mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-02 06:27:21 +00:00
[ie/kenh14] Simplify
This commit is contained in:
Mozi
bashonly
parent
38ed7e7d0d
commit
09d0a29721
|
|
@ -942,6 +942,10 @@
|
||||||
from .kankanews import KankaNewsIE
|
from .kankanews import KankaNewsIE
|
||||||
from .karaoketv import KaraoketvIE
|
from .karaoketv import KaraoketvIE
|
||||||
from .kelbyone import KelbyOneIE
|
from .kelbyone import KelbyOneIE
|
||||||
|
from .kenh14 import (
|
||||||
|
Kenh14PlaylistIE,
|
||||||
|
Kenh14VideoIE,
|
||||||
|
)
|
||||||
from .khanacademy import (
|
from .khanacademy import (
|
||||||
KhanAcademyIE,
|
KhanAcademyIE,
|
||||||
KhanAcademyUnitIE,
|
KhanAcademyUnitIE,
|
||||||
|
|
|
||||||
|
|
@ -1,321 +1,150 @@
|
||||||
|
import urllib.parse
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
clean_html,
|
clean_html,
|
||||||
extract_attributes,
|
extract_attributes,
|
||||||
get_element_by_class,
|
get_element_by_class,
|
||||||
get_element_html_by_attribute,
|
get_element_html_by_attribute,
|
||||||
get_elements_by_attribute,
|
get_elements_html_by_class,
|
||||||
get_elements_html_by_attribute,
|
|
||||||
int_or_none,
|
int_or_none,
|
||||||
parse_duration,
|
parse_duration,
|
||||||
parse_iso8601,
|
parse_iso8601,
|
||||||
remove_end,
|
|
||||||
remove_start,
|
remove_start,
|
||||||
|
str_or_none,
|
||||||
|
strip_or_none,
|
||||||
|
unescapeHTML,
|
||||||
|
url_or_none,
|
||||||
)
|
)
|
||||||
|
from ..utils.traversal import traverse_obj
|
||||||
|
|
||||||
|
|
||||||
class Kenh14IE(InfoExtractor):
|
class Kenh14VideoIE(InfoExtractor):
|
||||||
IE_NAME = 'kenh14'
|
_VALID_URL = r'https?://video\.kenh14\.vn/(?:video/)?[\w-]+-(?P<id>[0-9]+)\.chn'
|
||||||
_VALID_URL = r'https?://video.kenh14\.vn/(?:playlist/)?[^/]*-(?P<id>[0-9]+)\.chn'
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://video.kenh14.vn/video-mo-hop-iphone-14-pro-max-nguon-unbox-therapy-316173.chn',
|
'url': 'https://video.kenh14.vn/video/mo-hop-iphone-14-pro-max-nguon-unbox-therapy-316173.chn',
|
||||||
'note': 'Video URL',
|
'md5': '1ed67f9c3a1e74acf15db69590cf6210',
|
||||||
'md5': '525b9c4646a7aed819697cfd17dd25a9',
|
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '316173',
|
'id': '316173',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
|
'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
|
||||||
'description': 'Video mở hộp iPhone 14 Pro Max',
|
'description': 'Video mở hộp iPhone 14 Pro MaxVideo mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
|
||||||
'thumbnails': list,
|
'tags': [],
|
||||||
'formats': list,
|
|
||||||
'tags': ["iPhone 14 Pro", "iPhone 14 Pro Max", "iPhone 14"],
|
|
||||||
'display_id': 'video-mo-hop-iphone-14-pro-max-nguon-unbox-therapy',
|
|
||||||
'uploader': 'Unbox Therapy',
|
'uploader': 'Unbox Therapy',
|
||||||
'display_id': 'video-mo-hop-iphone-14-pro-max-nguon-unbox-therapy',
|
|
||||||
'upload_date': '20220517',
|
'upload_date': '20220517',
|
||||||
'view_count': int,
|
'view_count': int,
|
||||||
'release_date': '20220518',
|
|
||||||
'modified_date': '20220518',
|
|
||||||
'duration': 722.86,
|
'duration': 722.86,
|
||||||
'modified_timestamp': 1652848039,
|
'timestamp': 1652764468,
|
||||||
'release_timestamp': 1652848039,
|
|
||||||
'timestamp': int,
|
|
||||||
}
|
|
||||||
}, {
|
|
||||||
'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn',
|
|
||||||
'note': 'Playlist URL',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '316972',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'description': 'md5:4212062bf4c447efbad5f54e6ab8d132',
|
|
||||||
'thumbnail': 'https://kenh14cdn.com/203336854389633024/2022/6/5/1024-1281-1654416995812779954762.jpg',
|
|
||||||
|
|
||||||
'modified_timestamp': 1654376400,
|
|
||||||
'duration': 4602.09,
|
|
||||||
'timestamp': 1654398990,
|
|
||||||
'release_date': '20220604',
|
|
||||||
'tags': ['Sơn Soho', 'Linh Keen', 'Trần Tình (Naked Love) mùa 2', 'Naked Love', 'trần tình', 'ShowHot'],
|
|
||||||
'release_timestamp': 1654376400,
|
|
||||||
'view_count': int,
|
|
||||||
'modified_date': '20220604',
|
|
||||||
'title': '[4x5] FINAL - Naked Love EP4 - Moi quan he tieu cuc',
|
|
||||||
'upload_date': '20220605',
|
|
||||||
'display_id': 'md5:a27d1fbdeafeb740050de0e697c8e02e',
|
|
||||||
}
|
|
||||||
}, {
|
|
||||||
'url': 'https://video.kenh14.vn/video-316173.chn',
|
|
||||||
'note': 'javascript-based redirect; set via <body onload="window.location.href=URL">',
|
|
||||||
'md5': '525b9c4646a7aed819697cfd17dd25a9',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '316173',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
|
|
||||||
'description': 'Video mở hộp iPhone 14 Pro Max',
|
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
|
||||||
'thumbnails': list,
|
|
||||||
'formats': list,
|
|
||||||
'tags': ["iPhone 14 Pro", "iPhone 14 Pro Max", "iPhone 14"],
|
|
||||||
'display_id': 'video-mo-hop-iphone-14-pro-max-nguon-unbox-therapy',
|
|
||||||
'uploader': 'Unbox Therapy',
|
|
||||||
'display_id': 'video-mo-hop-iphone-14-pro-max-nguon-unbox-therapy',
|
|
||||||
'upload_date': '20220517',
|
|
||||||
'view_count': int,
|
|
||||||
'release_date': '20220518',
|
|
||||||
'modified_date': '20220518',
|
|
||||||
'duration': 722.86,
|
|
||||||
'modified_timestamp': 1652848039,
|
|
||||||
'release_timestamp': 1652848039,
|
|
||||||
'timestamp': int,
|
|
||||||
}
|
|
||||||
}, {
|
|
||||||
'url': 'https://video.kenh14.vn/0-316173.chn',
|
|
||||||
'note': 'HTTP 301 redirect to canonical URL',
|
|
||||||
'md5': '525b9c4646a7aed819697cfd17dd25a9',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '316173',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
|
|
||||||
'description': 'Video mở hộp iPhone 14 Pro Max',
|
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
|
||||||
'thumbnails': list,
|
|
||||||
'formats': list,
|
|
||||||
'tags': ["iPhone 14 Pro", "iPhone 14 Pro Max", "iPhone 14"],
|
|
||||||
'display_id': 'video-mo-hop-iphone-14-pro-max-nguon-unbox-therapy',
|
|
||||||
'uploader': 'Unbox Therapy',
|
|
||||||
'display_id': 'video-mo-hop-iphone-14-pro-max-nguon-unbox-therapy',
|
|
||||||
'upload_date': '20220517',
|
|
||||||
'view_count': int,
|
|
||||||
'release_date': '20220518',
|
|
||||||
'modified_date': '20220518',
|
|
||||||
'duration': 722.86,
|
|
||||||
'modified_timestamp': 1652848039,
|
|
||||||
'release_timestamp': 1652848039,
|
|
||||||
'timestamp': int,
|
|
||||||
}
|
|
||||||
}, {
|
|
||||||
'url': 'https://video.kenh14.vn/playlist/0-71.chn',
|
|
||||||
'note': 'HTTP 301 redirect to canonical playlist URL',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '316972',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'description': 'md5:4212062bf4c447efbad5f54e6ab8d132',
|
|
||||||
'thumbnail': 'https://kenh14cdn.com/203336854389633024/2022/6/5/1024-1281-1654416995812779954762.jpg',
|
|
||||||
|
|
||||||
'modified_timestamp': 1654376400,
|
|
||||||
'duration': 4602.09,
|
|
||||||
'timestamp': 1654398990,
|
|
||||||
'release_date': '20220604',
|
|
||||||
'tags': ['Sơn Soho', 'Linh Keen', 'Trần Tình (Naked Love) mùa 2', 'Naked Love', 'trần tình', 'ShowHot'],
|
|
||||||
'release_timestamp': 1654376400,
|
|
||||||
'view_count': int,
|
|
||||||
'modified_date': '20220604',
|
|
||||||
'title': '[4x5] FINAL - Naked Love EP4 - Moi quan he tieu cuc',
|
|
||||||
'upload_date': '20220605',
|
|
||||||
'display_id': 'md5:a27d1fbdeafeb740050de0e697c8e02e',
|
|
||||||
}
|
|
||||||
}, {
|
|
||||||
'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn',
|
|
||||||
'note': 'Playlist URL with --flat-playlist',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '316972',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'description': 'md5:4212062bf4c447efbad5f54e6ab8d132',
|
|
||||||
'thumbnail': 'https://videothumbs.mediacdn.vn/kenh14/203336854389633024/2022/6/5/4x5-final-naked-love-ep4-moi-quan-he-tieu-cuc-16544166609501118413296.jpg',
|
|
||||||
'tags': ['Sơn Soho', 'Linh Keen', 'Trần Tình (Naked Love) mùa 2', 'Naked Love', 'Trần tình', 'ShowHot'],
|
|
||||||
'title': 'Naked Love - Trần Tình tập 4: Sơn Soho, Linh Keen cùng câu chuyện bước ra khỏi mối quan hệ tiêu cực và yêu bản thân mình',
|
|
||||||
'display_id': 'md5:db3e1b63976a664b3576f3ef68a17c9a',
|
|
||||||
},
|
},
|
||||||
'params': {'extract_flat': 'in_playlist'}
|
}, {
|
||||||
|
'url': 'https://video.kenh14.vn/video-316174.chn',
|
||||||
|
'md5': '2b41877d2afaf4a3f487ceda8e5c7cbd',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '316174',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Khoảnh khắc VĐV nằm gục khóc sau chiến thắng: 7 năm trời Việt Nam mới có HCV kiếm chém nữ, chỉ có 8 tháng để khổ luyện trước khi lên sàn đấu',
|
||||||
|
'description': 'md5:de86aa22e143e2b277bce8ec9c6f17dc',
|
||||||
|
'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
|
||||||
|
'tags': [],
|
||||||
|
'upload_date': '20220517',
|
||||||
|
'view_count': int,
|
||||||
|
'duration': 70.04,
|
||||||
|
'timestamp': 1652766021,
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'url': 'https://video.kenh14.vn/0-344740.chn',
|
||||||
|
'md5': 'b843495d5e728142c8870c09b46df2a9',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '344740',
|
||||||
|
'ext': 'mov',
|
||||||
|
'title': 'Kỳ Duyên đầy căng thẳng trong buổi ra quân đi Miss Universe, nghi thức tuyên thuệ lần đầu xuất hiện gây nhiều tranh cãi',
|
||||||
|
'description': 'md5:2a2dbb4a7397169fb21ee68f09160497',
|
||||||
|
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.jpg$',
|
||||||
|
'tags': ['kỳ duyên', 'Kỳ Duyên tuyên thuệ', 'miss universe'],
|
||||||
|
'uploader': 'Quang Vũ',
|
||||||
|
'upload_date': '20241024',
|
||||||
|
'view_count': int,
|
||||||
|
'duration': 198.88,
|
||||||
|
'timestamp': 1729741590,
|
||||||
|
},
|
||||||
|
'expected_warnings': [
|
||||||
|
'Failed to download m3u8 information: HTTP Error 404: NOT FOUND',
|
||||||
|
],
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _try_get_redirect_url(self, webpage):
|
def _real_extract(self, url):
|
||||||
# javascript-based redirect; set via <body onload="window.location.href=URL">
|
video_id = self._match_id(url)
|
||||||
url = self._search_regex(r"onload=\"window.location.href='([^']*)'", webpage, 'redirect url', default=None, fatal=False)
|
webpage = self._download_webpage(url, video_id)
|
||||||
if url:
|
|
||||||
return 'https://video.kenh14.vn' + url
|
|
||||||
|
|
||||||
def _extract_formats_wrapper(self, video_id, direct_url):
|
attrs = extract_attributes(get_element_html_by_attribute('type', 'VideoStream', webpage) or '')
|
||||||
formats = [{'url': f'https://{direct_url}'}]
|
direct_url = attrs['data-vid']
|
||||||
formats.extend(self._extract_m3u8_formats(f'https://{direct_url}/master.m3u8', video_id))
|
|
||||||
self._sort_formats(formats)
|
|
||||||
return formats
|
|
||||||
|
|
||||||
def _extract_video(self, webpage, page_url, fallback_url=''):
|
metadata = self._download_json(
|
||||||
video_id = self._match_id(page_url)
|
'https://api.kinghub.vn/video/api/v1/detailVideoByGet?FileName={}'.format(
|
||||||
if webpage is None:
|
remove_start(direct_url, 'kenh14cdn.com/')), video_id, fatal=False)
|
||||||
webpage, page_url = self._download_webpage_wrapper(page_url, fatal=False)
|
|
||||||
attrs = extract_attributes(self._extract_video_div(webpage))
|
|
||||||
direct_url = attrs.get('data-vid', fallback_url)
|
|
||||||
filename = remove_start(direct_url, 'kenh14cdn.com/')
|
|
||||||
inline_metadata = self._parse_json(attrs.get('data-htmlcode', '{}'), video_id, fatal=False)
|
|
||||||
display_id = self._get_display_id(page_url)
|
|
||||||
|
|
||||||
formats = self._extract_formats_wrapper(video_id, direct_url)
|
return {
|
||||||
result = {
|
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': (
|
'title': (
|
||||||
clean_html(self._og_search_title(webpage))
|
strip_or_none(metadata.get('title'))
|
||||||
or inline_metadata.get('video_title')
|
or clean_html(self._og_search_title(webpage))
|
||||||
or self._extract_title(webpage)),
|
or clean_html(get_element_by_class('vdbw-title', webpage))),
|
||||||
'formats': formats,
|
'formats': [
|
||||||
'duration': parse_duration(inline_metadata.get('video_duration')),
|
{'url': f'https://{direct_url}', 'format_id': 'http'},
|
||||||
|
*self._extract_m3u8_formats(f'https://{direct_url}/master.m3u8', video_id, fatal=False),
|
||||||
|
],
|
||||||
|
'duration': parse_duration(metadata.get('duration')),
|
||||||
'description': (
|
'description': (
|
||||||
clean_html(self._og_search_description(webpage))
|
clean_html(self._og_search_description(webpage))
|
||||||
or clean_html(inline_metadata.get('video_description'))
|
or clean_html(get_element_by_class('vdbw-sapo', webpage))),
|
||||||
or self._extract_description(webpage)),
|
'thumbnail': (self._og_search_thumbnail(webpage) or attrs.get('data-thumb')),
|
||||||
'thumbnail': (
|
'uploader': strip_or_none(metadata.get('author')),
|
||||||
self._og_search_thumbnail(webpage)
|
'timestamp': parse_iso8601(metadata.get('uploadtime'), delimiter=' '),
|
||||||
or inline_metadata.get('video_thumb')
|
|
||||||
or attrs.get('data-thumb')),
|
|
||||||
'release_timestamp': parse_iso8601(self._html_search_meta('article:published_time', webpage)),
|
|
||||||
'modified_timestamp': parse_iso8601(self._html_search_meta('article:modified_time', webpage)),
|
|
||||||
'tags': self._extract_page_tags(webpage),
|
|
||||||
'webpage_url': page_url,
|
|
||||||
'display_id': display_id,
|
|
||||||
}
|
|
||||||
result['timestamp'] = result.get('release_timestamp') or result.get('modified_timestamp')
|
|
||||||
|
|
||||||
metadata = self._download_json(f'https://api.kinghub.vn/video/api/v1/detailVideoByGet?FileName={filename}', video_id) or {}
|
|
||||||
|
|
||||||
return {
|
|
||||||
# Note: API result contains 'videoID' but it's a different number that doesn't seem public-facing.
|
|
||||||
'id': video_id,
|
|
||||||
'title': metadata.get('title') or result.get('title'),
|
|
||||||
'formats': formats,
|
|
||||||
'duration': parse_duration(metadata.get('duration')) or result.get('duration'),
|
|
||||||
'timestamp': (
|
|
||||||
parse_iso8601(metadata.get('uploadtime'), delimiter=' ')
|
|
||||||
or result.get('timestamp')),
|
|
||||||
'release_timestamp': result.get('release_timestamp'),
|
|
||||||
'modified_timestamp': result.get('modified_timestamp'),
|
|
||||||
'thumbnail': metadata.get('thumbnail') or result.get('thumbnail'),
|
|
||||||
'description': result.get('description'),
|
|
||||||
'uploader': metadata.get('author'),
|
|
||||||
'view_count': int_or_none(metadata.get('views')),
|
'view_count': int_or_none(metadata.get('views')),
|
||||||
'tags': result.get('tags'),
|
'tags': traverse_obj(self._html_search_meta('keywords', webpage), (
|
||||||
'webpage_url': page_url,
|
{lambda x: x.split(';')}, lambda _, v: v, {str_or_none})),
|
||||||
'display_id': display_id,
|
|
||||||
}
|
}
|
||||||
|
|
||||||
def _extract_playlist(self, webpage, url):
|
|
||||||
playlist_id = self._match_id(url)
|
|
||||||
display_id = self._get_display_id(url)
|
|
||||||
|
|
||||||
def _extract_playlist_videos():
|
class Kenh14PlaylistIE(InfoExtractor):
|
||||||
for video_listitem in self._get_list_videos(webpage):
|
_VALID_URL = r'https?://video\.kenh14\.vn/playlist/[\w-]+-(?P<id>[0-9]+)\.chn'
|
||||||
attrs = extract_attributes(self._extract_video_div(video_listitem))
|
_TESTS = [{
|
||||||
direct_url = attrs.get('data-vid')
|
'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn',
|
||||||
if not direct_url:
|
'info_dict': {
|
||||||
self.report_warning(f'Could not find expected video in playlist {playlist_id}')
|
'id': '71',
|
||||||
continue
|
'title': 'Trần Tình (Naked love) mùa 2',
|
||||||
|
'description': 'md5:e9522339304956dea931722dd72eddb2',
|
||||||
video_id = attrs.get('data-item-id')
|
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
|
||||||
share_url = attrs.get('data-share')
|
},
|
||||||
if not share_url:
|
'playlist_count': 9,
|
||||||
share_url = f'https://video.kenh14.vn/video-{video_id}.chn'
|
}, {
|
||||||
|
'url': 'https://video.kenh14.vn/playlist/0-72.chn',
|
||||||
basename = remove_end(remove_start(direct_url, 'kenh14cdn.com/'), '.mp4')
|
'info_dict': {
|
||||||
video_result = {
|
'id': '72',
|
||||||
'_type': 'video',
|
'title': 'Lau Lại Đầu Từ',
|
||||||
'id': video_id,
|
'description': 'Cùng xem xưa và nay có gì khác biệt nhé!',
|
||||||
'webpage_url': share_url,
|
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
|
||||||
'display_id': display_id,
|
},
|
||||||
'title': self._extract_title(video_listitem),
|
'playlist_count': 6,
|
||||||
'description': self._extract_description(video_listitem),
|
}]
|
||||||
'thumbnail': f'https://videothumbs.mediacdn.vn/kenh14/{basename}.jpg',
|
|
||||||
'tags': self._extract_tag_list(video_listitem),
|
|
||||||
}
|
|
||||||
|
|
||||||
if not self.get_param('extract_flat', False):
|
|
||||||
video_result.update(self._extract_video(None, share_url, direct_url))
|
|
||||||
else:
|
|
||||||
video_result.update({'formats': self._extract_formats_wrapper(video_id, direct_url)})
|
|
||||||
|
|
||||||
yield video_result
|
|
||||||
|
|
||||||
return {
|
|
||||||
'_type': 'playlist',
|
|
||||||
'id': playlist_id,
|
|
||||||
'title': self._og_search_title(webpage),
|
|
||||||
'description': self._og_search_description(webpage),
|
|
||||||
'thumbnail': self._og_search_thumbnail(webpage),
|
|
||||||
'tags': self._extract_page_tags(webpage),
|
|
||||||
'display_id': display_id,
|
|
||||||
'entries': _extract_playlist_videos(),
|
|
||||||
}
|
|
||||||
pass
|
|
||||||
|
|
||||||
def _get_list_videos(self, webpage):
|
|
||||||
# get_elements_html_by_class('video-item', webpage) is NOT doing what I
|
|
||||||
# expect; it's matching list-video-item for some reason
|
|
||||||
return get_elements_html_by_attribute('class', 'video-item', webpage)
|
|
||||||
|
|
||||||
def _extract_video_div(self, content):
|
|
||||||
return get_element_html_by_attribute('type', 'VideoStream', content) or ''
|
|
||||||
|
|
||||||
def _extract_title(self, elem):
|
|
||||||
return clean_html(get_element_by_class('video-title', elem) or get_element_by_class('vdbw-title', elem))
|
|
||||||
|
|
||||||
def _extract_description(self, elem):
|
|
||||||
return clean_html(get_element_by_class('video-sapo', elem) or get_element_by_class('vdbw-sapo', elem))
|
|
||||||
|
|
||||||
def _extract_tag_list(self, elem):
|
|
||||||
in_class = list(get_elements_html_by_attribute('class', 'video-tag', elem))
|
|
||||||
in_attr = list(get_elements_by_attribute('data', 'video-tag', elem))
|
|
||||||
return list(filter(None, map(clean_html, in_class or in_attr)))
|
|
||||||
|
|
||||||
def _extract_page_tags(self, webpage):
|
|
||||||
tags = self._html_search_meta('article:tag', webpage) or ''
|
|
||||||
return list(filter(None, map(lambda x: x.strip(), tags.split(','))))
|
|
||||||
|
|
||||||
def _download_webpage_wrapper(self, url, fatal=True):
|
|
||||||
video_id = self._match_id(url)
|
|
||||||
webpage, urlh = self._download_webpage_handle(url, video_id, fatal=fatal)
|
|
||||||
redirect_url = self._try_get_redirect_url(webpage)
|
|
||||||
new_urlh = urlh
|
|
||||||
if redirect_url:
|
|
||||||
# Page load relies on a javascript redirect
|
|
||||||
webpage, new_urlh = self._download_webpage_handle(redirect_url, video_id, fatal=fatal)
|
|
||||||
return webpage, (new_urlh or urlh).geturl()
|
|
||||||
|
|
||||||
def _is_playlist(self, url):
|
|
||||||
return self._search_regex(
|
|
||||||
r'https?://video.kenh14\.vn/(?P<is_playlist>playlist/|)?.*\.chn',
|
|
||||||
url, 'url type and display id', default=False, group=('is_playlist'), fatal=False)
|
|
||||||
|
|
||||||
def _get_display_id(self, url):
|
|
||||||
return self._search_regex(
|
|
||||||
r'https?://video.kenh14\.vn/(?:playlist/|)?(?P<display_id>.*?)-?[0-9]+\.chn',
|
|
||||||
url, 'url type and display id', group=('display_id'), fatal=False)
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
webpage, url = self._download_webpage_wrapper(url)
|
playlist_id = self._match_id(url)
|
||||||
|
webpage = self._download_webpage(url, playlist_id)
|
||||||
|
|
||||||
is_playlist = self._is_playlist(url)
|
category_detail = get_element_by_class('category-detail', webpage)
|
||||||
self.write_debug('deduced page to be a ' + ('playlist' if is_playlist else 'video'))
|
embed_info = traverse_obj(
|
||||||
|
self._yield_json_ld(webpage, playlist_id),
|
||||||
|
(lambda _, v: v['name'] and v['alternateName']), get_all=False)
|
||||||
|
|
||||||
if is_playlist:
|
return self.playlist_from_matches(
|
||||||
return self._extract_playlist(webpage, url)
|
get_elements_html_by_class('video-item', webpage), playlist_id,
|
||||||
else:
|
(clean_html(get_element_by_class('name', category_detail)) or unescapeHTML(embed_info.get('name'))),
|
||||||
return self._extract_video(webpage, url)
|
getter=lambda x: 'https://video.kenh14.vn/video/{}.chn'.format(extract_attributes(x)['data-id']),
|
||||||
|
ie=Kenh14VideoIE.ie_key(), playlist_description=(
|
||||||
|
clean_html(get_element_by_class('description', category_detail))
|
||||||
|
or unescapeHTML(embed_info.get('alternateName'))),
|
||||||
|
thumbnail=traverse_obj(
|
||||||
|
self._og_search_thumbnail(webpage),
|
||||||
|
({url_or_none}, {lambda x: urllib.parse.urlunparse(urllib.parse.urlparse(x)._replace(query=None))})))
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue