[extractor/moview] Add extractor (#4607)

Authored by: HobbyistDev
This commit is contained in:
HobbyistDev 2022-08-15 05:09:05 +09:00 committed by GitHub
parent cb7cc448c0
commit 7695f5a0a7
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 99 additions and 44 deletions

View file

@ -975,6 +975,7 @@
from .motorsport import MotorsportIE
from .movieclips import MovieClipsIE
from .moviepilot import MoviepilotIE
from .moview import MoviewPlayIE
from .moviezine import MoviezineIE
from .movingimage import MovingImageIE
from .msn import MSNIE

51
yt_dlp/extractor/jixie.py Normal file
View file

@ -0,0 +1,51 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
float_or_none,
traverse_obj,
try_call,
)
# more info about jixie:
# [1] https://jixie.atlassian.net/servicedesk/customer/portal/2/article/1339654214?src=-1456335525,
# [2] https://scripts.jixie.media/jxvideo.3.1.min.js
class JixieBaseIE(InfoExtractor):
def _extract_data_from_jixie_id(self, display_id, video_id, webpage):
json_data = self._download_json(
'https://apidam.jixie.io/api/public/stream', display_id,
query={'metadata': 'full', 'video_id': video_id})['data']
formats, subtitles = [], {}
for stream in json_data['streams']:
if stream.get('type') == 'HLS':
fmt, sub = self._extract_m3u8_formats_and_subtitles(stream.get('url'), display_id, ext='mp4')
if json_data.get('drm'):
for f in fmt:
f['has_drm'] = True
formats.extend(fmt)
self._merge_subtitles(sub, target=subtitles)
else:
formats.append({
'url': stream.get('url'),
'width': stream.get('width'),
'height': stream.get('height'),
'ext': 'mp4',
})
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'formats': formats,
'subtitles': subtitles,
'title': json_data.get('title') or self._html_search_meta(['og:title', 'twitter:title'], webpage),
'description': (clean_html(traverse_obj(json_data, ('metadata', 'description')))
or self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage)),
'thumbnails': traverse_obj(json_data, ('metadata', 'thumbnails')),
'duration': float_or_none(traverse_obj(json_data, ('metadata', 'duration'))),
'tags': try_call(lambda: (json_data['metadata']['keywords'] or None).split(',')),
'categories': try_call(lambda: (json_data['metadata']['categories'] or None).split(',')),
'uploader_id': json_data.get('owner_id'),
}

View file

@ -1,17 +1,9 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
float_or_none,
traverse_obj,
try_call,
)
from .jixie import JixieBaseIE
# Video from www.kompas.tv and video.kompas.com seems use jixie player
# see [1] https://jixie.atlassian.net/servicedesk/customer/portal/2/article/1339654214?src=-1456335525,
# [2] https://scripts.jixie.media/jxvideo.3.1.min.js for more info
# Video from video.kompas.com seems use jixie player
class KompasVideoIE(InfoExtractor):
class KompasVideoIE(JixieBaseIE):
_VALID_URL = r'https?://video\.kompas\.com/\w+/(?P<id>\d+)/(?P<slug>[\w-]+)'
_TESTS = [{
'url': 'https://video.kompas.com/watch/164474/kim-jong-un-siap-kirim-nuklir-lawan-as-dan-korsel',
@ -33,36 +25,4 @@ def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).group('id', 'slug')
webpage = self._download_webpage(url, display_id)
json_data = self._download_json(
'https://apidam.jixie.io/api/public/stream', display_id,
query={'metadata': 'full', 'video_id': video_id})['data']
formats, subtitles = [], {}
for stream in json_data['streams']:
if stream.get('type') == 'HLS':
fmt, sub = self._extract_m3u8_formats_and_subtitles(stream.get('url'), display_id, ext='mp4')
formats.extend(fmt)
self._merge_subtitles(sub, target=subtitles)
else:
formats.append({
'url': stream.get('url'),
'width': stream.get('width'),
'height': stream.get('height'),
'ext': 'mp4',
})
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'formats': formats,
'subtitles': subtitles,
'title': json_data.get('title') or self._html_search_meta(['og:title', 'twitter:title'], webpage),
'description': (clean_html(traverse_obj(json_data, ('metadata', 'description')))
or self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage)),
'thumbnails': traverse_obj(json_data, ('metadata', 'thumbnails')),
'duration': float_or_none(traverse_obj(json_data, ('metadata', 'duration'))),
'tags': try_call(lambda: json_data['metadata']['keywords'].split(',')),
'categories': try_call(lambda: json_data['metadata']['categories'].split(',')),
'uploader_id': json_data.get('owner_id'),
}
return self._extract_data_from_jixie_id(display_id, video_id, webpage)

View file

@ -0,0 +1,43 @@
from .jixie import JixieBaseIE
class MoviewPlayIE(JixieBaseIE):
_VALID_URL = r'https?://www\.moview\.id/play/\d+/(?P<id>[\w-]+)'
_TESTS = [
{
# drm hls, only use direct link
'url': 'https://www.moview.id/play/174/Candy-Monster',
'info_dict': {
'id': '146182',
'ext': 'mp4',
'display_id': 'Candy-Monster',
'uploader_id': 'Mo165qXUUf',
'duration': 528.2,
'title': 'Candy Monster',
'description': 'Mengapa Candy Monster ingin mengambil permen Chloe?',
'thumbnail': 'https://video.jixie.media/1034/146182/146182_1280x720.jpg',
}
}, {
# non-drm hls
'url': 'https://www.moview.id/play/75/Paris-Van-Java-Episode-16',
'info_dict': {
'id': '28210',
'ext': 'mp4',
'duration': 2595.666667,
'display_id': 'Paris-Van-Java-Episode-16',
'uploader_id': 'Mo165qXUUf',
'thumbnail': 'https://video.jixie.media/1003/28210/28210_1280x720.jpg',
'description': 'md5:2a5e18d98eef9b39d7895029cac96c63',
'title': 'Paris Van Java Episode 16',
}
}
]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'video_id\s*=\s*"(?P<video_id>[^"]+)', webpage, 'video_id')
return self._extract_data_from_jixie_id(display_id, video_id, webpage)