youtube-dl/youtube_dl/extractor/rtve.py

254 lines
8.4 KiB
Python
Raw Normal View History

2014-04-07 14:56:15 +00:00
# encoding: utf-8
from __future__ import unicode_literals
import base64
import re
import time
2014-04-07 14:56:15 +00:00
from .common import InfoExtractor
from ..compat import (
compat_struct_unpack,
)
2014-04-07 14:56:15 +00:00
from ..utils import (
ExtractorError,
2015-02-27 11:24:51 +00:00
float_or_none,
remove_end,
remove_start,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
sanitized_Request,
2015-04-04 11:11:55 +00:00
std_headers,
2014-04-07 14:56:15 +00:00
)
def _decrypt_url(png):
2015-05-21 18:09:15 +00:00
encrypted_data = base64.b64decode(png.encode('utf-8'))
text_index = encrypted_data.find(b'tEXt')
text_chunk = encrypted_data[text_index - 4:]
length = compat_struct_unpack('!I', text_chunk[:4])[0]
# Use bytearray to get integers when iterating in both python 2.x and 3.x
data = bytearray(text_chunk[8:8 + length])
data = [chr(b) for b in data if b != 0]
hash_index = data.index('#')
alphabet_data = data[:hash_index]
url_data = data[hash_index + 1:]
alphabet = []
e = 0
d = 0
for l in alphabet_data:
if d == 0:
alphabet.append(l)
d = e = (e + 1) % 4
else:
d -= 1
url = ''
f = 0
e = 3
b = 1
for letter in url_data:
if f == 0:
l = int(letter) * 10
f = 1
else:
if e == 0:
l += int(letter)
url += alphabet[l]
e = (b + 3) % 4
f = 0
b += 1
else:
e -= 1
return url
2014-04-07 14:56:15 +00:00
class RTVEALaCartaIE(InfoExtractor):
IE_NAME = 'rtve.es:alacarta'
IE_DESC = 'RTVE a la carta'
2016-05-21 15:37:35 +00:00
_VALID_URL = r'https?://www\.rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
2014-04-07 14:56:15 +00:00
_TESTS = [{
2014-04-07 14:56:15 +00:00
'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
2014-04-07 14:56:15 +00:00
'info_dict': {
'id': '2491869',
'ext': 'mp4',
'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
2015-02-27 11:24:51 +00:00
'duration': 5024.566,
2014-04-07 14:56:15 +00:00
},
}, {
'note': 'Live stream',
'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
'info_dict': {
'id': '1694255',
'ext': 'flv',
'title': 'TODO',
},
'skip': 'The f4m manifest can\'t be used yet',
}, {
'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,
2016-05-21 15:37:35 +00:00
}, {
'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
'only_matching': True,
}]
2014-04-07 14:56:15 +00:00
2015-04-04 11:11:55 +00:00
def _real_initialize(self):
user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
manager_info = self._download_json(
'http://www.rtve.es/odin/loki/' + user_agent_b64,
None, 'Fetching manager info')
self._manager = manager_info['manager']
2014-04-07 14:56:15 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
info = self._download_json(
'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
video_id)['page']['items'][0]
if info['state'] == 'DESPU':
raise ExtractorError('The video is no longer available', expected=True)
2015-04-04 11:11:55 +00:00
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
png_request = sanitized_Request(png_url)
png_request.add_header('Referer', url)
png = self._download_webpage(png_request, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
if not video_url.endswith('.f4m'):
video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
2014-04-07 14:56:15 +00:00
2015-02-23 20:52:07 +00:00
subtitles = None
if info.get('sbtFile') is not None:
subtitles = self.extract_subtitles(video_id, info['sbtFile'])
2014-04-07 14:56:15 +00:00
return {
'id': video_id,
'title': info['title'],
'url': video_url,
'thumbnail': info.get('image'),
'page_url': url,
2015-02-23 20:52:07 +00:00
'subtitles': subtitles,
2015-02-27 11:24:51 +00:00
'duration': float_or_none(info.get('duration'), scale=1000),
}
2015-02-23 20:52:07 +00:00
def _get_subtitles(self, video_id, sub_file):
subs = self._download_json(
sub_file + '.json', video_id,
'Downloading subtitles info')['page']['items']
2015-02-24 10:37:27 +00:00
return dict(
(s['lang'], [{'ext': 'vtt', 'url': s['src']}])
2015-02-23 20:52:07 +00:00
for s in subs)
class RTVEInfantilIE(InfoExtractor):
IE_NAME = 'rtve.es:infantil'
IE_DESC = 'RTVE infantil'
_VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
_TESTS = [{
'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
'md5': '915319587b33720b8e0357caaa6617e6',
'info_dict': {
'id': '3040283',
'ext': 'mp4',
'title': 'Maneras de vivir',
'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
'duration': 357.958,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
info = self._download_json(
'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
video_id)['page']['items'][0]
webpage = self._download_webpage(url, video_id)
vidplayer_id = self._search_regex(
r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
png = self._download_webpage(png_url, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
return {
'id': video_id,
'ext': 'mp4',
'title': info['title'],
'url': video_url,
'thumbnail': info.get('image'),
'duration': float_or_none(info.get('duration'), scale=1000),
}
class RTVELiveIE(InfoExtractor):
IE_NAME = 'rtve.es:live'
IE_DESC = 'RTVE.es live streams'
_VALID_URL = r'https?://www\.rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
_TESTS = [{
'url': 'http://www.rtve.es/directo/la-1/',
'info_dict': {
'id': 'la-1',
'ext': 'mp4',
'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
},
'params': {
'skip_download': 'live stream',
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
start_time = time.gmtime()
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
title = remove_start(title, 'Estoy viendo ')
title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
vidplayer_id = self._search_regex(
r'playerId=player([0-9]+)', webpage, 'internal video ID')
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
png = self._download_webpage(png_url, video_id, 'Downloading url information')
m3u8_url = _decrypt_url(png)
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
'is_live': True,
2014-04-07 14:56:15 +00:00
}
class RTVETelevisionIE(InfoExtractor):
IE_NAME = 'rtve.es:television'
_VALID_URL = r'https?://www\.rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
_TEST = {
'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
'info_dict': {
'id': '3069778',
'ext': 'mp4',
'title': 'Documentos TV - La revolución del móvil',
'duration': 3496.948,
},
'params': {
'skip_download': True,
},
}
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
alacarta_url = self._search_regex(
r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(http://www\.rtve\.es/alacarta.+?)&',
webpage, 'alacarta url', default=None)
if alacarta_url is None:
raise ExtractorError(
'The webpage doesn\'t contain any video', expected=True)
return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())