This commit is contained in:
Gilles Habran 2016-07-05 08:29:37 +02:00
commit f51f4723f3
11 changed files with 132 additions and 49 deletions

View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.07.03.1*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.07.03.1**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.07.05*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.07.05**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2016.07.03.1
[debug] youtube-dl version 2016.07.05
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

View File

@ -103,9 +103,9 @@ which means you can modify it, redistribute it or use it however you like.
(experimental)
-6, --force-ipv6 Make all connections via IPv6
(experimental)
--cn-verification-proxy URL Use this proxy to verify the IP address for
some Chinese sites. The default proxy
specified by --proxy (or none, if the
--geo-verification-proxy URL Use this proxy to verify the IP address for
some geo-restricted sites. The default
proxy specified by --proxy (or none, if the
options is not present) is used for the
actual downloading. (experimental)

View File

@ -405,6 +405,12 @@ class TestUtil(unittest.TestCase):
self.assertEqual(res_url, url)
self.assertEqual(res_data, None)
smug_url = smuggle_url(url, {'a': 'b'})
smug_smug_url = smuggle_url(smug_url, {'c': 'd'})
res_url, res_data = unsmuggle_url(smug_smug_url)
self.assertEqual(res_url, url)
self.assertEqual(res_data, {'a': 'b', 'c': 'd'})
def test_shell_quote(self):
args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")

View File

@ -1066,6 +1066,7 @@ from .youtube import (
YoutubeSearchDateIE,
YoutubeSearchIE,
YoutubeSearchURLIE,
YoutubeSharedVideoIE,
YoutubeShowIE,
YoutubeSubscriptionsIE,
YoutubeTruncatedIDIE,

View File

@ -1295,6 +1295,21 @@ class GenericIE(InfoExtractor):
'uploader': 'cylus cyrus',
},
},
{
# video stored on custom kaltura server
'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
'md5': '537617d06e64dfed891fa1593c4b30cc',
'info_dict': {
'id': '0_1iotm5bh',
'ext': 'mp4',
'title': 'Elecciones británicas: 5 lecciones para Rajoy',
'description': 'md5:435a89d68b9760b92ce67ed227055f16',
'uploader_id': 'videos.expansion@el-mundo.net',
'upload_date': '20150429',
'timestamp': 1430303472,
},
'add_ie': ['Kaltura'],
},
]
def report_following_redirect(self, new_url):

View File

@ -6,7 +6,6 @@ import base64
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_urlparse,
compat_parse_qs,
)
@ -15,6 +14,7 @@ from ..utils import (
ExtractorError,
int_or_none,
unsmuggle_url,
smuggle_url,
)
@ -34,7 +34,8 @@ class KalturaIE(InfoExtractor):
)(?:/(?P<path>[^?]+))?(?:\?(?P<query>.*))?
)
'''
_API_BASE = 'http://cdnapi.kaltura.com/api_v3/index.php?'
_SERVICE_URL = 'http://cdnapi.kaltura.com'
_SERVICE_BASE = '/api_v3/index.php'
_TESTS = [
{
'url': 'kaltura:269692:1_1jc2y3e4',
@ -88,18 +89,26 @@ class KalturaIE(InfoExtractor):
(?P<q3>["\'])(?P<id>.+?)(?P=q3)
''', webpage))
if mobj:
return 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict()
embed_info = mobj.groupdict()
url = 'kaltura:%(partner_id)s:%(id)s' % embed_info
escaped_pid = re.escape(embed_info['partner_id'])
service_url = re.search(
r'<script[^>]+src=["\']((?:https?:)?//.+?)/p/%s/sp/%s00/embedIframeJs' % (escaped_pid, escaped_pid),
webpage)
if service_url:
url = smuggle_url(url, {'service_url': service_url.group(1)})
return url
def _kaltura_api_call(self, video_id, actions, *args, **kwargs):
def _kaltura_api_call(self, video_id, actions, service_url=None, *args, **kwargs):
params = actions[0]
if len(actions) > 1:
for i, a in enumerate(actions[1:], start=1):
for k, v in a.items():
params['%d:%s' % (i, k)] = v
query = compat_urllib_parse_urlencode(params)
url = self._API_BASE + query
data = self._download_json(url, video_id, *args, **kwargs)
data = self._download_json(
(service_url or self._SERVICE_URL) + self._SERVICE_BASE,
video_id, query=params, *args, **kwargs)
status = data if len(actions) == 1 else data[0]
if status.get('objectType') == 'KalturaAPIException':
@ -108,7 +117,7 @@ class KalturaIE(InfoExtractor):
return data
def _get_kaltura_signature(self, video_id, partner_id):
def _get_kaltura_signature(self, video_id, partner_id, service_url=None):
actions = [{
'apiVersion': '3.1',
'expiry': 86400,
@ -118,10 +127,10 @@ class KalturaIE(InfoExtractor):
'widgetId': '_%s' % partner_id,
}]
return self._kaltura_api_call(
video_id, actions, note='Downloading Kaltura signature')['ks']
video_id, actions, service_url, note='Downloading Kaltura signature')['ks']
def _get_video_info(self, video_id, partner_id):
signature = self._get_kaltura_signature(video_id, partner_id)
def _get_video_info(self, video_id, partner_id, service_url=None):
signature = self._get_kaltura_signature(video_id, partner_id, service_url)
actions = [
{
'action': 'null',
@ -144,7 +153,7 @@ class KalturaIE(InfoExtractor):
},
]
return self._kaltura_api_call(
video_id, actions, note='Downloading video info JSON')
video_id, actions, service_url, note='Downloading video info JSON')
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
@ -153,7 +162,7 @@ class KalturaIE(InfoExtractor):
partner_id, entry_id = mobj.group('partner_id', 'id')
ks = None
if partner_id and entry_id:
info, flavor_assets = self._get_video_info(entry_id, partner_id)
info, flavor_assets = self._get_video_info(entry_id, partner_id, smuggled_data.get('service_url'))
else:
path, query = mobj.group('path', 'query')
if not path and not query:
@ -201,12 +210,17 @@ class KalturaIE(InfoExtractor):
unsigned_url += '?referrer=%s' % referrer
return unsigned_url
data_url = info['dataUrl']
if '/flvclipper/' in data_url:
data_url = re.sub(r'/flvclipper/.*', '/serveFlavor', data_url)
formats = []
for f in flavor_assets:
# Continue if asset is not ready
if f['status'] != 2:
continue
video_url = sign_url('%s/flavorId/%s' % (info['dataUrl'], f['id']))
video_url = sign_url(
'%s/flavorId/%s' % (data_url, f['id']))
formats.append({
'format_id': '%(fileExt)s-%(bitrate)s' % f,
'ext': f.get('fileExt'),
@ -219,9 +233,12 @@ class KalturaIE(InfoExtractor):
'width': int_or_none(f.get('width')),
'url': video_url,
})
m3u8_url = sign_url(info['dataUrl'].replace('format/url', 'format/applehttp'))
formats.extend(self._extract_m3u8_formats(
m3u8_url, entry_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
if '/playManifest/' in data_url:
m3u8_url = sign_url(data_url.replace(
'format/url', 'format/applehttp'))
formats.extend(self._extract_m3u8_formats(
m3u8_url, entry_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
self._check_formats(formats, entry_id)
self._sort_formats(formats)

View File

@ -3,8 +3,8 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
determine_ext,
js_to_json,
smuggle_url,
)
@ -18,13 +18,16 @@ class LA7IE(InfoExtractor):
_TESTS = [{
# 'src' is a plain URL
'url': 'http://www.la7.it/crozza/video/inccool8-02-10-2015-163722',
'md5': '6054674766e7988d3e02f2148ff92180',
'md5': '8b613ffc0c4bf9b9e377169fc19c214c',
'info_dict': {
'id': 'inccool8-02-10-2015-163722',
'ext': 'mp4',
'title': 'Inc.Cool8',
'description': 'Benvenuti nell\'incredibile mondo della INC. COOL. 8. dove “INC.” sta per “Incorporated” “COOL” sta per “fashion” ed Eight sta per il gesto atletico',
'thumbnail': 're:^https?://.*',
'uploader_id': 'kdla7pillole@iltrovatore.it',
'timestamp': 1443814869,
'upload_date': '20151002',
},
}, {
# 'src' is a dictionary
@ -49,26 +52,14 @@ class LA7IE(InfoExtractor):
self._search_regex(r'videoLa7\(({[^;]+})\);', webpage, 'player data'),
video_id, transform_source=js_to_json)
source = player_data['src']
source_urls = source.values() if isinstance(source, dict) else [source]
formats = []
for source_url in source_urls:
ext = determine_ext(source_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id='hls'))
else:
formats.append({
'url': source_url,
})
self._sort_formats(formats)
return {
'_type': 'url_transparent',
'url': smuggle_url('kaltura:103:%s' % player_data['vid'], {
'service_url': 'http://kdam.iltrovatore.it',
}),
'id': video_id,
'title': player_data['title'],
'description': self._og_search_description(webpage, default=None),
'thumbnail': player_data.get('poster'),
'formats': formats,
'ie_key': 'Kaltura',
}

View File

@ -67,6 +67,20 @@ class XuiteIE(InfoExtractor):
'categories': ['電玩動漫'],
},
'skip': 'Video removed',
}, {
# Video with encoded media id
# from http://forgetfulbc.blogspot.com/2016/06/date.html
'url': 'http://vlog.xuite.net/embed/cE1xbENoLTI3NDQ3MzM2LmZsdg==?ar=0&as=0',
'info_dict': {
'id': 'cE1xbENoLTI3NDQ3MzM2LmZsdg==',
'ext': 'mp4',
'title': '男女平權只是口號?專家解釋約會時男生是否該幫女生付錢 (中字)',
'description': 'md5:f0abdcb69df300f522a5442ef3146f2a',
'timestamp': 1466160960,
'upload_date': '20160617',
'uploader': 'B.C. & Lowy',
'uploader_id': '232279340',
},
}, {
'url': 'http://vlog.xuite.net/play/S1dDUjdyLTMyOTc3NjcuZmx2/%E5%AD%AB%E7%87%95%E5%A7%BF-%E7%9C%BC%E6%B7%9A%E6%88%90%E8%A9%A9',
'only_matching': True,
@ -80,10 +94,9 @@ class XuiteIE(InfoExtractor):
def base64_encode_utf8(data):
return base64.b64encode(data.encode('utf-8')).decode('utf-8')
def _extract_flv_config(self, media_id):
base64_media_id = self.base64_encode_utf8(media_id)
def _extract_flv_config(self, encoded_media_id):
flv_config = self._download_xml(
'http://vlog.xuite.net/flash/player?media=%s' % base64_media_id,
'http://vlog.xuite.net/flash/player?media=%s' % encoded_media_id,
'flv config')
prop_dict = {}
for prop in flv_config.findall('./property'):
@ -108,9 +121,14 @@ class XuiteIE(InfoExtractor):
'%s returned error: %s' % (self.IE_NAME, error_msg),
expected=True)
video_id = self._html_search_regex(
r'data-mediaid="(\d+)"', webpage, 'media id')
flv_config = self._extract_flv_config(video_id)
encoded_media_id = self._search_regex(
r'attributes\.name\s*=\s*"([^"]+)"', webpage,
'encoded media id', default=None)
if encoded_media_id is None:
video_id = self._html_search_regex(
r'data-mediaid="(\d+)"', webpage, 'media id')
encoded_media_id = self.base64_encode_utf8(video_id)
flv_config = self._extract_flv_config(encoded_media_id)
FORMATS = {
'audio': 'mp3',

View File

@ -1730,6 +1730,39 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
}
class YoutubeSharedVideoIE(InfoExtractor):
_VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?ci=(?P<id>[0-9A-Za-z_-]{11})'
IE_NAME = 'youtube:shared'
_TEST = {
'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
'info_dict': {
'id': 'uPDB5I9wfp8',
'ext': 'webm',
'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
'upload_date': '20160219',
'uploader': 'Pocoyo - Português (BR)',
'uploader_id': 'PocoyoBrazil',
},
'add_ie': ['Youtube'],
'params': {
# There are already too many Youtube downloads
'skip_download': True,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
real_video_id = self._html_search_meta(
'videoId', webpage, 'YouTube video id', fatal=True)
return self.url_result(real_video_id, YoutubeIE.ie_key())
class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
IE_DESC = 'YouTube.com playlists'
_VALID_URL = r"""(?x)(?:

View File

@ -1444,6 +1444,8 @@ def shell_quote(args):
def smuggle_url(url, data):
""" Pass additional data in a URL for internal use. """
url, idata = unsmuggle_url(url, {})
data.update(idata)
sdata = compat_urllib_parse_urlencode(
{'__youtubedl_smuggle': json.dumps(data)})
return url + '#' + sdata

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2016.07.03.1'
__version__ = '2016.07.05'