From: Philipp Hagemeister Date: Fri, 3 Jan 2014 12:24:29 +0000 (+0100) Subject: [lynda] minor changes X-Git-Url: http://git.bitcoin.ninja/index.cgi?p=youtube-dl;a=commitdiff_plain;h=a7c26e7338ceed06b579775f315b078644a7482b [lynda] minor changes --- a7c26e7338ceed06b579775f315b078644a7482b diff --cc youtube_dl/extractor/__init__.py index 31bbda46f,2caa078b5..21d564dba --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@@ -102,7 -97,10 +102,11 @@@ from .kickstarter import KickStarterI from .keek import KeekIE from .liveleak import LiveLeakIE from .livestream import LivestreamIE, LivestreamOriginalIE + from .lynda import ( + LyndaIE, + LyndaCourseIE + ) +from .macgamestore import MacGameStoreIE from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE diff --cc youtube_dl/extractor/lynda.py index 000000000,dd59aa3e6..592ed747a mode 000000,100644..100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@@ -1,0 -1,96 +1,102 @@@ ++from __future__ import unicode_literals ++ + import re + import json + + from .common import InfoExtractor + from ..utils import ExtractorError + + + class LyndaIE(InfoExtractor): - IE_NAME = u'lynda' - IE_DESC = u'lynda.com videos' ++ IE_NAME = 'lynda' ++ IE_DESC = 'lynda.com videos' + _VALID_URL = r'https?://www\.lynda\.com/[^/]+/[^/]+/\d+/(\d+)-\d\.html' + + _TEST = { - u'url': u'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html', - u'file': u'114408.mp4', - u'md5': u'ecfc6862da89489161fb9cd5f5a6fac1', ++ 'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html', ++ 'file': '114408.mp4', ++ 'md5': 'ecfc6862da89489161fb9cd5f5a6fac1', + u"info_dict": { - u'title': u'Using the exercise files', - u'duration': 68 ++ '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, - video_id, u'Downloading video JSON') ++ video_id, 'Downloading video JSON') + video_json = json.loads(page) + - if u'Status' in video_json and video_json[u'Status'] == u'NotFound': - raise ExtractorError(u'Video %s does not exist' % video_id, expected=True) ++ if 'Status' in video_json and video_json['Status'] == 'NotFound': ++ raise ExtractorError('Video %s does not exist' % video_id, expected=True) + - if video_json[u'HasAccess'] is False: - raise ExtractorError(u'Video %s is only available for members' % video_id, expected=True) ++ if video_json['HasAccess'] is False: ++ raise ExtractorError('Video %s is only available for members' % video_id, expected=True) + - video_id = video_json[u'ID'] - duration = video_json[u'DurationInSeconds'] - title = video_json[u'Title'] ++ video_id = video_json['ID'] ++ duration = video_json['DurationInSeconds'] ++ title = video_json['Title'] + - formats = [{'url': fmt[u'Url'], - 'ext': fmt[u'Extension'], - 'width': fmt[u'Width'], - 'height': fmt[u'Height'], - 'filesize': fmt[u'FileSize'], - 'format_id': fmt[u'Resolution'] - } for fmt in video_json[u'Formats']] ++ 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): - IE_NAME = u'lynda:course' - IE_DESC = u'lynda.com online courses' ++ 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[^/]+/[^/]+/(?P\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, - course_id, u'Downloading course JSON') ++ course_id, 'Downloading course JSON') + course_json = json.loads(page) + - if u'Status' in course_json and course_json[u'Status'] == u'NotFound': - raise ExtractorError(u'Course %s does not exist' % course_id, expected=True) ++ 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 = [] + - for chapter in course_json[u'Chapters']: - for video in chapter[u'Videos']: - if video[u'HasAccess'] is not True: ++ for chapter in course_json['Chapters']: ++ for video in chapter['Videos']: ++ if video['HasAccess'] is not True: + unaccessible_videos += 1 + continue - videos.append(video[u'ID']) ++ videos.append(video['ID']) + + if unaccessible_videos > 0: - self._downloader.report_warning(u'%s videos are only available for members and will not be downloaded' % unaccessible_videos) ++ self._downloader.report_warning('%s videos are only available for members and will not be downloaded' % unaccessible_videos) + - entries = [self.url_result('http://www.lynda.com/%s/%s-4.html' % (course_path, video_id), 'Lynda') for video_id in videos] ++ 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_json[u'Title'] ++ course_title = course_json['Title'] + - return self.playlist_result(entries, course_id, course_title) ++ return self.playlist_result(entries, course_id, course_title)