Compare commits
15 Commits
2016.06.02
...
2016.06.05
| Author | SHA1 | Date | |
|---|---|---|---|
|
e642347492 | ||
|
|
4ea8d2ee76 | ||
|
|
bf4c6a38e1 | ||
|
|
7f3c3dfa52 | ||
|
9c3c447eb3 | ||
|
ad73083ff0 | ||
|
|
1e8b59243f | ||
|
c88270271e | ||
|
|
b96f007eeb | ||
|
|
9a4aec8b7e | ||
|
|
54fb199681 | ||
|
|
8c32e5dc32 | ||
|
|
0ea590076f | ||
|
4a684895c0 | ||
|
|
f4e4aa9b6b |
6
.github/ISSUE_TEMPLATE.md
vendored
6
.github/ISSUE_TEMPLATE.md
vendored
@@ -6,8 +6,8 @@
|
|||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.02*. 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 Issues with outdated version will be rejected.
|
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.05*. 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 Issues with outdated version will be rejected.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 **2016.06.02**
|
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.06.05**
|
||||||
|
|
||||||
### Before submitting an *issue* make sure you have:
|
### 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
|
- [ ] 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] User config: []
|
||||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
[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] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||||
[debug] youtube-dl version 2016.06.02
|
[debug] youtube-dl version 2016.06.05
|
||||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
[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] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||||
[debug] Proxy map: {}
|
[debug] Proxy map: {}
|
||||||
|
|||||||
@@ -339,6 +339,7 @@
|
|||||||
- **livestream**
|
- **livestream**
|
||||||
- **livestream:original**
|
- **livestream:original**
|
||||||
- **LnkGo**
|
- **LnkGo**
|
||||||
|
- **loc**: Library of Congress
|
||||||
- **LocalNews8**
|
- **LocalNews8**
|
||||||
- **LoveHomePorn**
|
- **LoveHomePorn**
|
||||||
- **lrt.lt**
|
- **lrt.lt**
|
||||||
@@ -528,7 +529,8 @@
|
|||||||
- **Restudy**
|
- **Restudy**
|
||||||
- **Reuters**
|
- **Reuters**
|
||||||
- **ReverbNation**
|
- **ReverbNation**
|
||||||
- **Revision3**
|
- **revision**
|
||||||
|
- **revision3:embed**
|
||||||
- **RICE**
|
- **RICE**
|
||||||
- **RingTV**
|
- **RingTV**
|
||||||
- **RottenTomatoes**
|
- **RottenTomatoes**
|
||||||
@@ -567,6 +569,7 @@
|
|||||||
- **ScreencastOMatic**
|
- **ScreencastOMatic**
|
||||||
- **ScreenJunkies**
|
- **ScreenJunkies**
|
||||||
- **ScreenwaveMedia**
|
- **ScreenwaveMedia**
|
||||||
|
- **Seeker**
|
||||||
- **SenateISVP**
|
- **SenateISVP**
|
||||||
- **SendtoNews**
|
- **SendtoNews**
|
||||||
- **ServingSys**
|
- **ServingSys**
|
||||||
|
|||||||
@@ -16,6 +16,15 @@ import threading
|
|||||||
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
|
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||||
|
|
||||||
|
|
||||||
|
def http_server_port(httpd):
|
||||||
|
if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket):
|
||||||
|
# In Jython SSLSocket is not a subclass of socket.socket
|
||||||
|
sock = httpd.socket.sock
|
||||||
|
else:
|
||||||
|
sock = httpd.socket
|
||||||
|
return sock.getsockname()[1]
|
||||||
|
|
||||||
|
|
||||||
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
|
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
|
||||||
def log_message(self, format, *args):
|
def log_message(self, format, *args):
|
||||||
pass
|
pass
|
||||||
@@ -31,6 +40,22 @@ class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
|
|||||||
self.send_header('Content-Type', 'video/mp4')
|
self.send_header('Content-Type', 'video/mp4')
|
||||||
self.end_headers()
|
self.end_headers()
|
||||||
self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]')
|
self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]')
|
||||||
|
elif self.path == '/302':
|
||||||
|
if sys.version_info[0] == 3:
|
||||||
|
# XXX: Python 3 http server does not allow non-ASCII header values
|
||||||
|
self.send_response(404)
|
||||||
|
self.end_headers()
|
||||||
|
return
|
||||||
|
|
||||||
|
new_url = 'http://localhost:%d/中文.html' % http_server_port(self.server)
|
||||||
|
self.send_response(302)
|
||||||
|
self.send_header(b'Location', new_url.encode('utf-8'))
|
||||||
|
self.end_headers()
|
||||||
|
elif self.path == '/%E4%B8%AD%E6%96%87.html':
|
||||||
|
self.send_response(200)
|
||||||
|
self.send_header('Content-Type', 'text/html; charset=utf-8')
|
||||||
|
self.end_headers()
|
||||||
|
self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
|
||||||
else:
|
else:
|
||||||
assert False
|
assert False
|
||||||
|
|
||||||
@@ -47,18 +72,32 @@ class FakeLogger(object):
|
|||||||
|
|
||||||
|
|
||||||
class TestHTTP(unittest.TestCase):
|
class TestHTTP(unittest.TestCase):
|
||||||
|
def setUp(self):
|
||||||
|
self.httpd = compat_http_server.HTTPServer(
|
||||||
|
('localhost', 0), HTTPTestRequestHandler)
|
||||||
|
self.port = http_server_port(self.httpd)
|
||||||
|
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
|
||||||
|
self.server_thread.daemon = True
|
||||||
|
self.server_thread.start()
|
||||||
|
|
||||||
|
def test_unicode_path_redirection(self):
|
||||||
|
# XXX: Python 3 http server does not allow non-ASCII header values
|
||||||
|
if sys.version_info[0] == 3:
|
||||||
|
return
|
||||||
|
|
||||||
|
ydl = YoutubeDL({'logger': FakeLogger()})
|
||||||
|
r = ydl.extract_info('http://localhost:%d/302' % self.port)
|
||||||
|
self.assertEqual(r['url'], 'http://localhost:%d/vid.mp4' % self.port)
|
||||||
|
|
||||||
|
|
||||||
|
class TestHTTPS(unittest.TestCase):
|
||||||
def setUp(self):
|
def setUp(self):
|
||||||
certfn = os.path.join(TEST_DIR, 'testcert.pem')
|
certfn = os.path.join(TEST_DIR, 'testcert.pem')
|
||||||
self.httpd = compat_http_server.HTTPServer(
|
self.httpd = compat_http_server.HTTPServer(
|
||||||
('localhost', 0), HTTPTestRequestHandler)
|
('localhost', 0), HTTPTestRequestHandler)
|
||||||
self.httpd.socket = ssl.wrap_socket(
|
self.httpd.socket = ssl.wrap_socket(
|
||||||
self.httpd.socket, certfile=certfn, server_side=True)
|
self.httpd.socket, certfile=certfn, server_side=True)
|
||||||
if os.name == 'java':
|
self.port = http_server_port(self.httpd)
|
||||||
# In Jython SSLSocket is not a subclass of socket.socket
|
|
||||||
sock = self.httpd.socket.sock
|
|
||||||
else:
|
|
||||||
sock = self.httpd.socket
|
|
||||||
self.port = sock.getsockname()[1]
|
|
||||||
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
|
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
|
||||||
self.server_thread.daemon = True
|
self.server_thread.daemon = True
|
||||||
self.server_thread.start()
|
self.server_thread.start()
|
||||||
@@ -94,14 +133,14 @@ class TestProxy(unittest.TestCase):
|
|||||||
def setUp(self):
|
def setUp(self):
|
||||||
self.proxy = compat_http_server.HTTPServer(
|
self.proxy = compat_http_server.HTTPServer(
|
||||||
('localhost', 0), _build_proxy_handler('normal'))
|
('localhost', 0), _build_proxy_handler('normal'))
|
||||||
self.port = self.proxy.socket.getsockname()[1]
|
self.port = http_server_port(self.proxy)
|
||||||
self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
|
self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
|
||||||
self.proxy_thread.daemon = True
|
self.proxy_thread.daemon = True
|
||||||
self.proxy_thread.start()
|
self.proxy_thread.start()
|
||||||
|
|
||||||
self.cn_proxy = compat_http_server.HTTPServer(
|
self.cn_proxy = compat_http_server.HTTPServer(
|
||||||
('localhost', 0), _build_proxy_handler('cn'))
|
('localhost', 0), _build_proxy_handler('cn'))
|
||||||
self.cn_port = self.cn_proxy.socket.getsockname()[1]
|
self.cn_port = http_server_port(self.cn_proxy)
|
||||||
self.cn_proxy_thread = threading.Thread(target=self.cn_proxy.serve_forever)
|
self.cn_proxy_thread = threading.Thread(target=self.cn_proxy.serve_forever)
|
||||||
self.cn_proxy_thread.daemon = True
|
self.cn_proxy_thread.daemon = True
|
||||||
self.cn_proxy_thread.start()
|
self.cn_proxy_thread.start()
|
||||||
|
|||||||
@@ -157,8 +157,8 @@ class TestUtil(unittest.TestCase):
|
|||||||
self.assertTrue(sanitize_filename(':', restricted=True) != '')
|
self.assertTrue(sanitize_filename(':', restricted=True) != '')
|
||||||
|
|
||||||
self.assertEqual(sanitize_filename(
|
self.assertEqual(sanitize_filename(
|
||||||
'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØŒÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøœùúûüýþÿ', restricted=True),
|
'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True),
|
||||||
'AAAAAAAECEEEEIIIIDNOOOOOOOEUUUUYPssaaaaaaaeceeeeiiiionoooooooeuuuuypy')
|
'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy')
|
||||||
|
|
||||||
def test_sanitize_ids(self):
|
def test_sanitize_ids(self):
|
||||||
self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
|
self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
|
||||||
|
|||||||
@@ -46,6 +46,62 @@ class BiliBiliIE(InfoExtractor):
|
|||||||
'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
|
'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
|
||||||
},
|
},
|
||||||
'playlist_count': 9,
|
'playlist_count': 9,
|
||||||
|
}, {
|
||||||
|
'url': 'http://www.bilibili.com/video/av4808130/',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '4808130',
|
||||||
|
'title': '【长篇】哆啦A梦443【钉铛】',
|
||||||
|
'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929',
|
||||||
|
},
|
||||||
|
'playlist': [{
|
||||||
|
'md5': '55cdadedf3254caaa0d5d27cf20a8f9c',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '4808130_part1',
|
||||||
|
'ext': 'flv',
|
||||||
|
'title': '【长篇】哆啦A梦443【钉铛】',
|
||||||
|
'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929',
|
||||||
|
'timestamp': 1464564180,
|
||||||
|
'upload_date': '20160529',
|
||||||
|
'uploader': '喜欢拉面',
|
||||||
|
'uploader_id': '151066',
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'md5': '926f9f67d0c482091872fbd8eca7ea3d',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '4808130_part2',
|
||||||
|
'ext': 'flv',
|
||||||
|
'title': '【长篇】哆啦A梦443【钉铛】',
|
||||||
|
'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929',
|
||||||
|
'timestamp': 1464564180,
|
||||||
|
'upload_date': '20160529',
|
||||||
|
'uploader': '喜欢拉面',
|
||||||
|
'uploader_id': '151066',
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'md5': '4b7b225b968402d7c32348c646f1fd83',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '4808130_part3',
|
||||||
|
'ext': 'flv',
|
||||||
|
'title': '【长篇】哆啦A梦443【钉铛】',
|
||||||
|
'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929',
|
||||||
|
'timestamp': 1464564180,
|
||||||
|
'upload_date': '20160529',
|
||||||
|
'uploader': '喜欢拉面',
|
||||||
|
'uploader_id': '151066',
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'md5': '7b795e214166501e9141139eea236e91',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '4808130_part4',
|
||||||
|
'ext': 'flv',
|
||||||
|
'title': '【长篇】哆啦A梦443【钉铛】',
|
||||||
|
'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929',
|
||||||
|
'timestamp': 1464564180,
|
||||||
|
'upload_date': '20160529',
|
||||||
|
'uploader': '喜欢拉面',
|
||||||
|
'uploader_id': '151066',
|
||||||
|
},
|
||||||
|
}],
|
||||||
}]
|
}]
|
||||||
|
|
||||||
# BiliBili blocks keys from time to time. The current key is extracted from
|
# BiliBili blocks keys from time to time. The current key is extracted from
|
||||||
@@ -144,6 +200,9 @@ class BiliBiliIE(InfoExtractor):
|
|||||||
if len(entries) == 1:
|
if len(entries) == 1:
|
||||||
return entries[0]
|
return entries[0]
|
||||||
else:
|
else:
|
||||||
|
for idx, entry in enumerate(entries):
|
||||||
|
entry['id'] = '%s_part%d' % (video_id, (idx + 1))
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'_type': 'multi_video',
|
'_type': 'multi_video',
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
|
|||||||
@@ -382,6 +382,7 @@ from .leeco import (
|
|||||||
LePlaylistIE,
|
LePlaylistIE,
|
||||||
LetvCloudIE,
|
LetvCloudIE,
|
||||||
)
|
)
|
||||||
|
from .libraryofcongress import LibraryOfCongressIE
|
||||||
from .libsyn import LibsynIE
|
from .libsyn import LibsynIE
|
||||||
from .lifenews import (
|
from .lifenews import (
|
||||||
LifeNewsIE,
|
LifeNewsIE,
|
||||||
@@ -639,7 +640,10 @@ from .regiotv import RegioTVIE
|
|||||||
from .restudy import RestudyIE
|
from .restudy import RestudyIE
|
||||||
from .reuters import ReutersIE
|
from .reuters import ReutersIE
|
||||||
from .reverbnation import ReverbNationIE
|
from .reverbnation import ReverbNationIE
|
||||||
from .revision3 import Revision3IE
|
from .revision3 import (
|
||||||
|
Revision3EmbedIE,
|
||||||
|
Revision3IE,
|
||||||
|
)
|
||||||
from .rice import RICEIE
|
from .rice import RICEIE
|
||||||
from .ringtv import RingTVIE
|
from .ringtv import RingTVIE
|
||||||
from .ro220 import Ro220IE
|
from .ro220 import Ro220IE
|
||||||
@@ -678,6 +682,7 @@ from .screencast import ScreencastIE
|
|||||||
from .screencastomatic import ScreencastOMaticIE
|
from .screencastomatic import ScreencastOMaticIE
|
||||||
from .screenjunkies import ScreenJunkiesIE
|
from .screenjunkies import ScreenJunkiesIE
|
||||||
from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
|
from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
|
||||||
|
from .seeker import SeekerIE
|
||||||
from .senateisvp import SenateISVPIE
|
from .senateisvp import SenateISVPIE
|
||||||
from .sendtonews import SendtoNewsIE
|
from .sendtonews import SendtoNewsIE
|
||||||
from .servingsys import ServingSysIE
|
from .servingsys import ServingSysIE
|
||||||
|
|||||||
84
youtube_dl/extractor/libraryofcongress.py
Normal file
84
youtube_dl/extractor/libraryofcongress.py
Normal file
@@ -0,0 +1,84 @@
|
|||||||
|
# coding: utf-8
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
from .common import InfoExtractor
|
||||||
|
|
||||||
|
from ..utils import (
|
||||||
|
determine_ext,
|
||||||
|
float_or_none,
|
||||||
|
int_or_none,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class LibraryOfCongressIE(InfoExtractor):
|
||||||
|
IE_NAME = 'loc'
|
||||||
|
IE_DESC = 'Library of Congress'
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?loc\.gov/item/(?P<id>[0-9]+)'
|
||||||
|
_TEST = {
|
||||||
|
'url': 'http://loc.gov/item/90716351/',
|
||||||
|
'md5': '353917ff7f0255aa6d4b80a034833de8',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '90716351',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': "Pa's trip to Mars",
|
||||||
|
'thumbnail': 're:^https?://.*\.jpg$',
|
||||||
|
'duration': 0,
|
||||||
|
'view_count': int,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
video_id = self._match_id(url)
|
||||||
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
|
||||||
|
media_id = self._search_regex(
|
||||||
|
(r'id=(["\'])media-player-(?P<id>.+?)\1',
|
||||||
|
r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1',
|
||||||
|
r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1'),
|
||||||
|
webpage, 'media id', group='id')
|
||||||
|
|
||||||
|
data = self._parse_json(
|
||||||
|
self._download_webpage(
|
||||||
|
'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id,
|
||||||
|
video_id),
|
||||||
|
video_id)['mediaObject']
|
||||||
|
|
||||||
|
derivative = data['derivatives'][0]
|
||||||
|
media_url = derivative['derivativeUrl']
|
||||||
|
|
||||||
|
# Following algorithm was extracted from setAVSource js function
|
||||||
|
# found in webpage
|
||||||
|
media_url = media_url.replace('rtmp', 'https')
|
||||||
|
|
||||||
|
is_video = data.get('mediaType', 'v').lower() == 'v'
|
||||||
|
ext = determine_ext(media_url)
|
||||||
|
if ext not in ('mp4', 'mp3'):
|
||||||
|
media_url += '.mp4' if is_video else '.mp3'
|
||||||
|
|
||||||
|
if 'vod/mp4:' in media_url:
|
||||||
|
formats = [{
|
||||||
|
'url': media_url.replace('vod/mp4:', 'hls-vod/media/') + '.m3u8',
|
||||||
|
'format_id': 'hls',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'protocol': 'm3u8_native',
|
||||||
|
}]
|
||||||
|
elif 'vod/mp3:' in media_url:
|
||||||
|
formats = [{
|
||||||
|
'url': media_url.replace('vod/mp3:', ''),
|
||||||
|
'vcodec': 'none',
|
||||||
|
}]
|
||||||
|
|
||||||
|
self._sort_formats(formats)
|
||||||
|
|
||||||
|
title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(webpage)
|
||||||
|
duration = float_or_none(data.get('duration'))
|
||||||
|
view_count = int_or_none(data.get('viewCount'))
|
||||||
|
|
||||||
|
return {
|
||||||
|
'id': video_id,
|
||||||
|
'title': title,
|
||||||
|
'thumbnail': self._og_search_thumbnail(webpage),
|
||||||
|
'duration': duration,
|
||||||
|
'view_count': view_count,
|
||||||
|
'formats': formats,
|
||||||
|
}
|
||||||
@@ -13,8 +13,64 @@ from ..utils import (
|
|||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class Revision3EmbedIE(InfoExtractor):
|
||||||
|
IE_NAME = 'revision3:embed'
|
||||||
|
_VALID_URL = r'(?:revision3:(?:(?P<playlist_type>[^:]+):)?|https?://(?:(?:(?:www|embed)\.)?(?:revision3|animalist)|(?:(?:api|embed)\.)?seekernetwork)\.com/player/embed\?videoId=)(?P<playlist_id>\d+)'
|
||||||
|
_TEST = {
|
||||||
|
'url': 'http://api.seekernetwork.com/player/embed?videoId=67558',
|
||||||
|
'md5': '83bcd157cab89ad7318dd7b8c9cf1306',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '67558',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'The Pros & Cons Of Zoos',
|
||||||
|
'description': 'Zoos are often depicted as a terrible place for animals to live, but is there any truth to this?',
|
||||||
|
'uploader_id': 'dnews',
|
||||||
|
'uploader': 'DNews',
|
||||||
|
}
|
||||||
|
}
|
||||||
|
_API_KEY = 'ba9c741bce1b9d8e3defcc22193f3651b8867e62'
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
playlist_id = mobj.group('playlist_id')
|
||||||
|
playlist_type = mobj.group('playlist_type') or 'video_id'
|
||||||
|
video_data = self._download_json(
|
||||||
|
'http://revision3.com/api/getPlaylist.json', playlist_id, query={
|
||||||
|
'api_key': self._API_KEY,
|
||||||
|
'codecs': 'h264,vp8,theora',
|
||||||
|
playlist_type: playlist_id,
|
||||||
|
})['items'][0]
|
||||||
|
|
||||||
|
formats = []
|
||||||
|
for vcodec, media in video_data['media'].items():
|
||||||
|
for quality_id, quality in media.items():
|
||||||
|
if quality_id == 'hls':
|
||||||
|
formats.extend(self._extract_m3u8_formats(
|
||||||
|
quality['url'], playlist_id, 'mp4',
|
||||||
|
'm3u8_native', m3u8_id='hls', fatal=False))
|
||||||
|
else:
|
||||||
|
formats.append({
|
||||||
|
'url': quality['url'],
|
||||||
|
'format_id': '%s-%s' % (vcodec, quality_id),
|
||||||
|
'tbr': int_or_none(quality.get('bitrate')),
|
||||||
|
'vcodec': vcodec,
|
||||||
|
})
|
||||||
|
self._sort_formats(formats)
|
||||||
|
|
||||||
|
return {
|
||||||
|
'id': playlist_id,
|
||||||
|
'title': unescapeHTML(video_data['title']),
|
||||||
|
'description': unescapeHTML(video_data.get('summary')),
|
||||||
|
'uploader': video_data.get('show', {}).get('name'),
|
||||||
|
'uploader_id': video_data.get('show', {}).get('slug'),
|
||||||
|
'duration': int_or_none(video_data.get('duration')),
|
||||||
|
'formats': formats,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
class Revision3IE(InfoExtractor):
|
class Revision3IE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:revision3|testtube|animalist)\.com)/(?P<id>[^/]+(?:/[^/?#]+)?)'
|
IE_NAME = 'revision'
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:revision3|animalist)\.com)/(?P<id>[^/]+(?:/[^/?#]+)?)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://www.revision3.com/technobuffalo/5-google-predictions-for-2016',
|
'url': 'http://www.revision3.com/technobuffalo/5-google-predictions-for-2016',
|
||||||
'md5': 'd94a72d85d0a829766de4deb8daaf7df',
|
'md5': 'd94a72d85d0a829766de4deb8daaf7df',
|
||||||
@@ -32,52 +88,14 @@ class Revision3IE(InfoExtractor):
|
|||||||
}
|
}
|
||||||
}, {
|
}, {
|
||||||
# Show
|
# Show
|
||||||
'url': 'http://testtube.com/brainstuff',
|
'url': 'http://revision3.com/variant',
|
||||||
'info_dict': {
|
'only_matching': True,
|
||||||
'id': '251',
|
|
||||||
'title': 'BrainStuff',
|
|
||||||
'description': 'Whether the topic is popcorn or particle physics, you can count on the HowStuffWorks team to explore-and explain-the everyday science in the world around us on BrainStuff.',
|
|
||||||
},
|
|
||||||
'playlist_mincount': 93,
|
|
||||||
}, {
|
|
||||||
'url': 'https://testtube.com/dnews/5-weird-ways-plants-can-eat-animals?utm_source=FB&utm_medium=DNews&utm_campaign=DNewsSocial',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '58227',
|
|
||||||
'display_id': 'dnews/5-weird-ways-plants-can-eat-animals',
|
|
||||||
'duration': 275,
|
|
||||||
'ext': 'webm',
|
|
||||||
'title': '5 Weird Ways Plants Can Eat Animals',
|
|
||||||
'description': 'Why have some plants evolved to eat meat?',
|
|
||||||
'upload_date': '20150120',
|
|
||||||
'timestamp': 1421763300,
|
|
||||||
'uploader': 'DNews',
|
|
||||||
'uploader_id': 'dnews',
|
|
||||||
},
|
|
||||||
}, {
|
|
||||||
'url': 'http://testtube.com/tt-editors-picks/the-israel-palestine-conflict-explained-in-ten-min',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '71618',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'display_id': 'tt-editors-picks/the-israel-palestine-conflict-explained-in-ten-min',
|
|
||||||
'title': 'The Israel-Palestine Conflict Explained in Ten Minutes',
|
|
||||||
'description': 'If you\'d like to learn about the struggle between Israelis and Palestinians, this video is a great place to start',
|
|
||||||
'uploader': 'Editors\' Picks',
|
|
||||||
'uploader_id': 'tt-editors-picks',
|
|
||||||
'timestamp': 1453309200,
|
|
||||||
'upload_date': '20160120',
|
|
||||||
},
|
|
||||||
'add_ie': ['Youtube'],
|
|
||||||
}, {
|
}, {
|
||||||
# Tag
|
# Tag
|
||||||
'url': 'http://testtube.com/tech-news',
|
'url': 'http://revision3.com/vr',
|
||||||
'info_dict': {
|
'only_matching': True,
|
||||||
'id': '21018',
|
|
||||||
'title': 'tech news',
|
|
||||||
},
|
|
||||||
'playlist_mincount': 9,
|
|
||||||
}]
|
}]
|
||||||
_PAGE_DATA_TEMPLATE = 'http://www.%s/apiProxy/ddn/%s?domain=%s'
|
_PAGE_DATA_TEMPLATE = 'http://www.%s/apiProxy/ddn/%s?domain=%s'
|
||||||
_API_KEY = 'ba9c741bce1b9d8e3defcc22193f3651b8867e62'
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
domain, display_id = re.match(self._VALID_URL, url).groups()
|
domain, display_id = re.match(self._VALID_URL, url).groups()
|
||||||
@@ -119,33 +137,9 @@ class Revision3IE(InfoExtractor):
|
|||||||
})
|
})
|
||||||
return info
|
return info
|
||||||
|
|
||||||
video_data = self._download_json(
|
|
||||||
'http://revision3.com/api/getPlaylist.json?api_key=%s&codecs=h264,vp8,theora&video_id=%s' % (self._API_KEY, video_id),
|
|
||||||
video_id)['items'][0]
|
|
||||||
|
|
||||||
formats = []
|
|
||||||
for vcodec, media in video_data['media'].items():
|
|
||||||
for quality_id, quality in media.items():
|
|
||||||
if quality_id == 'hls':
|
|
||||||
formats.extend(self._extract_m3u8_formats(
|
|
||||||
quality['url'], video_id, 'mp4',
|
|
||||||
'm3u8_native', m3u8_id='hls', fatal=False))
|
|
||||||
else:
|
|
||||||
formats.append({
|
|
||||||
'url': quality['url'],
|
|
||||||
'format_id': '%s-%s' % (vcodec, quality_id),
|
|
||||||
'tbr': int_or_none(quality.get('bitrate')),
|
|
||||||
'vcodec': vcodec,
|
|
||||||
})
|
|
||||||
self._sort_formats(formats)
|
|
||||||
|
|
||||||
info.update({
|
info.update({
|
||||||
'title': unescapeHTML(video_data['title']),
|
'_type': 'url_transparent',
|
||||||
'description': unescapeHTML(video_data.get('summary')),
|
'url': 'revision3:%s' % video_id,
|
||||||
'uploader': video_data.get('show', {}).get('name'),
|
|
||||||
'uploader_id': video_data.get('show', {}).get('slug'),
|
|
||||||
'duration': int_or_none(video_data.get('duration')),
|
|
||||||
'formats': formats,
|
|
||||||
})
|
})
|
||||||
return info
|
return info
|
||||||
else:
|
else:
|
||||||
|
|||||||
57
youtube_dl/extractor/seeker.py
Normal file
57
youtube_dl/extractor/seeker.py
Normal file
@@ -0,0 +1,57 @@
|
|||||||
|
# coding: utf-8
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import re
|
||||||
|
|
||||||
|
from .common import InfoExtractor
|
||||||
|
|
||||||
|
|
||||||
|
class SeekerIE(InfoExtractor):
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?seeker\.com/(?P<display_id>.*)-(?P<article_id>\d+)\.html'
|
||||||
|
_TESTS = [{
|
||||||
|
# player.loadRevision3Item
|
||||||
|
'url': 'http://www.seeker.com/should-trump-be-required-to-release-his-tax-returns-1833805621.html',
|
||||||
|
'md5': '30c1dc4030cc715cf05b423d0947ac18',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '76243',
|
||||||
|
'ext': 'webm',
|
||||||
|
'title': 'Should Trump Be Required To Release His Tax Returns?',
|
||||||
|
'description': 'Donald Trump has been secretive about his "big," "beautiful" tax returns. So what can we learn if he decides to release them?',
|
||||||
|
'uploader': 'Seeker Daily',
|
||||||
|
'uploader_id': 'seekerdaily',
|
||||||
|
}
|
||||||
|
}, {
|
||||||
|
'url': 'http://www.seeker.com/changes-expected-at-zoos-following-recent-gorilla-lion-shootings-1834116536.html',
|
||||||
|
'playlist': [
|
||||||
|
{
|
||||||
|
'md5': '83bcd157cab89ad7318dd7b8c9cf1306',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '67558',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'The Pros & Cons Of Zoos',
|
||||||
|
'description': 'Zoos are often depicted as a terrible place for animals to live, but is there any truth to this?',
|
||||||
|
'uploader': 'DNews',
|
||||||
|
'uploader_id': 'dnews',
|
||||||
|
},
|
||||||
|
}
|
||||||
|
],
|
||||||
|
'info_dict': {
|
||||||
|
'id': '1834116536',
|
||||||
|
'title': 'After Gorilla Killing, Changes Ahead for Zoos',
|
||||||
|
'description': 'The largest association of zoos and others are hoping to learn from recent incidents that led to the shooting deaths of a gorilla and two lions.',
|
||||||
|
},
|
||||||
|
}]
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
display_id, article_id = re.match(self._VALID_URL, url).groups()
|
||||||
|
webpage = self._download_webpage(url, display_id)
|
||||||
|
mobj = re.search(r"player\.loadRevision3Item\('([^']+)'\s*,\s*(\d+)\);", webpage)
|
||||||
|
if mobj:
|
||||||
|
playlist_type, playlist_id = mobj.groups()
|
||||||
|
return self.url_result(
|
||||||
|
'revision3:%s:%s' % (playlist_type, playlist_id), 'Revision3Embed', playlist_id)
|
||||||
|
else:
|
||||||
|
entries = [self.url_result('revision3:video_id:%s' % video_id, 'Revision3Embed', video_id) for video_id in re.findall(
|
||||||
|
r'<iframe[^>]+src=[\'"](?:https?:)?//api\.seekernetwork\.com/player/embed\?videoId=(\d+)', webpage)]
|
||||||
|
return self.playlist_result(
|
||||||
|
entries, article_id, self._og_search_title(webpage), self._og_search_description(webpage))
|
||||||
@@ -105,9 +105,9 @@ KNOWN_EXTENSIONS = (
|
|||||||
'f4f', 'f4m', 'm3u8', 'smil')
|
'f4f', 'f4m', 'm3u8', 'smil')
|
||||||
|
|
||||||
# needed for sanitizing filenames in restricted mode
|
# needed for sanitizing filenames in restricted mode
|
||||||
ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØŒÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøœùúûüýþÿ',
|
ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ',
|
||||||
itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOO', ['OE'], 'UUUUYP', ['ss'],
|
itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOO', ['OE'], 'UUUUUYP', ['ss'],
|
||||||
'aaaaaa', ['ae'], 'ceeeeiiiionoooooo', ['oe'], 'uuuuypy')))
|
'aaaaaa', ['ae'], 'ceeeeiiiionooooooo', ['oe'], 'uuuuuypy')))
|
||||||
|
|
||||||
|
|
||||||
def preferredencoding():
|
def preferredencoding():
|
||||||
@@ -861,9 +861,13 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
|
|||||||
# As of RFC 2616 default charset is iso-8859-1 that is respected by python 3
|
# As of RFC 2616 default charset is iso-8859-1 that is respected by python 3
|
||||||
if sys.version_info >= (3, 0):
|
if sys.version_info >= (3, 0):
|
||||||
location = location.encode('iso-8859-1').decode('utf-8')
|
location = location.encode('iso-8859-1').decode('utf-8')
|
||||||
|
else:
|
||||||
|
location = location.decode('utf-8')
|
||||||
location_escaped = escape_url(location)
|
location_escaped = escape_url(location)
|
||||||
if location != location_escaped:
|
if location != location_escaped:
|
||||||
del resp.headers['Location']
|
del resp.headers['Location']
|
||||||
|
if sys.version_info < (3, 0):
|
||||||
|
location_escaped = location_escaped.encode('utf-8')
|
||||||
resp.headers['Location'] = location_escaped
|
resp.headers['Location'] = location_escaped
|
||||||
return resp
|
return resp
|
||||||
|
|
||||||
|
|||||||
@@ -1,3 +1,3 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
__version__ = '2016.06.02'
|
__version__ = '2016.06.05'
|
||||||
|
|||||||
Reference in New Issue
Block a user