mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-21 20:46:36 -05:00
[atresplayer] improve extraction
- select hashlib.md5 constructor as digestmod(in python 3.4+ MD5 as implicit default digest for digestmod is deprecated.) - extract hls formats - update tests - extract errors
This commit is contained in:
remitamine
parent
5c5a3ecf1b
commit
61ebb401b7
1 changed files with 81 additions and 36 deletions
|
|
@ -2,6 +2,8 @@
|
|||
|
||||
import time
|
||||
import hmac
|
||||
import hashlib
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
|
|
@ -32,6 +34,19 @@ class AtresPlayerIE(InfoExtractor):
|
|||
'duration': 5527.6,
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
},
|
||||
'skip': 'This video is only available for registered users'
|
||||
},
|
||||
{
|
||||
'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html',
|
||||
'md5': '0d0e918533bbd4b263f2de4d197d4aac',
|
||||
'info_dict': {
|
||||
'id': 'capitulo-112-david-bustamante',
|
||||
'ext': 'flv',
|
||||
'title': 'David Bustamante',
|
||||
'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6',
|
||||
'duration': 1439.0,
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html',
|
||||
|
|
@ -50,6 +65,13 @@ class AtresPlayerIE(InfoExtractor):
|
|||
|
||||
_LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
|
||||
|
||||
_ERRORS = {
|
||||
'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.',
|
||||
'DELETED': 'This video has expired and is no longer available for online streaming.',
|
||||
'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.',
|
||||
# 'PREMIUM': 'PREMIUM',
|
||||
}
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
|
||||
|
|
@ -83,23 +105,55 @@ def _real_extract(self, url):
|
|||
episode_id = self._search_regex(
|
||||
r'episode="([^"]+)"', webpage, 'episode id')
|
||||
|
||||
request = sanitized_Request(
|
||||
self._PLAYER_URL_TEMPLATE % episode_id,
|
||||
headers={'User-Agent': self._USER_AGENT})
|
||||
player = self._download_json(request, episode_id, 'Downloading player JSON')
|
||||
|
||||
episode_type = player.get('typeOfEpisode')
|
||||
error_message = self._ERRORS.get(episode_type)
|
||||
if error_message:
|
||||
raise ExtractorError(
|
||||
'%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
|
||||
|
||||
formats = []
|
||||
video_url = player.get('urlVideo')
|
||||
if video_url:
|
||||
format_info = {
|
||||
'url': video_url,
|
||||
'format_id': 'http',
|
||||
}
|
||||
mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url)
|
||||
if mobj:
|
||||
format_info.update({
|
||||
'width': int_or_none(mobj.group('width')),
|
||||
'height': int_or_none(mobj.group('height')),
|
||||
'tbr': int_or_none(mobj.group('bitrate')),
|
||||
})
|
||||
formats.append(format_info)
|
||||
|
||||
m3u8_url = player.get('urlVideoHls')
|
||||
if m3u8_url:
|
||||
m3u8_formats = self._extract_m3u8_formats(
|
||||
m3u8_url, episode_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
|
||||
if m3u8_formats:
|
||||
formats.extend(m3u8_formats)
|
||||
|
||||
timestamp = int_or_none(self._download_webpage(
|
||||
self._TIME_API_URL,
|
||||
video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
|
||||
timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
|
||||
token = hmac.new(
|
||||
self._MAGIC.encode('ascii'),
|
||||
(episode_id + timestamp_shifted).encode('utf-8')
|
||||
(episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5
|
||||
).hexdigest()
|
||||
|
||||
formats = []
|
||||
for fmt in ['windows', 'android_tablet']:
|
||||
request = sanitized_Request(
|
||||
self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
|
||||
request.add_header('User-Agent', self._USER_AGENT)
|
||||
self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token),
|
||||
headers={'User-Agent': self._USER_AGENT})
|
||||
|
||||
fmt_json = self._download_json(
|
||||
request, video_id, 'Downloading %s video JSON' % fmt)
|
||||
request, video_id, 'Downloading windows video JSON')
|
||||
|
||||
result = fmt_json.get('resultDes')
|
||||
if result.lower() != 'ok':
|
||||
|
|
@ -109,7 +163,6 @@ def _real_extract(self, url):
|
|||
for format_id, video_url in fmt_json['resultObject'].items():
|
||||
if format_id == 'token' or not video_url.startswith('http'):
|
||||
continue
|
||||
if video_url.endswith('/Manifest'):
|
||||
if 'geodeswowsmpra3player' in video_url:
|
||||
f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
|
||||
f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
|
||||
|
|
@ -117,24 +170,16 @@ def _real_extract(self, url):
|
|||
continue
|
||||
else:
|
||||
f4m_url = video_url[:-9] + '/manifest.f4m'
|
||||
formats.extend(self._extract_f4m_formats(f4m_url, video_id))
|
||||
else:
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'format_id': 'android-%s' % format_id,
|
||||
'preference': 1,
|
||||
})
|
||||
f4m_formats = self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False)
|
||||
if f4m_formats:
|
||||
formats.extend(f4m_formats)
|
||||
self._sort_formats(formats)
|
||||
|
||||
player = self._download_json(
|
||||
self._PLAYER_URL_TEMPLATE % episode_id,
|
||||
episode_id)
|
||||
|
||||
path_data = player.get('pathData')
|
||||
|
||||
episode = self._download_xml(
|
||||
self._EPISODE_URL_TEMPLATE % path_data,
|
||||
video_id, 'Downloading episode XML')
|
||||
self._EPISODE_URL_TEMPLATE % path_data, video_id,
|
||||
'Downloading episode XML')
|
||||
|
||||
duration = float_or_none(xpath_text(
|
||||
episode, './media/asset/info/technical/contentDuration', 'duration'))
|
||||
|
|
|
|||
Loading…
Reference in a new issue