1 from __future__
import unicode_literals
6 from .common
import InfoExtractor
10 compat_urllib_request
,
19 class LyndaBaseIE(InfoExtractor
):
20 _LOGIN_URL
= 'https://www.lynda.com/login/login.aspx'
21 _ACCOUNT_CREDENTIALS_HINT
= 'Use --username and --password options to provide lynda.com account credentials.'
22 _NETRC_MACHINE
= 'lynda'
24 def _real_initialize(self
):
28 (username
, password
) = self
._get
_login
_info
()
33 'username': username
.encode('utf-8'),
34 'password': password
.encode('utf-8'),
38 request
= compat_urllib_request
.Request(
39 self
._LOGIN
_URL
, compat_urllib_parse
.urlencode(login_form
).encode('utf-8'))
40 login_page
= self
._download
_webpage
(
41 request
, None, 'Logging in as %s' % username
)
44 m
= re
.search(r
'loginResultJson\s*=\s*\'(?P
<json
>[^
\']+)\';', login_page)
46 response = m.group('json
')
47 response_json = json.loads(response)
48 state = response_json['state
']
50 if state == 'notlogged
':
52 'Unable to login
, incorrect username
and/or password
',
55 # This is when we get popup:
56 # > You're already logged
in to lynda
.com on two devices
.
57 # > If you log in here, we'll log you out of another device.
58 # So, we need to confirm this.
59 if state
== 'conflicted':
67 request
= compat_urllib_request
.Request(
68 self
._LOGIN
_URL
, compat_urllib_parse
.urlencode(confirm_form
).encode('utf-8'))
69 login_page
= self
._download
_webpage
(
71 'Confirming log in and log out from another device')
73 if all(not re
.search(p
, login_page
) for p
in ('isLoggedIn\s*:\s*true', r
'logout\.aspx', r
'>Log out<')):
74 if 'login error' in login_page
:
76 r
'(?s)<h1[^>]+class="topmost">(?P<title>[^<]+)</h1>\s*<div>(?P<description>.+?)</div>',
80 'lynda returned error: %s - %s'
81 % (mobj
.group('title'), clean_html(mobj
.group('description'))),
83 raise ExtractorError('Unable to log in')
86 class LyndaIE(LyndaBaseIE
):
88 IE_DESC
= 'lynda.com videos'
89 _VALID_URL
= r
'https?://www\.lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(?P<id>\d+)'
90 _NETRC_MACHINE
= 'lynda'
92 _TIMECODE_REGEX
= r
'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
95 'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
96 'md5': 'ecfc6862da89489161fb9cd5f5a6fac1',
100 'title': 'Using the exercise files',
104 'url': 'https://www.lynda.com/player/embed/133770?tr=foo=1;bar=g;fizz=rt&fs=0',
105 'only_matching': True,
108 def _real_extract(self
, url
):
109 video_id
= self
._match
_id
(url
)
111 page
= self
._download
_webpage
(
112 'http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id
,
113 video_id
, 'Downloading video JSON')
114 video_json
= json
.loads(page
)
116 if 'Status' in video_json
:
117 raise ExtractorError(
118 'lynda returned error: %s' % video_json
['Message'], expected
=True)
120 if video_json
['HasAccess'] is False:
121 self
.raise_login_required('Video %s is only available for members' % video_id
)
123 video_id
= compat_str(video_json
['ID'])
124 duration
= video_json
['DurationInSeconds']
125 title
= video_json
['Title']
129 fmts
= video_json
.get('Formats')
134 'ext': fmt
['Extension'],
135 'width': fmt
['Width'],
136 'height': fmt
['Height'],
137 'filesize': fmt
['FileSize'],
138 'format_id': str(fmt
['Resolution'])
141 prioritized_streams
= video_json
.get('PrioritizedStreams')
142 if prioritized_streams
:
146 'width': int_or_none(format_id
),
147 'format_id': format_id
,
148 } for format_id
, video_url
in prioritized_streams
['0'].items()
151 self
._check
_formats
(formats
, video_id
)
152 self
._sort
_formats
(formats
)
154 subtitles
= self
.extract_subtitles(video_id
, page
)
159 'duration': duration
,
160 'subtitles': subtitles
,
164 def _fix_subtitles(self
, subs
):
167 for pos
in range(0, len(subs
) - 1):
168 seq_current
= subs
[pos
]
169 m_current
= re
.match(self
._TIMECODE
_REGEX
, seq_current
['Timecode'])
170 if m_current
is None:
172 seq_next
= subs
[pos
+ 1]
173 m_next
= re
.match(self
._TIMECODE
_REGEX
, seq_next
['Timecode'])
176 appear_time
= m_current
.group('timecode')
177 disappear_time
= m_next
.group('timecode')
178 text
= seq_current
['Caption'].strip()
181 srt
+= '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (seq_counter
, appear_time
, disappear_time
, text
)
185 def _get_subtitles(self
, video_id
, webpage
):
186 url
= 'http://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
187 subs
= self
._download
_json
(url
, None, False)
189 return {'en': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}
]}
194 class LyndaCourseIE(LyndaBaseIE
):
195 IE_NAME
= 'lynda:course'
196 IE_DESC
= 'lynda.com online courses'
198 # Course link equals to welcome/introduction video link of same course
199 # We will recognize it as course link
200 _VALID_URL
= r
'https?://(?:www|m)\.lynda\.com/(?P<coursepath>[^/]+/[^/]+/(?P<courseid>\d+))-\d\.html'
202 def _real_extract(self
, url
):
203 mobj
= re
.match(self
._VALID
_URL
, url
)
204 course_path
= mobj
.group('coursepath')
205 course_id
= mobj
.group('courseid')
207 page
= self
._download
_webpage
(
208 'http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id
,
209 course_id
, 'Downloading course JSON')
210 course_json
= json
.loads(page
)
212 if 'Status' in course_json
and course_json
['Status'] == 'NotFound':
213 raise ExtractorError(
214 'Course %s does not exist' % course_id
, expected
=True)
216 unaccessible_videos
= 0
219 # Might want to extract videos right here from video['Formats'] as it seems 'Formats' is not provided
220 # by single video API anymore
222 for chapter
in course_json
['Chapters']:
223 for video
in chapter
['Videos']:
224 if video
['HasAccess'] is False:
225 unaccessible_videos
+= 1
227 videos
.append(video
['ID'])
229 if unaccessible_videos
> 0:
230 self
._downloader
.report_warning(
231 '%s videos are only available for members (or paid members) and will not be downloaded. '
232 % unaccessible_videos
+ self
._ACCOUNT
_CREDENTIALS
_HINT
)
236 'http://www.lynda.com/%s/%s-4.html' % (course_path
, video_id
),
238 for video_id
in videos
]
240 course_title
= course_json
['Title']
242 return self
.playlist_result(entries
, course_id
, course_title
)