1
0
mirror of https://gitlab.com/ytdl-org/youtube-dl.git synced 2026-01-24 00:00:10 -05:00

Compare commits

...

21 Commits

Author SHA1 Message Date
Sergey M․
92747e664a release 2016.06.26 2016-06-26 21:15:24 +07:00
Sergey M․
f1f336322d [msn] Fix extraction (Closes #8960, closes #9542) 2016-06-26 21:10:05 +07:00
Sergey M․
bf8dd79045 [extractor/common] Fix sorting with custom field preference 2016-06-26 21:09:07 +07:00
TRox1972
c6781156aa [MSN] add new extractor 2016-06-26 21:07:59 +07:00
Sergey M․
f484c5fa25 [vidbit] Improve (Closes #9759) 2016-06-26 16:59:28 +07:00
Sergey M․
88d9f6c0c4 [utils] Add support for name list in _html_search_meta 2016-06-26 16:57:14 +07:00
TRox1972
3c9c088f9c [Vidbit] Add new extractor 2016-06-26 16:52:52 +07:00
Yen Chi Hsuan
fc3996bfe1 [iqiyi] Remove codes for debugging 2016-06-26 15:45:41 +08:00
Yen Chi Hsuan
5b6ad8630c [iqiyi] Partially fix IqiyiIE
Use the HTML5 API. Only low-resolution formats available

Related: #9839

Thanks @zhangn1985 for the overall algorithm (soimort/you-get#1224)
2016-06-26 15:18:32 +08:00
Yen Chi Hsuan
30105f4ac0 [le] Move urshift() to utils.py 2016-06-26 15:17:26 +08:00
Yen Chi Hsuan
1143535d76 [utils] Add urshift()
Used in IqiyiIE and LeIE
2016-06-26 15:16:49 +08:00
Yen Chi Hsuan
7d52c052ef [generic] Fix test_Generic_76
Broken: https://travis-ci.org/rg3/youtube-dl/jobs/140251658
2016-06-26 11:56:27 +08:00
stepshal
a2406fce3c Fix misspelling 2016-06-26 01:28:55 +07:00
Sergey M․
3b34ab538c [svtplay] Extend _VALID_URL (#9900) 2016-06-26 00:29:53 +07:00
Sergey M․
ac782306f1 [iqiyi] Mark broken 2016-06-26 00:25:41 +07:00
Sergey M․
0c00e889f3 Credit @JakubAdamWieczorek for #9813 2016-06-25 23:35:57 +07:00
Sergey M․
ce96ed05f4 [polskieradio] Add test with video 2016-06-25 23:31:21 +07:00
Sergey M․
0463b77a1f [polskieradio] Improve extraction (Closes #9813) 2016-06-25 23:19:18 +07:00
Jakub Adam Wieczorek
2d185706ea [polskieradio] Add support for Polskie Radio.
Polskie Radio is the main Polish state-funded radio broadcasting service.
2016-06-25 23:19:18 +07:00
Sergey M․
b72b44318c [utils] Add strip_or_none 2016-06-25 23:19:18 +07:00
Sergey M․
46f59e89ea [utils] Add unified_timestamp 2016-06-25 23:19:18 +07:00
17 changed files with 583 additions and 362 deletions

View File

@@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.25*. 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 **2016.06.25**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.26*. 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 **2016.06.26**
### 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 2016.06.25
[debug] youtube-dl version 2016.06.26
[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

@@ -175,3 +175,4 @@ Tomáš Čech
Déstin Reed
Roman Tsiupa
Artur Krysiak
Jakub Adam Wieczorek

View File

@@ -385,6 +385,7 @@
- **MovieFap**
- **Moviezine**
- **MPORA**
- **MSN**
- **MTV**
- **mtv.de**
- **mtviggy.com**
@@ -501,6 +502,7 @@
- **plus.google**: Google Plus
- **pluzz.francetv.fr**
- **podomatic**
- **PolskieRadio**
- **PornHd**
- **PornHub**
- **PornHubPlaylist**
@@ -736,6 +738,7 @@
- **vh1.com**
- **Vice**
- **ViceShow**
- **Vidbit**
- **Viddler**
- **video.google:search**: Google Video search
- **video.mit.edu**

View File

@@ -11,7 +11,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL
from youtube_dl.extractor.common import InfoExtractor
from youtube_dl.extractor import YoutubeIE, get_info_extractor
from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError
from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError
class TestIE(InfoExtractor):
@@ -66,6 +66,11 @@ class TestInfoExtractor(unittest.TestCase):
self.assertEqual(ie._html_search_meta('d', html), '4')
self.assertEqual(ie._html_search_meta('e', html), '5')
self.assertEqual(ie._html_search_meta('f', html), '6')
self.assertEqual(ie._html_search_meta(('a', 'b', 'c'), html), '1')
self.assertEqual(ie._html_search_meta(('c', 'b', 'a'), html), '3')
self.assertEqual(ie._html_search_meta(('z', 'x', 'c'), html), '3')
self.assertRaises(RegexNotFoundError, ie._html_search_meta, 'z', html, None, fatal=True)
self.assertRaises(RegexNotFoundError, ie._html_search_meta, ('z', 'x'), html, None, fatal=True)
def test_download_json(self):
uri = encode_data_uri(b'{"foo": "blah"}', 'application/json')

View File

@@ -60,11 +60,13 @@ from youtube_dl.utils import (
timeconvert,
unescapeHTML,
unified_strdate,
unified_timestamp,
unsmuggle_url,
uppercase_escape,
lowercase_escape,
url_basename,
urlencode_postdata,
urshift,
update_url_query,
version_tuple,
xpath_with_ns,
@@ -283,8 +285,28 @@ class TestUtil(unittest.TestCase):
'20150202')
self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
self.assertEqual(unified_strdate('25-09-2014'), '20140925')
self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
def test_unified_timestamps(self):
self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
self.assertEqual(unified_timestamp('8/7/2009'), 1247011200)
self.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200)
self.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598)
self.assertEqual(unified_timestamp('1968 12 10'), -33436800)
self.assertEqual(unified_timestamp('1968-12-10'), -33436800)
self.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200)
self.assertEqual(
unified_timestamp('11/26/2014 11:30:00 AM PST', day_first=False),
1417001400)
self.assertEqual(
unified_timestamp('2/2/2015 6:47:40 PM', day_first=False),
1422902860)
self.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900)
self.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
def test_determine_ext(self):
self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
@@ -959,5 +981,9 @@ The first line
self.assertRaises(ValueError, encode_base_n, 0, 70)
self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
def test_urshift(self):
self.assertEqual(urshift(3, 1), 1)
self.assertEqual(urshift(-3, 1), 2147483646)
if __name__ == '__main__':
unittest.main()

View File

@@ -749,10 +749,12 @@ class InfoExtractor(object):
return self._og_search_property('url', html, **kargs)
def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs):
if not isinstance(name, (list, tuple)):
name = [name]
if display_name is None:
display_name = name
display_name = name[0]
return self._html_search_regex(
self._meta_regex(name),
[self._meta_regex(n) for n in name],
html, display_name, fatal=fatal, group='content', **kwargs)
def _dc_search_uploader(self, html):
@@ -876,7 +878,11 @@ class InfoExtractor(object):
f['ext'] = determine_ext(f['url'])
if isinstance(field_preference, (list, tuple)):
return tuple(f.get(field) if f.get(field) is not None else -1 for field in field_preference)
return tuple(
f.get(field)
if f.get(field) is not None
else ('' if field == 'format_id' else -1)
for field in field_preference)
preference = f.get('preference')
if preference is None:

View File

@@ -454,6 +454,7 @@ from .motherless import MotherlessIE
from .motorsport import MotorsportIE
from .movieclips import MovieClipsIE
from .moviezine import MoviezineIE
from .msn import MSNIE
from .mtv import (
MTVIE,
MTVServicesEmbeddedIE,
@@ -606,6 +607,7 @@ from .pluralsight import (
PluralsightCourseIE,
)
from .podomatic import PodomaticIE
from .polskieradio import PolskieRadioIE
from .porn91 import Porn91IE
from .pornhd import PornHdIE
from .pornhub import (
@@ -915,6 +917,7 @@ from .vice import (
ViceIE,
ViceShowIE,
)
from .vidbit import VidbitIE
from .viddler import ViddlerIE
from .videodetective import VideoDetectiveIE
from .videofyme import VideofyMeIE

View File

@@ -1091,12 +1091,17 @@ class GenericIE(InfoExtractor):
# Dailymotion Cloud video
{
'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
'md5': '49444254273501a64675a7e68c502681',
'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
'info_dict': {
'id': '5585de919473990de4bee11b',
'id': 'x2uy8t3',
'ext': 'mp4',
'title': 'Le débat',
'title': 'Sauvons les abeilles ! - Le débat',
'description': 'md5:d9082128b1c5277987825d684939ca26',
'thumbnail': 're:^https?://.*\.jpe?g$',
'timestamp': 1434970506,
'upload_date': '20150622',
'uploader': 'Public Sénat',
'uploader_id': 'xa9gza',
}
},
# OnionStudios embed

View File

@@ -1,30 +1,25 @@
# coding: utf-8
from __future__ import unicode_literals
import binascii
import hashlib
import itertools
import math
import os
import random
import re
import time
import uuid
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
)
from ..utils import (
decode_packed_codes,
ExtractorError,
intlist_to_bytes,
ohdave_rsa_encrypt,
remove_start,
sanitized_Request,
urlencode_postdata,
url_basename,
urshift,
)
@@ -171,70 +166,21 @@ class IqiyiIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.iqiyi.com/v_19rrojlavg.html',
'md5': '2cb594dc2781e6c941a110d8f358118b',
'md5': '470a6c160618577166db1a7aac5a3606',
'info_dict': {
'id': '9c1fb1b99d192b21c559e5a1a2cb3c73',
'ext': 'mp4',
'title': '美国德州空中惊现奇异云团 酷似UFO',
'ext': 'f4v',
}
}, {
'url': 'http://www.iqiyi.com/v_19rrhnnclk.html',
'md5': 'f09f0a6a59b2da66a26bf4eda669a4cc',
'info_dict': {
'id': 'e3f585b550a280af23c98b6cb2be19fb',
'title': '名侦探柯南第752集',
},
'playlist': [{
'info_dict': {
'id': 'e3f585b550a280af23c98b6cb2be19fb_part1',
'ext': 'f4v',
'title': '名侦探柯南第752集',
},
}, {
'info_dict': {
'id': 'e3f585b550a280af23c98b6cb2be19fb_part2',
'ext': 'f4v',
'title': '名侦探柯南第752集',
},
}, {
'info_dict': {
'id': 'e3f585b550a280af23c98b6cb2be19fb_part3',
'ext': 'f4v',
'title': '名侦探柯南第752集',
},
}, {
'info_dict': {
'id': 'e3f585b550a280af23c98b6cb2be19fb_part4',
'ext': 'f4v',
'title': '名侦探柯南第752集',
},
}, {
'info_dict': {
'id': 'e3f585b550a280af23c98b6cb2be19fb_part5',
'ext': 'f4v',
'title': '名侦探柯南第752集',
},
}, {
'info_dict': {
'id': 'e3f585b550a280af23c98b6cb2be19fb_part6',
'ext': 'f4v',
'title': '名侦探柯南第752集',
},
}, {
'info_dict': {
'id': 'e3f585b550a280af23c98b6cb2be19fb_part7',
'ext': 'f4v',
'title': '名侦探柯南第752集',
},
}, {
'info_dict': {
'id': 'e3f585b550a280af23c98b6cb2be19fb_part8',
'ext': 'f4v',
'title': '名侦探柯南第752集',
},
}],
'params': {
'skip_download': True,
'ext': 'mp4',
'title': '名侦探柯南 国语版',
},
'skip': 'Geo-restricted to China',
}, {
'url': 'http://www.iqiyi.com/w_19rt6o8t9p.html',
'only_matching': True,
@@ -287,13 +233,6 @@ class IqiyiIE(InfoExtractor):
('10', 'h1'),
]
AUTH_API_ERRORS = {
# No preview available (不允许试看鉴权失败)
'Q00505': 'This video requires a VIP account',
# End of preview time (试看结束鉴权失败)
'Q00506': 'Needs a VIP account for full video',
}
def _real_initialize(self):
self._login()
@@ -352,177 +291,101 @@ class IqiyiIE(InfoExtractor):
return True
def _authenticate_vip_video(self, api_video_url, video_id, tvid, _uuid, do_report_warning):
auth_params = {
# version and platform hard-coded in com/qiyi/player/core/model/remote/AuthenticationRemote.as
'version': '2.0',
'platform': 'b6c13e26323c537d',
'aid': tvid,
@staticmethod
def _gen_sc(tvid, timestamp):
M = [1732584193, -271733879]
M.extend([~M[0], ~M[1]])
I_table = [7, 12, 17, 22, 5, 9, 14, 20, 4, 11, 16, 23, 6, 10, 15, 21]
C_base = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8388608, 432]
def L(n, t):
if t is None:
t = 0
return trunc(((n >> 1) + (t >> 1) << 1) + (n & 1) + (t & 1))
def trunc(n):
n = n % 0x100000000
if n > 0x7fffffff:
n -= 0x100000000
return n
def transform(string, mod):
num = int(string, 16)
return (num >> 8 * (i % 4) & 255 ^ i % mod) << ((a & 3) << 3)
C = list(C_base)
o = list(M)
k = str(timestamp - 7)
for i in range(13):
a = i
C[a >> 2] |= ord(k[a]) << 8 * (a % 4)
for i in range(16):
a = i + 13
start = (i >> 2) * 8
r = '03967743b643f66763d623d637e30733'
C[a >> 2] |= transform(''.join(reversed(r[start:start + 8])), 7)
for i in range(16):
a = i + 29
start = (i >> 2) * 8
r = '7038766939776a32776a32706b337139'
C[a >> 2] |= transform(r[start:start + 8], 1)
for i in range(9):
a = i + 45
if i < len(tvid):
C[a >> 2] |= ord(tvid[i]) << 8 * (a % 4)
for a in range(64):
i = a
I = i >> 4
C_index = [i, 5 * i + 1, 3 * i + 5, 7 * i][I] % 16 + urshift(a, 6)
m = L(L(o[0], [
trunc(o[1] & o[2]) | trunc(~o[1] & o[3]),
trunc(o[3] & o[1]) | trunc(~o[3] & o[2]),
o[1] ^ o[2] ^ o[3],
o[2] ^ trunc(o[1] | ~o[3])
][I]), L(
trunc(int(abs(math.sin(i + 1)) * 4294967296)),
C[C_index] if C_index < len(C) else None))
I = I_table[4 * I + i % 4]
o = [o[3],
L(o[1], trunc(trunc(m << I) | urshift(m, 32 - I))),
o[1],
o[2]]
new_M = [L(o[0], M[0]), L(o[1], M[1]), L(o[2], M[2]), L(o[3], M[3])]
s = [new_M[a >> 3] >> (1 ^ a & 7) * 4 & 15 for a in range(32)]
return binascii.hexlify(intlist_to_bytes(s))[1::2].decode('ascii')
def get_raw_data(self, tvid, video_id):
tm = int(time.time() * 1000)
sc = self._gen_sc(tvid, tm)
params = {
'platForm': 'h5',
'rate': 1,
'tvid': tvid,
'uid': '',
'deviceId': _uuid,
'playType': 'main', # XXX: always main?
'filename': os.path.splitext(url_basename(api_video_url))[0],
}
qd_items = compat_parse_qs(compat_urllib_parse_urlparse(api_video_url).query)
for key, val in qd_items.items():
auth_params[key] = val[0]
auth_req = sanitized_Request(
'http://api.vip.iqiyi.com/services/ckn.action',
urlencode_postdata(auth_params))
# iQiyi server throws HTTP 405 error without the following header
auth_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
auth_result = self._download_json(
auth_req, video_id,
note='Downloading video authentication JSON',
errnote='Unable to download video authentication JSON')
code = auth_result.get('code')
msg = self.AUTH_API_ERRORS.get(code) or auth_result.get('msg') or code
if code == 'Q00506':
if do_report_warning:
self.report_warning(msg)
return False
if 'data' not in auth_result:
if msg is not None:
raise ExtractorError('%s said: %s' % (self.IE_NAME, msg), expected=True)
raise ExtractorError('Unexpected error from Iqiyi auth API')
return auth_result['data']
def construct_video_urls(self, data, video_id, _uuid, tvid):
def do_xor(x, y):
a = y % 3
if a == 1:
return x ^ 121
if a == 2:
return x ^ 72
return x ^ 103
def get_encode_code(l):
a = 0
b = l.split('-')
c = len(b)
s = ''
for i in range(c - 1, -1, -1):
a = do_xor(int(b[c - i - 1], 16), i)
s += chr(a)
return s[::-1]
def get_path_key(x, format_id, segment_index):
mg = ')(*&^flash@#$%a'
tm = self._download_json(
'http://data.video.qiyi.com/t?tn=' + str(random.random()), video_id,
note='Download path key of segment %d for format %s' % (segment_index + 1, format_id)
)['t']
t = str(int(math.floor(int(tm) / (600.0))))
return md5_text(t + mg + x)
video_urls_dict = {}
need_vip_warning_report = True
for format_item in data['vp']['tkl'][0]['vs']:
if 0 < int(format_item['bid']) <= 10:
format_id = self.get_format(format_item['bid'])
else:
continue
video_urls = []
video_urls_info = format_item['fs']
if not format_item['fs'][0]['l'].startswith('/'):
t = get_encode_code(format_item['fs'][0]['l'])
if t.endswith('mp4'):
video_urls_info = format_item['flvs']
for segment_index, segment in enumerate(video_urls_info):
vl = segment['l']
if not vl.startswith('/'):
vl = get_encode_code(vl)
is_vip_video = '/vip/' in vl
filesize = segment['b']
base_url = data['vp']['du'].split('/')
if not is_vip_video:
key = get_path_key(
vl.split('/')[-1].split('.')[0], format_id, segment_index)
base_url.insert(-1, key)
base_url = '/'.join(base_url)
param = {
'su': _uuid,
'qyid': uuid.uuid4().hex,
'client': '',
'z': '',
'bt': '',
'ct': '',
'tn': str(int(time.time()))
}
api_video_url = base_url + vl
if is_vip_video:
api_video_url = api_video_url.replace('.f4v', '.hml')
auth_result = self._authenticate_vip_video(
api_video_url, video_id, tvid, _uuid, need_vip_warning_report)
if auth_result is False:
need_vip_warning_report = False
break
param.update({
't': auth_result['t'],
# cid is hard-coded in com/qiyi/player/core/player/RuntimeData.as
'cid': 'afbe8fd3d73448c9',
'vid': video_id,
'QY00001': auth_result['u'],
})
api_video_url += '?' if '?' not in api_video_url else '&'
api_video_url += compat_urllib_parse_urlencode(param)
js = self._download_json(
api_video_url, video_id,
note='Download video info of segment %d for format %s' % (segment_index + 1, format_id))
video_url = js['l']
video_urls.append(
(video_url, filesize))
video_urls_dict[format_id] = video_urls
return video_urls_dict
def get_format(self, bid):
matched_format_ids = [_format_id for _bid, _format_id in self._FORMATS_MAP if _bid == str(bid)]
return matched_format_ids[0] if len(matched_format_ids) else None
def get_bid(self, format_id):
matched_bids = [_bid for _bid, _format_id in self._FORMATS_MAP if _format_id == format_id]
return matched_bids[0] if len(matched_bids) else None
def get_raw_data(self, tvid, video_id, enc_key, _uuid):
tm = str(int(time.time()))
tail = tm + tvid
param = {
'key': 'fvip',
'src': md5_text('youtube-dl'),
'tvId': tvid,
'vid': video_id,
'vinfo': 1,
'tm': tm,
'enc': md5_text(enc_key + tail),
'qyid': _uuid,
'tn': random.random(),
# In iQiyi's flash player, um is set to 1 if there's a logged user
# Some 1080P formats are only available with a logged user.
# Here force um=1 to trick the iQiyi server
'um': 1,
'authkey': md5_text(md5_text('') + tail),
'k_tag': 1,
'cupid': 'qc_100001_100186',
'type': 'mp4',
'nolimit': 0,
'agenttype': 13,
'src': 'd846d0c32d664d32b6b54ea48997a589',
'sc': sc,
't': tm - 7,
'__jsT': None,
}
api_url = 'http://cache.video.qiyi.com/vms' + '?' + \
compat_urllib_parse_urlencode(param)
raw_data = self._download_json(api_url, video_id)
return raw_data
def get_enc_key(self, video_id):
# TODO: automatic key extraction
# last update at 2016-01-22 for Zombie::bite
enc_key = '4a1caba4b4465345366f28da7c117d20'
return enc_key
headers = {}
cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
if cn_verification_proxy:
headers['Ytdl-request-proxy'] = cn_verification_proxy
return self._download_json(
'http://cache.m.iqiyi.com/jp/tmts/%s/%s/' % (tvid, video_id),
video_id, transform_source=lambda s: remove_start(s, 'var tvInfoJs='),
query=params, headers=headers)
def _extract_playlist(self, webpage):
PAGE_SIZE = 50
@@ -571,58 +434,27 @@ class IqiyiIE(InfoExtractor):
r'data-player-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid')
video_id = self._search_regex(
r'data-player-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id')
_uuid = uuid.uuid4().hex
enc_key = self.get_enc_key(video_id)
for _ in range(5):
raw_data = self.get_raw_data(tvid, video_id)
raw_data = self.get_raw_data(tvid, video_id, enc_key, _uuid)
if raw_data['code'] != 'A00000':
if raw_data['code'] == 'A00111':
self.raise_geo_restricted()
raise ExtractorError('Unable to load data. Error code: ' + raw_data['code'])
if raw_data['code'] != 'A000000':
raise ExtractorError('Unable to load data. Error code: ' + raw_data['code'])
data = raw_data['data']
data = raw_data['data']
# iQiYi sometimes returns Ads
if not isinstance(data['playInfo'], dict):
self._sleep(5, video_id)
continue
title = data['vi']['vn']
title = data['playInfo']['an']
break
# generate video_urls_dict
video_urls_dict = self.construct_video_urls(
data, video_id, _uuid, tvid)
# construct info
entries = []
for format_id in video_urls_dict:
video_urls = video_urls_dict[format_id]
for i, video_url_info in enumerate(video_urls):
if len(entries) < i + 1:
entries.append({'formats': []})
entries[i]['formats'].append(
{
'url': video_url_info[0],
'filesize': video_url_info[-1],
'format_id': format_id,
'preference': int(self.get_bid(format_id))
}
)
for i in range(len(entries)):
self._sort_formats(entries[i]['formats'])
entries[i].update(
{
'id': '%s_part%d' % (video_id, i + 1),
'title': title,
}
)
if len(entries) > 1:
info = {
'_type': 'multi_video',
'id': video_id,
'title': title,
'entries': entries,
}
else:
info = entries[0]
info['id'] = video_id
info['title'] = title
return info
return {
'id': video_id,
'title': title,
'url': data['m3u'],
}

View File

@@ -23,6 +23,7 @@ from ..utils import (
sanitized_Request,
str_or_none,
url_basename,
urshift,
)
@@ -74,15 +75,11 @@ class LeIE(InfoExtractor):
'only_matching': True,
}]
@staticmethod
def urshift(val, n):
return val >> n if val >= 0 else (val + 0x100000000) >> n
# ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf
def ror(self, param1, param2):
_loc3_ = 0
while _loc3_ < param2:
param1 = self.urshift(param1, 1) + ((param1 & 1) << 31)
param1 = urshift(param1, 1) + ((param1 & 1) << 31)
_loc3_ += 1
return param1

119
youtube_dl/extractor/msn.py Normal file
View File

@@ -0,0 +1,119 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
unescapeHTML,
)
class MSNIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?msn\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/[a-z]{2}-(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'http://www.msn.com/en-ae/foodanddrink/joinourtable/criminal-minds-shemar-moore-shares-a-touching-goodbye-message/vp-BBqQYNE',
'md5': '8442f66c116cbab1ff7098f986983458',
'info_dict': {
'id': 'BBqQYNE',
'display_id': 'criminal-minds-shemar-moore-shares-a-touching-goodbye-message',
'ext': 'mp4',
'title': 'Criminal Minds - Shemar Moore Shares A Touching Goodbye Message',
'description': 'md5:e8e89b897b222eb33a6b5067a8f1bc25',
'duration': 104,
'uploader': 'CBS Entertainment',
'uploader_id': 'IT0X5aoJ6bJgYerJXSDCgFmYPB1__54v',
},
}, {
'url': 'http://www.msn.com/en-ae/news/offbeat/meet-the-nine-year-old-self-made-millionaire/ar-BBt6ZKf',
'only_matching': True,
}, {
'url': 'http://www.msn.com/en-ae/video/watch/obama-a-lot-of-people-will-be-disappointed/vi-AAhxUMH',
'only_matching': True,
}, {
# geo restricted
'url': 'http://www.msn.com/en-ae/foodanddrink/joinourtable/the-first-fart-makes-you-laugh-the-last-fart-makes-you-cry/vp-AAhzIBU',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id, display_id = mobj.group('id', 'display_id')
webpage = self._download_webpage(url, display_id)
video = self._parse_json(
self._search_regex(
r'data-metadata\s*=\s*(["\'])(?P<data>.+?)\1',
webpage, 'video data', default='{}', group='data'),
display_id, transform_source=unescapeHTML)
if not video:
error = unescapeHTML(self._search_regex(
r'data-error=(["\'])(?P<error>.+?)\1',
webpage, 'error', group='error'))
raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
title = video['title']
formats = []
for file_ in video.get('videoFiles', []):
format_url = file_.get('url')
if not format_url:
continue
ext = determine_ext(format_url)
# .ism is not yet supported (see
# https://github.com/rg3/youtube-dl/issues/8118)
if ext == 'ism':
continue
if 'm3u8' in format_url:
# m3u8_native should not be used here until
# https://github.com/rg3/youtube-dl/issues/9913 is fixed
m3u8_formats = self._extract_m3u8_formats(
format_url, display_id, 'mp4',
m3u8_id='hls', fatal=False)
# Despite metadata in m3u8 all video+audio formats are
# actually video-only (no audio)
for f in m3u8_formats:
if f.get('acodec') != 'none' and f.get('vcodec') != 'none':
f['acodec'] = 'none'
formats.extend(m3u8_formats)
else:
formats.append({
'url': format_url,
'ext': 'mp4',
'format_id': 'http',
'width': int_or_none(file_.get('width')),
'height': int_or_none(file_.get('height')),
})
self._sort_formats(formats)
subtitles = {}
for file_ in video.get('files', []):
format_url = file_.get('url')
format_code = file_.get('formatCode')
if not format_url or not format_code:
continue
if compat_str(format_code) == '3100':
subtitles.setdefault(file_.get('culture', 'en'), []).append({
'ext': determine_ext(format_url, 'ttml'),
'url': format_url,
})
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': video.get('description'),
'thumbnail': video.get('headlineImage', {}).get('url'),
'duration': int_or_none(video.get('durationSecs')),
'uploader': video.get('sourceFriendly'),
'uploader_id': video.get('providerId'),
'creator': video.get('creator'),
'subtitles': subtitles,
'formats': formats,
}

View File

@@ -0,0 +1,95 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse_unquote,
)
from ..utils import (
int_or_none,
strip_or_none,
unified_timestamp,
)
class PolskieRadioIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?polskieradio\.pl/\d+/\d+/Artykul/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://www.polskieradio.pl/7/5102/Artykul/1587943,Prof-Andrzej-Nowak-o-historii-nie-da-sie-myslec-beznamietnie',
'info_dict': {
'id': '1587943',
'title': 'Prof. Andrzej Nowak: o historii nie da się myśleć beznamiętnie',
'description': 'md5:12f954edbf3120c5e7075e17bf9fc5c5',
},
'playlist': [{
'md5': '2984ee6ce9046d91fc233bc1a864a09a',
'info_dict': {
'id': '1540576',
'ext': 'mp3',
'title': 'md5:d4623290d4ac983bf924061c75c23a0d',
'timestamp': 1456594200,
'upload_date': '20160227',
'duration': 2364,
},
}],
}, {
'url': 'http://www.polskieradio.pl/265/5217/Artykul/1635803,Euro-2016-nie-ma-miejsca-na-blad-Polacy-graja-ze-Szwajcaria-o-cwiercfinal',
'info_dict': {
'id': '1635803',
'title': 'Euro 2016: nie ma miejsca na błąd. Polacy grają ze Szwajcarią o ćwierćfinał',
'description': 'md5:01cb7d0cad58664095d72b51a1ebada2',
},
'playlist_mincount': 12,
}, {
'url': 'http://polskieradio.pl/9/305/Artykul/1632955,Bardzo-popularne-slowo-remis',
'only_matching': True,
}, {
'url': 'http://www.polskieradio.pl/7/5102/Artykul/1587943',
'only_matching': True,
}, {
# with mp4 video
'url': 'http://www.polskieradio.pl/9/299/Artykul/1634903,Brexit-Leszek-Miller-swiat-sie-nie-zawali-Europa-bedzie-trwac-dalej',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
content = self._search_regex(
r'(?s)<div[^>]+class="audio atarticle"[^>]*>(.+?)<script>',
webpage, 'content')
timestamp = unified_timestamp(self._html_search_regex(
r'(?s)<span[^>]+id="datetime2"[^>]*>(.+?)</span>',
webpage, 'timestamp', fatal=False))
entries = []
media_urls = set()
for data_media in re.findall(r'<[^>]+data-media=({[^>]+})', content):
media = self._parse_json(data_media, playlist_id, fatal=False)
if not media.get('file') or not media.get('desc'):
continue
media_url = self._proto_relative_url(media['file'], 'http:')
if media_url in media_urls:
continue
media_urls.add(media_url)
entries.append({
'id': compat_str(media['id']),
'url': media_url,
'title': compat_urllib_parse_unquote(media['desc']),
'duration': int_or_none(media.get('length')),
'vcodec': 'none' if media.get('provider') == 'audio' else None,
'timestamp': timestamp,
})
title = self._og_search_title(webpage).strip()
description = strip_or_none(self._og_search_description(webpage))
return self.playlist_result(entries, playlist_id, title, description)

View File

@@ -120,7 +120,7 @@ class SVTIE(SVTBaseIE):
class SVTPlayIE(SVTBaseIE):
IE_DESC = 'SVT Play and Öppet arkiv'
_VALID_URL = r'https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/video/(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp)/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2',
'md5': '2b6704fe4a28801e1a098bbf3c5ac611',
@@ -141,6 +141,9 @@ class SVTPlayIE(SVTBaseIE):
# geo restricted to Sweden
'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
'only_matching': True,
}, {
'url': 'http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@@ -0,0 +1,84 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
int_or_none,
js_to_json,
remove_end,
unified_strdate,
)
class VidbitIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vidbit\.co/(?:watch|embed)\?.*?\bv=(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'http://www.vidbit.co/watch?v=jkL2yDOEq2',
'md5': '1a34b7f14defe3b8fafca9796892924d',
'info_dict': {
'id': 'jkL2yDOEq2',
'ext': 'mp4',
'title': 'Intro to VidBit',
'description': 'md5:5e0d6142eec00b766cbf114bfd3d16b7',
'thumbnail': 're:https?://.*\.jpg$',
'upload_date': '20160618',
'view_count': int,
'comment_count': int,
}
}, {
'url': 'http://www.vidbit.co/embed?v=jkL2yDOEq2&auto=0&water=0',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
compat_urlparse.urljoin(url, '/watch?v=%s' % video_id), video_id)
video_url, title = [None] * 2
config = self._parse_json(self._search_regex(
r'(?s)\.setup\(({.+?})\);', webpage, 'setup', default='{}'),
video_id, transform_source=js_to_json)
if config:
if config.get('file'):
video_url = compat_urlparse.urljoin(url, config['file'])
title = config.get('title')
if not video_url:
video_url = compat_urlparse.urljoin(url, self._search_regex(
r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'video URL', group='url'))
if not title:
title = remove_end(
self._html_search_regex(
(r'<h1>(.+?)</h1>', r'<title>(.+?)</title>'),
webpage, 'title', default=None) or self._og_search_title(webpage),
' - VidBit')
description = self._html_search_meta(
('description', 'og:description', 'twitter:description'),
webpage, 'description')
upload_date = unified_strdate(self._html_search_meta(
'datePublished', webpage, 'upload date'))
view_count = int_or_none(self._search_regex(
r'<strong>(\d+)</strong> views',
webpage, 'view count', fatal=False))
comment_count = int_or_none(self._search_regex(
r'id=["\']cmt_num["\'][^>]*>\((\d+)\)',
webpage, 'comment count', fatal=False))
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': self._og_search_thumbnail(webpage),
'upload_date': upload_date,
'view_count': view_count,
'comment_count': comment_count,
}

View File

@@ -76,7 +76,7 @@ class Socks4Error(ProxyError):
CODES = {
91: 'request rejected or failed',
92: 'request rejected becasue SOCKS server cannot connect to identd on the client',
92: 'request rejected because SOCKS server cannot connect to identd on the client',
93: 'request rejected because the client program and identd report different user-ids'
}

View File

@@ -110,6 +110,49 @@ ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙ
itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOO', ['OE'], 'UUUUUYP', ['ss'],
'aaaaaa', ['ae'], 'ceeeeiiiionooooooo', ['oe'], 'uuuuuypy')))
DATE_FORMATS = (
'%d %B %Y',
'%d %b %Y',
'%B %d %Y',
'%b %d %Y',
'%b %dst %Y %I:%M',
'%b %dnd %Y %I:%M',
'%b %dth %Y %I:%M',
'%Y %m %d',
'%Y-%m-%d',
'%Y/%m/%d',
'%Y/%m/%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S.%f',
'%d.%m.%Y %H:%M',
'%d.%m.%Y %H.%M',
'%Y-%m-%dT%H:%M:%SZ',
'%Y-%m-%dT%H:%M:%S.%fZ',
'%Y-%m-%dT%H:%M:%S.%f0Z',
'%Y-%m-%dT%H:%M:%S',
'%Y-%m-%dT%H:%M:%S.%f',
'%Y-%m-%dT%H:%M',
)
DATE_FORMATS_DAY_FIRST = list(DATE_FORMATS)
DATE_FORMATS_DAY_FIRST.extend([
'%d-%m-%Y',
'%d.%m.%Y',
'%d.%m.%y',
'%d/%m/%Y',
'%d/%m/%y',
'%d/%m/%Y %H:%M:%S',
])
DATE_FORMATS_MONTH_FIRST = list(DATE_FORMATS)
DATE_FORMATS_MONTH_FIRST.extend([
'%m-%d-%Y',
'%m.%d.%Y',
'%m/%d/%Y',
'%m/%d/%y',
'%m/%d/%Y %H:%M:%S',
])
def preferredencoding():
"""Get preferred encoding.
@@ -975,6 +1018,24 @@ class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor):
https_response = http_response
def extract_timezone(date_str):
m = re.search(
r'^.{8,}?(?P<tz>Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',
date_str)
if not m:
timezone = datetime.timedelta()
else:
date_str = date_str[:-len(m.group('tz'))]
if not m.group('sign'):
timezone = datetime.timedelta()
else:
sign = 1 if m.group('sign') == '+' else -1
timezone = datetime.timedelta(
hours=sign * int(m.group('hours')),
minutes=sign * int(m.group('minutes')))
return timezone, date_str
def parse_iso8601(date_str, delimiter='T', timezone=None):
""" Return a UNIX timestamp from the given date """
@@ -984,20 +1045,8 @@ def parse_iso8601(date_str, delimiter='T', timezone=None):
date_str = re.sub(r'\.[0-9]+', '', date_str)
if timezone is None:
m = re.search(
r'(?:Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',
date_str)
if not m:
timezone = datetime.timedelta()
else:
date_str = date_str[:-len(m.group(0))]
if not m.group('sign'):
timezone = datetime.timedelta()
else:
sign = 1 if m.group('sign') == '+' else -1
timezone = datetime.timedelta(
hours=sign * int(m.group('hours')),
minutes=sign * int(m.group('minutes')))
timezone, date_str = extract_timezone(date_str)
try:
date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
dt = datetime.datetime.strptime(date_str, date_format) - timezone
@@ -1006,6 +1055,10 @@ def parse_iso8601(date_str, delimiter='T', timezone=None):
pass
def date_formats(day_first=True):
return DATE_FORMATS_DAY_FIRST if day_first else DATE_FORMATS_MONTH_FIRST
def unified_strdate(date_str, day_first=True):
"""Return a string with the date in the format YYYYMMDD"""
@@ -1014,53 +1067,11 @@ def unified_strdate(date_str, day_first=True):
upload_date = None
# Replace commas
date_str = date_str.replace(',', ' ')
# %z (UTC offset) is only supported in python>=3.2
if not re.match(r'^[0-9]{1,2}-[0-9]{1,2}-[0-9]{4}$', date_str):
date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
# Remove AM/PM + timezone
date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
_, date_str = extract_timezone(date_str)
format_expressions = [
'%d %B %Y',
'%d %b %Y',
'%B %d %Y',
'%b %d %Y',
'%b %dst %Y %I:%M',
'%b %dnd %Y %I:%M',
'%b %dth %Y %I:%M',
'%Y %m %d',
'%Y-%m-%d',
'%Y/%m/%d',
'%Y/%m/%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S.%f',
'%d.%m.%Y %H:%M',
'%d.%m.%Y %H.%M',
'%Y-%m-%dT%H:%M:%SZ',
'%Y-%m-%dT%H:%M:%S.%fZ',
'%Y-%m-%dT%H:%M:%S.%f0Z',
'%Y-%m-%dT%H:%M:%S',
'%Y-%m-%dT%H:%M:%S.%f',
'%Y-%m-%dT%H:%M',
]
if day_first:
format_expressions.extend([
'%d-%m-%Y',
'%d.%m.%Y',
'%d.%m.%y',
'%d/%m/%Y',
'%d/%m/%y',
'%d/%m/%Y %H:%M:%S',
])
else:
format_expressions.extend([
'%m-%d-%Y',
'%m.%d.%Y',
'%m/%d/%Y',
'%m/%d/%y',
'%m/%d/%Y %H:%M:%S',
])
for expression in format_expressions:
for expression in date_formats(day_first):
try:
upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
except ValueError:
@@ -1076,6 +1087,29 @@ def unified_strdate(date_str, day_first=True):
return compat_str(upload_date)
def unified_timestamp(date_str, day_first=True):
if date_str is None:
return None
date_str = date_str.replace(',', ' ')
pm_delta = datetime.timedelta(hours=12 if re.search(r'(?i)PM', date_str) else 0)
timezone, date_str = extract_timezone(date_str)
# Remove AM/PM + timezone
date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
for expression in date_formats(day_first):
try:
dt = datetime.datetime.strptime(date_str, expression) - timezone + pm_delta
return calendar.timegm(dt.timetuple())
except ValueError:
pass
timetuple = email.utils.parsedate_tz(date_str)
if timetuple:
return calendar.timegm(timetuple.timetuple())
def determine_ext(url, default_ext='unknown_video'):
if url is None:
return default_ext
@@ -1626,6 +1660,10 @@ def float_or_none(v, scale=1, invscale=1, default=None):
return default
def strip_or_none(v):
return None if v is None else v.strip()
def parse_duration(s):
if not isinstance(s, compat_basestring):
return None
@@ -2861,3 +2899,7 @@ def parse_m3u8_attributes(attrib):
val = val[1:-1]
info[key] = val
return info
def urshift(val, n):
return val >> n if val >= 0 else (val + 0x100000000) >> n

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2016.06.25'
__version__ = '2016.06.26'