Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-20 09:52:50 +01:00
Code Issues Releases Activity

[NZOnScreenIE] Fix extractor

Browse Source
This commit is contained in:
grqx_wsl 2024-09-09 23:57:06 +12:00
parent a7d3235c84
commit f0cea43cde
1 changed files with 60 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

93
yt_dlp/extractor/nzonscreen.py
View File

@ -1,8 +1,8 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext,
float_or_none, float_or_none,
int_or_none, int_or_none,
remove_end,
strip_or_none, strip_or_none,
traverse_obj, traverse_obj,
url_or_none, url_or_none,
@ -15,12 +15,12 @@ class NZOnScreenIE(InfoExtractor):
'url': 'https://www.nzonscreen.com/title/shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982', 'url': 'https://www.nzonscreen.com/title/shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982',
'info_dict': { 'info_dict': {
'id': '726ed6585c6bfb30', 'id': '726ed6585c6bfb30',
'ext': 'mp4', 'ext': 'm3u8',
'format_id': 'hi', 'format_id': 'hd',
'display_id': 'shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982', 'display_id': 'shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982',
'title': 'Monte Video - "Shoop Shoop, Diddy Wop"', 'title': 'Monte Video - "Shoop Shoop, Diddy Wop"',
'description': 'Monte Video - "Shoop Shoop, Diddy Wop"', 'description': 'Monte Video - "Shoop Shoop, Diddy Wop"',
'alt_title': 'Shoop Shoop Diddy Wop Cumma Cumma Wang Dang | Music Video', 'alt_title': 'Shoop Shoop Diddy Wop Cumma Cumma Wang Dang',
'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg', 'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg',
'duration': 158, 'duration': 158,
}, },
@ -29,12 +29,12 @@ class NZOnScreenIE(InfoExtractor):
'url': 'https://www.nzonscreen.com/title/shes-a-mod-1964?collection=best-of-the-60s', 'url': 'https://www.nzonscreen.com/title/shes-a-mod-1964?collection=best-of-the-60s',
'info_dict': { 'info_dict': {
'id': '3dbe709ff03c36f1', 'id': '3dbe709ff03c36f1',
'ext': 'mp4', 'ext': 'm3u8',
'format_id': 'hi', 'format_id': 'hd',
'display_id': 'shes-a-mod-1964', 'display_id': 'shes-a-mod-1964',
'title': 'Ray Columbus - \'She\'s A Mod\'', 'title': 'Ray Columbus - \'She\'s A Mod\'',
'description': 'Ray Columbus - \'She\'s A Mod\'', 'description': 'Ray Columbus - \'She\'s A Mod\'',
'alt_title': 'She\'s a Mod | Music Video', 'alt_title': 'She\'s a Mod',
'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg', 'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg',
'duration': 130, 'duration': 130,
}, },
@ -43,51 +43,78 @@ class NZOnScreenIE(InfoExtractor):
'url': 'https://www.nzonscreen.com/title/puha-and-pakeha-1968/overview', 'url': 'https://www.nzonscreen.com/title/puha-and-pakeha-1968/overview',
'info_dict': { 'info_dict': {
'id': 'f86342544385ad8a', 'id': 'f86342544385ad8a',
'ext': 'mp4', 'ext': 'm3u8',
'format_id': 'hi', 'format_id': 'hd',
'display_id': 'puha-and-pakeha-1968', 'display_id': 'puha-and-pakeha-1968',
'title': 'Looking At New Zealand - Puha and Pakeha', 'title': 'Looking At New Zealand - Puha and Pakeha',
'alt_title': 'Looking at New Zealand - \'Pūhā and Pākehā\' | Television', 'alt_title': 'Looking at New Zealand - \'Pūhā and Pākehā\'',
'description': 'An excerpt from this television programme.', 'description': 'An excerpt from this television programme.',
'duration': 212, 'duration': 212,
'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg', 'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg',
}, },
'params': {'skip_download': 'm3u8'}, 'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.nzonscreen.com/title/flatmates-episode-one-1997',
'info_dict': {
'id': 'flatmates-episode-one-1997',
'title': 'Flatmates - 1, First Episode',
},
'playlist_count': 5,
}] }]
def _extract_formats(self, playlist): def _extract_formats(self, playlist):
for quality, (id_, url) in enumerate(traverse_obj( for quality, (id_, url) in enumerate(traverse_obj(
playlist, ('h264', {'lo': 'lo_res', 'hi': 'hi_res'}), expected_type=url_or_none).items()): playlist, ('h264', {'lo': 'lo_res', 'hi': 'hi_res', 'hd': 'hd_res'}), expected_type=url_or_none).items()):
yield { yield {
'url': url, 'url': url,
'format_id': id_, 'format_id': id_,
'ext': 'mp4', 'ext': determine_ext(url),
'quality': quality, 'quality': quality,
'height': int_or_none(playlist.get('height')) if id_ == 'hi' else None, 'height': int_or_none(playlist.get('height')) if id_ == 'hd' else None,
'width': int_or_none(playlist.get('width')) if id_ == 'hi' else None, 'width': int_or_none(playlist.get('width')) if id_ == 'hd' else None,
'filesize_approx': float_or_none(traverse_obj(playlist, ('h264', f'{id_}_res_mb')), invscale=1024**2), 'filesize_approx': float_or_none(traverse_obj(playlist, ('h264', f'{id_}_res_mb')), invscale=1024**2),
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = strip_or_none((
self._html_extract_title(webpage, default=None)
or self._og_search_title(webpage)).rsplit('|', 2)[0])
playlist = self._download_json(
f'https://www.nzonscreen.com/html5/video_data/{video_id}', video_id, 'media data')
playlist = self._parse_json(self._html_search_regex( if len(playlist) == 1:
r'data-video-config=\'([^\']+)\'', webpage, 'media data'), video_id) playinfo = playlist[0]
return {
return { 'alt_title': title,
'id': playlist['uuid'], 'display_id': video_id,
'display_id': video_id, 'formats': list(self._extract_formats(playinfo)),
'title': strip_or_none(playlist.get('label')), 'http_headers': {
'description': strip_or_none(playlist.get('description')), 'Referer': 'https://www.nzonscreen.com/',
'alt_title': strip_or_none(remove_end( 'Origin': 'https://www.nzonscreen.com/',
self._html_extract_title(webpage, default=None) or self._og_search_title(webpage), },
' | NZ On Screen')), **traverse_obj(playinfo, {
'thumbnail': traverse_obj(playlist, ('thumbnail', 'path')), 'id': ('uuid'),
'duration': float_or_none(playlist.get('duration')), 'title': ('label', {strip_or_none}),
'formats': list(self._extract_formats(playlist)), 'description': ('description', {strip_or_none}),
'http_headers': { 'thumbnail': ('thumbnail', 'path'),
'Referer': 'https://www.nzonscreen.com/', 'duration': ('duration', {float_or_none}),
'Origin': 'https://www.nzonscreen.com/', }),
}, }
} else:
return self.playlist_result([{
'display_id': video_id,
'formats': list(self._extract_formats(playinfo)),
'http_headers': {
'Referer': 'https://www.nzonscreen.com/',
'Origin': 'https://www.nzonscreen.com/',
},
**traverse_obj(playinfo, {
'id': ('uuid'),
'title': ('label', {strip_or_none}),
'description': ('description', {strip_or_none}),
'thumbnail': ('thumbnail', 'path'),
'duration': ('duration', {float_or_none}),
}),
} for playinfo in playlist], video_id, title)