yt-dlp/youtube_dl/extractor/lynda.py

103 lines
3.5 KiB
Python
Raw Normal View History

2014-01-03 13:24:29 +01:00
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import ExtractorError
class LyndaIE(InfoExtractor):
2014-01-03 13:24:29 +01:00
IE_NAME = 'lynda'
IE_DESC = 'lynda.com videos'
_VALID_URL = r'https?://www\.lynda\.com/[^/]+/[^/]+/\d+/(\d+)-\d\.html'
_TEST = {
2014-01-03 13:24:29 +01:00
'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
'file': '114408.mp4',
'md5': 'ecfc6862da89489161fb9cd5f5a6fac1',
u"info_dict": {
2014-01-03 13:24:29 +01:00
'title': 'Using the exercise files',
'duration': 68
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
page = self._download_webpage('http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id,
2014-01-03 13:24:29 +01:00
video_id, 'Downloading video JSON')
video_json = json.loads(page)
2014-01-03 13:24:29 +01:00
if 'Status' in video_json and video_json['Status'] == 'NotFound':
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
2014-01-03 13:24:29 +01:00
if video_json['HasAccess'] is False:
raise ExtractorError('Video %s is only available for members' % video_id, expected=True)
2014-01-03 13:24:29 +01:00
video_id = video_json['ID']
duration = video_json['DurationInSeconds']
title = video_json['Title']
2014-01-03 13:24:29 +01:00
formats = [{'url': fmt['Url'],
'ext': fmt['Extension'],
'width': fmt['Width'],
'height': fmt['Height'],
'filesize': fmt['FileSize'],
'format_id': fmt['Resolution']
} for fmt in video_json['Formats']]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'duration': duration,
'formats': formats
}
class LyndaCourseIE(InfoExtractor):
2014-01-03 13:24:29 +01:00
IE_NAME = 'lynda:course'
IE_DESC = 'lynda.com online courses'
# 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'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
course_path = mobj.group('coursepath')
course_id = mobj.group('courseid')
page = self._download_webpage('http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
2014-01-03 13:24:29 +01:00
course_id, 'Downloading course JSON')
course_json = json.loads(page)
2014-01-03 13:24:29 +01:00
if 'Status' in course_json and course_json['Status'] == 'NotFound':
raise ExtractorError('Course %s does not exist' % course_id, expected=True)
unaccessible_videos = 0
videos = []
2014-01-03 13:24:29 +01:00
for chapter in course_json['Chapters']:
for video in chapter['Videos']:
if video['HasAccess'] is not True:
unaccessible_videos += 1
continue
2014-01-03 13:24:29 +01:00
videos.append(video['ID'])
if unaccessible_videos > 0:
2014-01-03 13:24:29 +01:00
self._downloader.report_warning('%s videos are only available for members and will not be downloaded' % unaccessible_videos)
2014-01-03 13:24:29 +01:00
entries = [
self.url_result('http://www.lynda.com/%s/%s-4.html' %
(course_path, video_id),
'Lynda')
for video_id in videos]
2014-01-03 13:24:29 +01:00
course_title = course_json['Title']
2014-01-03 13:24:29 +01:00
return self.playlist_result(entries, course_id, course_title)