Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-03 05:47:55 +01:00
Code Issues Releases Wiki Activity

Merge branch 'master' of https://github.com/speakerender/youtube-dl into directvnow-auth-fix

Browse Source
This commit is contained in:
SpeakerEnder 2019-05-26 19:30:53 -04:00
commit b729ea0ad5
85 changed files with 841 additions and 932 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/ISSUE_TEMPLATE/1_broken_site.md vendored
View File

@ -18,7 +18,7 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.04.30. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.05.20. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support
- [ ] I've verified that I'm running youtube-dl version **2019.04.30**
- [ ] I've verified that I'm running youtube-dl version **2019.05.20**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar issues including closed ones
@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[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 2019.04.30
[debug] youtube-dl version 2019.05.20
[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: {}

4
.github/ISSUE_TEMPLATE/2_site_support_request.md vendored
View File

@ -19,7 +19,7 @@ labels: 'site-support-request'
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.04.30. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.05.20. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
- Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a new site support request
- [ ] I've verified that I'm running youtube-dl version **2019.04.30**
- [ ] I've verified that I'm running youtube-dl version **2019.05.20**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that none of provided URLs violate any copyrights
- [ ] I've searched the bugtracker for similar site support requests including closed ones

4
.github/ISSUE_TEMPLATE/3_site_feature_request.md vendored
View File

@ -18,13 +18,13 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.04.30. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.05.20. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x])
-->
- [ ] I'm reporting a site feature request
- [ ] I've verified that I'm running youtube-dl version **2019.04.30**
- [ ] I've verified that I'm running youtube-dl version **2019.05.20**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones

6
.github/ISSUE_TEMPLATE/4_bug_report.md vendored
View File

@ -18,7 +18,7 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.04.30. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.05.20. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support issue
- [ ] I've verified that I'm running youtube-dl version **2019.04.30**
- [ ] I've verified that I'm running youtube-dl version **2019.05.20**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar bug reports including closed ones
@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[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 2019.04.30
[debug] youtube-dl version 2019.05.20
[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: {}

4
.github/ISSUE_TEMPLATE/5_feature_request.md vendored
View File

@ -19,13 +19,13 @@ labels: 'request'
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.04.30. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.05.20. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x])
-->
- [ ] I'm reporting a feature request
- [ ] I've verified that I'm running youtube-dl version **2019.04.30**
- [ ] I've verified that I'm running youtube-dl version **2019.05.20**
- [ ] I've searched the bugtracker for similar feature requests including closed ones

1
.travis.yml
View File

@ -9,6 +9,7 @@ python:
- "3.6"
- "pypy"
- "pypy3"
dist: trusty
env:
- YTDL_TEST_SET=core
- YTDL_TEST_SET=download

42
ChangeLog
View File

@ -1,3 +1,45 @@
version 2019.05.20
Core
+ [extractor/common] Move workaround for applying first Set-Cookie header
into a separate _apply_first_set_cookie_header method
Extractors
* [safari] Fix authentication (#21090)
* [vk] Use _apply_first_set_cookie_header
* [vrt] Fix extraction (#20527)
+ [canvas] Add support for vrtnieuws and sporza site ids and extract
AES HLS formats
+ [vrv] Extract captions (#19238)
* [tele5] Improve video id extraction
* [tele5] Relax URL regular expression (#21020, #21063)
* [svtplay] Update API URL (#21075)
+ [yahoo:gyao] Add X-User-Agent header to dam proxy requests (#21071)
version 2019.05.11
Core
* [utils] Transliterate "þ" as "th" (#20897)
Extractors
+ [cloudflarestream] Add support for videodelivery.net (#21049)
+ [byutv] Add support for DVR videos (#20574, #20676)
+ [gfycat] Add support for URLs with tags (#20696, #20731)
+ [openload] Add support for verystream.com (#20701, #20967)
* [youtube] Use sp field value for signature field name (#18841, #18927,
#21028)
+ [yahoo:gyao] Extend URL regular expression (#21008)
* [youtube] Fix channel id extraction (#20982, #21003)
+ [sky] Add support for news.sky.com (#13055)
+ [youtube:entrylistbase] Retry on 5xx HTTP errors (#20965)
+ [francetvinfo] Extend video id extraction (#20619, #20740)
* [4tube] Update token hosts (#20918)
* [hotstar] Move to API v2 (#20931)
* [fox] Fix API error handling under python 2 (#20925)
+ [redbulltv] Extend URL regular expression (#20922)
version 2019.04.30
Extractors

8
devscripts/check-porn.py
View File

@ -45,12 +45,12 @@ for test in gettestcases():
RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST)
if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict'] or
test['info_dict']['age_limit'] != 18):
if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict']
or test['info_dict']['age_limit'] != 18):
print('\nPotential missing age_limit check: {0}'.format(test['name']))
elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict'] and
test['info_dict']['age_limit'] == 18):
elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict']
and test['info_dict']['age_limit'] == 18):
print('\nPotential false negative: {0}'.format(test['name']))
else:

4
docs/supportedsites.md
View File

@ -805,6 +805,7 @@
- **ShowRoomLive**
- **Sina**
- **SkylineWebcams**
- **SkyNews**
- **skynewsarabia:article**
- **skynewsarabia:video**
- **SkySports**
@ -999,6 +1000,7 @@
- **Vbox7**
- **VeeHD**
- **Veoh**
- **verystream**
- **Vessel**
- **Vesti**: Вести.Ru
- **Vevo**
@ -1069,7 +1071,7 @@
- **VoxMediaVolume**
- **vpro**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
- **Vrak**
- **VRT**: deredactie.be, sporza.be, cobra.be and cobra.canvas.be
- **VRT**: VRT NWS, Flanders News, Flandern Info and Sporza
- **VrtNU**: VrtNU.be
- **vrv**
- **vrv:series**

2
setup.cfg
View File

@ -3,4 +3,4 @@ universal = True
[flake8]
exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git,venv
ignore = E402,E501,E731,E741
ignore = E402,E501,E731,E741,W503

8
test/test_aes.py
View File

@ -44,16 +44,16 @@ class TestAES(unittest.TestCase):
def test_decrypt_text(self):
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8]) +
b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
intlist_to_bytes(self.iv[:8])
+ b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
).decode('utf-8')
decrypted = (aes_decrypt_text(encrypted, password, 16))
self.assertEqual(decrypted, self.secret_msg)
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8]) +
b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
intlist_to_bytes(self.iv[:8])
+ b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
).decode('utf-8')
decrypted = (aes_decrypt_text(encrypted, password, 32))
self.assertEqual(decrypted, self.secret_msg)

4
test/test_swfinterp.py
View File

@ -34,8 +34,8 @@ def _make_testfunc(testfile):
def test_func(self):
as_file = os.path.join(TEST_DIR, testfile)
swf_file = os.path.join(TEST_DIR, test_id + '.swf')
if ((not os.path.exists(swf_file)) or
os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
if ((not os.path.exists(swf_file))
or os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
# Recompile
try:
subprocess.check_call([

15
test/test_utils.py
View File

@ -73,6 +73,7 @@ from youtube_dl.utils import (
smuggle_url,
str_to_int,
strip_jsonp,
strip_or_none,
timeconvert,
unescapeHTML,
unified_strdate,
@ -183,7 +184,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(sanitize_filename(
'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True),
'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy')
'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYTHssaaaaaaaeceeeeiiiionooooooooeuuuuuythy')
def test_sanitize_ids(self):
self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
@ -752,6 +753,18 @@ class TestUtil(unittest.TestCase):
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
def test_strip_or_none(self):
self.assertEqual(strip_or_none(' abc'), 'abc')
self.assertEqual(strip_or_none('abc '), 'abc')
self.assertEqual(strip_or_none(' abc '), 'abc')
self.assertEqual(strip_or_none('\tabc\t'), 'abc')
self.assertEqual(strip_or_none('\n\tabc\n\t'), 'abc')
self.assertEqual(strip_or_none('abc'), 'abc')
self.assertEqual(strip_or_none(''), '')
self.assertEqual(strip_or_none(None), None)
self.assertEqual(strip_or_none(42), None)
self.assertEqual(strip_or_none([]), None)
def test_uppercase_escape(self):
self.assertEqual(uppercase_escape('aä'), 'aä')
self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')

42
youtube_dl/YoutubeDL.py
View File

@ -400,9 +400,9 @@ class YoutubeDL(object):
else:
raise
if (sys.platform != 'win32' and
sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] and
not params.get('restrictfilenames', False)):
if (sys.platform != 'win32'
and sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968']
and not params.get('restrictfilenames', False)):
# Unicode filesystem API will throw errors (#1474, #13027)
self.report_warning(
'Assuming --restrict-filenames since file system encoding '
@ -440,9 +440,9 @@ class YoutubeDL(object):
if re.match(r'^-[0-9A-Za-z_-]{10}$', a)]
if idxs:
correct_argv = (
['youtube-dl'] +
[a for i, a in enumerate(argv) if i not in idxs] +
['--'] + [argv[i] for i in idxs]
['youtube-dl']
+ [a for i, a in enumerate(argv) if i not in idxs]
+ ['--'] + [argv[i] for i in idxs]
)
self.report_warning(
'Long argument string detected. '
@ -850,8 +850,8 @@ class YoutubeDL(object):
if result_type in ('url', 'url_transparent'):
ie_result['url'] = sanitize_url(ie_result['url'])
extract_flat = self.params.get('extract_flat', False)
if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or
extract_flat is True):
if ((extract_flat == 'in_playlist' and 'playlist' in extra_info)
or extract_flat is True):
if self.params.get('forcejson', False):
self.to_stdout(json.dumps(ie_result))
return ie_result
@ -1619,9 +1619,9 @@ class YoutubeDL(object):
# https://github.com/ytdl-org/youtube-dl/issues/10083).
incomplete_formats = (
# All formats are video-only or
all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats) or
all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats)
# all formats are audio-only
all(f.get('vcodec') == 'none' and f.get('acodec') != 'none' for f in formats))
or all(f.get('vcodec') == 'none' and f.get('acodec') != 'none' for f in formats))
ctx = {
'formats': formats,
@ -1947,8 +1947,8 @@ class YoutubeDL(object):
else:
assert fixup_policy in ('ignore', 'never')
if (info_dict.get('requested_formats') is None and
info_dict.get('container') == 'm4a_dash'):
if (info_dict.get('requested_formats') is None
and info_dict.get('container') == 'm4a_dash'):
if fixup_policy == 'warn':
self.report_warning(
'%s: writing DASH m4a. '
@ -1967,9 +1967,9 @@ class YoutubeDL(object):
else:
assert fixup_policy in ('ignore', 'never')
if (info_dict.get('protocol') == 'm3u8_native' or
info_dict.get('protocol') == 'm3u8' and
self.params.get('hls_prefer_native')):
if (info_dict.get('protocol') == 'm3u8_native'
or info_dict.get('protocol') == 'm3u8'
and self.params.get('hls_prefer_native')):
if fixup_policy == 'warn':
self.report_warning('%s: malformed AAC bitstream detected.' % (
info_dict['id']))
@ -1995,10 +1995,10 @@ class YoutubeDL(object):
def download(self, url_list):
"""Download a given list of URLs."""
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
if (len(url_list) > 1 and
outtmpl != '-' and
'%' not in outtmpl and
self.params.get('max_downloads') != 1):
if (len(url_list) > 1
and outtmpl != '-'
and '%' not in outtmpl
and self.params.get('max_downloads') != 1):
raise SameFileError(outtmpl)
for url in url_list:
@ -2143,8 +2143,8 @@ class YoutubeDL(object):
if res:
res += ', '
res += '%s container' % fdict['container']
if (fdict.get('vcodec') is not None and
fdict.get('vcodec') != 'none'):
if (fdict.get('vcodec') is not None
and fdict.get('vcodec') != 'none'):
if res:
res += ', '
res += fdict['vcodec']

16
youtube_dl/__init__.py
View File

@ -230,14 +230,14 @@ def _real_main(argv=None):
if opts.allsubtitles and not opts.writeautomaticsub:
opts.writesubtitles = True
outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
(opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
(opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
(opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or
(opts.usetitle and '%(title)s-%(id)s.%(ext)s') or
(opts.useid and '%(id)s.%(ext)s') or
(opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or
DEFAULT_OUTTMPL)
outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
or (opts.useid and '%(id)s.%(ext)s')
or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
or DEFAULT_OUTTMPL)
if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
parser.error('Cannot download a video and extract audio into the same'
' file! Use "{0}.%(ext)s" instead of "{0}" as the output'

6
youtube_dl/compat.py
View File

@ -2649,9 +2649,9 @@ else:
try:
args = shlex.split('中文')
assert (isinstance(args, list) and
isinstance(args[0], compat_str) and
args[0] == '中文')
assert (isinstance(args, list)
and isinstance(args[0], compat_str)
and args[0] == '中文')
compat_shlex_split = shlex.split
except (AssertionError, UnicodeEncodeError):
# Working around shlex issue with unicode strings on some python 2

10
youtube_dl/downloader/common.py
View File

@ -330,15 +330,15 @@ class FileDownloader(object):
"""
nooverwrites_and_exists = (
self.params.get('nooverwrites', False) and
os.path.exists(encodeFilename(filename))
self.params.get('nooverwrites', False)
and os.path.exists(encodeFilename(filename))
)
if not hasattr(filename, 'write'):
continuedl_and_exists = (
self.params.get('continuedl', True) and
os.path.isfile(encodeFilename(filename)) and
not self.params.get('nopart', False)
self.params.get('continuedl', True)
and os.path.isfile(encodeFilename(filename))
and not self.params.get('nopart', False)
)
# Check file already present

8
youtube_dl/downloader/f4m.py
View File

@ -238,8 +238,8 @@ def write_metadata_tag(stream, metadata):
def remove_encrypted_media(media):
return list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib and
'drmAdditionalHeaderSetId' not in e.attrib,
return list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib
and 'drmAdditionalHeaderSetId' not in e.attrib,
media))
@ -267,8 +267,8 @@ class F4mFD(FragmentFD):
media = doc.findall(_add_ns('media'))
if not media:
self.report_error('No media found')
for e in (doc.findall(_add_ns('drmAdditionalHeader')) +
doc.findall(_add_ns('drmAdditionalHeaderSet'))):
for e in (doc.findall(_add_ns('drmAdditionalHeader'))
+ doc.findall(_add_ns('drmAdditionalHeaderSet'))):
# If id attribute is missing it's valid for all media nodes
# without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
if 'id' not in e.attrib:

4
youtube_dl/downloader/fragment.py
View File

@ -219,8 +219,8 @@ class FragmentFD(FileDownloader):
frag_total_bytes = s.get('total_bytes') or 0
if not ctx['live']:
estimated_size = (
(ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) /
(state['fragment_index'] + 1) * total_frags)
(ctx['complete_frags_downloaded_bytes'] + frag_total_bytes)
/ (state['fragment_index'] + 1) * total_frags)
state['total_bytes_estimate'] = estimated_size
if s['status'] == 'finished':

8
youtube_dl/downloader/hls.py
View File

@ -76,12 +76,12 @@ class HlsFD(FragmentFD):
return fd.real_download(filename, info_dict)
def is_ad_fragment_start(s):
return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s or
s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad'))
return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s
or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad'))
def is_ad_fragment_end(s):
return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s or
s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment'))
return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s
or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment'))
media_frags = 0
ad_frags = 0

14
youtube_dl/downloader/http.py
View File

@ -46,8 +46,8 @@ class HttpFD(FileDownloader):
is_test = self.params.get('test', False)
chunk_size = self._TEST_FILE_SIZE if is_test else (
info_dict.get('downloader_options', {}).get('http_chunk_size') or
self.params.get('http_chunk_size') or 0)
info_dict.get('downloader_options', {}).get('http_chunk_size')
or self.params.get('http_chunk_size') or 0)
ctx.open_mode = 'wb'
ctx.resume_len = 0
@ -123,11 +123,11 @@ class HttpFD(FileDownloader):
content_len = int_or_none(content_range_m.group(3))
accept_content_len = (
# Non-chunked download
not ctx.chunk_size or
not ctx.chunk_size
# Chunked download and requested piece or
# its part is promised to be served
content_range_end == range_end or
content_len < range_end)
or content_range_end == range_end
or content_len < range_end)
if accept_content_len:
ctx.data_len = content_len
return
@ -152,8 +152,8 @@ class HttpFD(FileDownloader):
raise
else:
# Examine the reported length
if (content_length is not None and
(ctx.resume_len - 100 < int(content_length) < ctx.resume_len + 100)):
if (content_length is not None
and (ctx.resume_len - 100 < int(content_length) < ctx.resume_len + 100)):
# The file had already been fully downloaded.
# Explanation to the above condition: in issue #175 it was revealed that
# YouTube sometimes adds or removes a few bytes from the end of the file,

6
youtube_dl/extractor/addanime.py
View File

@ -59,9 +59,9 @@ class AddAnimeIE(InfoExtractor):
parsed_url = compat_urllib_parse_urlparse(url)
av_val = av_res + len(parsed_url.netloc)
confirm_url = (
parsed_url.scheme + '://' + parsed_url.netloc +
action + '?' +
compat_urllib_parse_urlencode({
parsed_url.scheme + '://' + parsed_url.netloc
+ action + '?'
+ compat_urllib_parse_urlencode({
'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
self._download_webpage(
confirm_url, video_id,

5
youtube_dl/extractor/bitchute.py
View File

@ -65,8 +65,9 @@ class BitChuteIE(InfoExtractor):
webpage, default=None) or self._html_search_meta(
'twitter:image:src', webpage, 'thumbnail')
uploader = self._html_search_regex(
r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>', webpage,
'uploader', fatal=False)
(r'(?s)<div class=["\']channel-banner.*?<p\b[^>]+\bclass=["\']name[^>]+>(.+?)</p>',
r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'),
webpage, 'uploader', fatal=False)
return {
'id': video_id,

4
youtube_dl/extractor/blinkx.py
View File

@ -32,8 +32,8 @@ class BlinkxIE(InfoExtractor):
video_id = self._match_id(url)
display_id = video_id[:8]
api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' +
'video=%s' % video_id)
api_url = ('https://apib4.blinkx.com/api.php?action=play_video&'
+ 'video=%s' % video_id)
data_json = self._download_webpage(api_url, display_id)
data = json.loads(data_json)['api']['results'][0]
duration = None

50
youtube_dl/extractor/byutv.py
View File

@ -3,11 +3,13 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import parse_duration
class BYUtvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?byutv\.org/(?:watch|player)/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?'
_TESTS = [{
# ooyalaVOD
'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
'info_dict': {
'id': 'ZvanRocTpW-G5_yZFeltTAMv6jxOU9KH',
@ -22,6 +24,20 @@ class BYUtvIE(InfoExtractor):
'skip_download': True,
},
'add_ie': ['Ooyala'],
}, {
# dvr
'url': 'https://www.byutv.org/player/8f1dab9b-b243-47c8-b525-3e2d021a3451/byu-softball-pacific-vs-byu-41219---game-2',
'info_dict': {
'id': '8f1dab9b-b243-47c8-b525-3e2d021a3451',
'display_id': 'byu-softball-pacific-vs-byu-41219---game-2',
'ext': 'mp4',
'title': 'Pacific vs. BYU (4/12/19)',
'description': 'md5:1ac7b57cb9a78015910a4834790ce1f3',
'duration': 11645,
},
'params': {
'skip_download': True
},
}, {
'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
'only_matching': True,
@ -35,24 +51,42 @@ class BYUtvIE(InfoExtractor):
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
ep = self._download_json(
'https://api.byutv.org/api3/catalog/getvideosforcontent', video_id,
query={
info = self._download_json(
'https://api.byutv.org/api3/catalog/getvideosforcontent',
display_id, query={
'contentid': video_id,
'channel': 'byutv',
'x-byutv-context': 'web$US',
}, headers={
'x-byutv-context': 'web$US',
'x-byutv-platformkey': 'xsaaw9c7y5',
})['ooyalaVOD']
})
ep = info.get('ooyalaVOD')
if ep:
return {
'_type': 'url_transparent',
'ie_key': 'Ooyala',
'url': 'ooyala:%s' % ep['providerId'],
'id': video_id,
'display_id': display_id,
'title': ep.get('title'),
'description': ep.get('description'),
'thumbnail': ep.get('imageThumbnail'),
}
ep = info['dvr']
title = ep['title']
formats = self._extract_m3u8_formats(
ep['videoUrl'], video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
self._sort_formats(formats)
return {
'_type': 'url_transparent',
'ie_key': 'Ooyala',
'url': 'ooyala:%s' % ep['providerId'],
'id': video_id,
'display_id': display_id,
'title': ep.get('title'),
'title': title,
'description': ep.get('description'),
'thumbnail': ep.get('imageThumbnail'),
'duration': parse_duration(ep.get('length')),
'formats': formats,
}

10
youtube_dl/extractor/canvas.py
View File

@ -17,7 +17,7 @@ from ..utils import (
class CanvasIE(InfoExtractor):
_VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrtvideo)/assets/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza)/assets/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
'md5': '90139b746a0a9bd7bb631283f6e2a64e',
@ -35,6 +35,10 @@ class CanvasIE(InfoExtractor):
'url': 'https://mediazone.vrt.be/api/v1/canvas/assets/mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e',
'only_matching': True,
}]
_HLS_ENTRY_PROTOCOLS_MAP = {
'HLS': 'm3u8_native',
'HLS_AES': 'm3u8',
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@ -52,9 +56,9 @@ class CanvasIE(InfoExtractor):
format_url, format_type = target.get('url'), target.get('type')
if not format_url or not format_type:
continue
if format_type == 'HLS':
if format_type in self._HLS_ENTRY_PROTOCOLS_MAP:
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
format_url, video_id, 'mp4', self._HLS_ENTRY_PROTOCOLS_MAP[format_type],
m3u8_id=format_type, fatal=False))
elif format_type == 'HDS':
formats.extend(self._extract_f4m_formats(

9
youtube_dl/extractor/cloudflarestream.py
View File

@ -10,8 +10,8 @@ class CloudflareStreamIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
(?:watch\.)?cloudflarestream\.com/|
embed\.cloudflarestream\.com/embed/[^/]+\.js\?.*?\bvideo=
(?:watch\.)?(?:cloudflarestream\.com|videodelivery\.net)/|
embed\.(?:cloudflarestream\.com|videodelivery\.net)/embed/[^/]+\.js\?.*?\bvideo=
)
(?P<id>[\da-f]+)
'''
@ -31,6 +31,9 @@ class CloudflareStreamIE(InfoExtractor):
}, {
'url': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/manifest/video.mpd',
'only_matching': True,
}, {
'url': 'https://embed.videodelivery.net/embed/r4xu.fla9.latest.js?video=81d80727f3022488598f68d323c1ad5e',
'only_matching': True,
}]
@staticmethod
@ -38,7 +41,7 @@ class CloudflareStreamIE(InfoExtractor):
return [
mobj.group('url')
for mobj in re.finditer(
r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.cloudflarestream\.com/embed/[^/]+\.js\?.*?\bvideo=[\da-f]+?.*?)\1',
r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.(?:cloudflarestream\.com|videodelivery\.net)/embed/[^/]+\.js\?.*?\bvideo=[\da-f]+?.*?)\1',
webpage)]
def _real_extract(self, url):

76
youtube_dl/extractor/common.py
View File

@ -67,6 +67,7 @@ from ..utils import (
sanitized_Request,
sanitize_filename,
str_or_none,
strip_or_none,
unescapeHTML,
unified_strdate,
unified_timestamp,
@ -117,7 +118,7 @@ class InfoExtractor(object):
unfragmented media)
- URL of the MPD manifest or base URL
representing the media if MPD manifest
is parsed froma string (in case of
is parsed from a string (in case of
fragmented media)
for MSS - URL of the ISM manifest.
* manifest_url
@ -542,11 +543,11 @@ class InfoExtractor(object):
raise ExtractorError('An extractor error has occurred.', cause=e)
def __maybe_fake_ip_and_retry(self, countries):
if (not self._downloader.params.get('geo_bypass_country', None) and
self._GEO_BYPASS and
self._downloader.params.get('geo_bypass', True) and
not self._x_forwarded_for_ip and
countries):
if (not self._downloader.params.get('geo_bypass_country', None)
and self._GEO_BYPASS
and self._downloader.params.get('geo_bypass', True)
and not self._x_forwarded_for_ip
and countries):
country_code = random.choice(countries)
self._x_forwarded_for_ip = GeoUtils.random_ipv4(country_code)
if self._x_forwarded_for_ip:
@ -682,8 +683,8 @@ class InfoExtractor(object):
def __check_blocked(self, content):
first_block = content[:512]
if ('<title>Access to this site is blocked</title>' in content and
'Websense' in first_block):
if ('<title>Access to this site is blocked</title>' in content
and 'Websense' in first_block):
msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
blocked_iframe = self._html_search_regex(
r'<iframe src="([^"]+)"', content,
@ -701,8 +702,8 @@ class InfoExtractor(object):
if block_msg:
msg += ' (Message: "%s")' % block_msg.replace('\n', ' ')
raise ExtractorError(msg, expected=True)
if ('<title>TTK :: Доступ к ресурсу ограничен</title>' in content and
'blocklist.rkn.gov.ru' in content):
if ('<title>TTK :: Доступ к ресурсу ограничен</title>' in content
and 'blocklist.rkn.gov.ru' in content):
raise ExtractorError(
'Access to this webpage has been blocked by decision of the Russian government. '
'Visit http://blocklist.rkn.gov.ru/ for a block reason.',
@ -1709,8 +1710,8 @@ class InfoExtractor(object):
continue
else:
tbr = float_or_none(
last_stream_inf.get('AVERAGE-BANDWIDTH') or
last_stream_inf.get('BANDWIDTH'), scale=1000)
last_stream_inf.get('AVERAGE-BANDWIDTH')
or last_stream_inf.get('BANDWIDTH'), scale=1000)
format_id = []
if m3u8_id:
format_id.append(m3u8_id)
@ -2480,7 +2481,7 @@ class InfoExtractor(object):
'subtitles': {},
}
media_attributes = extract_attributes(media_tag)
src = media_attributes.get('src')
src = strip_or_none(media_attributes.get('src'))
if src:
_, formats = _media_formats(src, media_type)
media_info['formats'].extend(formats)
@ -2490,7 +2491,7 @@ class InfoExtractor(object):
s_attr = extract_attributes(source_tag)
# data-video-src and data-src are non standard but seen
# several times in the wild
src = dict_get(s_attr, ('src', 'data-video-src', 'data-src'))
src = strip_or_none(dict_get(s_attr, ('src', 'data-video-src', 'data-src')))
if not src:
continue
f = parse_content_type(s_attr.get('type'))
@ -2504,8 +2505,8 @@ class InfoExtractor(object):
if str_or_none(s_attr.get(lbl))
]
width = int_or_none(s_attr.get('width'))
height = (int_or_none(s_attr.get('height')) or
int_or_none(s_attr.get('res')))
height = (int_or_none(s_attr.get('height'))
or int_or_none(s_attr.get('res')))
if not width or not height:
for lbl in labels:
resolution = parse_resolution(lbl)
@ -2533,7 +2534,7 @@ class InfoExtractor(object):
track_attributes = extract_attributes(track_tag)
kind = track_attributes.get('kind')
if not kind or kind in ('subtitles', 'captions'):
src = track_attributes.get('src')
src = strip_or_none(track_attributes.get('src'))
if not src:
continue
lang = track_attributes.get('srclang') or track_attributes.get('lang') or track_attributes.get('label')
@ -2817,6 +2818,33 @@ class InfoExtractor(object):
self._downloader.cookiejar.add_cookie_header(req)
return compat_cookies.SimpleCookie(req.get_header('Cookie'))
def _apply_first_set_cookie_header(self, url_handle, cookie):
"""
Apply first Set-Cookie header instead of the last. Experimental.
Some sites (e.g. [1-3]) may serve two cookies under the same name
in Set-Cookie header and expect the first (old) one to be set rather
than second (new). However, as of RFC6265 the newer one cookie
should be set into cookie store what actually happens.
We will workaround this issue by resetting the cookie to
the first one manually.
1. https://new.vk.com/
2. https://github.com/ytdl-org/youtube-dl/issues/9841#issuecomment-227871201
3. https://learning.oreilly.com/
"""
for header, cookies in url_handle.headers.items():
if header.lower() != 'set-cookie':
continue
if sys.version_info[0] >= 3:
cookies = cookies.encode('iso-8859-1')
cookies = cookies.decode('utf-8')
cookie_value = re.search(
r'%s=(.+?);.*?\b[Dd]omain=(.+?)(?:[,;]|$)' % cookie, cookies)
if cookie_value:
value, domain = cookie_value.groups()
self._set_cookie(domain, cookie, value)
break
def get_testcases(self, include_onlymatching=False):
t = getattr(self, '_TEST', None)
if t:
@ -2847,8 +2875,8 @@ class InfoExtractor(object):
return not any_restricted
def extract_subtitles(self, *args, **kwargs):
if (self._downloader.params.get('writesubtitles', False) or
self._downloader.params.get('listsubtitles')):
if (self._downloader.params.get('writesubtitles', False)
or self._downloader.params.get('listsubtitles')):
return self._get_subtitles(*args, **kwargs)
return {}
@ -2873,8 +2901,8 @@ class InfoExtractor(object):
return ret
def extract_automatic_captions(self, *args, **kwargs):
if (self._downloader.params.get('writeautomaticsub', False) or
self._downloader.params.get('listsubtitles')):
if (self._downloader.params.get('writeautomaticsub', False)
or self._downloader.params.get('listsubtitles')):
return self._get_automatic_captions(*args, **kwargs)
return {}
@ -2882,9 +2910,9 @@ class InfoExtractor(object):
raise NotImplementedError('This method must be implemented by subclasses')
def mark_watched(self, *args, **kwargs):
if (self._downloader.params.get('mark_watched', False) and
(self._get_login_info()[0] is not None or
self._downloader.params.get('cookiefile') is not None)):
if (self._downloader.params.get('mark_watched', False)
and (self._get_login_info()[0] is not None
or self._downloader.params.get('cookiefile') is not None)):
self._mark_watched(*args, **kwargs)
def _mark_watched(self, *args, **kwargs):

28
youtube_dl/extractor/commonmistakes.py
View File

@ -32,19 +32,19 @@ class CommonMistakesIE(InfoExtractor):
class UnicodeBOMIE(InfoExtractor):
IE_DESC = False
_VALID_URL = r'(?P<bom>\ufeff)(?P<id>.*)$'
IE_DESC = False
_VALID_URL = r'(?P<bom>\ufeff)(?P<id>.*)$'
# Disable test for python 3.2 since BOM is broken in re in this version
# (see https://github.com/ytdl-org/youtube-dl/issues/9751)
_TESTS = [] if (3, 0) < sys.version_info <= (3, 3) else [{
'url': '\ufeffhttp://www.youtube.com/watch?v=BaW_jenozKc',
'only_matching': True,
}]
# Disable test for python 3.2 since BOM is broken in re in this version
# (see https://github.com/ytdl-org/youtube-dl/issues/9751)
_TESTS = [] if (3, 0) < sys.version_info <= (3, 3) else [{
'url': '\ufeffhttp://www.youtube.com/watch?v=BaW_jenozKc',
'only_matching': True,
}]
def _real_extract(self, url):
real_url = self._match_id(url)
self.report_warning(
'Your URL starts with a Byte Order Mark (BOM). '
'Removing the BOM and looking for "%s" ...' % real_url)
return self.url_result(real_url)
def _real_extract(self, url):
real_url = self._match_id(url)
self.report_warning(
'Your URL starts with a Byte Order Mark (BOM). '
'Removing the BOM and looking for "%s" ...' % real_url)
return self.url_result(real_url)

39
youtube_dl/extractor/criterion.py
View File

@ -1,39 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class CriterionIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?criterion\.com/films/(?P<id>[0-9]+)-.+'
_TEST = {
'url': 'http://www.criterion.com/films/184-le-samourai',
'md5': 'bc51beba55685509883a9a7830919ec3',
'info_dict': {
'id': '184',
'ext': 'mp4',
'title': 'Le Samouraï',
'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
'thumbnail': r're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
final_url = self._search_regex(
r'so\.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
title = self._og_search_title(webpage)
description = self._html_search_meta('description', webpage)
thumbnail = self._search_regex(
r'so\.addVariable\("thumbnailURL", "(.+?)"\)\;',
webpage, 'thumbnail url')
return {
'id': video_id,
'url': final_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
}

4
youtube_dl/extractor/dailymail.py
View File

@ -45,8 +45,8 @@ class DailyMailIE(InfoExtractor):
sources_url = (try_get(
video_data,
(lambda x: x['plugins']['sources']['url'],
lambda x: x['sources']['url']), compat_str) or
'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id)
lambda x: x['sources']['url']), compat_str)
or 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id)
video_sources = self._download_json(sources_url, video_id)
body = video_sources.get('body')

4
youtube_dl/extractor/dctp.py
View File

@ -70,8 +70,8 @@ class DctpTvIE(InfoExtractor):
endpoint = next(
server['endpoint']
for server in servers
if url_or_none(server.get('endpoint')) and
'cloudfront' in server['endpoint'])
if url_or_none(server.get('endpoint'))
and 'cloudfront' in server['endpoint'])
else:
endpoint = 'rtmpe://s2pqqn4u96e4j8.cloudfront.net/cfx/st/'

4
youtube_dl/extractor/expressen.py
View File

@ -82,8 +82,8 @@ class ExpressenIE(InfoExtractor):
title = info.get('titleRaw') or data['title']
description = info.get('descriptionRaw')
thumbnail = info.get('socialMediaImage') or data.get('image')
duration = int_or_none(info.get('videoTotalSecondsDuration') or
data.get('totalSecondsDuration'))
duration = int_or_none(info.get('videoTotalSecondsDuration')
or data.get('totalSecondsDuration'))
timestamp = unified_timestamp(info.get('publishDate'))
return {

19
youtube_dl/extractor/extractors.py
View File

@ -240,7 +240,6 @@ from .condenast import CondeNastIE
from .corus import CorusIE
from .cracked import CrackedIE
from .crackle import CrackleIE
from .criterion import CriterionIE
from .crooksandliars import CrooksAndLiarsIE
from .crunchyroll import (
CrunchyrollIE,
@ -772,13 +771,6 @@ from .nova import (
NovaEmbedIE,
NovaIE,
)
from .novamov import (
AuroraVidIE,
CloudTimeIE,
NowVideoIE,
VideoWeedIE,
WholeCloudIE,
)
from .nowness import (
NownessIE,
NownessPlaylistIE,
@ -833,7 +825,10 @@ from .ooyala import (
OoyalaIE,
OoyalaExternalIE,
)
from .openload import OpenloadIE
from .openload import (
OpenloadIE,
VerystreamIE,
)
from .ora import OraTVIE
from .orf import (
ORFTVthekIE,
@ -893,7 +888,6 @@ from .polskieradio import (
from .popcorntv import PopcornTVIE
from .porn91 import Porn91IE
from .porncom import PornComIE
from .pornflip import PornFlipIE
from .pornhd import PornHdIE
from .pornhub import (
PornHubIE,
@ -1033,7 +1027,10 @@ from .skynewsarabia import (
SkyNewsArabiaIE,
SkyNewsArabiaArticleIE,
)
from .skysports import SkySportsIE
from .sky import (
SkyNewsIE,
SkySportsIE,
)
from .slideshare import SlideshareIE
from .slideslive import SlidesLiveIE
from .slutload import SlutloadIE

5
youtube_dl/extractor/fourtube.py
View File

@ -22,8 +22,6 @@ from ..utils import (
class FourTubeBaseIE(InfoExtractor):
_TKN_HOST = 'tkn.kodicdn.com'
def _extract_formats(self, url, video_id, media_id, sources):
token_url = 'https://%s/%s/desktop/%s' % (
self._TKN_HOST, media_id, '+'.join(sources))
@ -120,6 +118,7 @@ class FourTubeIE(FourTubeBaseIE):
IE_NAME = '4tube'
_VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?4tube\.com/(?:videos|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
_URL_TEMPLATE = 'https://www.4tube.com/videos/%s/video'
_TKN_HOST = 'token.4tube.com'
_TESTS = [{
'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
'md5': '6516c8ac63b03de06bc8eac14362db4f',
@ -149,6 +148,7 @@ class FourTubeIE(FourTubeBaseIE):
class FuxIE(FourTubeBaseIE):
_VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?fux\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
_URL_TEMPLATE = 'https://www.fux.com/video/%s/video'
_TKN_HOST = 'token.fux.com'
_TESTS = [{
'url': 'https://www.fux.com/video/195359/awesome-fucking-kitchen-ends-cum-swallow',
'info_dict': {
@ -280,6 +280,7 @@ class PornTubeIE(FourTubeBaseIE):
class PornerBrosIE(FourTubeBaseIE):
_VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?pornerbros\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)'
_URL_TEMPLATE = 'https://www.pornerbros.com/videos/video_%s'
_TKN_HOST = 'token.pornerbros.com'
_TESTS = [{
'url': 'https://www.pornerbros.com/videos/skinny-brunette-takes-big-cock-down-her-anal-hole_181369',
'md5': '6516c8ac63b03de06bc8eac14362db4f',

9
youtube_dl/extractor/francetv.py
View File

@ -371,12 +371,13 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
self.url_result(dailymotion_url, DailymotionIE.ie_key())
for dailymotion_url in dailymotion_urls])
video_id, catalogue = self._search_regex(
(r'id-video=([^@]+@[^"]+)',
video_id = self._search_regex(
(r'player\.load[^;]+src:\s*["\']([^"\']+)',
r'id-video=([^@]+@[^"]+)',
r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"'),
webpage, 'video id').split('@')
webpage, 'video id')
return self._make_url_result(video_id, catalogue)
return self._make_url_result(video_id)
class FranceTVInfoSportIE(FranceTVBaseInfoExtractor):

4
youtube_dl/extractor/frontendmasters.py
View File

@ -94,8 +94,8 @@ class FrontendMastersPageBaseIE(FrontendMastersBaseIE):
chapter_number = None
index = lesson.get('index')
element_index = lesson.get('elementIndex')
if (isinstance(index, int) and isinstance(element_index, int) and
index < element_index):
if (isinstance(index, int) and isinstance(element_index, int)
and index < element_index):
chapter_number = element_index - index
chapter = (chapters[chapter_number - 1]
if chapter_number - 1 < len(chapters) else None)

38
youtube_dl/extractor/generic.py
View File

@ -89,7 +89,10 @@ from .piksel import PikselIE
from .videa import VideaIE
from .twentymin import TwentyMinutenIE
from .ustream import UstreamIE
from .openload import OpenloadIE
from .openload import (
OpenloadIE,
VerystreamIE,
)
from .videopress import VideoPressIE
from .rutube import RutubeIE
from .limelight import LimelightBaseIE
@ -2546,11 +2549,11 @@ class GenericIE(InfoExtractor):
return self.url_result(mobj.group('url'))
# Look for Ooyala videos
mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
if mobj is not None:
embed_token = self._search_regex(
r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
@ -2580,19 +2583,6 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return self.url_result(mobj.group(1), 'Mpora')
# Look for embedded NovaMov-based player
mobj = re.search(
r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
(?P<url>http://(?:(?:embed|www)\.)?
(?:novamov\.com|
nowvideo\.(?:ch|sx|eu|at|ag|co)|
videoweed\.(?:es|com)|
movshare\.(?:net|sx|ag)|
divxstage\.(?:eu|net|ch|co|at|ag))
/embed\.php.+?)\1''', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for embedded Facebook player
facebook_urls = FacebookIE._extract_urls(webpage)
if facebook_urls:
@ -3017,6 +3007,12 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
# Look for Verystream embeds
verystream_urls = VerystreamIE._extract_urls(webpage)
if verystream_urls:
return self.playlist_from_matches(
verystream_urls, video_id, video_title, ie=VerystreamIE.ie_key())
# Look for VideoPress embeds
videopress_urls = VideoPressIE._extract_urls(webpage)
if videopress_urls:
@ -3212,8 +3208,8 @@ class GenericIE(InfoExtractor):
else:
formats.append({
'url': src,
'ext': (mimetype2ext(src_type) or
ext if ext in KNOWN_EXTENSIONS else 'mp4'),
'ext': (mimetype2ext(src_type)
or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
})
if formats:
self._sort_formats(formats)

5
youtube_dl/extractor/gfycat.py
View File

@ -11,7 +11,7 @@ from ..utils import (
class GfycatIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?:ifr/|gifs/detail/)?(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?:ifr/|gifs/detail/)?(?P<id>[^-/?#]+)'
_TESTS = [{
'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
'info_dict': {
@ -47,6 +47,9 @@ class GfycatIE(InfoExtractor):
}, {
'url': 'https://gfycat.com/gifs/detail/UnconsciousLankyIvorygull',
'only_matching': True
}, {
'url': 'https://gfycat.com/acceptablehappygoluckyharborporpoise-baseball',
'only_matching': True
}]
def _real_extract(self, url):

4
youtube_dl/extractor/heise.py
View File

@ -155,8 +155,8 @@ class HeiseIE(InfoExtractor):
'id': video_id,
'title': title,
'description': description,
'thumbnail': (xpath_text(doc, './/{http://rss.jwpcdn.com/}image') or
self._og_search_thumbnail(webpage)),
'thumbnail': (xpath_text(doc, './/{http://rss.jwpcdn.com/}image')
or self._og_search_thumbnail(webpage)),
'timestamp': parse_iso8601(
self._html_search_meta('date', webpage)),
'formats': formats,

4
youtube_dl/extractor/hitbox.py
View File

@ -58,8 +58,8 @@ class HitboxIE(InfoExtractor):
title = video_meta.get('media_status')
alt_title = video_meta.get('media_title')
description = clean_html(
video_meta.get('media_description') or
video_meta.get('media_description_md'))
video_meta.get('media_description')
or video_meta.get('media_description_md'))
duration = float_or_none(video_meta.get('media_duration'))
uploader = video_meta.get('media_user_name')
views = int_or_none(video_meta.get('media_views'))

4
youtube_dl/extractor/hitrecord.py
View File

@ -47,8 +47,8 @@ class HitRecordIE(InfoExtractor):
tags = [
t['text']
for t in tags_list
if isinstance(t, dict) and t.get('text') and
isinstance(t['text'], compat_str)]
if isinstance(t, dict) and t.get('text')
and isinstance(t['text'], compat_str)]
return {
'id': video_id,

12
youtube_dl/extractor/hketv.py
View File

@ -77,13 +77,13 @@ class HKETVIE(InfoExtractor):
title = (
self._html_search_meta(
('ed_title', 'search.ed_title'), webpage, default=None) or
self._search_regex(
('ed_title', 'search.ed_title'), webpage, default=None)
or self._search_regex(
r'data-favorite_title_(?:eng|chi)=(["\'])(?P<id>(?:(?!\1).)+)\1',
webpage, 'title', default=None, group='url') or
self._html_search_regex(
r'<h1>([^<]+)</h1>', webpage, 'title', default=None) or
self._og_search_title(webpage)
webpage, 'title', default=None, group='url')
or self._html_search_regex(
r'<h1>([^<]+)</h1>', webpage, 'title', default=None)
or self._og_search_title(webpage)
)
file_id = self._search_regex(

87
youtube_dl/extractor/hotstar.py
View File

@ -4,40 +4,59 @@ from __future__ import unicode_literals
import hashlib
import hmac
import time
import uuid
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..compat import (
compat_HTTPError,
compat_str,
)
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
str_or_none,
try_get,
url_or_none,
)
class HotStarBaseIE(InfoExtractor):
_AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
def _call_api(self, path, video_id, query_name='contentId'):
def _call_api_impl(self, path, video_id, query):
st = int(time.time())
exp = st + 6000
auth = 'st=%d~exp=%d~acl=/*' % (st, exp)
auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
response = self._download_json(
'https://api.hotstar.com/' + path,
video_id, headers={
'https://api.hotstar.com/' + path, video_id, headers={
'hotstarauth': auth,
'x-country-code': 'IN',
'x-platform-code': 'JIO',
}, query={
query_name: video_id,
'tas': 10000,
})
}, query=query)
if response['statusCode'] != 'OK':
raise ExtractorError(
response['body']['message'], expected=True)
return response['body']['results']
def _call_api(self, path, video_id, query_name='contentId'):
return self._call_api_impl(path, video_id, {
query_name: video_id,
'tas': 10000,
})
def _call_api_v2(self, path, video_id):
return self._call_api_impl(
'%s/in/contents/%s' % (path, video_id), video_id, {
'desiredConfig': 'encryption:plain;ladder:phone,tv;package:hls,dash',
'client': 'mweb',
'clientVersion': '6.18.0',
'deviceId': compat_str(uuid.uuid4()),
'osName': 'Windows',
'osVersion': '10',
})
class HotStarIE(HotStarBaseIE):
IE_NAME = 'hotstar'
@ -68,6 +87,10 @@ class HotStarIE(HotStarBaseIE):
}, {
'url': 'http://www.hotstar.com/1000000515',
'only_matching': True,
}, {
# only available via api v2
'url': 'https://www.hotstar.com/tv/ek-bhram-sarvagun-sampanna/s-2116/janhvi-targets-suman/1000234847',
'only_matching': True,
}]
_GEO_BYPASS = False
@ -95,26 +118,40 @@ class HotStarIE(HotStarBaseIE):
raise ExtractorError('This video is DRM protected.', expected=True)
formats = []
format_data = self._call_api('h/v1/play', video_id)['item']
format_url = format_data['playbackUrl']
ext = determine_ext(format_url)
if ext == 'm3u8':
geo_restricted = False
playback_sets = self._call_api_v2('h/v2/play', video_id)['playBackSets']
for playback_set in playback_sets:
if not isinstance(playback_set, dict):
continue
format_url = url_or_none(playback_set.get('playbackUrl'))
if not format_url:
continue
tags = str_or_none(playback_set.get('tagsCombination')) or ''
if tags and 'encryption:plain' not in tags:
continue
ext = determine_ext(format_url)
try:
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', m3u8_id='hls'))
if 'package:hls' in tags or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', m3u8_id='hls'))
elif 'package:dash' in tags or ext == 'mpd':
formats.extend(self._extract_mpd_formats(
format_url, video_id, mpd_id='dash'))
elif ext == 'f4m':
# produce broken files
pass
else:
formats.append({
'url': format_url,
'width': int_or_none(playback_set.get('width')),
'height': int_or_none(playback_set.get('height')),
})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
self.raise_geo_restricted(countries=['IN'])
raise
elif ext == 'f4m':
# produce broken files
pass
else:
formats.append({
'url': format_url,
'width': int_or_none(format_data.get('width')),
'height': int_or_none(format_data.get('height')),
})
geo_restricted = True
continue
if not formats and geo_restricted:
self.raise_geo_restricted(countries=['IN'])
self._sort_formats(formats)
return {

4
youtube_dl/extractor/hrti.py
View File

@ -60,8 +60,8 @@ class HRTiBaseIE(InfoExtractor):
language=self._APP_LANGUAGE,
application_id=self._APP_PUBLICATION_ID)
self._login_url = (modules['user']['resources']['login']['uri'] +
'/format/json').format(session_id=self._session_id)
self._login_url = (modules['user']['resources']['login']['uri']
+ '/format/json').format(session_id=self._session_id)
self._logout_url = modules['user']['resources']['logout']['uri']

6
youtube_dl/extractor/infoq.py
View File

@ -122,9 +122,9 @@ class InfoQIE(BokeCCBaseIE):
formats = self._extract_bokecc_formats(webpage, video_id)
else:
formats = (
self._extract_rtmp_video(webpage) +
self._extract_http_video(webpage) +
self._extract_http_audio(webpage, video_id))
self._extract_rtmp_video(webpage)
+ self._extract_http_video(webpage)
+ self._extract_http_audio(webpage, video_id))
self._sort_formats(formats)

6
youtube_dl/extractor/iqiyi.py
View File

@ -383,9 +383,9 @@ class IqiyiIE(InfoExtractor):
self._sleep(5, video_id)
self._sort_formats(formats)
title = (get_element_by_id('widget-videotitle', webpage) or
clean_html(get_element_by_attribute('class', 'mod-play-tit', webpage)) or
self._html_search_regex(r'<span[^>]+data-videochanged-title="word"[^>]*>([^<]+)</span>', webpage, 'title'))
title = (get_element_by_id('widget-videotitle', webpage)
or clean_html(get_element_by_attribute('class', 'mod-play-tit', webpage))
or self._html_search_regex(r'<span[^>]+data-videochanged-title="word"[^>]*>([^<]+)</span>', webpage, 'title'))
return {
'id': video_id,

8
youtube_dl/extractor/itv.py
View File

@ -77,10 +77,10 @@ class ITVIE(InfoExtractor):
return etree.SubElement(element, _add_ns(name))
production_id = (
params.get('data-video-autoplay-id') or
'%s#001' % (
params.get('data-video-episode-id') or
video_id.replace('a', '/')))
params.get('data-video-autoplay-id')
or '%s#001' % (
params.get('data-video-episode-id')
or video_id.replace('a', '/')))
req_env = etree.Element(_add_ns('soapenv:Envelope'))
_add_sub_element(req_env, 'soapenv:Header')

8
youtube_dl/extractor/kaltura.py
View File

@ -118,8 +118,8 @@ class KalturaIE(InfoExtractor):
(?P<q2>['"])_?(?P<partner_id>(?:(?!(?P=q2)).)+)(?P=q2),.*?
(?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s*
(?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
""", webpage) or
re.search(
""", webpage)
or re.search(
r'''(?xs)
(?P<q1>["'])
(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
@ -132,8 +132,8 @@ class KalturaIE(InfoExtractor):
\[\s*(?P<q2_1>["'])entry_?[Ii]d(?P=q2_1)\s*\]\s*=\s*
)
(?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
''', webpage) or
re.search(
''', webpage)
or re.search(
r'''(?xs)
<(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])
(?:https?:)?//(?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)

4
youtube_dl/extractor/karrierevideos.py
View File

@ -47,8 +47,8 @@ class KarriereVideosIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
title = (self._html_search_meta('title', webpage, default=None) or
self._search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'video title'))
title = (self._html_search_meta('title', webpage, default=None)
or self._search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'video title'))
video_id = self._search_regex(
r'/config/video/(.+?)\.xml', webpage, 'video id')

4
youtube_dl/extractor/motherless.py
View File

@ -80,8 +80,8 @@ class MotherlessIE(InfoExtractor):
video_url = (self._html_search_regex(
(r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
r'fileurl\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
webpage, 'video URL', default=None, group='url') or
'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
webpage, 'video URL', default=None, group='url')
or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
age_limit = self._rta_search(webpage)
view_count = str_to_int(self._html_search_regex(
r'<strong>Views</strong>\s+([^<]+)<',

4
youtube_dl/extractor/ndtv.py
View File

@ -84,8 +84,8 @@ class NDTVIE(InfoExtractor):
# '__title' does not contain extra words such as sub-site name, "Video" etc.
title = compat_urllib_parse_unquote_plus(
self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title', default=None) or
self._og_search_title(webpage))
self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title', default=None)
or self._og_search_title(webpage))
filename = self._search_regex(
r"(?:__)?filename\s*[:=]\s*'([^']+)'", webpage, 'video filename')

4
youtube_dl/extractor/nextmedia.py
View File

@ -180,8 +180,8 @@ class AppleDailyIE(NextMediaIE):
_URL_PATTERN = r'\{url: \'(.+)\'\}'
def _fetch_title(self, page):
return (self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title', default=None) or
self._html_search_meta('description', page, 'news title'))
return (self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title', default=None)
or self._html_search_meta('description', page, 'news title'))
def _fetch_thumbnail(self, page):
return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False)

26
youtube_dl/extractor/niconico.py
View File

@ -369,14 +369,14 @@ class NiconicoIE(InfoExtractor):
video_detail = watch_api_data.get('videoDetail', {})
thumbnail = (
get_video_info(['thumbnail_url', 'thumbnailURL']) or
self._html_search_meta('image', webpage, 'thumbnail', default=None) or
video_detail.get('thumbnail'))
get_video_info(['thumbnail_url', 'thumbnailURL'])
or self._html_search_meta('image', webpage, 'thumbnail', default=None)
or video_detail.get('thumbnail'))
description = get_video_info('description')
timestamp = (parse_iso8601(get_video_info('first_retrieve')) or
unified_timestamp(get_video_info('postedDateTime')))
timestamp = (parse_iso8601(get_video_info('first_retrieve'))
or unified_timestamp(get_video_info('postedDateTime')))
if not timestamp:
match = self._html_search_meta('datePublished', webpage, 'date published', default=None)
if match:
@ -395,9 +395,9 @@ class NiconicoIE(InfoExtractor):
view_count = int_or_none(match.replace(',', ''))
view_count = view_count or video_detail.get('viewCount')
comment_count = (int_or_none(get_video_info('comment_num')) or
video_detail.get('commentCount') or
try_get(api_data, lambda x: x['thread']['commentCount']))
comment_count = (int_or_none(get_video_info('comment_num'))
or video_detail.get('commentCount')
or try_get(api_data, lambda x: x['thread']['commentCount']))
if not comment_count:
match = self._html_search_regex(
r'>Comments: <strong[^>]*>([^<]+)</strong>',
@ -406,11 +406,11 @@ class NiconicoIE(InfoExtractor):
comment_count = int_or_none(match.replace(',', ''))
duration = (parse_duration(
get_video_info('length') or
self._html_search_meta(
'video:duration', webpage, 'video duration', default=None)) or
video_detail.get('length') or
get_video_info('duration'))
get_video_info('length')
or self._html_search_meta(
'video:duration', webpage, 'video duration', default=None))
or video_detail.get('length')
or get_video_info('duration'))
webpage_url = get_video_info('watch_url') or url

212
youtube_dl/extractor/novamov.py
View File

@ -1,212 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
NO_DEFAULT,
sanitized_Request,
urlencode_postdata,
)
class NovaMovIE(InfoExtractor):
IE_NAME = 'novamov'
IE_DESC = 'NovaMov'
_VALID_URL_TEMPLATE = r'''(?x)
http://
(?:
(?:www\.)?%(host)s/(?:file|video|mobile/\#/videos)/|
(?:(?:embed|www)\.)%(host)s/embed(?:\.php|/)?\?(?:.*?&)?\bv=
)
(?P<id>[a-z\d]{13})
'''
_VALID_URL = _VALID_URL_TEMPLATE % {'host': r'novamov\.com'}
_HOST = 'www.novamov.com'
_FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
_FILEKEY_REGEX = r'flashvars\.filekey=(?P<filekey>"?[^"]+"?);'
_TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
_DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
_URL_TEMPLATE = 'http://%s/video/%s'
_TEST = None
def _check_existence(self, webpage, video_id):
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
def _real_extract(self, url):
video_id = self._match_id(url)
url = self._URL_TEMPLATE % (self._HOST, video_id)
webpage = self._download_webpage(
url, video_id, 'Downloading video page')
self._check_existence(webpage, video_id)
def extract_filekey(default=NO_DEFAULT):
filekey = self._search_regex(
self._FILEKEY_REGEX, webpage, 'filekey', default=default)
if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'):
return self._search_regex(
r'var\s+%s\s*=\s*"([^"]+)"' % re.escape(filekey), webpage, 'filekey', default=default)
else:
return filekey
filekey = extract_filekey(default=None)
if not filekey:
fields = self._hidden_inputs(webpage)
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage,
'post url', default=url, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(url, post_url)
request = sanitized_Request(
post_url, urlencode_postdata(fields))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
request.add_header('Referer', post_url)
webpage = self._download_webpage(
request, video_id, 'Downloading continue to the video page')
self._check_existence(webpage, video_id)
filekey = extract_filekey()
title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title')
description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
api_response = self._download_webpage(
'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
'Downloading video api response')
response = compat_urlparse.parse_qs(api_response)
if 'error_msg' in response:
raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
video_url = response['url'][0]
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description
}
class WholeCloudIE(NovaMovIE):
IE_NAME = 'wholecloud'
IE_DESC = 'WholeCloud'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'(?:wholecloud\.net|movshare\.(?:net|sx|ag))'}
_HOST = 'www.wholecloud.net'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
_DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
_TEST = {
'url': 'http://www.wholecloud.net/video/559e28be54d96',
'md5': 'abd31a2132947262c50429e1d16c1bfd',
'info_dict': {
'id': '559e28be54d96',
'ext': 'flv',
'title': 'dissapeared image',
'description': 'optical illusion dissapeared image magic illusion',
}
}
class NowVideoIE(NovaMovIE):
IE_NAME = 'nowvideo'
IE_DESC = 'NowVideo'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
_HOST = 'www.nowvideo.to'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<h4>([^<]+)</h4>'
_DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
_TEST = {
'url': 'http://www.nowvideo.sx/video/f1d6fce9a968b',
'md5': '12c82cad4f2084881d8bc60ee29df092',
'info_dict': {
'id': 'f1d6fce9a968b',
'ext': 'flv',
'title': 'youtubedl test video BaWjenozKc',
'description': 'Description',
},
}
class VideoWeedIE(NovaMovIE):
IE_NAME = 'videoweed'
IE_DESC = 'VideoWeed'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'videoweed\.(?:es|com)'}
_HOST = 'www.videoweed.es'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
_URL_TEMPLATE = 'http://%s/file/%s'
_TEST = {
'url': 'http://www.videoweed.es/file/b42178afbea14',
'md5': 'abd31a2132947262c50429e1d16c1bfd',
'info_dict': {
'id': 'b42178afbea14',
'ext': 'flv',
'title': 'optical illusion dissapeared image magic illusion',
'description': ''
},
}
class CloudTimeIE(NovaMovIE):
IE_NAME = 'cloudtime'
IE_DESC = 'CloudTime'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'cloudtime\.to'}
_HOST = 'www.cloudtime.to'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>'
_TEST = None
class AuroraVidIE(NovaMovIE):
IE_NAME = 'auroravid'
IE_DESC = 'AuroraVid'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'auroravid\.to'}
_HOST = 'www.auroravid.to'
_FILE_DELETED_REGEX = r'This file no longer exists on our servers!<'
_TESTS = [{
'url': 'http://www.auroravid.to/video/4rurhn9x446jj',
'md5': '7205f346a52bbeba427603ba10d4b935',
'info_dict': {
'id': '4rurhn9x446jj',
'ext': 'flv',
'title': 'search engine optimization',
'description': 'search engine optimization is used to rank the web page in the google search engine'
},
'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
}, {
'url': 'http://www.auroravid.to/embed/?v=4rurhn9x446jj',
'only_matching': True,
}]

4
youtube_dl/extractor/nrk.py
View File

@ -45,8 +45,8 @@ class NRKBaseIE(InfoExtractor):
entries = []
conviva = data.get('convivaStatistics') or {}
live = (data.get('mediaElementType') == 'Live' or
data.get('isLive') is True or conviva.get('isLive'))
live = (data.get('mediaElementType') == 'Live'
or data.get('isLive') is True or conviva.get('isLive'))
def make_title(t):
return self._live_title(t) if live else t

4
youtube_dl/extractor/ooyala.py
View File

@ -31,8 +31,8 @@ class OoyalaBaseIE(InfoExtractor):
title = metadata['title']
auth_data = self._download_json(
self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code) +
compat_urllib_parse_urlencode({
self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code)
+ compat_urllib_parse_urlencode({
'domain': domain,
'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds,dash,smooth',
'embedToken': embed_token,

97
youtube_dl/extractor/openload.py
View File

@ -43,9 +43,9 @@ def cookie_to_dict(cookie):
if cookie.discard is not None:
cookie_dict['discard'] = cookie.discard
try:
if (cookie.has_nonstandard_attr('httpOnly') or
cookie.has_nonstandard_attr('httponly') or
cookie.has_nonstandard_attr('HttpOnly')):
if (cookie.has_nonstandard_attr('httpOnly')
or cookie.has_nonstandard_attr('httponly')
or cookie.has_nonstandard_attr('HttpOnly')):
cookie_dict['httponly'] = True
except TypeError:
pass
@ -244,7 +244,7 @@ class PhantomJSwrapper(object):
class OpenloadIE(InfoExtractor):
_DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live|space|services)|oladblock\.(?:services|xyz|me)|openloed\.co)'
_DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|live|space|services)|oladblock\.(?:services|xyz|me)|openloed\.co)'
_VALID_URL = r'''(?x)
https?://
(?P<host>
@ -254,7 +254,10 @@ class OpenloadIE(InfoExtractor):
(?:f|embed)/
(?P<id>[a-zA-Z0-9-_]+)
''' % _DOMAINS
_EMBED_WORD = 'embed'
_STREAM_WORD = 'f'
_REDIR_WORD = 'stream'
_URL_IDS = ('streamurl', 'streamuri', 'streamurj')
_TESTS = [{
'url': 'https://openload.co/f/kUEfGclsU9o',
'md5': 'bf1c059b004ebc7a256f89408e65c36e',
@ -354,6 +357,9 @@ class OpenloadIE(InfoExtractor):
}, {
'url': 'https://oload.services/embed/bs1NWj1dCag/',
'only_matching': True,
}, {
'url': 'https://oload.press/embed/drTBl1aOTvk/',
'only_matching': True,
}, {
'url': 'https://oladblock.services/f/b8NWEgkqNLI/',
'only_matching': True,
@ -1948,11 +1954,16 @@ class OpenloadIE(InfoExtractor):
'69.0.3497.28',
)
@staticmethod
def _extract_urls(webpage):
@classmethod
def _extract_urls(cls, webpage):
return re.findall(
r'<iframe[^>]+src=["\']((?:https?://)?%s/embed/[a-zA-Z0-9-_]+)'
% OpenloadIE._DOMAINS, webpage)
r'<iframe[^>]+src=["\']((?:https?://)?%s/%s/[a-zA-Z0-9-_]+)'
% (cls._DOMAINS, cls._EMBED_WORD), webpage)
def _extract_decrypted_page(self, page_url, webpage, video_id, headers):
phantom = PhantomJSwrapper(self, required_version='2.0')
webpage, _ = phantom.get(page_url, html=webpage, video_id=video_id, headers=headers)
return webpage
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@ -1964,9 +1975,9 @@ class OpenloadIE(InfoExtractor):
'User-Agent': self._USER_AGENT_TPL % random.choice(self._CHROME_VERSIONS),
}
for path in ('embed', 'f'):
for path in (self._EMBED_WORD, self._STREAM_WORD):
page_url = url_pattern % path
last = path == 'f'
last = path == self._STREAM_WORD
webpage = self._download_webpage(
page_url, video_id, 'Downloading %s webpage' % path,
headers=headers, fatal=last)
@ -1978,21 +1989,20 @@ class OpenloadIE(InfoExtractor):
raise ExtractorError('File not found', expected=True, video_id=video_id)
break
phantom = PhantomJSwrapper(self, required_version='2.0')
webpage, _ = phantom.get(page_url, html=webpage, video_id=video_id, headers=headers)
decoded_id = (get_element_by_id('streamurl', webpage) or
get_element_by_id('streamuri', webpage) or
get_element_by_id('streamurj', webpage) or
self._search_regex(
(r'>\s*([\w-]+~\d{10,}~\d+\.\d+\.0\.0~[\w-]+)\s*<',
r'>\s*([\w~-]+~\d+\.\d+\.\d+\.\d+~[\w~-]+)',
r'>\s*([\w-]+~\d{10,}~(?:[a-f\d]+:){2}:~[\w-]+)\s*<',
r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)\s*<',
r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)'), webpage,
'stream URL'))
video_url = 'https://%s/stream/%s?mime=true' % (host, decoded_id)
webpage = self._extract_decrypted_page(page_url, webpage, video_id, headers)
for element_id in self._URL_IDS:
decoded_id = get_element_by_id(element_id, webpage)
if decoded_id:
break
if not decoded_id:
decoded_id = self._search_regex(
(r'>\s*([\w-]+~\d{10,}~\d+\.\d+\.0\.0~[\w-]+)\s*<',
r'>\s*([\w~-]+~\d+\.\d+\.\d+\.\d+~[\w~-]+)',
r'>\s*([\w-]+~\d{10,}~(?:[a-f\d]+:){2}:~[\w-]+)\s*<',
r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)\s*<',
r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)'), webpage,
'stream URL')
video_url = 'https://%s/%s/%s?mime=true' % (host, self._REDIR_WORD, decoded_id)
title = self._og_search_title(webpage, default=None) or self._search_regex(
r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
@ -2012,3 +2022,38 @@ class OpenloadIE(InfoExtractor):
'subtitles': subtitles,
'http_headers': headers,
}
class VerystreamIE(OpenloadIE):
IE_NAME = 'verystream'
_DOMAINS = r'(?:verystream\.com)'
_VALID_URL = r'''(?x)
https?://
(?P<host>
(?:www\.)?
%s
)/
(?:stream|e)/
(?P<id>[a-zA-Z0-9-_]+)
''' % _DOMAINS
_EMBED_WORD = 'e'
_STREAM_WORD = 'stream'
_REDIR_WORD = 'gettoken'
_URL_IDS = ('videolink', )
_TESTS = [{
'url': 'https://verystream.com/stream/c1GWQ9ngBBx/',
'md5': 'd3e8c5628ccb9970b65fd65269886795',
'info_dict': {
'id': 'c1GWQ9ngBBx',
'ext': 'mp4',
'title': 'Big Buck Bunny.mp4',
'thumbnail': r're:^https?://.*\.jpg$',
},
}, {
'url': 'https://verystream.com/e/c1GWQ9ngBBx/',
'only_matching': True,
}]
def _extract_decrypted_page(self, page_url, webpage, video_id, headers):
return webpage # for Verystream, the webpage is already decrypted

4
youtube_dl/extractor/podomatic.py
View File

@ -50,8 +50,8 @@ class PodomaticIE(InfoExtractor):
video_id = mobj.group('id')
channel = mobj.group('channel') or mobj.group('channel_2')
json_url = (('%s://%s.podomatic.com/entry/embed_params/%s' +
'?permalink=true&rtmp=0') %
json_url = (('%s://%s.podomatic.com/entry/embed_params/%s'
+ '?permalink=true&rtmp=0') %
(mobj.group('proto'), channel, video_id))
data_json = self._download_webpage(
json_url, video_id, 'Downloading video info')

101
youtube_dl/extractor/pornflip.py
View File

@ -1,101 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
)
from ..utils import (
int_or_none,
try_get,
unified_timestamp,
)
class PornFlipIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:v|embed)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.pornflip.com/v/wz7DfNhMmep',
'md5': '98c46639849145ae1fd77af532a9278c',
'info_dict': {
'id': 'wz7DfNhMmep',
'ext': 'mp4',
'title': '2 Amateurs swallow make his dream cumshots true',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 112,
'timestamp': 1481655502,
'upload_date': '20161213',
'uploader_id': '106786',
'uploader': 'figifoto',
'view_count': int,
'age_limit': 18,
}
}, {
'url': 'https://www.pornflip.com/embed/wz7DfNhMmep',
'only_matching': True,
}, {
'url': 'https://www.pornflip.com/v/EkRD6-vS2-s',
'only_matching': True,
}, {
'url': 'https://www.pornflip.com/embed/EkRD6-vS2-s',
'only_matching': True,
}, {
'url': 'https://www.pornflip.com/v/NG9q6Pb_iK8',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://www.pornflip.com/v/%s' % video_id, video_id)
flashvars = compat_parse_qs(self._search_regex(
r'<embed[^>]+flashvars=(["\'])(?P<flashvars>(?:(?!\1).)+)\1',
webpage, 'flashvars', group='flashvars'))
title = flashvars['video_vars[title]'][0]
def flashvar(kind):
return try_get(
flashvars, lambda x: x['video_vars[%s]' % kind][0], compat_str)
formats = []
for key, value in flashvars.items():
if not (value and isinstance(value, list)):
continue
format_url = value[0]
if key == 'video_vars[hds_manifest]':
formats.extend(self._extract_mpd_formats(
format_url, video_id, mpd_id='dash', fatal=False))
continue
height = self._search_regex(
r'video_vars\[video_urls\]\[(\d+)', key, 'height', default=None)
if not height:
continue
formats.append({
'url': format_url,
'format_id': 'http-%s' % height,
'height': int_or_none(height),
})
self._sort_formats(formats)
uploader = self._html_search_regex(
(r'<span[^>]+class="name"[^>]*>\s*<a[^>]+>\s*<strong>(?P<uploader>[^<]+)',
r'<meta[^>]+content=(["\'])[^>]*\buploaded by (?P<uploader>.+?)\1'),
webpage, 'uploader', fatal=False, group='uploader')
return {
'id': video_id,
'formats': formats,
'title': title,
'thumbnail': flashvar('big_thumb'),
'duration': int_or_none(flashvar('duration')),
'timestamp': unified_timestamp(self._html_search_meta(
'uploadDate', webpage, 'timestamp')),
'uploader_id': flashvar('author_id'),
'uploader': uploader,
'view_count': int_or_none(flashvar('views')),
'age_limit': 18,
}

2
youtube_dl/extractor/pornhub.py
View File

@ -170,7 +170,7 @@ class PornHubIE(PornHubBaseIE):
def dl_webpage(platform):
self._set_cookie(host, 'platform', platform)
return self._download_webpage(
'http://www.%s/view_video.php?viewkey=%s' % (host, video_id),
'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
video_id, 'Downloading %s webpage' % platform)
webpage = dl_webpage('pc')

4
youtube_dl/extractor/ruutu.py
View File

@ -91,8 +91,8 @@ class RuutuIE(InfoExtractor):
extract_formats(child)
elif child.tag.endswith('File'):
video_url = child.text
if (not video_url or video_url in processed_urls or
any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
if (not video_url or video_url in processed_urls
or any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
continue
processed_urls.append(video_url)
ext = determine_ext(video_url)

87
youtube_dl/extractor/safari.py
View File

@ -1,15 +1,18 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
compat_urlparse,
)
from ..utils import (
ExtractorError,
sanitized_Request,
std_headers,
urlencode_postdata,
update_url_query,
)
@ -31,44 +34,52 @@ class SafariBaseIE(InfoExtractor):
if username is None:
return
headers = std_headers.copy()
if 'Referer' not in headers:
headers['Referer'] = self._LOGIN_URL
_, urlh = self._download_webpage_handle(
'https://learning.oreilly.com/accounts/login-check/', None,
'Downloading login page')
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login form', headers=headers)
def is_logged(urlh):
return 'learning.oreilly.com/home/' in compat_str(urlh.geturl())
def is_logged(webpage):
return any(re.search(p, webpage) for p in (
r'href=["\']/accounts/logout/', r'>Sign Out<'))
if is_logged(login_page):
if is_logged(urlh):
self.LOGGED_IN = True
return
csrf = self._html_search_regex(
r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
login_page, 'csrf token')
redirect_url = compat_str(urlh.geturl())
parsed_url = compat_urlparse.urlparse(redirect_url)
qs = compat_parse_qs(parsed_url.query)
next_uri = compat_urlparse.urljoin(
'https://api.oreilly.com', qs['next'][0])
login_form = {
'csrfmiddlewaretoken': csrf,
'email': username,
'password1': password,
'login': 'Sign In',
'next': '',
}
auth, urlh = self._download_json_handle(
'https://www.oreilly.com/member/auth/login/', None, 'Logging in',
data=json.dumps({
'email': username,
'password': password,
'redirect_uri': next_uri,
}).encode(), headers={
'Content-Type': 'application/json',
'Referer': redirect_url,
}, expected_status=400)
request = sanitized_Request(
self._LOGIN_URL, urlencode_postdata(login_form), headers=headers)
login_page = self._download_webpage(
request, None, 'Logging in')
if not is_logged(login_page):
credentials = auth.get('credentials')
if (not auth.get('logged_in') and not auth.get('redirect_uri')
and credentials):
raise ExtractorError(
'Login failed; make sure your credentials are correct and try again.',
expected=True)
'Unable to login: %s' % credentials, expected=True)
self.LOGGED_IN = True
# oreilly serves two same groot_sessionid cookies in Set-Cookie header
# and expects first one to be actually set
self._apply_first_set_cookie_header(urlh, 'groot_sessionid')
_, urlh = self._download_webpage_handle(
auth.get('redirect_uri') or next_uri, None, 'Completing login',)
if is_logged(urlh):
self.LOGGED_IN = True
return
raise ExtractorError('Unable to log in')
class SafariIE(SafariBaseIE):
@ -76,7 +87,7 @@ class SafariIE(SafariBaseIE):
IE_DESC = 'safaribooksonline.com online video'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/
(?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
(?:
library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html|
videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+)
@ -107,6 +118,9 @@ class SafariIE(SafariBaseIE):
}, {
'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro',
'only_matching': True,
}, {
'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/00_SeriesIntro.html',
'only_matching': True,
}]
_PARTNER_ID = '1926081'
@ -163,7 +177,7 @@ class SafariIE(SafariBaseIE):
class SafariApiIE(SafariBaseIE):
IE_NAME = 'safari:api'
_VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
_VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
_TESTS = [{
'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
@ -188,7 +202,7 @@ class SafariCourseIE(SafariBaseIE):
_VALID_URL = r'''(?x)
https?://
(?:
(?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/
(?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
(?:
library/view/[^/]+|
api/v1/book|
@ -219,6 +233,9 @@ class SafariCourseIE(SafariBaseIE):
}, {
'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838',
'only_matching': True,
}, {
'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
'only_matching': True,
}]
@classmethod

4
youtube_dl/extractor/sbs.py
View File

@ -55,8 +55,8 @@ class SBSIE(InfoExtractor):
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
urls = player_params['releaseUrls']
theplatform_url = (urls.get('progressive') or urls.get('html') or
urls.get('standard') or player_params['relatedItemsURL'])
theplatform_url = (urls.get('progressive') or urls.get('html')
or urls.get('standard') or player_params['relatedItemsURL'])
return {
'_type': 'url_transparent',

37
youtube_dl/extractor/shared.py
View File

@ -3,8 +3,11 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_b64decode
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
KNOWN_EXTENSIONS,
parse_filesize,
url_or_none,
urlencode_postdata,
)
@ -22,10 +25,8 @@ class SharedBaseIE(InfoExtractor):
video_url = self._extract_video_url(webpage, video_id, url)
title = compat_b64decode(self._html_search_meta(
'full:title', webpage, 'title')).decode('utf-8')
filesize = int_or_none(self._html_search_meta(
'full:size', webpage, 'file size', fatal=False))
title = self._extract_title(webpage)
filesize = int_or_none(self._extract_filesize(webpage))
return {
'id': video_id,
@ -35,6 +36,14 @@ class SharedBaseIE(InfoExtractor):
'title': title,
}
def _extract_title(self, webpage):
return compat_b64decode(self._html_search_meta(
'full:title', webpage, 'title')).decode('utf-8')
def _extract_filesize(self, webpage):
return self._html_search_meta(
'full:size', webpage, 'file size', fatal=False)
class SharedIE(SharedBaseIE):
IE_DESC = 'shared.sx'
@ -82,11 +91,27 @@ class VivoIE(SharedBaseIE):
'id': 'd7ddda0e78',
'ext': 'mp4',
'title': 'Chicken',
'filesize': 528031,
'filesize': 515659,
},
}
def _extract_video_url(self, webpage, video_id, *args):
def _extract_title(self, webpage):
title = self._html_search_regex(
r'data-name\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', webpage,
'title', default=None, group='title')
if title:
ext = determine_ext(title)
if ext.lower() in KNOWN_EXTENSIONS:
title = title.rpartition('.' + ext)[0]
return title
return self._og_search_title(webpage)
def _extract_filesize(self, webpage):
return parse_filesize(self._search_regex(
r'data-type=["\']video["\'][^>]*>Watch.*?<strong>\s*\((.+?)\)',
webpage, 'filesize', fatal=False))
def _extract_video_url(self, webpage, video_id, url):
def decode_url(encoded_url):
return compat_b64decode(encoded_url).decode('utf-8')

57
youtube_dl/extractor/skysports.py → youtube_dl/extractor/sky.py
View File

@ -10,34 +10,25 @@ from ..utils import (
)
class SkySportsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?skysports\.com/watch/video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.skysports.com/watch/video/10328419/bale-its-our-time-to-shine',
'md5': '77d59166cddc8d3cb7b13e35eaf0f5ec',
'info_dict': {
'id': '10328419',
'ext': 'mp4',
'title': 'Bale: It\'s our time to shine',
'description': 'md5:e88bda94ae15f7720c5cb467e777bb6d',
},
'add_ie': ['Ooyala'],
}
class SkyBaseIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_data = extract_attributes(self._search_regex(
r'(<div.+?class="sdc-article-video__media-ooyala"[^>]+>)', webpage, 'video data'))
r'(<div.+?class="[^"]*sdc-article-video__media-ooyala[^"]*"[^>]+>)',
webpage, 'video data'))
video_url = 'ooyala:%s' % video_data['data-video-id']
if video_data.get('data-token-required') == 'true':
token_fetch_options = self._parse_json(video_data.get('data-token-fetch-options', '{}'), video_id, fatal=False) or {}
token_fetch_options = self._parse_json(video_data.get(
'data-token-fetch-options', '{}'), video_id, fatal=False) or {}
token_fetch_url = token_fetch_options.get('url')
if token_fetch_url:
embed_token = self._download_webpage(urljoin(url, token_fetch_url), video_id, fatal=False)
embed_token = self._download_webpage(urljoin(
url, token_fetch_url), video_id, fatal=False)
if embed_token:
video_url = smuggle_url(video_url, {'embed_token': embed_token.strip('"')})
video_url = smuggle_url(
video_url, {'embed_token': embed_token.strip('"')})
return {
'_type': 'url_transparent',
@ -47,3 +38,33 @@ class SkySportsIE(InfoExtractor):
'description': strip_or_none(self._og_search_description(webpage)),
'ie_key': 'Ooyala',
}
class SkySportsIE(SkyBaseIE):
_VALID_URL = r'https?://(?:www\.)?skysports\.com/watch/video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.skysports.com/watch/video/10328419/bale-its-our-time-to-shine',
'md5': '77d59166cddc8d3cb7b13e35eaf0f5ec',
'info_dict': {
'id': 'o3eWJnNDE6l7kfNO8BOoBlRxXRQ4ANNQ',
'ext': 'mp4',
'title': 'Bale: It\'s our time to shine',
'description': 'md5:e88bda94ae15f7720c5cb467e777bb6d',
},
'add_ie': ['Ooyala'],
}
class SkyNewsIE(SkyBaseIE):
_VALID_URL = r'https?://news\.sky\.com/video/[0-9a-z-]+-(?P<id>[0-9]+)'
_TEST = {
'url': 'https://news.sky.com/video/russian-plane-inspected-after-deadly-fire-11712962',
'md5': 'd6327e581473cea9976a3236ded370cd',
'info_dict': {
'id': '1ua21xaDE6lCtZDmbYfl8kwsKLooJbNM',
'ext': 'mp4',
'title': 'Russian plane inspected after deadly fire',
'description': 'The Russian Investigative Committee has released video of the wreckage of a passenger plane which caught fire near Moscow.',
},
'add_ie': ['Ooyala'],
}

19
youtube_dl/extractor/srgssr.py
View File

@ -106,7 +106,16 @@ class SRGSSRIE(InfoExtractor):
class SRGSSRPlayIE(InfoExtractor):
IE_DESC = 'srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites'
_VALID_URL = r'https?://(?:(?:www|play)\.)?(?P<bu>srf|rts|rsi|rtr|swissinfo)\.ch/play/(?:tv|radio)/[^/]+/(?P<type>video|audio)/[^?]+\?id=(?P<id>[0-9a-f\-]{36}|\d+)'
_VALID_URL = r'''(?x)
https?://
(?:(?:www|play)\.)?
(?P<bu>srf|rts|rsi|rtr|swissinfo)\.ch/play/(?:tv|radio)/
(?:
[^/]+/(?P<type>video|audio)/[^?]+|
popup(?P<type_2>video|audio)player
)
\?id=(?P<id>[0-9a-f\-]{36}|\d+)
'''
_TESTS = [{
'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
@ -163,9 +172,15 @@ class SRGSSRPlayIE(InfoExtractor):
# m3u8 download
'skip_download': True,
}
}, {
'url': 'https://www.srf.ch/play/tv/popupvideoplayer?id=c4dba0ca-e75b-43b2-a34f-f708a4932e01',
'only_matching': True,
}]
def _real_extract(self, url):
bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
mobj = re.match(self._VALID_URL, url)
bu = mobj.group('bu')
media_type = mobj.group('type') or mobj.group('type_2')
media_id = mobj.group('id')
# other info can be extracted from url + '&layout=json'
return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')

2
youtube_dl/extractor/streamcloud.py
View File

@ -45,7 +45,7 @@ class StreamcloudIE(InfoExtractor):
value="([^"]*)"
''', orig_webpage)
self._sleep(12, video_id)
self._sleep(6, video_id)
webpage = self._download_webpage(
url, video_id, data=urlencode_postdata(fields), headers={

2
youtube_dl/extractor/svt.py
View File

@ -185,7 +185,7 @@ class SVTPlayIE(SVTPlayBaseIE):
def _extract_by_video_id(self, video_id, webpage=None):
data = self._download_json(
'https://api.svt.se/video/%s' % video_id,
'https://api.svt.se/videoplayer-api/video/%s' % video_id,
video_id, headers=self.geo_verification_headers())
info_dict = self._extract_video(data, video_id)
if not info_dict.get('title'):

23
youtube_dl/extractor/tele5.py
View File

@ -7,7 +7,7 @@ from ..compat import compat_urlparse
class Tele5IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:mediathek|tv)/(?P<id>[^?#&]+)'
_VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
'info_dict': {
@ -21,10 +21,22 @@ class Tele5IE(InfoExtractor):
'skip_download': True,
},
}, {
'url': 'https://www.tele5.de/tv/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
'only_matching': True,
}, {
'url': 'https://www.tele5.de/tv/dark-matter/videos',
'url': 'https://www.tele5.de/video-clip/?ve_id=1609440',
'only_matching': True,
}, {
'url': 'https://www.tele5.de/filme/schlefaz-dragon-crusaders/',
'only_matching': True,
}, {
'url': 'https://www.tele5.de/filme/making-of/avengers-endgame/',
'only_matching': True,
}, {
'url': 'https://www.tele5.de/star-trek/raumschiff-voyager/ganze-folge/das-vinculum/',
'only_matching': True,
}, {
'url': 'https://www.tele5.de/anders-ist-sevda/',
'only_matching': True,
}]
@ -36,8 +48,9 @@ class Tele5IE(InfoExtractor):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(
r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)',
webpage, 'video id')
(r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)',
r'\s+id\s*=\s*["\']player_(\d{6,})',
r'\bdata-id\s*=\s*["\'](\d{6,})'), webpage, 'video id')
return self.url_result(
'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id,

2
youtube_dl/extractor/tvnow.py
View File

@ -207,7 +207,7 @@ class TVNowNewBaseIE(InfoExtractor):
return result
"""
r"""
TODO: new apigw.tvnow.de based version of TVNowIE. Replace old TVNowIE with it
when api.tvnow.de is shut down. This version can't bypass premium checks though.
class TVNowIE(TVNowNewBaseIE):

19
youtube_dl/extractor/twentyfourvideo.py
View File

@ -14,7 +14,18 @@ from ..utils import (
class TwentyFourVideoIE(InfoExtractor):
IE_NAME = '24video'
_VALID_URL = r'https?://(?P<host>(?:www\.)?24video\.(?:net|me|xxx|sexy?|tube|adult))/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
_VALID_URL = r'''(?x)
https?://
(?P<host>
(?:(?:www|porno)\.)?24video\.
(?:net|me|xxx|sexy?|tube|adult|site)
)/
(?:
video/(?:(?:view|xml)/)?|
player/new24_play\.swf\?id=
)
(?P<id>\d+)
'''
_TESTS = [{
'url': 'http://www.24video.net/video/view/1044982',
@ -42,6 +53,12 @@ class TwentyFourVideoIE(InfoExtractor):
}, {
'url': 'http://www.24video.tube/video/view/2363750',
'only_matching': True,
}, {
'url': 'https://www.24video.site/video/view/2640421',
'only_matching': True,
}, {
'url': 'https://porno.24video.net/video/2640421-vsya-takaya-gibkaya-i-v-masle',
'only_matching': True,
}]
def _real_extract(self, url):

4
youtube_dl/extractor/vevo.py
View File

@ -275,8 +275,8 @@ class VevoIE(VevoBaseIE):
genres = video_info.get('genres')
genre = (
genres[0] if genres and isinstance(genres, list) and
isinstance(genres[0], compat_str) else None)
genres[0] if genres and isinstance(genres, list)
and isinstance(genres[0], compat_str) else None)
is_explicit = video_info.get('isExplicit')
if is_explicit is True:

26
youtube_dl/extractor/vk.py
View File

@ -3,7 +3,6 @@ from __future__ import unicode_literals
import collections
import re
import sys
from .common import InfoExtractor
from ..compat import compat_urlparse
@ -45,24 +44,9 @@ class VKBaseIE(InfoExtractor):
'pass': password.encode('cp1251'),
})
# https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header
# and expects the first one to be set rather than second (see
# https://github.com/ytdl-org/youtube-dl/issues/9841#issuecomment-227871201).
# As of RFC6265 the newer one cookie should be set into cookie store
# what actually happens.
# We will workaround this VK issue by resetting the remixlhk cookie to
# the first one manually.
for header, cookies in url_handle.headers.items():
if header.lower() != 'set-cookie':
continue
if sys.version_info[0] >= 3:
cookies = cookies.encode('iso-8859-1')
cookies = cookies.decode('utf-8')
remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
if remixlhk:
value, domain = remixlhk.groups()
self._set_cookie(domain, 'remixlhk', value)
break
# vk serves two same remixlhk cookies in Set-Cookie header and expects
# first one to be actually set
self._apply_first_set_cookie_header(url_handle, 'remixlhk')
login_page = self._download_webpage(
'https://login.vk.com/?act=login', None,
@ -443,8 +427,8 @@ class VKIE(VKBaseIE):
format_url = url_or_none(format_url)
if not format_url or not format_url.startswith(('http', '//', 'rtmp')):
continue
if (format_id.startswith(('url', 'cache')) or
format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
if (format_id.startswith(('url', 'cache'))
or format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
height = int_or_none(self._search_regex(
r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
formats.append({

193
youtube_dl/extractor/vrt.py
View File

@ -5,150 +5,83 @@ import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
float_or_none,
get_element_by_class,
strip_or_none,
unified_timestamp,
)
class VRTIE(InfoExtractor):
IE_DESC = 'deredactie.be, sporza.be, cobra.be and cobra.canvas.be'
_VALID_URL = r'https?://(?:deredactie|sporza|cobra(?:\.canvas)?)\.be/cm/(?:[^/]+/)+(?P<id>[^/]+)/*'
_TESTS = [
# deredactie.be
{
'url': 'http://deredactie.be/cm/vrtnieuws/videozone/programmas/journaal/EP_141025_JOL',
'md5': '4cebde1eb60a53782d4f3992cbd46ec8',
'info_dict': {
'id': '2129880',
'ext': 'flv',
'title': 'Het journaal L - 25/10/14',
'description': None,
'timestamp': 1414271750.949,
'upload_date': '20141025',
'duration': 929,
},
'skip': 'HTTP Error 404: Not Found',
IE_DESC = 'VRT NWS, Flanders News, Flandern Info and Sporza'
_VALID_URL = r'https?://(?:www\.)?(?P<site>vrt\.be/vrtnws|sporza\.be)/[a-z]{2}/\d{4}/\d{2}/\d{2}/(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://www.vrt.be/vrtnws/nl/2019/05/15/beelden-van-binnenkant-notre-dame-een-maand-na-de-brand/',
'md5': 'e1663accf5cf13f375f3cd0d10476669',
'info_dict': {
'id': 'pbs-pub-7855fc7b-1448-49bc-b073-316cb60caa71$vid-2ca50305-c38a-4762-9890-65cbd098b7bd',
'ext': 'mp4',
'title': 'Beelden van binnenkant Notre-Dame, één maand na de brand',
'description': 'Op maandagavond 15 april ging een deel van het dakgebinte van de Parijse kathedraal in vlammen op.',
'timestamp': 1557924660,
'upload_date': '20190515',
'duration': 31.2,
},
# sporza.be
{
'url': 'http://sporza.be/cm/sporza/videozone/programmas/extratime/EP_141020_Extra_time',
'md5': '11f53088da9bf8e7cfc42456697953ff',
'info_dict': {
'id': '2124639',
'ext': 'flv',
'title': 'Bekijk Extra Time van 20 oktober',
'description': 'md5:83ac5415a4f1816c6a93f8138aef2426',
'timestamp': 1413835980.560,
'upload_date': '20141020',
'duration': 3238,
},
'skip': 'HTTP Error 404: Not Found',
}, {
'url': 'https://sporza.be/nl/2019/05/15/de-belgian-cats-zijn-klaar-voor-het-ek/',
'md5': '910bba927566e9ab992278f647eb4b75',
'info_dict': {
'id': 'pbs-pub-f2c86a46-8138-413a-a4b9-a0015a16ce2c$vid-1f112b31-e58e-4379-908d-aca6d80f8818',
'ext': 'mp4',
'title': 'De Belgian Cats zijn klaar voor het EK mét Ann Wauters',
'timestamp': 1557923760,
'upload_date': '20190515',
'duration': 115.17,
},
# cobra.be
{
'url': 'http://cobra.be/cm/cobra/videozone/rubriek/film-videozone/141022-mv-ellis-cafecorsari',
'md5': '78a2b060a5083c4f055449a72477409d',
'info_dict': {
'id': '2126050',
'ext': 'flv',
'title': 'Bret Easton Ellis in Café Corsari',
'description': 'md5:f699986e823f32fd6036c1855a724ee9',
'timestamp': 1413967500.494,
'upload_date': '20141022',
'duration': 661,
},
'skip': 'HTTP Error 404: Not Found',
},
{
# YouTube video
'url': 'http://deredactie.be/cm/vrtnieuws/videozone/nieuws/cultuurenmedia/1.2622957',
'md5': 'b8b93da1df1cea6c8556255a796b7d61',
'info_dict': {
'id': 'Wji-BZ0oCwg',
'ext': 'mp4',
'title': 'ROGUE ONE: A STAR WARS STORY Official Teaser Trailer',
'description': 'md5:8e468944dce15567a786a67f74262583',
'uploader': 'Star Wars',
'uploader_id': 'starwars',
'upload_date': '20160407',
},
'add_ie': ['Youtube'],
},
{
'url': 'http://cobra.canvas.be/cm/cobra/videozone/rubriek/film-videozone/1.2377055',
'info_dict': {
'id': '2377055',
'ext': 'mp4',
'title': 'Cafe Derby',
'description': 'Lenny Van Wesemael debuteert met de langspeelfilm Café Derby. Een waar gebeurd maar ook verzonnen verhaal.',
'upload_date': '20150626',
'timestamp': 1435305240.769,
},
'params': {
# m3u8 download
'skip_download': True,
}
}
]
}, {
'url': 'https://www.vrt.be/vrtnws/en/2019/05/15/belgium_s-eurovision-entry-falls-at-the-first-hurdle/',
'only_matching': True,
}, {
'url': 'https://www.vrt.be/vrtnws/de/2019/05/15/aus-fuer-eliott-im-halbfinale-des-eurosongfestivals/',
'only_matching': True,
}]
_CLIENT_MAP = {
'vrt.be/vrtnws': 'vrtnieuws',
'sporza.be': 'sporza',
}
def _real_extract(self, url):
video_id = self._match_id(url)
site, display_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, display_id)
attrs = extract_attributes(self._search_regex(
r'(<[^>]+class="vrtvideo"[^>]*>)', webpage, 'vrt video'))
webpage = self._download_webpage(url, video_id)
asset_id = attrs['data-videoid']
publication_id = attrs.get('data-publicationid')
if publication_id:
asset_id = publication_id + '$' + asset_id
client = attrs.get('data-client') or self._CLIENT_MAP[site]
video_id = self._search_regex(
r'data-video-id="([^"]+)_[^"]+"', webpage, 'video id', fatal=False)
src = self._search_regex(
r'data-video-src="([^"]+)"', webpage, 'video src', default=None)
video_type = self._search_regex(
r'data-video-type="([^"]+)"', webpage, 'video type', default=None)
if video_type == 'YouTubeVideo':
return self.url_result(src, 'Youtube')
formats = []
mobj = re.search(
r'data-video-iphone-server="(?P<server>[^"]+)"\s+data-video-iphone-path="(?P<path>[^"]+)"',
webpage)
if mobj:
formats.extend(self._extract_m3u8_formats(
'%s/%s' % (mobj.group('server'), mobj.group('path')),
video_id, 'mp4', m3u8_id='hls', fatal=False))
if src:
formats = self._extract_wowza_formats(src, video_id)
if 'data-video-geoblocking="true"' not in webpage:
for f in formats:
if f['url'].startswith('rtsp://'):
http_format = f.copy()
http_format.update({
'url': f['url'].replace('rtsp://', 'http://').replace('vod.', 'download.').replace('/_definst_/', '/').replace('mp4:', ''),
'format_id': f['format_id'].replace('rtsp', 'http'),
'protocol': 'http',
})
formats.append(http_format)
if not formats and 'data-video-geoblocking="true"' in webpage:
self.raise_geo_restricted('This video is only available in Belgium')
self._sort_formats(formats)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage, default=None)
thumbnail = self._og_search_thumbnail(webpage)
timestamp = float_or_none(self._search_regex(
r'data-video-sitestat-pubdate="(\d+)"', webpage, 'timestamp', fatal=False), 1000)
duration = float_or_none(self._search_regex(
r'data-video-duration="(\d+)"', webpage, 'duration', fatal=False), 1000)
title = strip_or_none(get_element_by_class(
'vrt-title', webpage) or self._html_search_meta(
['og:title', 'twitter:title', 'name'], webpage))
description = self._html_search_meta(
['og:description', 'twitter:description', 'description'], webpage)
if description == '…':
description = None
timestamp = unified_timestamp(self._html_search_meta(
'article:published_time', webpage))
return {
'id': video_id,
'_type': 'url_transparent',
'id': asset_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'thumbnail': attrs.get('data-posterimage'),
'timestamp': timestamp,
'duration': duration,
'formats': formats,
'duration': float_or_none(attrs.get('data-duration'), 1000),
'url': 'https://mediazone.vrt.be/api/v1/%s/assets/%s' % (client, asset_id),
'ie_key': 'Canvas',
}

17
youtube_dl/extractor/vrv.py
View File

@ -198,14 +198,15 @@ class VRVIE(VRVBaseIE):
self._sort_formats(formats)
subtitles = {}
for subtitle in streams_json.get('subtitles', {}).values():
subtitle_url = subtitle.get('url')
if not subtitle_url:
continue
subtitles.setdefault(subtitle.get('locale', 'en-US'), []).append({
'url': subtitle_url,
'ext': subtitle.get('format', 'ass'),
})
for k in ('captions', 'subtitles'):
for subtitle in streams_json.get(k, {}).values():
subtitle_url = subtitle.get('url')
if not subtitle_url:
continue
subtitles.setdefault(subtitle.get('locale', 'en-US'), []).append({
'url': subtitle_url,
'ext': subtitle.get('format', 'ass'),
})
thumbnails = []
for thumbnail in video_data.get('images', {}).get('thumbnails', []):

7
youtube_dl/extractor/yahoo.py
View File

@ -511,6 +511,8 @@ class YahooGyaOPlayerIE(InfoExtractor):
'https://gyao.yahoo.co.jp/dam/v1/videos/' + video_id,
video_id, query={
'fields': 'longDescription,title,videoId',
}, headers={
'X-User-Agent': 'Unknown Pc GYAO!/2.0.0 Web',
})
return {
'_type': 'url_transparent',
@ -526,7 +528,7 @@ class YahooGyaOPlayerIE(InfoExtractor):
class YahooGyaOIE(InfoExtractor):
IE_NAME = 'yahoo:gyao'
_VALID_URL = r'https?://(?:gyao\.yahoo\.co\.jp/p|streaming\.yahoo\.co\.jp/p/y)/(?P<id>\d+/v\d+)'
_VALID_URL = r'https?://(?:gyao\.yahoo\.co\.jp/(?:p|title/[^/]+)|streaming\.yahoo\.co\.jp/p/y)/(?P<id>\d+/v\d+|[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_TESTS = [{
'url': 'https://gyao.yahoo.co.jp/p/00449/v03102/',
'info_dict': {
@ -536,6 +538,9 @@ class YahooGyaOIE(InfoExtractor):
}, {
'url': 'https://streaming.yahoo.co.jp/p/y/01034/v00133/',
'only_matching': True,
}, {
'url': 'https://gyao.yahoo.co.jp/title/%E3%81%97%E3%82%83%E3%81%B9%E3%81%8F%E3%82%8A007/5b025a49-b2e5-4dc7-945c-09c6634afacf',
'only_matching': True,
}]
def _real_extract(self, url):

6
youtube_dl/extractor/yandexvideo.py
View File

@ -70,9 +70,9 @@ class YandexVideoIE(InfoExtractor):
description = content.get('description')
thumbnail = content.get('thumbnail')
timestamp = (int_or_none(content.get('release_date')) or
int_or_none(content.get('release_date_ut')) or
int_or_none(content.get('start_time')))
timestamp = (int_or_none(content.get('release_date'))
or int_or_none(content.get('release_date_ut'))
or int_or_none(content.get('start_time')))
duration = int_or_none(content.get('duration'))
series = content.get('program_title')
age_limit = int_or_none(content.get('restriction_age'))

4
youtube_dl/extractor/youku.py
View File

@ -258,8 +258,8 @@ class YoukuShowIE(InfoExtractor):
transform_source=lambda s: js_to_json(strip_jsonp(s))).get('html')
if playlist_data is None:
return [None, None]
drama_list = (get_element_by_class('p-drama-grid', playlist_data) or
get_element_by_class('p-drama-half-row', playlist_data))
drama_list = (get_element_by_class('p-drama-grid', playlist_data)
or get_element_by_class('p-drama-half-row', playlist_data))
if drama_list is None:
raise ExtractorError('No episodes found')
video_urls = re.findall(r'<a[^>]+href="([^"]+)"', drama_list)

54
youtube_dl/extractor/youtube.py
View File

@ -16,6 +16,7 @@ from ..jsinterp import JSInterpreter
from ..swfinterp import SWFInterpreter
from ..compat import (
compat_chr,
compat_HTTPError,
compat_kwargs,
compat_parse_qs,
compat_urllib_parse_unquote,
@ -288,10 +289,25 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
if not mobj:
break
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), playlist_id,
'Downloading page #%s' % page_num,
transform_source=uppercase_escape)
count = 0
retries = 3
while count <= retries:
try:
# Downloading page may result in intermittent 5xx HTTP error
# that is usually worked around with a retry
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), playlist_id,
'Downloading page #%s%s'
% (page_num, ' (retry #%d)' % count if count else ''),
transform_source=uppercase_escape)
break
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503):
count += 1
if count <= retries:
continue
raise
content_html = more['content_html']
if not content_html.strip():
# Some webpages show a "Load more" button but they don't
@ -1773,9 +1789,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
raise ExtractorError(
'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
if video_info.get('license_info'):
raise ExtractorError('This video is DRM protected.', expected=True)
video_details = try_get(
player_response, lambda x: x['videoDetails'], dict) or {}
@ -1911,7 +1924,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
formats = []
for url_data_str in encoded_url_map.split(','):
url_data = compat_parse_qs(url_data_str)
if 'itag' not in url_data or 'url' not in url_data:
if 'itag' not in url_data or 'url' not in url_data or url_data.get('drm_families'):
continue
stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
# Unsupported FORMAT_STREAM_TYPE_OTF
@ -1971,7 +1984,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
signature = self._decrypt_signature(
encrypted_sig, video_id, player_url, age_gate)
url += '&signature=' + signature
sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature'
url += '&%s=%s' % (sp, signature)
if 'ratebypass' not in url:
url += '&ratebypass=yes'
@ -2035,8 +2049,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
url_or_none(try_get(
player_response,
lambda x: x['streamingData']['hlsManifestUrl'],
compat_str)) or
url_or_none(try_get(
compat_str))
or url_or_none(try_get(
video_info, lambda x: x['hlsvp'][0], compat_str)))
if manifest_url:
formats = []
@ -2084,8 +2098,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
else:
self._downloader.report_warning('unable to extract uploader nickname')
channel_id = self._html_search_meta(
'channelId', video_webpage, 'channel id')
channel_id = (
str_or_none(video_details.get('channelId'))
or self._html_search_meta(
'channelId', video_webpage, 'channel id', default=None)
or self._search_regex(
r'data-channel-external-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
video_webpage, 'channel id', default=None, group='id'))
channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
# thumbnail image
@ -2301,6 +2320,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'"token" parameter not in video info for unknown reason',
video_id=video_id)
if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])):
raise ExtractorError('This video is DRM protected.', expected=True)
self._sort_formats(formats)
self.mark_watched(video_id, video_info, player_response)
@ -2542,9 +2564,9 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
title_span = (
search_title('playlist-title') or
search_title('title long-title') or
search_title('title'))
search_title('playlist-title')
or search_title('title long-title')
or search_title('title'))
title = clean_html(title_span)
return self.playlist_result(url_results, playlist_id, title)

4
youtube_dl/extractor/zattoo.py
View File

@ -86,8 +86,8 @@ class ZattooPlatformBaseIE(InfoExtractor):
return next(
chan['cid'] for chan in channel_list
if chan.get('cid') and (
chan.get('display_alias') == channel_name or
chan.get('cid') == channel_name))
chan.get('display_alias') == channel_name
or chan.get('cid') == channel_name))
except StopIteration:
raise ExtractorError('Could not extract channel id')

10
youtube_dl/postprocessor/ffmpeg.py
View File

@ -221,9 +221,9 @@ class FFmpegPostProcessor(PostProcessor):
# avconv does not have repeat option
if self.basename == 'ffmpeg':
cmd += [encodeArgument('-loglevel'), encodeArgument('repeat+info')]
cmd += (files_cmd +
[encodeArgument(o) for o in opts] +
[encodeFilename(self._ffmpeg_filename_argument(out_path), True)])
cmd += (files_cmd
+ [encodeArgument(o) for o in opts]
+ [encodeFilename(self._ffmpeg_filename_argument(out_path), True)])
if self._downloader.params.get('verbose', False):
self._downloader.to_screen('[debug] ffmpeg command line: %s' % shell_quote(cmd))
@ -326,8 +326,8 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
information['ext'] = extension
# If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
if (new_path == path or
(self._nopostoverwrites and os.path.exists(encodeFilename(new_path)))):
if (new_path == path
or (self._nopostoverwrites and os.path.exists(encodeFilename(new_path)))):
self._downloader.to_screen('[ffmpeg] Post-process file %s exists, skipping' % new_path)
return [], information

4
youtube_dl/postprocessor/xattrpp.py
View File

@ -64,8 +64,8 @@ class XAttrMetadataPP(PostProcessor):
except XAttrMetadataError as e:
if e.reason == 'NO_SPACE':
self._downloader.report_warning(
'There\'s no disk space left, disk quota exceeded or filesystem xattr limit exceeded. ' +
(('Some ' if num_written else '') + 'extended attributes are not written.').capitalize())
'There\'s no disk space left, disk quota exceeded or filesystem xattr limit exceeded. '
+ (('Some ' if num_written else '') + 'extended attributes are not written.').capitalize())
elif e.reason == 'VALUE_TOO_LONG':
self._downloader.report_warning(
'Unable to write extended attributes due to too long values.')

42
youtube_dl/utils.py
View File

@ -125,8 +125,8 @@ KNOWN_EXTENSIONS = (
# needed for sanitizing filenames in restricted mode
ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ',
itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOO', ['OE'], 'UUUUUYP', ['ss'],
'aaaaaa', ['ae'], 'ceeeeiiiionooooooo', ['oe'], 'uuuuuypy')))
itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOO', ['OE'], 'UUUUUY', ['TH', 'ss'],
'aaaaaa', ['ae'], 'ceeeeiiiionooooooo', ['oe'], 'uuuuuy', ['th'], 'y')))
DATE_FORMATS = (
'%d %B %Y',
@ -861,8 +861,8 @@ class XAttrMetadataError(YoutubeDLError):
self.msg = msg
# Parsing code and msg
if (self.code in (errno.ENOSPC, errno.EDQUOT) or
'No space left' in self.msg or 'Disk quota excedded' in self.msg):
if (self.code in (errno.ENOSPC, errno.EDQUOT)
or 'No space left' in self.msg or 'Disk quota excedded' in self.msg):
self.reason = 'NO_SPACE'
elif self.code == errno.E2BIG or 'Argument list too long' in self.msg:
self.reason = 'VALUE_TOO_LONG'
@ -1453,8 +1453,8 @@ def _windows_write_string(s, out):
def not_a_console(handle):
if handle == INVALID_HANDLE_VALUE or handle is None:
return True
return ((GetFileType(handle) & ~FILE_TYPE_REMOTE) != FILE_TYPE_CHAR or
GetConsoleMode(handle, ctypes.byref(ctypes.wintypes.DWORD())) == 0)
return ((GetFileType(handle) & ~FILE_TYPE_REMOTE) != FILE_TYPE_CHAR
or GetConsoleMode(handle, ctypes.byref(ctypes.wintypes.DWORD())) == 0)
if not_a_console(h):
return False
@ -1490,8 +1490,8 @@ def write_string(s, out=None, encoding=None):
if _windows_write_string(s, out):
return
if ('b' in getattr(out, 'mode', '') or
sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr
if ('b' in getattr(out, 'mode', '')
or sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr
byt = s.encode(encoding or preferredencoding(), 'ignore')
out.write(byt)
elif hasattr(out, 'buffer'):
@ -1951,8 +1951,8 @@ def bool_or_none(v, default=None):
return v if isinstance(v, bool) else default
def strip_or_none(v):
return None if v is None else v.strip()
def strip_or_none(v, default=None):
return v.strip() if isinstance(v, compat_str) else default
def url_or_none(url):
@ -2328,10 +2328,10 @@ def merge_dicts(*dicts):
for k, v in a_dict.items():
if v is None:
continue
if (k not in merged or
(isinstance(v, compat_str) and v and
isinstance(merged[k], compat_str) and
not merged[k])):
if (k not in merged
or (isinstance(v, compat_str) and v
and isinstance(merged[k], compat_str)
and not merged[k])):
merged[k] = v
return merged
@ -2657,14 +2657,14 @@ def _match_one(filter_part, dct):
if m:
op = COMPARISON_OPERATORS[m.group('op')]
actual_value = dct.get(m.group('key'))
if (m.group('quotedstrval') is not None or
m.group('strval') is not None or
if (m.group('quotedstrval') is not None
or m.group('strval') is not None
# If the original field is a string and matching comparisonvalue is
# a number we should respect the origin of the original field
# and process comparison value as a string (see
# https://github.com/ytdl-org/youtube-dl/issues/11082).
actual_value is not None and m.group('intval') is not None and
isinstance(actual_value, compat_str)):
or actual_value is not None and m.group('intval') is not None
and isinstance(actual_value, compat_str)):
if m.group('op') not in ('=', '!='):
raise ValueError(
'Operator %s does not support string values!' % m.group('op'))
@ -3973,9 +3973,9 @@ def write_xattr(path, key, value):
executable = 'xattr'
opts = ['-w', key, value]
cmd = ([encodeFilename(executable, True)] +
[encodeArgument(o) for o in opts] +
[encodeFilename(path, True)])
cmd = ([encodeFilename(executable, True)]
+ [encodeArgument(o) for o in opts]
+ [encodeFilename(path, True)])
try:
p = subprocess.Popen(

2
youtube_dl/version.py
View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2019.04.30'
__version__ = '2019.05.20'