mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 02:42:30 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

[RCTIPlusSeries] Lazy extraction and video type selection (#2050)

Browse Source 
Authored by: MinePlayersPE
This commit is contained in:
MinePlayersPE 2021-12-24 06:35:40 +07:00 committed by GitHub
parent 4e260d1a56
commit c8b80b9643
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 76 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

123
yt_dlp/extractor/rcti.py
View File

@ -1,7 +1,6 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import itertools
import json import json
import random import random
import time import time
@ -12,6 +11,7 @@
dict_get, dict_get,
ExtractorError, ExtractorError,
strip_or_none, strip_or_none,
traverse_obj,
try_get try_get
) )
@ -26,7 +26,7 @@ def _call_api(self, url, video_id, note=None):
json = self._download_json( json = self._download_json(
url, video_id, note=note, headers={'Authorization': self._AUTH_KEY}) url, video_id, note=note, headers={'Authorization': self._AUTH_KEY})
if json.get('status', {}).get('code', 0) != 0: if json.get('status', {}).get('code', 0) != 0:
raise ExtractorError('%s said: %s' % (self.IE_NAME, json["status"]["message_client"]), cause=json) raise ExtractorError(f'{self.IE_NAME} said: {json["status"]["message_client"]}', cause=json)
return json.get('data'), json.get('meta') return json.get('data'), json.get('meta')
@ -223,18 +223,30 @@ def _real_extract(self, url):
class RCTIPlusSeriesIE(RCTIPlusBaseIE): class RCTIPlusSeriesIE(RCTIPlusBaseIE):
_VALID_URL = r'https://www\.rctiplus\.com/programs/(?P<id>\d+)/(?P<display_id>[^/?#&]+)' _VALID_URL = r'https://www\.rctiplus\.com/programs/(?P<id>\d+)/(?P<display_id>[^/?#&]+)(?:/(?P<type>episodes|extras|clips))?'
_TESTS = [{ _TESTS = [{
'url': 'https://www.rctiplus.com/programs/540/upin-ipin', 'url': 'https://www.rctiplus.com/programs/829/putri-untuk-pangeran',
'playlist_mincount': 417, 'playlist_mincount': 1019,
'info_dict': { 'info_dict': {
'id': '540', 'id': '829',
'title': 'Upin & Ipin', 'title': 'Putri Untuk Pangeran',
'description': 'md5:22cc912381f389664416844e1ec4f86b', 'description': 'md5:aca7b54d05bd95a67d4f4613cc1d622d',
'age_limit': 2,
'cast': ['Verrel Bramasta', 'Ranty Maria', 'Riza Syah', 'Ivan Fadilla', 'Nicole Parham', 'Dll', 'Aviv Elham'],
'display_id': 'putri-untuk-pangeran',
'tag': 'count:18',
}, },
}, { }, { # No episodes
'url': 'https://www.rctiplus.com/programs/540/upin-ipin/episodes?utm_source=Rplusdweb&utm_medium=share_copy&utm_campaign=programsupin-ipin', 'url': 'https://www.rctiplus.com/programs/615/inews-pagi',
'only_matching': True, 'playlist_mincount': 388,
'info_dict': {
'id': '615',
'title': 'iNews Pagi',
'description': 'md5:f18ee3d4643cfb41c358e5a9b693ee04',
'age_limit': 2,
'tag': 'count:11',
'display_id': 'inews-pagi',
}
}] }]
_AGE_RATINGS = { # Based off https://id.wikipedia.org/wiki/Sistem_rating_konten_televisi with additional ratings _AGE_RATINGS = { # Based off https://id.wikipedia.org/wiki/Sistem_rating_konten_televisi with additional ratings
'S-SU': 2, 'S-SU': 2,
@ -269,47 +281,63 @@ def _entries(self, url, display_id=None, note='Downloading entries JSON', metada
display_id, '%s page %s' % (note, page_num))[0] or [] display_id, '%s page %s' % (note, page_num))[0] or []
for video_json in episode_list: for video_json in episode_list:
link = video_json['share_link'] yield {
url_res = self.url_result(link, 'RCTIPlus', video_json.get('product_id'), video_json.get('title')) '_type': 'url',
url_res.update(metadata) 'url': video_json['share_link'],
yield url_res 'ie_key': RCTIPlusIE.ie_key(),
'id': video_json.get('product_id'),
def _real_extract(self, url): 'title': video_json.get('title'),
series_id, display_id = self._match_valid_url(url).groups() 'display_id': video_json.get('title_code').replace('_', '-'),
'description': video_json.get('summary'),
series_meta, meta_paths = self._call_api( 'timestamp': video_json.get('release_date'),
'https://api.rctiplus.com/api/v1/program/%s/detail' % series_id, display_id, 'Downloading series metadata') 'duration': video_json.get('duration'),
metadata = { 'season_number': video_json.get('season'),
'age_limit': try_get(series_meta, lambda x: self._AGE_RATINGS[x['age_restriction'][0]['code']]) 'episode_number': video_json.get('episode'),
**metadata
} }
cast = [] def _series_entries(self, series_id, display_id=None, video_type=None, metadata={}):
for star in series_meta.get('starring', []): if not video_type or video_type in 'episodes':
cast.append(strip_or_none(star.get('name'))) try:
for star in series_meta.get('creator', []):
cast.append(strip_or_none(star.get('name')))
for star in series_meta.get('writer', []):
cast.append(strip_or_none(star.get('name')))
metadata['cast'] = cast
tags = []
for tag in series_meta.get('tag', []):
tags.append(strip_or_none(tag.get('name')))
metadata['tag'] = tags
entries = []
seasons_list = self._call_api( seasons_list = self._call_api(
'https://api.rctiplus.com/api/v1/program/%s/season' % series_id, display_id, 'Downloading seasons list JSON')[0] f'https://api.rctiplus.com/api/v1/program/{series_id}/season',
display_id, 'Downloading seasons list JSON')[0]
except ExtractorError as e:
if 'not found' not in str(e):
raise
seasons_list = []
for season in seasons_list: for season in seasons_list:
entries.append(self._entries('https://api.rctiplus.com/api/v2/program/%s/episode?season=%s' % (series_id, season['season']), yield from self._entries(
display_id, 'Downloading season %s episode entries' % season['season'], metadata)) f'https://api.rctiplus.com/api/v2/program/{series_id}/episode?season={season["season"]}',
display_id, f'Downloading season {season["season"]} episode entries', metadata)
if not video_type or video_type in 'extras':
yield from self._entries(
f'https://api.rctiplus.com/api/v2/program/{series_id}/extra?content_id=0',
display_id, 'Downloading extra entries', metadata)
if not video_type or video_type in 'clips':
yield from self._entries(
f'https://api.rctiplus.com/api/v2/program/{series_id}/clip?content_id=0',
display_id, 'Downloading clip entries', metadata)
entries.append(self._entries('https://api.rctiplus.com/api/v2/program/%s/clip?content_id=0' % series_id, def _real_extract(self, url):
display_id, 'Downloading clip entries', metadata)) series_id, display_id, video_type = self._match_valid_url(url).group('id', 'display_id', 'type')
entries.append(self._entries('https://api.rctiplus.com/api/v2/program/%s/extra?content_id=0' % series_id, if video_type:
display_id, 'Downloading extra entries', metadata)) self.report_warning(
f'Only {video_type} will be downloaded. '
f'To download everything from the series, remove "/{video_type}" from the URL')
return self.playlist_result(itertools.chain(*entries), series_id, series_meta.get('title'), series_meta.get('summary'), **metadata) series_meta, meta_paths = self._call_api(
f'https://api.rctiplus.com/api/v1/program/{series_id}/detail', display_id, 'Downloading series metadata')
metadata = {
'age_limit': try_get(series_meta, lambda x: self._AGE_RATINGS[x['age_restriction'][0]['code']]),
'cast': traverse_obj(series_meta, (('starring', 'creator', 'writer'), ..., 'name'),
expected_type=lambda x: strip_or_none(x) or None),
'tag': traverse_obj(series_meta, ('tag', ..., 'name'),
expected_type=lambda x: strip_or_none(x) or None),
}
return self.playlist_result(
self._series_entries(series_id, display_id, video_type, metadata), series_id,
series_meta.get('title'), series_meta.get('summary'), display_id=display_id, **metadata)
class RCTIPlusTVIE(RCTIPlusBaseIE): class RCTIPlusTVIE(RCTIPlusBaseIE):
@ -345,5 +373,6 @@ def _real_extract(self, url):
tv_id = match.get('tvname') or match.get('eventname') tv_id = match.get('tvname') or match.get('eventname')
webpage = self._download_webpage(url, tv_id) webpage = self._download_webpage(url, tv_id)
video_type, video_id = self._search_regex( video_type, video_id = self._search_regex(
r'url\s*:\s*["\']https://api\.rctiplus\.com/api/v./(?P<type>[^/]+)/(?P<id>\d+)/url', webpage, 'video link', group=('type', 'id')) r'url\s*:\s*["\']https://api\.rctiplus\.com/api/v./(?P<type>[^/]+)/(?P<id>\d+)/url',
webpage, 'video link', group=('type', 'id'))
return self.url_result(f'https://www.rctiplus.com/{video_type}/{video_id}/{tv_id}', 'RCTIPlus') return self.url_result(f'https://www.rctiplus.com/{video_type}/{video_id}/{tv_id}', 'RCTIPlus')