aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/adobetv.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/adobetv.py')
-rw-r--r--youtube_dl/extractor/adobetv.py67
1 files changed, 64 insertions, 3 deletions
diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py
index 28e07f8b0..5e43adc51 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,
)
@@ -28,7 +30,6 @@ class AdobeTVIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
-
webpage = self._download_webpage(url, video_id)
player = self._parse_json(
@@ -44,8 +45,10 @@ class AdobeTVIE(InfoExtractor):
self._html_search_meta('datepublished', webpage, 'upload date'))
duration = parse_duration(
- self._html_search_meta('duration', webpage, 'duration')
- or self._search_regex(r'Runtime:\s*(\d{2}:\d{2}:\d{2})', webpage, 'duration'))
+ self._html_search_meta('duration', webpage, 'duration') or
+ self._search_regex(
+ r'Runtime:\s*(\d{2}:\d{2}:\d{2})',
+ webpage, 'duration', fatal=False))
view_count = str_to_int(self._search_regex(
r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
@@ -68,3 +71,61 @@ 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 = {
+ # From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
+ '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,
+ }