New upstream version 2018.03.14

[youtubedl] / youtube_dl / extractor / lynda.py

diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py
index d4e1ae99d4d91c887cfc2d55c29d8211fc48a80f..f5c7abc13eb431605355c080ade55da197fc04e3 100644 (file)
--- a/youtube_dl/extractor/lynda.py
+++ b/youtube_dl/extractor/lynda.py
@@ -1,108 +1,114 @@
 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re

-import json

 
 from .common import InfoExtractor
 from ..compat import (
 
 from .common import InfoExtractor
 from ..compat import (

+    compat_HTTPError,

     compat_str,
     compat_str,

-    compat_urllib_parse,
+    compat_urlparse,

 )
 from ..utils import (
     ExtractorError,
 )
 from ..utils import (
     ExtractorError,

-    clean_html,

     int_or_none,
     int_or_none,

-    sanitized_Request,
+    urlencode_postdata,

 )
 
 
 class LyndaBaseIE(InfoExtractor):
 )
 
 
 class LyndaBaseIE(InfoExtractor):

-    _LOGIN_URL = 'https://www.lynda.com/login/login.aspx'
+    _SIGNIN_URL = 'https://www.lynda.com/signin'
+    _PASSWORD_URL = 'https://www.lynda.com/signin/password'
+    _USER_URL = 'https://www.lynda.com/signin/user'

     _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.'
     _NETRC_MACHINE = 'lynda'
 
     def _real_initialize(self):
         self._login()
 
     _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.'
     _NETRC_MACHINE = 'lynda'
 
     def _real_initialize(self):
         self._login()
 

+    @staticmethod
+    def _check_error(json_string, key_or_keys):
+        keys = [key_or_keys] if isinstance(key_or_keys, compat_str) else key_or_keys
+        for key in keys:
+            error = json_string.get(key)
+            if error:
+                raise ExtractorError('Unable to login: %s' % error, expected=True)
+
+    def _login_step(self, form_html, fallback_action_url, extra_form_data, note, referrer_url):
+        action_url = self._search_regex(
+            r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_html,
+            'post url', default=fallback_action_url, group='url')
+
+        if not action_url.startswith('http'):
+            action_url = compat_urlparse.urljoin(self._SIGNIN_URL, action_url)
+
+        form_data = self._hidden_inputs(form_html)
+        form_data.update(extra_form_data)
+
+        try:
+            response = self._download_json(
+                action_url, None, note,
+                data=urlencode_postdata(form_data),
+                headers={
+                    'Referer': referrer_url,
+                    'X-Requested-With': 'XMLHttpRequest',
+                })
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
+                response = self._parse_json(e.cause.read().decode('utf-8'), None)
+                self._check_error(response, ('email', 'password'))
+            raise
+
+        self._check_error(response, 'ErrorMessage')
+
+        return response, action_url
+

     def _login(self):
         username, password = self._get_login_info()
         if username is None:
             return
 
     def _login(self):
         username, password = self._get_login_info()
         if username is None:
             return
 

-        login_form = {
-            'username': username.encode('utf-8'),
-            'password': password.encode('utf-8'),
-            'remember': 'false',
-            'stayPut': 'false'
-        }
-        request = sanitized_Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
-        login_page = self._download_webpage(
-            request, None, 'Logging in as %s' % username)
-
-        # Not (yet) logged in
-        m = re.search(r'loginResultJson\s*=\s*\'(?P<json>[^\']+)\';', login_page)
-        if m is not None:
-            response = m.group('json')
-            response_json = json.loads(response)
-            state = response_json['state']
-
-            if state == 'notlogged':
-                raise ExtractorError(
-                    'Unable to login, incorrect username and/or password',
-                    expected=True)
-
-            # This is when we get popup:
-            # > You're already logged in to lynda.com on two devices.
-            # > If you log in here, we'll log you out of another device.
-            # So, we need to confirm this.
-            if state == 'conflicted':
-                confirm_form = {
-                    'username': '',
-                    'password': '',
-                    'resolve': 'true',
-                    'remember': 'false',
-                    'stayPut': 'false',
-                }
-                request = sanitized_Request(
-                    self._LOGIN_URL, compat_urllib_parse.urlencode(confirm_form).encode('utf-8'))
-                login_page = self._download_webpage(
-                    request, None,
-                    'Confirming log in and log out from another device')
-
-        if all(not re.search(p, login_page) for p in ('isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')):
-            if 'login error' in login_page:
-                mobj = re.search(
-                    r'(?s)<h1[^>]+class="topmost">(?P<title>[^<]+)</h1>\s*<div>(?P<description>.+?)</div>',
-                    login_page)
-                if mobj:
-                    raise ExtractorError(
-                        'lynda returned error: %s - %s'
-                        % (mobj.group('title'), clean_html(mobj.group('description'))),
-                        expected=True)
-            raise ExtractorError('Unable to log in')
-
-    def _logout(self):
-        username, _ = self._get_login_info()
-        if username is None:
+        # Step 1: download signin page
+        signin_page = self._download_webpage(
+            self._SIGNIN_URL, None, 'Downloading signin page')
+
+        # Already logged in
+        if any(re.search(p, signin_page) for p in (
+                r'isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')):

             return
 
             return
 

-        self._download_webpage(
-            'http://www.lynda.com/ajax/logout.aspx', None,
-            'Logging out', 'Unable to log out', fatal=False)
+        # Step 2: submit email
+        signin_form = self._search_regex(
+            r'(?s)(<form[^>]+data-form-name=["\']signin["\'][^>]*>.+?</form>)',
+            signin_page, 'signin form')
+        signin_page, signin_url = self._login_step(
+            signin_form, self._PASSWORD_URL, {'email': username},
+            'Submitting email', self._SIGNIN_URL)
+
+        # Step 3: submit password
+        password_form = signin_page['body']
+        self._login_step(
+            password_form, self._USER_URL, {'email': username, 'password': password},
+            'Submitting password', signin_url)

 
 
 class LyndaIE(LyndaBaseIE):
     IE_NAME = 'lynda'
     IE_DESC = 'lynda.com videos'
 
 
 class LyndaIE(LyndaBaseIE):
     IE_NAME = 'lynda'
     IE_DESC = 'lynda.com videos'

-    _VALID_URL = r'https?://www\.lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(?P<id>\d+)'
-    _NETRC_MACHINE = 'lynda'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?(?:lynda\.com|educourse\.ga)/
+                        (?:
+                            (?:[^/]+/){2,3}(?P<course_id>\d+)|
+                            player/embed
+                        )/
+                        (?P<id>\d+)
+                    '''

 
     _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
 
     _TESTS = [{
 
     _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
 
     _TESTS = [{

-        'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
-        'md5': 'ecfc6862da89489161fb9cd5f5a6fac1',
+        'url': 'https://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
+        # md5 is unstable

         'info_dict': {
             'id': '114408',
             'ext': 'mp4',
         'info_dict': {
             'id': '114408',
             'ext': 'mp4',


@@ -112,21 +118,79 @@ class LyndaIE(LyndaBaseIE):
     }, {
         'url': 'https://www.lynda.com/player/embed/133770?tr=foo=1;bar=g;fizz=rt&fs=0',
         'only_matching': True,
     }, {
         'url': 'https://www.lynda.com/player/embed/133770?tr=foo=1;bar=g;fizz=rt&fs=0',
         'only_matching': True,

+    }, {
+        'url': 'https://educourse.ga/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Willkommen-Grundlagen-guten-Gestaltung/393570/393572-4.html',
+        'only_matching': True,

     }]
 
     }]
 

+    def _raise_unavailable(self, video_id):
+        self.raise_login_required(
+            'Video %s is only available for members' % video_id)
+

     def _real_extract(self, url):
     def _real_extract(self, url):

-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        course_id = mobj.group('course_id')
+
+        query = {
+            'videoId': video_id,
+            'type': 'video',
+        }

 
         video = self._download_json(
 
         video = self._download_json(

-            'http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id,
-            video_id, 'Downloading video JSON')
+            'https://www.lynda.com/ajax/player', video_id,
+            'Downloading video JSON', fatal=False, query=query)
+
+        # Fallback scenario
+        if not video:
+            query['courseId'] = course_id
+
+            play = self._download_json(
+                'https://www.lynda.com/ajax/course/%s/%s/play'
+                % (course_id, video_id), video_id, 'Downloading play JSON')
+
+            if not play:
+                self._raise_unavailable(video_id)
+
+            formats = []
+            for formats_dict in play:
+                urls = formats_dict.get('urls')
+                if not isinstance(urls, dict):
+                    continue
+                cdn = formats_dict.get('name')
+                for format_id, format_url in urls.items():
+                    if not format_url:
+                        continue
+                    formats.append({
+                        'url': format_url,
+                        'format_id': '%s-%s' % (cdn, format_id) if cdn else format_id,
+                        'height': int_or_none(format_id),
+                    })
+            self._sort_formats(formats)
+
+            conviva = self._download_json(
+                'https://www.lynda.com/ajax/player/conviva', video_id,
+                'Downloading conviva JSON', query=query)
+
+            return {
+                'id': video_id,
+                'title': conviva['VideoTitle'],
+                'description': conviva.get('VideoDescription'),
+                'release_year': int_or_none(conviva.get('ReleaseYear')),
+                'duration': int_or_none(conviva.get('Duration')),
+                'creator': conviva.get('Author'),
+                'formats': formats,
+            }

 
         if 'Status' in video:
             raise ExtractorError(
                 'lynda returned error: %s' % video['Message'], expected=True)
 
         if video.get('HasAccess') is False:
 
         if 'Status' in video:
             raise ExtractorError(
                 'lynda returned error: %s' % video['Message'], expected=True)
 
         if video.get('HasAccess') is False:

-            self.raise_login_required('Video %s is only available for members' % video_id)
+            self._raise_unavailable(video_id)

 
         video_id = compat_str(video.get('ID') or video_id)
         duration = int_or_none(video.get('DurationInSeconds'))
 
         video_id = compat_str(video.get('ID') or video_id)
         duration = int_or_none(video.get('DurationInSeconds'))


@@ -150,7 +214,7 @@ class LyndaIE(LyndaBaseIE):
             for prioritized_stream_id, prioritized_stream in prioritized_streams.items():
                 formats.extend([{
                     'url': video_url,
             for prioritized_stream_id, prioritized_stream in prioritized_streams.items():
                 formats.extend([{
                     'url': video_url,

-                    'width': int_or_none(format_id),
+                    'height': int_or_none(format_id),

                     'format_id': '%s-%s' % (prioritized_stream_id, format_id),
                 } for format_id, video_url in prioritized_stream.items()])
 
                     'format_id': '%s-%s' % (prioritized_stream_id, format_id),
                 } for format_id, video_url in prioritized_stream.items()])
 


@@ -189,10 +253,11 @@ class LyndaIE(LyndaBaseIE):
             return srt
 
     def _get_subtitles(self, video_id):
             return srt
 
     def _get_subtitles(self, video_id):

-        url = 'http://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
+        url = 'https://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id

         subs = self._download_json(url, None, False)
         subs = self._download_json(url, None, False)

-        if subs:
-            return {'en': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]}
+        fixed_subs = self._fix_subtitles(subs)
+        if fixed_subs:
+            return {'en': [{'ext': 'srt', 'data': fixed_subs}]}

         else:
             return {}
 
         else:
             return {}
 


@@ -203,25 +268,46 @@ class LyndaCourseIE(LyndaBaseIE):
 
     # Course link equals to welcome/introduction video link of same course
     # We will recognize it as course link
 
     # Course link equals to welcome/introduction video link of same course
     # We will recognize it as course link

-    _VALID_URL = r'https?://(?:www|m)\.lynda\.com/(?P<coursepath>[^/]+/[^/]+/(?P<courseid>\d+))-\d\.html'
+    _VALID_URL = r'https?://(?:www|m)\.(?:lynda\.com|educourse\.ga)/(?P<coursepath>(?:[^/]+/){2,3}(?P<courseid>\d+))-2\.html'
+
+    _TESTS = [{
+        'url': 'https://www.lynda.com/Graphic-Design-tutorials/Grundlagen-guten-Gestaltung/393570-2.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Grundlagen-guten-Gestaltung/393570-2.html',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         course_path = mobj.group('coursepath')
         course_id = mobj.group('courseid')
 
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         course_path = mobj.group('coursepath')
         course_id = mobj.group('courseid')
 

-        course = self._download_json(
-            'http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
-            course_id, 'Downloading course JSON')
+        item_template = 'https://www.lynda.com/%s/%%s-4.html' % course_path

 
 

-        self._logout()
+        course = self._download_json(
+            'https://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
+            course_id, 'Downloading course JSON', fatal=False)
+
+        if not course:
+            webpage = self._download_webpage(url, course_id)
+            entries = [
+                self.url_result(
+                    item_template % video_id, ie=LyndaIE.ie_key(),
+                    video_id=video_id)
+                for video_id in re.findall(
+                    r'data-video-id=["\'](\d+)', webpage)]
+            return self.playlist_result(
+                entries, course_id,
+                self._og_search_title(webpage, fatal=False),
+                self._og_search_description(webpage))

 
         if course.get('Status') == 'NotFound':
             raise ExtractorError(
                 'Course %s does not exist' % course_id, expected=True)
 
         unaccessible_videos = 0
 
         if course.get('Status') == 'NotFound':
             raise ExtractorError(
                 'Course %s does not exist' % course_id, expected=True)
 
         unaccessible_videos = 0

-        videos = []
+        entries = []

 
         # Might want to extract videos right here from video['Formats'] as it seems 'Formats' is not provided
         # by single video API anymore
 
         # Might want to extract videos right here from video['Formats'] as it seems 'Formats' is not provided
         # by single video API anymore


@@ -231,20 +317,23 @@ class LyndaCourseIE(LyndaBaseIE):
                 if video.get('HasAccess') is False:
                     unaccessible_videos += 1
                     continue
                 if video.get('HasAccess') is False:
                     unaccessible_videos += 1
                     continue

-                if video.get('ID'):
-                    videos.append(video['ID'])
+                video_id = video.get('ID')
+                if video_id:
+                    entries.append({
+                        '_type': 'url_transparent',
+                        'url': item_template % video_id,
+                        'ie_key': LyndaIE.ie_key(),
+                        'chapter': chapter.get('Title'),
+                        'chapter_number': int_or_none(chapter.get('ChapterIndex')),
+                        'chapter_id': compat_str(chapter.get('ID')),
+                    })

 
         if unaccessible_videos > 0:
             self._downloader.report_warning(
                 '%s videos are only available for members (or paid members) and will not be downloaded. '
                 % unaccessible_videos + self._ACCOUNT_CREDENTIALS_HINT)
 
 
         if unaccessible_videos > 0:
             self._downloader.report_warning(
                 '%s videos are only available for members (or paid members) and will not be downloaded. '
                 % unaccessible_videos + self._ACCOUNT_CREDENTIALS_HINT)
 

-        entries = [
-            self.url_result(
-                'http://www.lynda.com/%s/%s-4.html' % (course_path, video_id),
-                'Lynda')
-            for video_id in videos]
-

         course_title = course.get('Title')
         course_title = course.get('Title')

+        course_description = course.get('Description')

 
 

-        return self.playlist_result(entries, course_id, course_title)
+        return self.playlist_result(entries, course_id, course_title, course_description)