4 from .common
import InfoExtractor
5 from ..compat
import compat_str
19 class AdobeTVBaseIE(InfoExtractor
):
20 def _call_api(self
, path
, video_id
, query
, note
=None):
21 return self
._download
_json
(
22 'http://tv.adobe.com/api/v4/' + path
,
23 video_id
, note
, query
=query
)['data']
25 def _parse_subtitles(self
, video_data
, url_key
):
27 for translation
in video_data
.get('translations', []):
28 vtt_path
= translation
.get(url_key
)
31 lang
= translation
.get('language_w3c') or ISO639Utils
.long2short(translation
['language_medium'])
32 subtitles
.setdefault(lang
, []).append({
38 def _parse_video_data(self
, video_data
):
39 video_id
= compat_str(video_data
['id'])
40 title
= video_data
['title']
44 for source
in video_data
.get('videos', []):
45 source_url
= source
.get('url')
49 'format_id': source
.get('quality_level'),
50 'fps': int_or_none(source
.get('frame_rate')),
51 'height': int_or_none(source
.get('height')),
52 'tbr': int_or_none(source
.get('video_data_rate')),
53 'width': int_or_none(source
.get('width')),
56 original_filename
= source
.get('original_filename')
58 if not (f
.get('height') and f
.get('width')):
59 mobj
= re
.search(r
'_(\d+)x(\d+)', original_filename
)
62 'height': int(mobj
.group(2)),
63 'width': int(mobj
.group(1)),
65 if original_filename
.startswith('s3://') and not s3_extracted
:
67 'format_id': 'original',
69 'url': original_filename
.replace('s3://', 'https://s3.amazonaws.com/'),
73 self
._sort
_formats
(formats
)
78 'description': video_data
.get('description'),
79 'thumbnail': video_data
.get('thumbnail'),
80 'upload_date': unified_strdate(video_data
.get('start_date')),
81 'duration': parse_duration(video_data
.get('duration')),
82 'view_count': str_to_int(video_data
.get('playcount')),
84 'subtitles': self
._parse
_subtitles
(video_data
, 'vtt'),
88 class AdobeTVEmbedIE(AdobeTVBaseIE
):
89 IE_NAME
= 'adobetv:embed'
90 _VALID_URL
= r
'https?://tv\.adobe\.com/embed/\d+/(?P<id>\d+)'
92 'url': 'https://tv.adobe.com/embed/22/4153',
93 'md5': 'c8c0461bf04d54574fc2b4d07ac6783a',
97 'title': 'Creating Graphics Optimized for BlackBerry',
98 'description': 'md5:eac6e8dced38bdaae51cd94447927459',
99 'thumbnail': r
're:https?://.*\.jpg$',
100 'upload_date': '20091109',
106 def _real_extract(self
, url
):
107 video_id
= self
._match
_id
(url
)
109 video_data
= self
._call
_api
(
110 'episode/' + video_id
, video_id
, {'disclosure': 'standard'}
)[0]
111 return self
._parse
_video
_data
(video_data
)
114 class AdobeTVIE(AdobeTVBaseIE
):
116 _VALID_URL
= r
'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
119 'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
120 'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
124 'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
125 'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
126 'thumbnail': r
're:https?://.*\.jpg$',
127 'upload_date': '20110914',
133 def _real_extract(self
, url
):
134 language
, show_urlname
, urlname
= self
._match
_valid
_url
(url
).groups()
138 video_data
= self
._call
_api
(
139 'episode/get', urlname
, {
140 'disclosure': 'standard',
141 'language': language
,
142 'show_urlname': show_urlname
,
145 return self
._parse
_video
_data
(video_data
)
148 class AdobeTVPlaylistBaseIE(AdobeTVBaseIE
):
151 def _fetch_page(self
, display_id
, query
, page
):
154 for element_data
in self
._call
_api
(
155 self
._RESOURCE
, display_id
, query
, 'Download Page %d' % page
):
156 yield self
._process
_data
(element_data
)
158 def _extract_playlist_entries(self
, display_id
, query
):
159 return OnDemandPagedList(functools
.partial(
160 self
._fetch
_page
, display_id
, query
), self
._PAGE
_SIZE
)
163 class AdobeTVShowIE(AdobeTVPlaylistBaseIE
):
164 IE_NAME
= 'adobetv:show'
165 _VALID_URL
= r
'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
168 'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
171 'title': 'The Complete Picture with Julieanne Kost',
172 'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
174 'playlist_mincount': 136,
176 _RESOURCE
= 'episode'
177 _process_data
= AdobeTVBaseIE
._parse
_video
_data
179 def _real_extract(self
, url
):
180 language
, show_urlname
= self
._match
_valid
_url
(url
).groups()
184 'disclosure': 'standard',
185 'language': language
,
186 'show_urlname': show_urlname
,
189 show_data
= self
._call
_api
(
190 'show/get', show_urlname
, query
)[0]
192 return self
.playlist_result(
193 self
._extract
_playlist
_entries
(show_urlname
, query
),
194 str_or_none(show_data
.get('id')),
195 show_data
.get('show_name'),
196 show_data
.get('show_description'))
199 class AdobeTVChannelIE(AdobeTVPlaylistBaseIE
):
200 IE_NAME
= 'adobetv:channel'
201 _VALID_URL
= r
'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
204 'url': 'http://tv.adobe.com/channel/development',
208 'playlist_mincount': 96,
212 def _process_data(self
, show_data
):
213 return self
.url_result(
214 show_data
['url'], 'AdobeTVShow', str_or_none(show_data
.get('id')))
216 def _real_extract(self
, url
):
217 language
, channel_urlname
, category_urlname
= self
._match
_valid
_url
(url
).groups()
221 'channel_urlname': channel_urlname
,
222 'language': language
,
225 query
['category_urlname'] = category_urlname
227 return self
.playlist_result(
228 self
._extract
_playlist
_entries
(channel_urlname
, query
),
232 class AdobeTVVideoIE(AdobeTVBaseIE
):
233 IE_NAME
= 'adobetv:video'
234 _VALID_URL
= r
'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
237 # From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
238 'url': 'https://video.tv.adobe.com/v/2456/',
239 'md5': '43662b577c018ad707a63766462b1e87',
243 'title': 'New experience with Acrobat DC',
244 'description': 'New experience with Acrobat DC',
249 def _real_extract(self
, url
):
250 video_id
= self
._match
_id
(url
)
251 webpage
= self
._download
_webpage
(url
, video_id
)
253 video_data
= self
._parse
_json
(self
._search
_regex
(
254 r
'var\s+bridge\s*=\s*([^;]+);', webpage
, 'bridged data'), video_id
)
255 title
= video_data
['title']
258 sources
= video_data
.get('sources') or []
259 for source
in sources
:
260 source_src
= source
.get('src')
264 'filesize': int_or_none(source
.get('kilobytes') or None, invscale
=1000),
265 'format_id': join_nonempty(source
.get('format'), source
.get('label')),
266 'height': int_or_none(source
.get('height') or None),
267 'tbr': int_or_none(source
.get('bitrate') or None),
268 'width': int_or_none(source
.get('width') or None),
271 self
._sort
_formats
(formats
)
273 # For both metadata and downloaded files the duration varies among
274 # formats. I just pick the max one
275 duration
= max(filter(None, [
276 float_or_none(source
.get('duration'), scale
=1000)
277 for source
in sources
]))
283 'description': video_data
.get('description'),
284 'thumbnail': video_data
.get('video', {}).get('poster'),
285 'duration': duration
,
286 'subtitles': self
._parse
_subtitles
(video_data
, 'vttPath'),