|
|
|
@ -3,7 +3,6 @@ from __future__ import unicode_literals
|
|
|
|
|
import re
|
|
|
|
|
import json
|
|
|
|
|
|
|
|
|
|
from .subtitles import SubtitlesInfoExtractor
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
from ..compat import (
|
|
|
|
|
compat_str,
|
|
|
|
@ -16,7 +15,7 @@ from ..utils import (
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class LyndaIE(SubtitlesInfoExtractor):
|
|
|
|
|
class LyndaIE(InfoExtractor):
|
|
|
|
|
IE_NAME = 'lynda'
|
|
|
|
|
IE_DESC = 'lynda.com videos'
|
|
|
|
|
_VALID_URL = r'https?://www\.lynda\.com/[^/]+/[^/]+/\d+/(\d+)-\d\.html'
|
|
|
|
@ -88,11 +87,7 @@ class LyndaIE(SubtitlesInfoExtractor):
|
|
|
|
|
self._check_formats(formats, video_id)
|
|
|
|
|
self._sort_formats(formats)
|
|
|
|
|
|
|
|
|
|
if self._downloader.params.get('listsubtitles', False):
|
|
|
|
|
self._list_available_subtitles(video_id, page)
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
subtitles = self._fix_subtitles(self.extract_subtitles(video_id, page))
|
|
|
|
|
subtitles = self.extract_subtitles(video_id, page)
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
'id': video_id,
|
|
|
|
@ -144,15 +139,7 @@ class LyndaIE(SubtitlesInfoExtractor):
|
|
|
|
|
if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
|
|
|
|
|
raise ExtractorError('Unable to log in')
|
|
|
|
|
|
|
|
|
|
def _fix_subtitles(self, subtitles):
|
|
|
|
|
if subtitles is None:
|
|
|
|
|
return subtitles # subtitles not requested
|
|
|
|
|
|
|
|
|
|
fixed_subtitles = {}
|
|
|
|
|
for k, v in subtitles.items():
|
|
|
|
|
subs = json.loads(v)
|
|
|
|
|
if len(subs) == 0:
|
|
|
|
|
continue
|
|
|
|
|
def _fix_subtitles(self, subs):
|
|
|
|
|
srt = ''
|
|
|
|
|
for pos in range(0, len(subs) - 1):
|
|
|
|
|
seq_current = subs[pos]
|
|
|
|
@ -168,14 +155,15 @@ class LyndaIE(SubtitlesInfoExtractor):
|
|
|
|
|
text = seq_current['Caption']
|
|
|
|
|
srt += '%s\r\n%s --> %s\r\n%s' % (str(pos), appear_time, disappear_time, text)
|
|
|
|
|
if srt:
|
|
|
|
|
fixed_subtitles[k] = srt
|
|
|
|
|
return fixed_subtitles
|
|
|
|
|
return srt
|
|
|
|
|
|
|
|
|
|
def _get_available_subtitles(self, video_id, webpage):
|
|
|
|
|
def _get_subtitles(self, video_id, webpage):
|
|
|
|
|
url = 'http://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
|
|
|
|
|
sub = self._download_webpage(url, None, False)
|
|
|
|
|
sub_json = json.loads(sub)
|
|
|
|
|
return {'en': url} if len(sub_json) > 0 else {}
|
|
|
|
|
subs = self._download_json(url, None, False)
|
|
|
|
|
if subs:
|
|
|
|
|
return {'en': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]}
|
|
|
|
|
else:
|
|
|
|
|
return {}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class LyndaCourseIE(InfoExtractor):
|
|
|
|
|