[rtve:alacarta] Fix extraction (closes #14290)

This commit is contained in:
Giuseppe Fabiano 2017-09-30 22:21:17 +02:00 committed by Sergey M
parent 3836b02ce8
commit 2c53bd51c6

View file

@ -10,6 +10,7 @@ from ..compat import (
compat_struct_unpack, compat_struct_unpack,
) )
from ..utils import ( from ..utils import (
determine_ext,
ExtractorError, ExtractorError,
float_or_none, float_or_none,
remove_end, remove_end,
@ -84,6 +85,18 @@ class RTVEALaCartaIE(InfoExtractor):
'title': 'TODO', 'title': 'TODO',
}, },
'skip': 'The f4m manifest can\'t be used yet', 'skip': 'The f4m manifest can\'t be used yet',
}, {
'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
'md5': 'e55e162379ad587e9640eda4f7353c0f',
'info_dict': {
'id': '4236788',
'ext': 'mp4',
'title': 'Servir y proteger - Capítulo 104 ',
'duration': 3222.0,
},
'params': {
'skip_download': True, # requires ffmpeg
},
}, { }, {
'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve', 'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
'only_matching': True, 'only_matching': True,
@ -107,24 +120,41 @@ class RTVEALaCartaIE(InfoExtractor):
video_id)['page']['items'][0] video_id)['page']['items'][0]
if info['state'] == 'DESPU': if info['state'] == 'DESPU':
raise ExtractorError('The video is no longer available', expected=True) raise ExtractorError('The video is no longer available', expected=True)
title = info['title']
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id) png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
png_request = sanitized_Request(png_url) png_request = sanitized_Request(png_url)
png_request.add_header('Referer', url) png_request.add_header('Referer', url)
png = self._download_webpage(png_request, video_id, 'Downloading url information') png = self._download_webpage(png_request, video_id, 'Downloading url information')
video_url = _decrypt_url(png) video_url = _decrypt_url(png)
if not video_url.endswith('.f4m'): ext = determine_ext(video_url)
formats = []
if not video_url.endswith('.f4m') and ext != 'm3u8':
if '?' not in video_url: if '?' not in video_url:
video_url = video_url.replace('resources/', 'auth/resources/') video_url = video_url.replace('resources/', 'auth/resources/')
video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve') video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
video_url, video_id, f4m_id='hds', fatal=False))
else:
formats.append({
'url': video_url,
})
self._sort_formats(formats)
subtitles = None subtitles = None
if info.get('sbtFile') is not None: if info.get('sbtFile') is not None:
subtitles = self.extract_subtitles(video_id, info['sbtFile']) subtitles = self.extract_subtitles(video_id, info['sbtFile'])
return { return {
'id': video_id, 'id': video_id,
'title': info['title'], 'title': title,
'url': video_url, 'formats': formats,
'thumbnail': info.get('image'), 'thumbnail': info.get('image'),
'page_url': url, 'page_url': url,
'subtitles': subtitles, 'subtitles': subtitles,