Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2025-02-17 01:17:54 +01:00
Code Issues Releases Wiki Activity

Fixed format names and added tests

Browse Source
This commit is contained in:
Olivier Berger 2020-05-01 22:40:10 +02:00
parent a7756ff597
commit 7f84a8f13c
1 changed files with 40 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

64
youtube_dl/extractor/bbb.py
View File

@ -5,13 +5,15 @@
# Extract material from recordings made inside BigBlueButton # Extract material from recordings made inside BigBlueButton
# BigBlueButton records multiple videos : # BigBlueButton records multiple videos :
# - speaker speech & webcam # - webcams feed : sound & webcam views : useful for extracting sound
# - screesharing # - deskshare captures : screensharing, but not the slides
# for slides, annotations, etc. the playback app typically renders them on the fly upon playback
# so it may not be easy to capture that with youtube-dl
# Extract a merged video, without the slides with # For slides, annotations, polls and other stuff displayed to the
# youtube-dl --merge-output-format mkv -f slides+speaker "https://mybbb.example.com/playback/presentation/2.0/playback.html?meetingId=12345679a50a715e8d6dc692df996dceb8d788f8-1234566973639" # audience the playback app typically renders them on the fly upon
# playback (SVG) so it may not be easy to capture that with youtube-dl
# To extract a merged video, which will miss the slides and webcam views, proceed with :
# youtube-dl --merge-output-format mkv -f deskshare+webcams "https://mybbb.example.com/playback/presentation/2.0/playback.html?meetingId=12345679a50a715e8d6dc692df996dceb8d788f8-1234566973639"
from __future__ import unicode_literals from __future__ import unicode_literals
@ -28,21 +30,35 @@ _x = lambda p: xpath_with_ns(p, {'xlink': 'http://www.w3.org/1999/xlink'})
class BigBlueButtonIE(InfoExtractor): class BigBlueButtonIE(InfoExtractor):
_VALID_URL = r'(?P<website>https?://[^/]+)/playback/presentation/2.0/playback.html\?meetingId=(?P<id>[0-9a-f\-]+)' _VALID_URL = r'(?P<website>https?://[^/]+)/playback/presentation/2.0/playback.html\?meetingId=(?P<id>[0-9a-f\-]+)'
_TEST = { _TESTS = [
'url': 'https://mybbb.example.com/playback/presentation/2.0/playback.html?meetingId=12345679a50a715e8d6dc692df996dceb8d788f8-1234566973639', {
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', 'url': 'https://webconf.imtbs-tsp.eu/playback/presentation/2.0/playback.html?meetingId=522d1d51bee82a57b535ced7091addeecb074d47-1588254659509',
'info_dict': { 'md5': 'dc98924b35c2234a8c7b3a61b30d968e',
'id': '42', 'info_dict': {
'ext': 'mp4', 'id': '522d1d51bee82a57b535ced7091addeecb074d47-1588254659509',
'title': 'Video title goes here', 'ext': 'webm',
'thumbnail': r're:^https?://.*\.jpg$', 'title': 'PRO 3600',
# TODO more properties, either as: 'timestamp': 1588254659509,
# * A value 'format': 'webcams - unknown'
# * MD5 checksum; start the string with md5: },
# * A regular expression; start the string with re: 'params': {
# * Any Python type (for example int or float) 'format': 'webcams',
} }
} },
{
'url': 'https://webconf.imtbs-tsp.eu/playback/presentation/2.0/playback.html?meetingId=522d1d51bee82a57b535ced7091addeecb074d47-1588254659509',
'md5': '99c9191dbe03dd5eab34ba02352f1742',
'info_dict': {
'id': '522d1d51bee82a57b535ced7091addeecb074d47-1588254659509',
'ext': 'webm',
'title': 'PRO 3600',
'timestamp': 1588254659509,
'format': 'deskshare - unknown'
},
'params': {
'format': 'deskshare',
}
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -81,12 +97,12 @@ class BigBlueButtonIE(InfoExtractor):
slides.append(image.get(_x('xlink:href'))) slides.append(image.get(_x('xlink:href')))
# We produce 2 formats : # We produce 2 formats :
# - the 'webcams.webm' one, for speaker (can be used for merging its audio) # - the 'webcams.webm' one, for webcams (can be used for merging its audio)
# - the 'deskshare.webm' one, for screen sharing (can be used # - the 'deskshare.webm' one, for screen sharing (can be used
# for merging its video) - it lacks the slides unfortunately # for merging its video) - it lacks the slides, unfortunately
formats = [] formats = []
sources = { 'speaker': '/video/webcams.webm', 'slides': '/deskshare/deskshare.webm' } sources = { 'webcams': '/video/webcams.webm', 'deskshare': '/deskshare/deskshare.webm' }
for format_id, source in sources.items(): for format_id, source in sources.items():
video_url = website + '/presentation/' + video_id + source video_url = website + '/presentation/' + video_id + source
formats.append({ formats.append({