mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-07-03 20:08:30 +00:00
Code Issues Projects Releases Wiki Activity

[ie/tvw:News] Add extractor

Browse Source
This commit is contained in:
Fries 2025-04-13 20:27:40 -07:00
parent 74e90dd9b8
commit 9615ae99c0
No known key found for this signature in database
GPG Key ID: B594BC20DB6FE5AA
2 changed files with 55 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
yt_dlp/extractor/_extractors.py
View File

@ -2237,7 +2237,7 @@
TVPlayIE, TVPlayIE,
) )
from .tvplayer import TVPlayerIE from .tvplayer import TVPlayerIE
from .tvw import TvwIE from .tvw import TvwIE, TvwNewsIE
from .tweakers import TweakersIE from .tweakers import TweakersIE
from .twentymin import TwentyMinutenIE from .twentymin import TwentyMinutenIE
from .twentythreevideo import TwentyThreeVideoIE from .twentythreevideo import TwentyThreeVideoIE

59
yt_dlp/extractor/tvw.py
View File

@ -1,11 +1,19 @@
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import clean_html, remove_end, unified_timestamp, url_or_none from ..utils import clean_html, extract_attributes, remove_end, unified_timestamp, url_or_none
from ..utils.traversal import traverse_obj from ..utils.traversal import find_elements, traverse_obj
class TvwIE(InfoExtractor): class TvwBaseIE(InfoExtractor):
def _get_title(self, webpage):
return remove_end(self._og_search_title(webpage, default=None), ' - TVW')
def _get_description(self, webpage):
return self._og_search_description(webpage, default=None)
class TvwIE(TvwBaseIE):
_VALID_URL = r'https?://(?:www\.)?tvw\.org/video/(?P<id>[^/?#]+)' _VALID_URL = r'https?://(?:www\.)?tvw\.org/video/(?P<id>[^/?#]+)'
_TESTS = [{ _TESTS = [{
@ -103,8 +111,8 @@ def _real_extract(self, url):
'display_id': display_id, 'display_id': display_id,
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
'title': remove_end(self._og_search_title(webpage, default=None), ' - TVW'), 'title': self._get_title(webpage),
'description': self._og_search_description(webpage, default=None), 'description': self._get_description(webpage),
**traverse_obj(video_data, { **traverse_obj(video_data, {
'title': ('title', {str}), 'title': ('title', {str}),
'description': ('description', {clean_html}), 'description': ('description', {clean_html}),
@ -115,3 +123,44 @@ def _real_extract(self, url):
'is_live': ('eventStatus', {lambda x: x == 'live'}), 'is_live': ('eventStatus', {lambda x: x == 'live'}),
}), }),
} }
class TvwNewsIE(TvwBaseIE):
IE_NAME = 'Tvw:News'
_VALID_URL = r'https?://(?:www\.)?tvw\.org/(\d{4})/(0[1-9]|1[0-2])/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://tvw.org/2024/01/the-impact-issues-to-watch-in-the-2024-legislative-session/',
'info_dict': {
'id': 'the-impact-issues-to-watch-in-the-2024-legislative-session',
'title': 'The Impact - Issues to Watch in the 2024 Legislative Session',
'description': 'md5:65f0b33ec8f18ff1cd401c5547aa5441',
},
'playlist_count': 6,
}, {
'url': 'https://tvw.org/2024/06/the-impact-water-rights-and-the-skookumchuck-dam-debate/',
'info_dict': {
'id': 'the-impact-water-rights-and-the-skookumchuck-dam-debate',
'title': 'The Impact - Water Rights and the Skookumchuck Dam Debate',
'description': 'md5:185f3a2350ef81e3fa159ac3e040a94b',
},
'playlist_count': 1,
}, {
'url': 'https://tvw.org/2023/09/5th-annual-tvw-open-thank-you/',
'info_dict': {
'id': '5th-annual-tvw-open-thank-you',
'title': '5th Annual TVW Open THANK YOU!',
'description': 'md5:5306eef5b03c87108797cb6261c5f16c',
},
'playlist_count': 0,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
video_ids = traverse_obj(webpage, (
{find_elements(cls='invintus-player', html=True)}, ..., {extract_attributes}, 'data-eventid'))
return self.playlist_result(
(self.url_result(f'https://tvw.org/watch?eventID={video_id}') for video_id in video_ids), playlist_id,
playlist_title=self._get_title(webpage), playlist_description=self._get_description(webpage))