yt_dlp/extractor/microsoftvirtualacademy.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     int_or_none,
   8     parse_duration,
   9     smuggle_url,
  10     unsmuggle_url,
  11     xpath_text,
  12 )
  13
  14
  15 class MicrosoftVirtualAcademyBaseIE(InfoExtractor):
  16     def _extract_base_url(self, course_id, display_id):
  17         return self._download_json(
  18             'https://api-mlxprod.microsoft.com/services/products/anonymous/%s' % course_id,
  19             display_id, 'Downloading course base URL')
  20
  21     def _extract_chapter_and_title(self, title):
  22         if not title:
  23             return None, None
  24         m = re.search(r'(?P<chapter>\d+)\s*\|\s*(?P<title>.+)', title)
  25         return (int(m.group('chapter')), m.group('title')) if m else (None, title)
  26
  27
  28 class MicrosoftVirtualAcademyIE(MicrosoftVirtualAcademyBaseIE):
  29     IE_NAME = 'mva'
  30     IE_DESC = 'Microsoft Virtual Academy videos'
  31     _VALID_URL = r'(?:%s:|https?://(?:mva\.microsoft|(?:www\.)?microsoftvirtualacademy)\.com/[^/]+/training-courses/[^/?#&]+-)(?P<course_id>\d+)(?::|\?l=)(?P<id>[\da-zA-Z]+_\d+)' % IE_NAME
  32
  33     _TESTS = [{
  34         'url': 'https://mva.microsoft.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788?l=gfVXISmEB_6804984382',
  35         'md5': '7826c44fc31678b12ad8db11f6b5abb9',
  36         'info_dict': {
  37             'id': 'gfVXISmEB_6804984382',
  38             'ext': 'mp4',
  39             'title': 'Course Introduction',
  40             'formats': 'mincount:3',
  41             'subtitles': {
  42                 'en': [{
  43                     'ext': 'ttml',
  44                 }],
  45             },
  46         }
  47     }, {
  48         'url': 'mva:11788:gfVXISmEB_6804984382',
  49         'only_matching': True,
  50     }]
  51
  52     def _real_extract(self, url):
  53         url, smuggled_data = unsmuggle_url(url, {})
  54
  55         mobj = self._match_valid_url(url)
  56         course_id = mobj.group('course_id')
  57         video_id = mobj.group('id')
  58
  59         base_url = smuggled_data.get('base_url') or self._extract_base_url(course_id, video_id)
  60
  61         settings = self._download_xml(
  62             '%s/content/content_%s/videosettings.xml?v=1' % (base_url, video_id),
  63             video_id, 'Downloading video settings XML')
  64
  65         _, title = self._extract_chapter_and_title(xpath_text(
  66             settings, './/Title', 'title', fatal=True))
  67
  68         formats = []
  69
  70         for sources in settings.findall('.//MediaSources'):
  71             sources_type = sources.get('videoType')
  72             for source in sources.findall('./MediaSource'):
  73                 video_url = source.text
  74                 if not video_url or not video_url.startswith('http'):
  75                     continue
  76                 if sources_type == 'smoothstreaming':
  77                     formats.extend(self._extract_ism_formats(
  78                         video_url, video_id, 'mss', fatal=False))
  79                     continue
  80                 video_mode = source.get('videoMode')
  81                 height = int_or_none(self._search_regex(
  82                     r'^(\d+)[pP]$', video_mode or '', 'height', default=None))
  83                 codec = source.get('codec')
  84                 acodec, vcodec = [None] * 2
  85                 if codec:
  86                     codecs = codec.split(',')
  87                     if len(codecs) == 2:
  88                         acodec, vcodec = codecs
  89                     elif len(codecs) == 1:
  90                         vcodec = codecs[0]
  91                 formats.append({
  92                     'url': video_url,
  93                     'format_id': video_mode,
  94                     'height': height,
  95                     'acodec': acodec,
  96                     'vcodec': vcodec,
  97                 })
  98         self._sort_formats(formats)
  99
 100         subtitles = {}
 101         for source in settings.findall('.//MarkerResourceSource'):
 102             subtitle_url = source.text
 103             if not subtitle_url:
 104                 continue
 105             subtitles.setdefault('en', []).append({
 106                 'url': '%s/%s' % (base_url, subtitle_url),
 107                 'ext': source.get('type'),
 108             })
 109
 110         return {
 111             'id': video_id,
 112             'title': title,
 113             'subtitles': subtitles,
 114             'formats': formats
 115         }
 116
 117
 118 class MicrosoftVirtualAcademyCourseIE(MicrosoftVirtualAcademyBaseIE):
 119     IE_NAME = 'mva:course'
 120     IE_DESC = 'Microsoft Virtual Academy courses'
 121     _VALID_URL = r'(?:%s:|https?://(?:mva\.microsoft|(?:www\.)?microsoftvirtualacademy)\.com/[^/]+/training-courses/(?P<display_id>[^/?#&]+)-)(?P<id>\d+)' % IE_NAME
 122
 123     _TESTS = [{
 124         'url': 'https://mva.microsoft.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788',
 125         'info_dict': {
 126             'id': '11788',
 127             'title': 'Microsoft Azure Fundamentals: Virtual Machines',
 128         },
 129         'playlist_count': 36,
 130     }, {
 131         # with emphasized chapters
 132         'url': 'https://mva.microsoft.com/en-US/training-courses/developing-windows-10-games-with-construct-2-16335',
 133         'info_dict': {
 134             'id': '16335',
 135             'title': 'Developing Windows 10 Games with Construct 2',
 136         },
 137         'playlist_count': 10,
 138     }, {
 139         'url': 'https://www.microsoftvirtualacademy.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788',
 140         'only_matching': True,
 141     }, {
 142         'url': 'mva:course:11788',
 143         'only_matching': True,
 144     }]
 145
 146     @classmethod
 147     def suitable(cls, url):
 148         return False if MicrosoftVirtualAcademyIE.suitable(url) else super(
 149             MicrosoftVirtualAcademyCourseIE, cls).suitable(url)
 150
 151     def _real_extract(self, url):
 152         mobj = self._match_valid_url(url)
 153         course_id = mobj.group('id')
 154         display_id = mobj.group('display_id')
 155
 156         base_url = self._extract_base_url(course_id, display_id)
 157
 158         manifest = self._download_json(
 159             '%s/imsmanifestlite.json' % base_url,
 160             display_id, 'Downloading course manifest JSON')['manifest']
 161
 162         organization = manifest['organizations']['organization'][0]
 163
 164         entries = []
 165         for chapter in organization['item']:
 166             chapter_number, chapter_title = self._extract_chapter_and_title(chapter.get('title'))
 167             chapter_id = chapter.get('@identifier')
 168             for item in chapter.get('item', []):
 169                 item_id = item.get('@identifier')
 170                 if not item_id:
 171                     continue
 172                 metadata = item.get('resource', {}).get('metadata') or {}
 173                 if metadata.get('learningresourcetype') != 'Video':
 174                     continue
 175                 _, title = self._extract_chapter_and_title(item.get('title'))
 176                 duration = parse_duration(metadata.get('duration'))
 177                 description = metadata.get('description')
 178                 entries.append({
 179                     '_type': 'url_transparent',
 180                     'url': smuggle_url(
 181                         'mva:%s:%s' % (course_id, item_id), {'base_url': base_url}),
 182                     'title': title,
 183                     'description': description,
 184                     'duration': duration,
 185                     'chapter': chapter_title,
 186                     'chapter_number': chapter_number,
 187                     'chapter_id': chapter_id,
 188                 })
 189
 190         title = organization.get('title') or manifest.get('metadata', {}).get('title')
 191
 192         return self.playlist_result(entries, course_id, title)