aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/lynda.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/lynda.py')
-rw-r--r--youtube_dl/extractor/lynda.py209
1 files changed, 130 insertions, 79 deletions
diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py
index 655627479..f4dcfd93f 100644
--- a/youtube_dl/extractor/lynda.py
+++ b/youtube_dl/extractor/lynda.py
@@ -1,106 +1,106 @@
from __future__ import unicode_literals
import re
-import json
from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import (
+ compat_HTTPError,
+ compat_str,
+ compat_urlparse,
+)
from ..utils import (
ExtractorError,
- clean_html,
int_or_none,
- sanitized_Request,
urlencode_postdata,
)
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()
+ @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
- login_form = {
- 'username': username.encode('utf-8'),
- 'password': password.encode('utf-8'),
- 'remember': 'false',
- 'stayPut': 'false'
- }
- request = sanitized_Request(
- self._LOGIN_URL, urlencode_postdata(login_form))
- 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, urlencode_postdata(confirm_form))
- 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 (
+ 'isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')):
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'
- _VALID_URL = r'https?://www\.lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(?P<id>\d+)'
- _NETRC_MACHINE = 'lynda'
+ _VALID_URL = r'https?://(?:www\.)?lynda\.com/(?:[^/]+/[^/]+/(?P<course_id>\d+)|player/embed)/(?P<id>\d+)'
_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',
@@ -112,19 +112,71 @@ class LyndaIE(LyndaBaseIE):
'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):
- 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(
- '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:
- 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'))
@@ -148,7 +200,7 @@ class LyndaIE(LyndaBaseIE):
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()])
@@ -187,7 +239,7 @@ class LyndaIE(LyndaBaseIE):
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)
if subs:
return {'en': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]}
@@ -209,11 +261,9 @@ class LyndaCourseIE(LyndaBaseIE):
course_id = mobj.group('courseid')
course = self._download_json(
- 'http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
+ 'https://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
course_id, 'Downloading course JSON')
- self._logout()
-
if course.get('Status') == 'NotFound':
raise ExtractorError(
'Course %s does not exist' % course_id, expected=True)
@@ -233,7 +283,7 @@ class LyndaCourseIE(LyndaBaseIE):
if video_id:
entries.append({
'_type': 'url_transparent',
- 'url': 'http://www.lynda.com/%s/%s-4.html' % (course_path, video_id),
+ 'url': 'https://www.lynda.com/%s/%s-4.html' % (course_path, video_id),
'ie_key': LyndaIE.ie_key(),
'chapter': chapter.get('Title'),
'chapter_number': int_or_none(chapter.get('ChapterIndex')),
@@ -246,5 +296,6 @@ class LyndaCourseIE(LyndaBaseIE):
% unaccessible_videos + self._ACCOUNT_CREDENTIALS_HINT)
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)
generated by cgit v1.2.3 (git 2.26.2) at 2025-04-04 21:38:27 +0000