%02d.%02d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 100) - def _get_subtitles(self, sub_path, video_id): + def _get_subtitles(self, sub_path, video_id, url, webpage): if not sub_path: return None @@ -70,10 +293,36 @@ class ADNIE(InfoExtractor): if not enc_subtitles: return None - # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js + # Get the second half of the encryption key + phantom = PhantomJSwrapper(self, required_version='2.0') + _, logs = phantom.get(url, html=webpage, video_id=video_id, jscode=""" + function getKey() { + var key = page.evaluate(function() { + return window.videojs && + window.videojs.players["adn-video-js"] && + window.videojs.players["adn-video-js"].onChromecastCustomData().key; + }) + if (key) { + console.log('Key is : ' + key); + saveAndExit(); + } else { + setTimeout(getKey, 1 * 1000); + } + } + getKey(); + window.setTimeout(function() { + console.error('Timed out'); + saveAndExit(); + }, 60 * 1000); + """) + match = re.match(re.compile(r'Key is : (.+)\n', re.MULTILINE), logs) + if 'Timed out' in logs or match is None: + raise ExtractorError('Could not get the key') + key = match.group(1).strip() + dec_subtitles = intlist_to_bytes(aes_cbc_decrypt( bytes_to_intlist(compat_b64decode(enc_subtitles[24:])), - bytes_to_intlist(binascii.unhexlify(self._K + '4b8ef13ec1872730')), + bytes_to_intlist(binascii.unhexlify(self._K + key)), bytes_to_intlist(compat_b64decode(enc_subtitles[:24])) )) subtitles_json = self._parse_json( @@ -201,7 +450,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text''' 'description': strip_or_none(metas.get('summary') or video_info.get('resume')), 'thumbnail': video_info.get('image'), 'formats': formats, - 'subtitles': self.extract_subtitles(sub_path, video_id), + 'subtitles': self.extract_subtitles(sub_path, video_id, url, webpage), 'episode': metas.get('subtitle') or video_info.get('videoTitle'), 'series': video_info.get('playlistTitle'), } From 7a3b118ed1025eb03bfddae071da42cdbe6c124d Mon Sep 17 00:00:00 2001 From: skybt Date: Sun, 18 Aug 2019 23:58:15 +0200 Subject: [PATCH 2/2] [ADN] Remove redundant code --- youtube_dl/extractor/adn.py | 223 +----------------------------------- 1 file changed, 1 insertion(+), 222 deletions(-) diff --git a/youtube_dl/extractor/adn.py b/youtube_dl/extractor/adn.py index 1529e355d..2c614b644 100644 --- a/youtube_dl/extractor/adn.py +++ b/youtube_dl/extractor/adn.py @@ -6,8 +6,6 @@ import binascii import json import os import random -import subprocess -import tempfile import re from .common import InfoExtractor @@ -15,15 +13,8 @@ from ..aes import aes_cbc_decrypt from ..compat import ( compat_b64decode, compat_ord, - compat_kwargs, - compat_urlparse, ) from ..utils import ( - check_executable, - get_exe_version, - is_outdated_version, - encodeArgument, - std_headers, bytes_to_intlist, bytes_to_long, ExtractorError, @@ -34,219 +25,7 @@ from ..utils import ( strip_or_none, urljoin, ) - - -def cookie_to_dict(cookie): - cookie_dict = { - 'name': cookie.name, - 'value': cookie.value, - } - if cookie.port_specified: - cookie_dict['port'] = cookie.port - if cookie.domain_specified: - cookie_dict['domain'] = cookie.domain - if cookie.path_specified: - cookie_dict['path'] = cookie.path - if cookie.expires is not None: - cookie_dict['expires'] = cookie.expires - if cookie.secure is not None: - cookie_dict['secure'] = cookie.secure - if cookie.discard is not None: - cookie_dict['discard'] = cookie.discard - try: - if (cookie.has_nonstandard_attr('httpOnly') - or cookie.has_nonstandard_attr('httponly') - or cookie.has_nonstandard_attr('HttpOnly')): - cookie_dict['httponly'] = True - except TypeError: - pass - return cookie_dict - - -def cookie_jar_to_list(cookie_jar): - return [cookie_to_dict(cookie) for cookie in cookie_jar] - - -class PhantomJSwrapper(object): - """PhantomJS wrapper class - This class is experimental. - """ - - _TEMPLATE = r''' - phantom.onError = function(msg, trace) {{ - var msgStack = ['PHANTOM ERROR: ' + msg]; - if(trace && trace.length) {{ - msgStack.push('TRACE:'); - trace.forEach(function(t) {{ - msgStack.push(' -> ' + (t.file || t.sourceURL) + ': ' + t.line - + (t.function ? ' (in function ' + t.function +')' : '')); - }}); - }} - console.error(msgStack.join('\n')); - phantom.exit(1); - }}; - var page = require('webpage').create(); - var fs = require('fs'); - var read = {{ mode: 'r', charset: 'utf-8' }}; - var write = {{ mode: 'w', charset: 'utf-8' }}; - JSON.parse(fs.read("{cookies}", read)).forEach(function(x) {{ - phantom.addCookie(x); - }}); - page.settings.resourceTimeout = {timeout}; - page.settings.userAgent = "{ua}"; - page.onLoadStarted = function() {{ - page.evaluate(function() {{ - delete window._phantom; - delete window.callPhantom; - }}); - }}; - var saveAndExit = function() {{ - fs.write("{html}", page.content, write); - fs.write("{cookies}", JSON.stringify(phantom.cookies), write); - phantom.exit(); - }}; - page.onLoadFinished = function(status) {{ - if(page.url === "") {{ - page.setContent(fs.read("{html}", read), "{url}"); - }} - else {{ - {jscode} - }} - }}; - page.open(""); - ''' - - _TMP_FILE_NAMES = ['script', 'html', 'cookies'] - - @staticmethod - def _version(): - return get_exe_version('phantomjs', version_re=r'([0-9.]+)') - - def __init__(self, extractor, required_version=None, timeout=10000): - self._TMP_FILES = {} - - self.exe = check_executable('phantomjs', ['-v']) - if not self.exe: - raise ExtractorError('PhantomJS executable not found in PATH, ' - 'download it from http://phantomjs.org', - expected=True) - - self.extractor = extractor - - if required_version: - version = self._version() - if is_outdated_version(version, required_version): - self.extractor._downloader.report_warning( - 'Your copy of PhantomJS is outdated, update it to version ' - '%s or newer if you encounter any errors.' % required_version) - - self.options = { - 'timeout': timeout, - } - for name in self._TMP_FILE_NAMES: - tmp = tempfile.NamedTemporaryFile(delete=False) - tmp.close() - self._TMP_FILES[name] = tmp - - def __del__(self): - for name in self._TMP_FILE_NAMES: - try: - os.remove(self._TMP_FILES[name].name) - except (IOError, OSError, KeyError): - pass - - def _save_cookies(self, url): - cookies = cookie_jar_to_list(self.extractor._downloader.cookiejar) - for cookie in cookies: - if 'path' not in cookie: - cookie['path'] = '/' - if 'domain' not in cookie: - cookie['domain'] = compat_urlparse.urlparse(url).netloc - with open(self._TMP_FILES['cookies'].name, 'wb') as f: - f.write(json.dumps(cookies).encode('utf-8')) - - def _load_cookies(self): - with open(self._TMP_FILES['cookies'].name, 'rb') as f: - cookies = json.loads(f.read().decode('utf-8')) - for cookie in cookies: - if cookie['httponly'] is True: - cookie['rest'] = {'httpOnly': None} - if 'expiry' in cookie: - cookie['expire_time'] = cookie['expiry'] - self.extractor._set_cookie(**compat_kwargs(cookie)) - - def get(self, url, html=None, video_id=None, note=None, note2='Executing JS on webpage', headers={}, jscode='saveAndExit();'): - """ - Downloads webpage (if needed) and executes JS - Params: - url: website url - html: optional, html code of website - video_id: video id - note: optional, displayed when downloading webpage - note2: optional, displayed when executing JS - headers: custom http headers - jscode: code to be executed when page is loaded - Returns tuple with: - * downloaded website (after JS execution) - * anything you print with `console.log` (but not inside `page.execute`!) - In most cases you don't need to add any `jscode`. - It is executed in `page.onLoadFinished`. - `saveAndExit();` is mandatory, use it instead of `phantom.exit()` - It is possible to wait for some element on the webpage, for example: - var check = function() { - var elementFound = page.evaluate(function() { - return document.querySelector('#b.done') !== null; - }); - if(elementFound) - saveAndExit(); - else - window.setTimeout(check, 500); - } - page.evaluate(function(){ - document.querySelector('#a').click(); - }); - check(); - """ - if 'saveAndExit();' not in jscode: - raise ExtractorError('`saveAndExit();` not found in `jscode`') - if not html: - html = self.extractor._download_webpage(url, video_id, note=note, headers=headers) - with open(self._TMP_FILES['html'].name, 'wb') as f: - f.write(html.encode('utf-8')) - - self._save_cookies(url) - - replaces = self.options - replaces['url'] = url - user_agent = headers.get('User-Agent') or std_headers['User-Agent'] - replaces['ua'] = user_agent.replace('"', '\\"') - replaces['jscode'] = jscode - - for x in self._TMP_FILE_NAMES: - replaces[x] = self._TMP_FILES[x].name.replace('\\', '\\\\').replace('"', '\\"') - - with open(self._TMP_FILES['script'].name, 'wb') as f: - f.write(self._TEMPLATE.format(**replaces).encode('utf-8')) - - if video_id is None: - self.extractor.to_screen('%s' % (note2,)) - else: - self.extractor.to_screen('%s: %s' % (video_id, note2)) - - p = subprocess.Popen([ - self.exe, '--ssl-protocol=any', - self._TMP_FILES['script'].name - ], stdout=subprocess.PIPE, stderr=subprocess.PIPE) - out, err = p.communicate() - if p.returncode != 0: - raise ExtractorError( - 'Executing JS failed\n:' + encodeArgument(err)) - with open(self._TMP_FILES['html'].name, 'rb') as f: - html = f.read().decode('utf-8') - - self._load_cookies() - - return (html, encodeArgument(out)) +from .openload import PhantomJSwrapper class ADNIE(InfoExtractor):