artem/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-04-29 03:55:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

simplify/fix _VALID_URL, fix metadata, fix tests

Browse Source
This commit is contained in:
bashonly 2024-12-01 22:22:32 +00:00 committed by GitHub
parent 41af2972f9
commit 29179f8309
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 19 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
yt_dlp/extractor/duoplay.py
View File

@ -5,15 +5,16 @@ from ..utils import (
get_element_text_and_html_by_tag, get_element_text_and_html_by_tag,
int_or_none, int_or_none,
join_nonempty, join_nonempty,
parse_qs,
str_or_none, str_or_none,
try_call, try_call,
unified_timestamp, unified_timestamp,
) )
from ..utils.traversal import traverse_obj from ..utils.traversal import traverse_obj, value
class DuoplayIE(InfoExtractor): class DuoplayIE(InfoExtractor):
_VALID_URL = r'https?://duoplay\.ee/(?P<id>\d+)(?:/[\w-]+/?(?:\?(?:[^#]+&))?ep=(?P<ep>\d+))?' _VALID_URL = r'https?://duoplay\.ee/(?P<id>\d+)(?:[/?#]|$)'
_TESTS = [{ _TESTS = [{
'note': 'Siberi võmm S02E12', 'note': 'Siberi võmm S02E12',
'url': 'https://duoplay.ee/4312/siberi-vomm?ep=24', 'url': 'https://duoplay.ee/4312/siberi-vomm?ep=24',
@ -38,12 +39,12 @@ class DuoplayIE(InfoExtractor):
}, { }, {
'note': 'Empty title', 'note': 'Empty title',
'url': 'https://duoplay.ee/17/uhikarotid?ep=14', 'url': 'https://duoplay.ee/17/uhikarotid?ep=14',
'md5': '6aca68be71112314738dd17cced7f8bf', 'md5': 'cba9f5dabf2582b224d80ac44fb80e47',
'info_dict': { 'info_dict': {
'id': '17_14', 'id': '17_14',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Ühikarotid', 'title': 'Episode 14',
'thumbnail': r're:https://.+\.jpg(?:\?c=\d+)?$', 'thumbnail': r're:https?://.+\.jpg',
'description': 'md5:4719b418e058c209def41d48b601276e', 'description': 'md5:4719b418e058c209def41d48b601276e',
'upload_date': '20100916', 'upload_date': '20100916',
'timestamp': 1284661800, 'timestamp': 1284661800,
@ -53,6 +54,8 @@ class DuoplayIE(InfoExtractor):
'season_number': 2, 'season_number': 2,
'episode_id': '14', 'episode_id': '14',
'release_year': 2010, 'release_year': 2010,
'episode': 'Episode 14',
'episode_number': 14,
}, },
}, { }, {
'note': 'Movie without expiry', 'note': 'Movie without expiry',
@ -75,12 +78,11 @@ class DuoplayIE(InfoExtractor):
'url': 'https://duoplay.ee/9644?ep=185', 'url': 'https://duoplay.ee/9644?ep=185',
'md5': '63f324b4fe2dbd8194dca16a6d52184a', 'md5': '63f324b4fe2dbd8194dca16a6d52184a',
'info_dict': { 'info_dict': {
'id': '9644', 'id': '9644_185',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Episode 63', 'title': 'Episode 185',
'thumbnail': r're:https?://.+\.jpg(?:%3Fc%3D\d+)?$', 'thumbnail': r're:https?://.+\.jpg',
'description': 'md5:ed25ba4e9e5d54bc291a4a0cdd241467', 'description': 'md5:ed25ba4e9e5d54bc291a4a0cdd241467',
'cast': 'count:1',
'upload_date': '20241120', 'upload_date': '20241120',
'timestamp': 1732077000, 'timestamp': 1732077000,
'episode': 'Episode 63', 'episode': 'Episode 63',
@ -94,7 +96,8 @@ class DuoplayIE(InfoExtractor):
}] }]
def _real_extract(self, url): def _real_extract(self, url):
telecast_id, episode = self._match_valid_url(url).group('id', 'ep') telecast_id = self._match_id(url)
episode = traverse_obj(parse_qs(url), ('ep', 0, {int_or_none}, {str_or_none}))
video_id = join_nonempty(telecast_id, episode, delim='_') video_id = join_nonempty(telecast_id, episode, delim='_')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_player = try_call(lambda: extract_attributes( video_player = try_call(lambda: extract_attributes(
@ -116,19 +119,19 @@ class DuoplayIE(InfoExtractor):
'id': video_id, 'id': video_id,
'formats': self._extract_m3u8_formats(manifest_url, video_id, 'mp4', query={'s': session_token}), 'formats': self._extract_m3u8_formats(manifest_url, video_id, 'mp4', query={'s': session_token}),
**traverse_obj(episode_attr, { **traverse_obj(episode_attr, {
'title': 'title', 'title': ('title', {str}),
'description': 'synopsis', 'description': ('synopsis', {str}),
'thumbnail': ('images', 'original'), 'thumbnail': ('images', 'original'),
'timestamp': ('airtime', {lambda x: unified_timestamp(x + ' +0200')}), 'timestamp': ('airtime', {lambda x: unified_timestamp(x + ' +0200')}),
'cast': ('cast', {lambda x: x.split(', ')}), 'cast': ('cast', filter, {lambda x: x.split(', ')}),
'release_year': ('year', {int_or_none}), 'release_year': ('year', {int_or_none}),
}), }),
**(traverse_obj(episode_attr, { **(traverse_obj(episode_attr, {
'title': (None, ('subtitle', ('episode_nr', {lambda x: f'Episode {x}' if x else None}))), 'title': (('subtitle', {str}, filter), ({value(f'Episode {episode}' if episode else None)})),
'series': 'title', 'series': ('title', {str}),
'series_id': ('telecast_id', {str_or_none}), 'series_id': ('telecast_id', {str_or_none}),
'season_number': ('season_id', {int_or_none}), 'season_number': ('season_id', {int_or_none}),
'episode': 'subtitle', 'episode': ('subtitle', {str}, filter),
'episode_number': ('episode_nr', {int_or_none}), 'episode_number': ('episode_nr', {int_or_none}),
'episode_id': ('episode_id', {str_or_none}), 'episode_id': ('episode_id', {str_or_none}),
}, get_all=False) if episode_attr.get('category') != 'movies' else {}), }, get_all=False) if episode_attr.get('category') != 'movies' else {}),