aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2015-06-21 18:55:26 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2015-06-21 18:55:26 +0800
commit607841af64d308eaf577e528fd7317a8b382b8e6 (patch)
treeebb745e0187916dae75c44c229bb602e7f66577a
parent396726244a9096f142f5420ba5f3a1a36abb9a86 (diff)
[adobetv] Support embeddable videos (closes #6039)
-rw-r--r--youtube_dl/extractor/__init__.py5
-rw-r--r--youtube_dl/extractor/adobetv.py59
2 files changed, 63 insertions, 1 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 6c548d8e9..0f4af88f0 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -4,7 +4,10 @@ from .abc import ABCIE
from .abc7news import Abc7NewsIE
from .academicearth import AcademicEarthCourseIE
from .addanime import AddAnimeIE
-from .adobetv import AdobeTVIE
+from .adobetv import (
+ AdobeTVIE,
+ AdobeTVVideoIE,
+)
from .adultswim import AdultSwimIE
from .aftenposten import AftenpostenIE
from .aftonbladet import AftonbladetIE
diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py
index 97d128560..695a4a15c 100644
--- a/youtube_dl/extractor/adobetv.py
+++ b/youtube_dl/extractor/adobetv.py
@@ -5,6 +5,8 @@ from ..utils import (
parse_duration,
unified_strdate,
str_to_int,
+ float_or_none,
+ ISO639Utils,
)
@@ -69,3 +71,60 @@ class AdobeTVIE(InfoExtractor):
'view_count': view_count,
'formats': formats,
}
+
+
+class AdobeTVVideoIE(InfoExtractor):
+ _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
+
+ _TEST = {
+ 'url': 'https://video.tv.adobe.com/v/2456/',
+ 'md5': '43662b577c018ad707a63766462b1e87',
+ 'info_dict': {
+ 'id': '2456',
+ 'ext': 'mp4',
+ 'title': 'New experience with Acrobat DC',
+ 'description': 'New experience with Acrobat DC',
+ 'duration': 248.667,
+ },
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ player_params = self._parse_json(self._search_regex(
+ r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'),
+ video_id)
+
+ formats = [{
+ 'url': source['src'],
+ 'width': source.get('width'),
+ 'height': source.get('height'),
+ 'tbr': source.get('bitrate'),
+ } for source in player_params['sources']]
+
+ # For both metadata and downloaded files the duration varies among
+ # formats. I just pick the max one
+ duration = max(filter(None, [
+ float_or_none(source.get('duration'), scale=1000)
+ for source in player_params['sources']]))
+
+ subtitles = {}
+ for translation in player_params.get('translations', []):
+ lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
+ if lang_id not in subtitles:
+ subtitles[lang_id] = []
+ subtitles[lang_id].append({
+ 'url': translation['vttPath'],
+ 'ext': 'vtt',
+ })
+
+ return {
+ 'id': video_id,
+ 'formats': formats,
+ 'title': player_params['title'],
+ 'description': self._og_search_description(webpage),
+ 'duration': duration,
+ 'subtitles': subtitles,
+ }