mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-07-19 19:58:30 +00:00
Code Issues Projects Releases Wiki Activity

chore: support for episodes split into parts

Browse Source
This commit is contained in:
red-acid 2025-07-03 12:41:36 +01:00 committed by GitHub
parent 0b41746964
commit 557234219d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 31 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
yt_dlp/extractor/rtp.py
View File

@ -16,7 +16,7 @@
class RTPIE(InfoExtractor): class RTPIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/(?:[^/#?]+/)?p(?P<program_id>\d+)/(?P<id>e\d+)' _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/(?:[^/#?]+/)?p(?P<program_id>\d+)/(?P<id>e\d+)(?:/[A-Za-z0-9_-]+/(?P<part_id>\d+))?'
_TESTS = [{ _TESTS = [{
'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas', 'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
'md5': 'e736ce0c665e459ddb818546220b4ef8', 'md5': 'e736ce0c665e459ddb818546220b4ef8',
@ -51,6 +51,22 @@ class RTPIE(InfoExtractor):
'episode': 'Estudar ou não estudar', 'episode': 'Estudar ou não estudar',
'modified_date': '20240404', 'modified_date': '20240404',
}, },
}, {
'url': 'https://www.rtp.pt/play/p14263/e819812/telejornal/1297689',
'md5': '46b303dfe1be1d85222b9689d4dd6659',
'info_dict': {
'id': 'e819812_2',
'ext': 'mp4',
'title': 'Telejornal',
'thumbnail': r're:^https?://.*\.jpg',
'timestamp': 1735764807,
'duration': 4191.0,
'upload_date': '20250101',
'modified_timestamp': 1735766883,
'series': 'Telejornal',
'modified_date': '20250101',
'season': '2025'
},
}, { }, {
# Episode not accessible through API # Episode not accessible through API
'url': 'https://www.rtp.pt/play/estudoemcasa/p7776/e500050/portugues-1-ano', 'url': 'https://www.rtp.pt/play/estudoemcasa/p7776/e500050/portugues-1-ano',
@ -114,7 +130,7 @@ def _extract_formats(self, media_urls, episode_id):
}) })
return formats, subtitles return formats, subtitles
def _extract_from_api(self, program_id, episode_id): def _extract_from_api(self, program_id, episode_id, part_id):
auth_token = self._fetch_auth_token() auth_token = self._fetch_auth_token()
if not auth_token: if not auth_token:
return return
@ -128,7 +144,15 @@ def _extract_from_api(self, program_id, episode_id):
}, fatal=False), 'result', {dict}) }, fatal=False), 'result', {dict})
if not episode_data: if not episode_data:
return return
asset_urls = traverse_obj(episode_data, ('assets', 0, 'asset_url', {dict}))
asset_index = 0
if part_id:
for idx, asset in enumerate(traverse_obj(episode_data, ('assets', ..., {dict})) or []):
if str(traverse_obj(asset, ('asset_id', {int_or_none}))) == part_id:
asset_index = idx
break
asset_urls = traverse_obj(episode_data, ('assets', asset_index, 'asset_url', {dict}))
media_urls = traverse_obj(asset_urls, ( media_urls = traverse_obj(asset_urls, (
((('hls', 'dash'), 'stream_url'), ('multibitrate', ('url_hls', 'url_dash'))),)) ((('hls', 'dash'), 'stream_url'), ('multibitrate', ('url_hls', 'url_dash'))),))
formats, subtitles = self._extract_formats(media_urls, episode_id) formats, subtitles = self._extract_formats(media_urls, episode_id)
@ -140,10 +164,10 @@ def _extract_from_api(self, program_id, episode_id):
}) })
return { return {
'id': episode_id, 'id': f"{episode_id}_{asset_index + 1}" if asset_index > 0 else episode_id,
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
'thumbnail': traverse_obj(episode_data, ('assets', 0, 'asset_thumbnail', {url_or_none})), 'thumbnail': traverse_obj(episode_data, ('assets', asset_index, 'asset_thumbnail', {url_or_none})),
**traverse_obj(episode_data, ('episode', { **traverse_obj(episode_data, ('episode', {
'title': (('episode_title', 'program_title'), {str}, filter, any), 'title': (('episode_title', 'program_title'), {str}, filter, any),
'alt_title': ('episode_subtitle', {str}, filter), 'alt_title': ('episode_subtitle', {str}, filter),
@ -192,5 +216,5 @@ def _extract_from_html(self, url, episode_id):
} }
def _real_extract(self, url): def _real_extract(self, url):
program_id, episode_id = self._match_valid_url(url).group('program_id', 'id') program_id, episode_id, part_id = self._match_valid_url(url).group('program_id', 'id', 'part_id')
return self._extract_from_api(program_id, episode_id) or self._extract_from_html(url, episode_id) return self._extract_from_api(program_id, episode_id, part_id) or self._extract_from_html(url, episode_id)