Compare commits

...

6 Commits

Author SHA1 Message Date
red-acid
b19adadbd7
Merge 049862b803 into b83ca24eb7 2024-11-10 00:54:43 +01:00
sepro
b83ca24eb7
[core] Catch broken Cryptodome installations (#11486)
Authored by: seproDev
2024-11-10 00:53:49 +01:00
bashonly
240a7d43c8
[build] Pin websockets version to >=13.0,<14 (#11488)
websockets 14.0 causes CI test failures (a lot more of them)

Authored by: bashonly
2024-11-09 23:46:47 +00:00
bashonly
f13df591d4
[build] Enable attestations for trusted publishing (#11420)
Reverts 428ffb75aa

Authored by: bashonly
2024-11-09 23:26:02 +00:00
red-acid
049862b803
Apply suggestions from code review
Co-authored-by: N/Ame <173015200+grqz@users.noreply.github.com>
2024-10-23 11:11:24 +01:00
red-acid
c2b5c7025c
Update rtp.py 2024-10-14 12:36:35 +01:00
7 changed files with 185 additions and 49 deletions

View File

@ -504,7 +504,8 @@ jobs:
- windows32 - windows32
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- uses: actions/download-artifact@v4 - name: Download artifacts
uses: actions/download-artifact@v4
with: with:
path: artifact path: artifact
pattern: build-bin-* pattern: build-bin-*

View File

@ -28,3 +28,20 @@ jobs:
actions: write # For cleaning up cache actions: write # For cleaning up cache
id-token: write # mandatory for trusted publishing id-token: write # mandatory for trusted publishing
secrets: inherit secrets: inherit
publish_pypi:
needs: [release]
if: vars.MASTER_PYPI_PROJECT != ''
runs-on: ubuntu-latest
permissions:
id-token: write # mandatory for trusted publishing
steps:
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: dist
name: build-pypi
- name: Publish to PyPI
uses: pypa/gh-action-pypi-publish@release/v1
with:
verbose: true

View File

@ -41,3 +41,20 @@ jobs:
actions: write # For cleaning up cache actions: write # For cleaning up cache
id-token: write # mandatory for trusted publishing id-token: write # mandatory for trusted publishing
secrets: inherit secrets: inherit
publish_pypi:
needs: [release]
if: vars.NIGHTLY_PYPI_PROJECT != ''
runs-on: ubuntu-latest
permissions:
id-token: write # mandatory for trusted publishing
steps:
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: dist
name: build-pypi
- name: Publish to PyPI
uses: pypa/gh-action-pypi-publish@release/v1
with:
verbose: true

View File

@ -2,10 +2,6 @@ name: Release
on: on:
workflow_call: workflow_call:
inputs: inputs:
prerelease:
required: false
default: true
type: boolean
source: source:
required: false required: false
default: '' default: ''
@ -18,6 +14,10 @@ on:
required: false required: false
default: '' default: ''
type: string type: string
prerelease:
required: false
default: true
type: boolean
workflow_dispatch: workflow_dispatch:
inputs: inputs:
source: source:
@ -278,11 +278,20 @@ jobs:
make clean-cache make clean-cache
python -m build --no-isolation . python -m build --no-isolation .
- name: Upload artifacts
if: github.event_name != 'workflow_dispatch'
uses: actions/upload-artifact@v4
with:
name: build-pypi
path: |
dist/*
compression-level: 0
- name: Publish to PyPI - name: Publish to PyPI
if: github.event_name == 'workflow_dispatch'
uses: pypa/gh-action-pypi-publish@release/v1 uses: pypa/gh-action-pypi-publish@release/v1
with: with:
verbose: true verbose: true
attestations: false # Currently doesn't work w/ reusable workflows (breaks nightly)
publish: publish:
needs: [prepare, build] needs: [prepare, build]

View File

@ -52,7 +52,7 @@ default = [
"pycryptodomex", "pycryptodomex",
"requests>=2.32.2,<3", "requests>=2.32.2,<3",
"urllib3>=1.26.17,<3", "urllib3>=1.26.17,<3",
"websockets>=13.0", "websockets>=13.0,<14",
] ]
curl-cffi = [ curl-cffi = [
"curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'", "curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'",

View File

@ -24,7 +24,7 @@ try:
from Crypto.Cipher import AES, PKCS1_OAEP, Blowfish, PKCS1_v1_5 # noqa: F401 from Crypto.Cipher import AES, PKCS1_OAEP, Blowfish, PKCS1_v1_5 # noqa: F401
from Crypto.Hash import CMAC, SHA1 # noqa: F401 from Crypto.Hash import CMAC, SHA1 # noqa: F401
from Crypto.PublicKey import RSA # noqa: F401 from Crypto.PublicKey import RSA # noqa: F401
except ImportError: except (ImportError, OSError):
__version__ = f'broken {__version__}'.strip() __version__ = f'broken {__version__}'.strip()

View File

@ -4,40 +4,97 @@ import re
import urllib.parse import urllib.parse
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import js_to_json from ..utils import (
ExtractorError,
determine_ext,
join_nonempty,
js_to_json,
)
class RTPIE(InfoExtractor): class RTPIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/(?:(?:estudoemcasa|palco|zigzag)/)?p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)' _VALID_URL = r'https?://(?:(?:www\.)?rtp\.pt/play/(?P<subarea>.*/)?p(?P<program_id>\d+)/|arquivos\.rtp\.pt/conteudos/)(?P<id>[^/?#]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas', 'url': 'https://www.rtp.pt/play/p9165/e562949/por-do-sol',
'md5': 'e736ce0c665e459ddb818546220b4ef8',
'info_dict': { 'info_dict': {
'id': 'e174042', 'id': 'e562949',
'ext': 'mp3',
'title': 'Paixões Cruzadas',
'description': 'As paixões musicais de António Cartaxo e António Macedo',
'thumbnail': r're:^https?://.*\.jpg',
},
}, {
'url': 'https://www.rtp.pt/play/zigzag/p13166/e757904/25-curiosidades-25-de-abril',
'md5': '9a81ed53f2b2197cfa7ed455b12f8ade',
'info_dict': {
'id': 'e757904',
'ext': 'mp4', 'ext': 'mp4',
'title': '25 Curiosidades, 25 de Abril', 'title': 'Pôr do Sol Episódio 1',
'description': 'Estudar ou não estudar - Em cada um dos episódios descobrimos uma curiosidade acerca de como era viver em Portugal antes da revolução do 25 de abr', 'description': 'Madalena Bourbon de Linhaça vive atormentada pelo segredo que esconde desde 1990. Matilde Bourbon de Linhaça sonha fugir com o seu amor proibido. O',
'thumbnail': r're:^https?://.*\.jpg', 'thumbnail': r're:https?://.*\.(?:jpg|png)',
}, },
}, { }, {
'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas', 'url': 'https://www.rtp.pt/play/p12646/e738493/telejornal',
'only_matching': True, 'info_dict': {
'id': 'e738493',
'ext': 'mp4',
'title': 'Telejornal de 01 jan 2024 PARTE 1',
'description': 'A mais rigorosa seleção de notícias, todos os dias às 20h00. De segunda a domingo, João Adelino Faria, José Rodrigues dos Santos e Ana Lourenço',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
}, { }, {
'url': 'https://www.rtp.pt/play/estudoemcasa/p7776/portugues-1-ano', 'url': 'https://www.rtp.pt/play/p6646/e457262/grande-entrevista',
'only_matching': True, 'info_dict': {
'id': 'e457262',
'ext': 'mp4',
'title': 'Grande Entrevista Episódio 7 - de 19 fev 2020',
'description': 'Bruno Nogueira - É um dos mais originais humoristas portugueses e de maior êxito! Bruno Nogueira na Grande Entrevista com Vítor Gonçalves.',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
}, { }, {
'url': 'https://www.rtp.pt/play/palco/p13785/l7nnon', 'url': 'https://www.rtp.pt/play/p1525/e738522/a-mosca',
'only_matching': True, 'info_dict': {
'id': 'e738522',
'ext': 'mp4',
'title': 'A Mosca de 02 jan 2024',
'description': 'Ano novo, vida nova - Ano novo, vida nova',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
}, {
'url': 'https://www.rtp.pt/play/estudoemcasa/p7776/e539826/portugues-1-ano',
'info_dict': {
'id': 'e539826',
'ext': 'mp4',
'title': 'Português - 1.º ano , aula 45 - 27 abr 2021',
'description': 'A História do Pedrito Coelho, de Beatrix Potter. O dígrafo \'lh\' - A História do Pedrito Coelho, de Beatrix Potter. O dígrafo \'lh\'.',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
}, {
'url': 'https://www.rtp.pt/play/zigzag/p13857/e794575/zig-zag-zzz-e-amigos',
'info_dict': {
'id': 'e794575',
'ext': 'mp4',
'title': 'Zig, Zag, Zzz e Amigos Episódio 1 - de 16 set 2024',
'description': 'O Brinquedo Perdido - Zig, Zag e Zzz são três amigos inseparáveis que partilham aventuras emocionantes e cheias de imaginação. Exploram o mundo <20>',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
}, {
'url': 'https://www.rtp.pt/play/palco/p13151/premio-miguel-rovisco-2023-requiem-por-isabel',
'info_dict': {
'id': 'premio-miguel-rovisco-2023-requiem-por-isabel',
'ext': 'mp4',
'title': 'Prémio Miguel Rovisco 23: Requiem Por Isabel de 30 mar 2024',
'description': 'Lucrécia foi a atriz mais famosa e requisitada do seu tempo. Este já não é o seu tempo. A debater-se com a decrepitude física e financeira, foi o',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
}, {
'url': 'https://arquivos.rtp.pt/conteudos/liga-dos-ultimos-152/',
'info_dict': {
'id': 'liga-dos-ultimos-152',
'ext': 'mp4',
'title': 'Liga dos Últimos RTP Arquivos',
'description': 'Magazine desportivo, com apresentação de Álvaro Costa e comentários em estúdio do professor Hernâni Gonçalves e do sociólogo João Nuno Coelho. Destaque para os jogos de futebol das equipas dos escalões secundários de Portugal, com momentos dos jogos: Agrário de Lamas vs Pampilhoense e Apúlia vs Fragoso.',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
}, {
'url': 'https://www.rtp.pt/play/p510/e786608/aleixo-fm',
'info_dict': {
'id': 'e786608',
'ext': 'mp3',
'title': 'Aleixo FM de 31 jul 2024',
'description': 'Melhor dia pra casar - Já o diz Joaquim de Magalhães Fernandes Barreiros, comummente conhecido como Quim Barreiros. Mas será mesmo este o melhor di',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
}] }]
_RX_OBFUSCATION = re.compile(r'''(?xs) _RX_OBFUSCATION = re.compile(r'''(?xs)
@ -60,42 +117,77 @@ class RTPIE(InfoExtractor):
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 = self._html_search_meta(
'twitter:title', webpage, display_name='title', fatal=True)
# Title tag includes relevant data
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title', default='')
# Raise error if episode is unavailable
if 'Este episódio não se encontra disponível' in title:
raise ExtractorError('Episode unavailable', expected=True)
# Replace irrelevant text in title
title = re.sub(r' - ?(RTP Play|Estudo Em Casa|Zig Zag Play|RTP Palco)( - RTP)?', '', title)
# Check if it's a episode split in parts
part = self._html_search_regex(r'section\-parts.*<span.*>(.+?)</span>.*</ul>', webpage, 'part', default=None)
# Add episode part identification to title if it exists
title = join_nonempty(title, part, delim=' ')
# Extract f and config from page
f, config = self._search_regex( f, config = self._search_regex(
r'''(?sx) r'''(?sx)
(?:var\s+f\s*=\s*(?P<f>".*?"|{[^;]+?});\s*)? (?:var\s+f\s*=\s*(?P<f>".*?"|{[^;]+?});\s*)?
var\s+player1\s+=\s+new\s+RTPPlayer\s*\((?P<config>{(?:(?!\*/).)+?})\);(?!\s*\*/) var\s+player1?\s+=\s+new\s+RTPPlayer\s*\((?P<config>{(?:(?!\*/).)+?})\);(?!\s*\*/)
''', webpage, ''', webpage,
'player config', group=('f', 'config')) 'player config', group=('f', 'config'))
config = self._parse_json( config = self._parse_json(
config, video_id, config, video_id,
lambda data: self.__unobfuscate(data, video_id=video_id)) lambda data: self.__unobfuscate(data, video_id=video_id))
# Estudo em Casa / Zig Zag / Palco / RTP Arquivos subareas don't include f
f = config['file'] if not f else self._parse_json( f = config['file'] if not f else self._parse_json(
f, video_id, f, video_id,
lambda data: self.__unobfuscate(data, video_id=video_id)) lambda data: self.__unobfuscate(data, video_id=video_id))
formats = [] formats = []
if isinstance(f, dict): if isinstance(f, dict):
f_hls = f.get('hls') file_hls = f.get('hls')
if f_hls is not None: file_fps = f.get('fps')
formats.extend(self._extract_m3u8_formats(
f_hls, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'))
f_dash = f.get('dash') if file_fps is not None:
if f_dash is not None: # RTP Arquivos specific use case
formats.extend(self._extract_mpd_formats(f_dash, video_id, mpd_id='dash')) if '/arquivo/' in file_fps:
file_key = config['fileKey']
split_file_key = file_key.split('/')
filename = split_file_key[-1]
del split_file_key[-1]
split_file_key.extend([f'index.m3u8?tlm=hls&streams={filename}.m3u8'])
path = '/'.join(split_file_key)
file_hls = f'https://streaming-arquivo-ondemand.rtp.pt/nas2.share{path}'
elif file_hls is None:
file_hls = file_fps.replace('drm-fps', 'hls')
formats.extend(self._extract_m3u8_formats(
file_hls, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'))
else: else:
formats.append({ ext = determine_ext(f)
'format_id': 'f',
'url': f, if ext == 'm3u8':
'vcodec': 'none' if config.get('mediaType') == 'audio' else None, formats.extend(self._extract_m3u8_formats(
}) f, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'))
else:
formats.append({
'format_id': 'f',
'url': f,
'vcodec': 'none' if config.get('mediaType') == 'audio' else None,
})
subtitles = {} subtitles = {}
vtt = config.get('vtt') vtt = config.get('vtt')
if vtt is not None: if vtt is not None:
for lcode, lname, url in vtt: for lcode, lname, url in vtt:
@ -108,7 +200,7 @@ class RTPIE(InfoExtractor):
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'formats': formats, 'formats': formats,
'description': self._html_search_meta(['description', 'twitter:description'], webpage), 'description': self._html_search_meta(['og:description', 'description'], webpage),
'thumbnail': config.get('poster') or self._og_search_thumbnail(webpage), 'thumbnail': config.get('poster') or self._og_search_thumbnail(webpage),
'subtitles': subtitles, 'subtitles': subtitles,
} }