Miroirs/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2025-01-01 06:21:09 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Added RTVE play compatibility

Browse source
This commit is contained in:
Florentin Le Moal 2024-07-08 20:07:13 +02:00
parent cba7868502
commit 7d27c259ac
2 changed files with 60 additions and 36 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
yt_dlp/extractor/_extractors.py
View file

@ -1764,6 +1764,7 @@ from .rtve import (
RTVEInfantilIE, RTVEInfantilIE,
RTVELiveIE, RTVELiveIE,
RTVETelevisionIE, RTVETelevisionIE,
RTVEPlayIE,
) )
from .rtvs import RTVSIE from .rtvs import RTVSIE
from .rtvslo import ( from .rtvslo import (

55
yt_dlp/extractor/rtve.py
View file

@ -20,7 +20,7 @@ class RTVEALaCartaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/', 'url': 'https://www.rtve.es/play/videos/balonmano/liga-guerreras-iberdrola-4-jornada/6974343/',
'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43', 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
'info_dict': { 'info_dict': {
'id': '2491869', 'id': '2491869',
@ -70,23 +70,31 @@ class RTVEALaCartaIE(InfoExtractor):
def _decrypt_url(png): def _decrypt_url(png):
encrypted_data = io.BytesIO(base64.b64decode(png)[8:]) encrypted_data = io.BytesIO(base64.b64decode(png)[8:])
while True: while True:
length = struct.unpack('!I', encrypted_data.read(4))[0] length_data = encrypted_data.read(4)
length = struct.unpack('!I', length_data)[0]
chunk_type = encrypted_data.read(4) chunk_type = encrypted_data.read(4)
if chunk_type == b'IEND': if chunk_type == b'IEND':
break break
data = encrypted_data.read(length) data = encrypted_data.read(length)
if chunk_type == b'tEXt': if chunk_type == b'tEXt':
if b'%%' in data:
alphabet_data, text = data.split(b'\0') alphabet_data, text = data.split(b'\0')
quality, url_data = text.split(b'%%') quality, url_data = text.split(b'%%')
alphabet = [] alphabet = RTVEPlayIE._get_alfabet(alphabet_data)
e = 0 url = RTVEPlayIE._get_url(alphabet, url_data)
d = 0 quality_str = quality.decode()
for l in alphabet_data.decode('iso-8859-1'):
if d == 0:
alphabet.append(l)
d = e = (e + 1) % 4
else: else:
d -= 1 data = bytes(filter(None, data))
alphabet_data, url_data = data.split(b'#')
alphabet = RTVEPlayIE._get_alfabet(alphabet_data)
url = RTVEPlayIE._get_url(alphabet, url_data)
quality_str = ""
yield quality_str, url
encrypted_data.read(4) # CRC
@staticmethod
def _get_url(alphabet, url_data):
url = '' url = ''
f = 0 f = 0
e = 3 e = 3
@ -104,9 +112,20 @@ class RTVEALaCartaIE(InfoExtractor):
b += 1 b += 1
else: else:
e -= 1 e -= 1
return url
yield quality.decode(), url @staticmethod
encrypted_data.read(4) # CRC def _get_alfabet(alphabet_data):
alphabet = []
e = 0
d = 0
for l in alphabet_data.decode('iso-8859-1'):
if d == 0:
alphabet.append(l)
d = e = (e + 1) % 4
else:
d -= 1
return alphabet
def _extract_png_formats(self, video_id): def _extract_png_formats(self, video_id):
png = self._download_webpage( png = self._download_webpage(
@ -141,9 +160,7 @@ class RTVEALaCartaIE(InfoExtractor):
title = info['title'].strip() title = info['title'].strip()
formats = self._extract_png_formats(video_id) formats = self._extract_png_formats(video_id)
subtitles = None sbt_file = "https://api2.rtve.es/api/videos/%s/subtitulos.json" % video_id
sbt_file = info.get('sbtFile')
if sbt_file:
subtitles = self.extract_subtitles(video_id, sbt_file) subtitles = self.extract_subtitles(video_id, sbt_file)
is_live = info.get('live') is True is_live = info.get('live') is True
@ -161,7 +178,7 @@ class RTVEALaCartaIE(InfoExtractor):
def _get_subtitles(self, video_id, sub_file): def _get_subtitles(self, video_id, sub_file):
subs = self._download_json( subs = self._download_json(
sub_file + '.json', video_id, sub_file, video_id,
'Downloading subtitles info')['page']['items'] 'Downloading subtitles info')['page']['items']
return dict( return dict(
(s['lang'], [{'ext': 'vtt', 'url': s['src']}]) (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
@ -340,3 +357,9 @@ class RTVETelevisionIE(InfoExtractor):
'The webpage doesn\'t contain any video', expected=True) 'The webpage doesn\'t contain any video', expected=True)
return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key()) return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())
class RTVEPlayIE(RTVEALaCartaIE):
IE_NAME = 'rtve.es:play'
IE_DESC = 'RTVE play'
_VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?play/videos/[^/]+/[^/]+/(?P<id>\d+)'