From 40e41780f1d770a355f01e3c1e6fb09ff392f97e Mon Sep 17 00:00:00 2001 From: Tithen-Firion Date: Tue, 25 Apr 2017 15:12:54 +0200 Subject: [PATCH] [phantomjs] add cookie support --- youtube_dl/extractor/common.py | 8 +++-- youtube_dl/utils.py | 62 +++++++++++++++++++++++++++++++++- 2 files changed, 66 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index dcc9d628a..e54adc9f0 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2343,10 +2343,12 @@ class InfoExtractor(object): self._downloader.report_warning(msg) return res - def _set_cookie(self, domain, name, value, expire_time=None): + def _set_cookie(self, domain, name, value, expire_time=None, port=None, + path='/', secure=False, discard=False, rest={}, **kwargs): cookie = compat_cookiejar.Cookie( - 0, name, value, None, None, domain, None, - None, '/', True, False, expire_time, '', None, None, None) + 0, name, value, port, not port is None, domain, True, + domain.startswith('.'), path, True, secure, expire_time, + discard, None, None, rest) self._downloader.cookiejar.set_cookie(cookie) def _get_cookies(self, url): diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 94e1b07a6..9c94b7ec9 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -3654,6 +3654,37 @@ def write_xattr(path, key, value): "or the 'xattr' binary.") +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 not cookie.expires is None: + cookie_dict['expires'] = cookie.expires + if not cookie.secure is None: + cookie_dict['secure'] = cookie.secure + if not cookie.discard is 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""" @@ -3674,6 +3705,9 @@ class PhantomJSwrapper(object): 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() {{ @@ -3684,6 +3718,7 @@ class PhantomJSwrapper(object): }}; var saveAndExit = function() {{ fs.write("{html}", page.content, write); + fs.write("{cookies}", JSON.stringify(phantom.cookies), write); phantom.exit(); }}; page.onLoadFinished = function(status) {{ @@ -3697,7 +3732,7 @@ class PhantomJSwrapper(object): page.open(""); ''' - _TMP_FILE_NAMES = ['script', 'html'] + _TMP_FILE_NAMES = ['script', 'html', 'cookies'] def __init__(self, extractor, timeout=10000): self.exe = check_executable('phantomjs', ['-v']) @@ -3722,6 +3757,26 @@ class PhantomJSwrapper(object): except: 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(**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 @@ -3765,6 +3820,8 @@ class PhantomJSwrapper(object): 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'] @@ -3791,5 +3848,8 @@ class PhantomJSwrapper(object): + 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))