R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'master' of https://github.com/rg3/youtube-dl

Browse Source
This commit is contained in:
Gilles Habran 2016-06-02 13:32:32 +02:00
commit c47a6d5240
4 changed files with 115 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
test/test_http.py
View File

@ -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()

4
test/test_utils.py
View File

@ -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')

59
youtube_dl/extractor/bilibili.py
View File

@ -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;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;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;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;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;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;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;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;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;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;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,

10
youtube_dl/utils.py
View File

@ -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