Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[telewebion] fix extraction #32634

Merged
merged 5 commits into from
Dec 2, 2023
Merged

[telewebion] fix extraction #32634

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
e7be5ab
[telewebion] fix extraction
mimvahedi Nov 11, 2023
25afca6
Apply suggestions from code review
mimvahedi Nov 27, 2023
9a039c1
Apply suggestions
mimvahedi Nov 27, 2023
11e1e17
Use native M3U8 downloader
dirkf Dec 2, 2023
1fcdc82
Sort formats!
dirkf Dec 2, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 23 additions & 24 deletions youtube_dl/extractor/telewebion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,17 +3,23 @@

from .common import InfoExtractor

from ..utils import (
float_or_none,
int_or_none,
url_or_none,
)


class TelewebionIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?telewebion\.com/#!/episode/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?telewebion\.com/(episode|clip)/(?P<id>[a-zA-Z0-9]+)'

_TEST = {
'url': 'http://www.telewebion.com/#!/episode/1263668/',
'url': 'http://www.telewebion.com/episode/0x1b3139c/',
'info_dict': {
'id': '1263668',
'id': '0x1b3139c',
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Weirdly, you can replace the hexadecimal ID with its decimal equivalent (28513180).

'ext': 'mp4',
'title': 'قرعه\u200cکشی لیگ قهرمانان اروپا',
'thumbnail': r're:^https?://.*\.jpg',
'thumbnail': r're:^https?://static\.telewebion\.com/episodeImages/.*/default',
'view_count': int,
},
'params': {
Expand All @@ -25,31 +31,24 @@ class TelewebionIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)

secure_token = self._download_webpage(
'http://m.s2.telewebion.com/op/op?action=getSecurityToken', video_id)
episode_details = self._download_json(
'http://m.s2.telewebion.com/op/op', video_id,
query={'action': 'getEpisodeDetails', 'episode_id': video_id})

m3u8_url = 'http://m.s1.telewebion.com/smil/%s.m3u8?filepath=%s&m3u8=1&secure_token=%s' % (
video_id, episode_details['file_path'], secure_token)
formats = self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4', m3u8_id='hls')
episode_details = self._download_json('https://gateway.telewebion.ir/kandoo/episode/getEpisodeDetail/?EpisodeId={0}'.format(video_id), video_id)
episode_details = episode_details['body']['queryEpisode'][0]

picture_paths = [
episode_details.get('picture_path'),
episode_details.get('large_picture_path'),
]
channel_id = episode_details['channel']['descriptor']
episode_image_id = episode_details.get('image')
episode_image = 'https://static.telewebion.com/episodeImages/{0}/default'.format(episode_image_id) if episode_image_id else None

thumbnails = [{
'url': picture_path,
'preference': idx,
} for idx, picture_path in enumerate(picture_paths) if picture_path is not None]
m3u8_url = 'https://cdna.telewebion.com/{0}/episode/{1}/playlist.m3u8'.format(channel_id, video_id)
formats = self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4', m3u8_id='hls',
entry_protocol='m3u8_native')
dirkf marked this conversation as resolved.
Show resolved Hide resolved
self._sort_formats(formats)

return {
'id': video_id,
'title': episode_details['title'],
'formats': formats,
'thumbnails': thumbnails,
'view_count': episode_details.get('view_count'),
'thumbnail': url_or_none(episode_image),
'view_count': int_or_none(episode_details.get('view_count')),
'duration': float_or_none(episode_details.get('duration')),
}