mirror/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-03-09 12:50:23 -05:00
Code Activity

[ie/Tvw] Apply suggestions from PR

Browse source
This commit is contained in:
Fries 2025-03-02 16:14:12 -08:00
parent bdba60a7df
commit 3b0091a260
1 changed files with 55 additions and 38 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

77
yt_dlp/extractor/tvw.py
View file

@ -1,11 +1,12 @@
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ExtractorError, clean_html, traverse_obj, unified_timestamp, url_or_none from ..utils import clean_html, remove_end, traverse_obj, unified_timestamp, url_or_none
class TvwIE(InfoExtractor): class TvwIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tvw\.org/video/(?P<id>[^/?#]+)' _VALID_URL = r'https?://(?:www\.)?tvw\.org/video/(?P<id>[^/?#]+)'
_VALID_THUMBNAIL_URLS = r're:^https?://.*\.(?:jpe?g|png)$'
_TESTS = [{ _TESTS = [{
'url': 'https://tvw.org/video/billy-frank-jr-statue-maquette-unveiling-ceremony-2024011211/', 'url': 'https://tvw.org/video/billy-frank-jr-statue-maquette-unveiling-ceremony-2024011211/',
'md5': '9ceb94fe2bb7fd726f74f16356825703', 'md5': '9ceb94fe2bb7fd726f74f16356825703',
@ -13,11 +14,13 @@ class TvwIE(InfoExtractor):
'id': '2024011211', 'id': '2024011211',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Billy Frank Jr. Statue Maquette Unveiling Ceremony', 'title': 'Billy Frank Jr. Statue Maquette Unveiling Ceremony',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': _VALID_THUMBNAIL_URLS,
'description': 'md5:58a8150017d985b4f377e11ee8f6f36e', 'description': 'md5:58a8150017d985b4f377e11ee8f6f36e',
'timestamp': 1704902400, 'timestamp': 1704902400,
'upload_date': '20240110', 'upload_date': '20240110',
'location': 'Legislative Building', 'location': 'Legislative Building',
'display_id': 'billy-frank-jr-statue-maquette-unveiling-ceremony-2024011211',
'categories': ['General Interest'],
}}, { }}, {
'url': 'https://tvw.org/video/ebeys-landing-state-park-2024081007/', 'url': 'https://tvw.org/video/ebeys-landing-state-park-2024081007/',
'md5': '71e87dae3deafd65d75ff3137b9a32fc', 'md5': '71e87dae3deafd65d75ff3137b9a32fc',
@ -25,11 +28,13 @@ class TvwIE(InfoExtractor):
'id': '2024081007', 'id': '2024081007',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Ebey\'s Landing State Park', 'title': 'Ebey\'s Landing State Park',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': _VALID_THUMBNAIL_URLS,
'description': 'md5:50c5bd73bde32fa6286a008dbc853386', 'description': 'md5:50c5bd73bde32fa6286a008dbc853386',
'timestamp': 1724310900, 'timestamp': 1724310900,
'upload_date': '20240822', 'upload_date': '20240822',
'location': 'Ebey’s Landing State Park', 'location': 'Ebey’s Landing State Park',
'display_id': 'ebeys-landing-state-park-2024081007',
'categories': ['Washington State Parks'],
}}, { }}, {
'url': 'https://tvw.org/video/home-warranties-workgroup-2', 'url': 'https://tvw.org/video/home-warranties-workgroup-2',
'md5': 'f678789bf94d07da89809f213cf37150', 'md5': 'f678789bf94d07da89809f213cf37150',
@ -37,36 +42,37 @@ class TvwIE(InfoExtractor):
'id': '1999121000', 'id': '1999121000',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Home Warranties Workgroup', 'title': 'Home Warranties Workgroup',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': _VALID_THUMBNAIL_URLS,
'description': 'md5:861396cc523c9641d0dce690bc5c35f3', 'description': 'md5:861396cc523c9641d0dce690bc5c35f3',
'timestamp': 946389600, 'timestamp': 946389600,
'upload_date': '19991228', 'upload_date': '19991228',
'display_id': 'home-warranties-workgroup-2',
'categories': ['Legislative'],
}}, {
'url': 'https://tvw.org/video/washington-to-washington-a-new-space-race-2022041111/?eventID=2022041111',
'md5': '6f5551090b351aba10c0d08a881b4f30',
'info_dict': {
'id': '2022041111',
'ext': 'mp4',
'title': 'Washington to Washington - A New Space Race',
'thumbnail': _VALID_THUMBNAIL_URLS,
'description': 'md5:f65a24eec56107afbcebb3aa5cd26341',
'timestamp': 1650394800,
'upload_date': '20220419',
'location': 'Hayner Media Center',
'display_id': 'washington-to-washington-a-new-space-race-2022041111',
'categories': ['Washington to Washington', 'General Interest'],
}}] }}]
def _extract_formats(self, response, video_id):
extract_formats = lambda url, video_id: self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
stream_urls = traverse_obj(response, 'streamingURIs', {
'main': ('main', {url_or_none}),
'backup': ('backup', {url_or_none}),
})
try:
return extract_formats(stream_urls.get('main'), video_id)
except ExtractorError:
self.report_warning('Failed to parse the m3u8 stream. Falling back to the backup stream if it exists.')
try:
return extract_formats(stream_urls.get('backup'), video_id)
except ExtractorError:
raise
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, display_id)
client_id = self._html_search_meta('clientID', webpage, fatal=True) client_id = self._html_search_meta('clientID', webpage, fatal=True)
video_id = self._html_search_meta('eventID', webpage, fatal=True) video_id = self._html_search_meta('eventID', webpage, fatal=True)
video_data = self._download_json('https://api.v3.invintus.com/v2/Event/getDetailed', video_id, video_data = self._download_json(
'https://api.v3.invintus.com/v2/Event/getDetailed', video_id,
headers={ headers={
'authorization': 'embedder', 'authorization': 'embedder',
'wsc-api-key': '7WhiEBzijpritypp8bqcU7pfU9uicDR', 'wsc-api-key': '7WhiEBzijpritypp8bqcU7pfU9uicDR',
@ -75,19 +81,30 @@ def _real_extract(self, url):
'clientID': client_id, 'clientID': client_id,
'eventID': video_id, 'eventID': video_id,
'showStreams': True, 'showStreams': True,
}).encode()).get('data') }).encode())['data']
formats, subtitles = self._extract_formats(video_data, video_id) formats = []
subtitles = {}
for stream_url in traverse_obj(video_data, ('streamingURIs', ..., {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
if caption_url := traverse_obj(video_data, ('captionPath', {url_or_none})):
self._merge_subtitles({'en': [{'en': 'vtt', 'url': caption_url}]}, target=subtitles)
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id,
'formats': formats, 'formats': formats,
'subtitles': subtitles,
'title': remove_end(self._og_search_title(webpage), ' - TVW'),
'description': self._og_search_description(webpage),
**traverse_obj(video_data, { **traverse_obj(video_data, {
'title': ('title', {lambda x: x or self._og_search_title(webpage)}), 'title': ('title', {str}),
'description': ('description', {lambda x: clean_html(x) or self._og_search_description(webpage)}), 'description': ('description', {clean_html}),
'subtitles': ('captionPath', { 'categories': ('categories', ..., {str}),
lambda x: self._merge_subtitles({'en': [{'ext': 'vtt', 'url': x}]}, target=subtitles),
}),
'thumbnail': ('videoThumbnail', {url_or_none}), 'thumbnail': ('videoThumbnail', {url_or_none}),
'timestamp': ('startDateTime', {unified_timestamp}), 'timestamp': ('startDateTime', {unified_timestamp}),
'location': ('locationName', {str}), 'location': ('locationName', {str}),