Compare commits

...

5 Commits

Author SHA1 Message Date
dirkf
cc179df346 [XHamster] Support xhday.com alias, extract uploader_id
* support xhday.com alias for xhamster.com (resolves #31023)
  Authored by: dirkf
* extract `uploader_id`:
  from 908b56eaf7
  (PR https://github.com/yt-dlp/yt-dlp/pull/844)
  Authored by: octotherp
2022-06-12 14:10:38 +01:00
pukkandan
0700fde640 [utils, etc] Kill child processes when yt-dl is killed
* derived from PR #26592, closes #26592

Authored by: Unrud
2022-06-10 19:57:46 +01:00
dirkf
811c480f7b [YouTube] Support JSON3 subtitle format
* subtitle tests updated to match
2022-06-09 15:25:23 +01:00
dirkf
3aa94d7945 [test] Fix workable subtitle tests (except YT) and mark others as skip, broken
* broken tests need to be fixed when fixing the respective IE
2022-06-08 23:11:33 +01:00
dirkf
ef044be34b [test] Skip not _WORKING IE in subtitle tests; use unittest.skipTest throughout 2022-06-08 15:52:21 +01:00
12 changed files with 134 additions and 56 deletions

View File

@ -88,7 +88,6 @@ class TestDownload(unittest.TestCase):
# Dynamically generate tests # Dynamically generate tests
def generator(test_case, tname): def generator(test_case, tname):
def test_template(self): def test_template(self):
@ -100,9 +99,10 @@ def generator(test_case, tname):
def print_skipping(reason): def print_skipping(reason):
print('Skipping %s: %s' % (test_case['name'], reason)) print('Skipping %s: %s' % (test_case['name'], reason))
self.skipTest(reason)
if not ie.working(): if not ie.working():
print_skipping('IE marked as not _WORKING') print_skipping('IE marked as not _WORKING')
return
for tc in test_cases: for tc in test_cases:
info_dict = tc.get('info_dict', {}) info_dict = tc.get('info_dict', {})
@ -111,11 +111,10 @@ def generator(test_case, tname):
if 'skip' in test_case: if 'skip' in test_case:
print_skipping(test_case['skip']) print_skipping(test_case['skip'])
return
for other_ie in other_ies: for other_ie in other_ies:
if not other_ie.working(): if not other_ie.working():
print_skipping('test depends on %sIE, marked as not WORKING' % other_ie.ie_key()) print_skipping('test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
return
params = get_params(test_case.get('params', {})) params = get_params(test_case.get('params', {}))
params['outtmpl'] = tname + '_' + params['outtmpl'] params['outtmpl'] = tname + '_' + params['outtmpl']

View File

@ -38,6 +38,9 @@ class BaseTestSubtitles(unittest.TestCase):
self.DL = FakeYDL() self.DL = FakeYDL()
self.ie = self.IE() self.ie = self.IE()
self.DL.add_info_extractor(self.ie) self.DL.add_info_extractor(self.ie)
if not self.IE.working():
print('Skipping: %s marked as not _WORKING' % self.IE.ie_key())
self.skipTest('IE marked as not _WORKING')
def getInfoDict(self): def getInfoDict(self):
info_dict = self.DL.extract_info(self.url, download=False) info_dict = self.DL.extract_info(self.url, download=False)
@ -56,6 +59,21 @@ class BaseTestSubtitles(unittest.TestCase):
class TestYoutubeSubtitles(BaseTestSubtitles): class TestYoutubeSubtitles(BaseTestSubtitles):
# Available subtitles for QRS8MkLhQmM:
# Language formats
# ru vtt, ttml, srv3, srv2, srv1, json3
# fr vtt, ttml, srv3, srv2, srv1, json3
# en vtt, ttml, srv3, srv2, srv1, json3
# nl vtt, ttml, srv3, srv2, srv1, json3
# de vtt, ttml, srv3, srv2, srv1, json3
# ko vtt, ttml, srv3, srv2, srv1, json3
# it vtt, ttml, srv3, srv2, srv1, json3
# zh-Hant vtt, ttml, srv3, srv2, srv1, json3
# hi vtt, ttml, srv3, srv2, srv1, json3
# pt-BR vtt, ttml, srv3, srv2, srv1, json3
# es-MX vtt, ttml, srv3, srv2, srv1, json3
# ja vtt, ttml, srv3, srv2, srv1, json3
# pl vtt, ttml, srv3, srv2, srv1, json3
url = 'QRS8MkLhQmM' url = 'QRS8MkLhQmM'
IE = YoutubeIE IE = YoutubeIE
@ -64,41 +82,60 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 13) self.assertEqual(len(subtitles.keys()), 13)
self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06') self.assertEqual(md5(subtitles['en']), 'ae1bd34126571a77aabd4d276b28044d')
self.assertEqual(md5(subtitles['it']), '6d752b98c31f1cf8d597050c7a2cb4b5') self.assertEqual(md5(subtitles['it']), '0e0b667ba68411d88fd1c5f4f4eab2f9')
for lang in ['fr', 'de']: for lang in ['fr', 'de']:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
def test_youtube_subtitles_ttml_format(self): def _test_subtitles_format(self, fmt, md5_hash, lang='en'):
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['subtitlesformat'] = 'ttml' self.DL.params['subtitlesformat'] = fmt
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), 'e306f8c42842f723447d9f63ad65df54') self.assertEqual(md5(subtitles[lang]), md5_hash)
def test_youtube_subtitles_ttml_format(self):
self._test_subtitles_format('ttml', 'c97ddf1217390906fa9fbd34901f3da2')
def test_youtube_subtitles_vtt_format(self): def test_youtube_subtitles_vtt_format(self):
self.DL.params['writesubtitles'] = True self._test_subtitles_format('vtt', 'ae1bd34126571a77aabd4d276b28044d')
self.DL.params['subtitlesformat'] = 'vtt'
def test_youtube_subtitles_json3_format(self):
self._test_subtitles_format('json3', '688dd1ce0981683867e7fe6fde2a224b')
def _test_automatic_captions(self, url, lang):
self.url = url
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslangs'] = [lang]
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06') self.assertTrue(subtitles[lang] is not None)
def test_youtube_automatic_captions(self): def test_youtube_automatic_captions(self):
self.url = '8YoUxe5ncPo' # Available automatic captions for 8YoUxe5ncPo:
self.DL.params['writeautomaticsub'] = True # Language formats (all in vtt, ttml, srv3, srv2, srv1, json3)
self.DL.params['subtitleslangs'] = ['it'] # gu, zh-Hans, zh-Hant, gd, ga, gl, lb, la, lo, tt, tr,
subtitles = self.getSubtitles() # lv, lt, tk, th, tg, te, fil, haw, yi, ceb, yo, de, da,
self.assertTrue(subtitles['it'] is not None) # el, eo, en, eu, et, es, ru, rw, ro, bn, be, bg, uk, jv,
# bs, ja, or, xh, co, ca, cy, cs, ps, pt, pa, vi, pl, hy,
# hr, ht, hu, hmn, hi, ha, mg, uz, ml, mn, mi, mk, ur,
# mt, ms, mr, ug, ta, my, af, sw, is, am,
# *it*, iw, sv, ar,
# su, zu, az, id, ig, nl, no, ne, ny, fr, ku, fy, fa, fi,
# ka, kk, sr, sq, ko, kn, km, st, sk, si, so, sn, sm, sl,
# ky, sd
# ...
self._test_automatic_captions('8YoUxe5ncPo', 'it')
@unittest.skip('ASR subs all in all supported langs now')
def test_youtube_translated_subtitles(self): def test_youtube_translated_subtitles(self):
# This video has a subtitles track, which can be translated # This video has a subtitles track, which can be translated (#4555)
self.url = 'Ky9eprVWzlI' self._test_automatic_captions('Ky9eprVWzlI', 'it')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslangs'] = ['it']
subtitles = self.getSubtitles()
self.assertTrue(subtitles['it'] is not None)
def test_youtube_nosubtitles(self): def test_youtube_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles') self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'n5BB19UTcdA' # Available automatic captions for 8YoUxe5ncPo:
# ...
# 8YoUxe5ncPo has no subtitles
self.url = '8YoUxe5ncPo'
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
@ -128,6 +165,7 @@ class TestDailymotionSubtitles(BaseTestSubtitles):
self.assertFalse(subtitles) self.assertFalse(subtitles)
@unittest.skip('IE broken')
class TestTedSubtitles(BaseTestSubtitles): class TestTedSubtitles(BaseTestSubtitles):
url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html' url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html'
IE = TEDIE IE = TEDIE
@ -152,18 +190,19 @@ class TestVimeoSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr'])) self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr']))
self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888') self.assertEqual(md5(subtitles['en']), '386cbc9320b94e25cb364b97935e5dd1')
self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8') self.assertEqual(md5(subtitles['fr']), 'c9b69eef35bc6641c0d4da8a04f9dfac')
def test_nosubtitles(self): def test_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles') self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'http://vimeo.com/56015672' self.url = 'http://vimeo.com/68093876'
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertFalse(subtitles) self.assertFalse(subtitles)
@unittest.skip('IE broken')
class TestWallaSubtitles(BaseTestSubtitles): class TestWallaSubtitles(BaseTestSubtitles):
url = 'http://vod.walla.co.il/movie/2705958/the-yes-men' url = 'http://vod.walla.co.il/movie/2705958/the-yes-men'
IE = WallaIE IE = WallaIE
@ -185,6 +224,7 @@ class TestWallaSubtitles(BaseTestSubtitles):
self.assertFalse(subtitles) self.assertFalse(subtitles)
@unittest.skip('IE broken')
class TestCeskaTelevizeSubtitles(BaseTestSubtitles): class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky' url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky'
IE = CeskaTelevizeIE IE = CeskaTelevizeIE
@ -206,6 +246,7 @@ class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
self.assertFalse(subtitles) self.assertFalse(subtitles)
@unittest.skip('IE broken')
class TestLyndaSubtitles(BaseTestSubtitles): class TestLyndaSubtitles(BaseTestSubtitles):
url = 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html' url = 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html'
IE = LyndaIE IE = LyndaIE
@ -218,6 +259,7 @@ class TestLyndaSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['en']), '09bbe67222259bed60deaa26997d73a7') self.assertEqual(md5(subtitles['en']), '09bbe67222259bed60deaa26997d73a7')
@unittest.skip('IE broken')
class TestNPOSubtitles(BaseTestSubtitles): class TestNPOSubtitles(BaseTestSubtitles):
url = 'http://www.npo.nl/nos-journaal/28-08-2014/POW_00722860' url = 'http://www.npo.nl/nos-journaal/28-08-2014/POW_00722860'
IE = NPOIE IE = NPOIE
@ -230,6 +272,7 @@ class TestNPOSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['nl']), 'fc6435027572b63fb4ab143abd5ad3f4') self.assertEqual(md5(subtitles['nl']), 'fc6435027572b63fb4ab143abd5ad3f4')
@unittest.skip('IE broken')
class TestMTVSubtitles(BaseTestSubtitles): class TestMTVSubtitles(BaseTestSubtitles):
url = 'http://www.cc.com/video-clips/p63lk0/adam-devine-s-house-party-chasing-white-swans' url = 'http://www.cc.com/video-clips/p63lk0/adam-devine-s-house-party-chasing-white-swans'
IE = ComedyCentralIE IE = ComedyCentralIE
@ -253,8 +296,8 @@ class TestNRKSubtitles(BaseTestSubtitles):
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['no'])) self.assertEqual(set(subtitles.keys()), set(['nb-ttv']))
self.assertEqual(md5(subtitles['no']), '544fa917d3197fcbee64634559221cc2') self.assertEqual(md5(subtitles['nb-ttv']), '67e06ff02d0deaf975e68f6cb8f6a149')
class TestRaiPlaySubtitles(BaseTestSubtitles): class TestRaiPlaySubtitles(BaseTestSubtitles):
@ -277,6 +320,7 @@ class TestRaiPlaySubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['it']), '4b3264186fbb103508abe5311cfcb9cd') self.assertEqual(md5(subtitles['it']), '4b3264186fbb103508abe5311cfcb9cd')
@unittest.skip('IE broken - DRM only')
class TestVikiSubtitles(BaseTestSubtitles): class TestVikiSubtitles(BaseTestSubtitles):
url = 'http://www.viki.com/videos/1060846v-punch-episode-18' url = 'http://www.viki.com/videos/1060846v-punch-episode-18'
IE = VikiIE IE = VikiIE
@ -303,6 +347,7 @@ class TestThePlatformSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['en']), '97e7670cbae3c4d26ae8bcc7fdd78d4b') self.assertEqual(md5(subtitles['en']), '97e7670cbae3c4d26ae8bcc7fdd78d4b')
@unittest.skip('IE broken')
class TestThePlatformFeedSubtitles(BaseTestSubtitles): class TestThePlatformFeedSubtitles(BaseTestSubtitles):
url = 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207' url = 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207'
IE = ThePlatformFeedIE IE = ThePlatformFeedIE
@ -338,7 +383,7 @@ class TestDemocracynowSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en'])) self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c') self.assertEqual(md5(subtitles['en']), 'a3cc4c0b5eadd74d9974f1c1f5101045')
def test_subtitles_in_page(self): def test_subtitles_in_page(self):
self.url = 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree' self.url = 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree'
@ -346,7 +391,7 @@ class TestDemocracynowSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en'])) self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c') self.assertEqual(md5(subtitles['en']), 'a3cc4c0b5eadd74d9974f1c1f5101045')
if __name__ == '__main__': if __name__ == '__main__':

View File

@ -73,6 +73,7 @@ from .utils import (
PostProcessingError, PostProcessingError,
preferredencoding, preferredencoding,
prepend_extension, prepend_extension,
process_communicate_or_kill,
register_socks_protocols, register_socks_protocols,
render_table, render_table,
replace_extension, replace_extension,
@ -2323,7 +2324,7 @@ class YoutubeDL(object):
['git', 'rev-parse', '--short', 'HEAD'], ['git', 'rev-parse', '--short', 'HEAD'],
stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE,
cwd=os.path.dirname(os.path.abspath(__file__))) cwd=os.path.dirname(os.path.abspath(__file__)))
out, err = sp.communicate() out, err = process_communicate_or_kill(sp)
out = out.decode().strip() out = out.decode().strip()
if re.match('[0-9a-f]+', out): if re.match('[0-9a-f]+', out):
self._write_string('[debug] Git HEAD: ' + out + '\n') self._write_string('[debug] Git HEAD: ' + out + '\n')

View File

@ -2890,6 +2890,7 @@ else:
_terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines']) _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
def compat_get_terminal_size(fallback=(80, 24)): def compat_get_terminal_size(fallback=(80, 24)):
from .utils import process_communicate_or_kill
columns = compat_getenv('COLUMNS') columns = compat_getenv('COLUMNS')
if columns: if columns:
columns = int(columns) columns = int(columns)
@ -2906,7 +2907,7 @@ else:
sp = subprocess.Popen( sp = subprocess.Popen(
['stty', 'size'], ['stty', 'size'],
stdout=subprocess.PIPE, stderr=subprocess.PIPE) stdout=subprocess.PIPE, stderr=subprocess.PIPE)
out, err = sp.communicate() out, err = process_communicate_or_kill(sp)
_lines, _columns = map(int, out.split()) _lines, _columns = map(int, out.split())
except Exception: except Exception:
_columns, _lines = _terminal_size(*fallback) _columns, _lines = _terminal_size(*fallback)

View File

@ -22,6 +22,7 @@ from ..utils import (
handle_youtubedl_headers, handle_youtubedl_headers,
check_executable, check_executable,
is_outdated_version, is_outdated_version,
process_communicate_or_kill,
) )
@ -104,7 +105,7 @@ class ExternalFD(FileDownloader):
p = subprocess.Popen( p = subprocess.Popen(
cmd, stderr=subprocess.PIPE) cmd, stderr=subprocess.PIPE)
_, stderr = p.communicate() _, stderr = process_communicate_or_kill(p)
if p.returncode != 0: if p.returncode != 0:
self.to_stderr(stderr.decode('utf-8', 'replace')) self.to_stderr(stderr.decode('utf-8', 'replace'))
return p.returncode return p.returncode
@ -141,7 +142,7 @@ class CurlFD(ExternalFD):
# curl writes the progress to stderr so don't capture it. # curl writes the progress to stderr so don't capture it.
p = subprocess.Popen(cmd) p = subprocess.Popen(cmd)
p.communicate() process_communicate_or_kill(p)
return p.returncode return p.returncode
@ -336,14 +337,17 @@ class FFmpegFD(ExternalFD):
proc = subprocess.Popen(args, stdin=subprocess.PIPE, env=env) proc = subprocess.Popen(args, stdin=subprocess.PIPE, env=env)
try: try:
retval = proc.wait() retval = proc.wait()
except KeyboardInterrupt: except BaseException as e:
# subprocces.run would send the SIGKILL signal to ffmpeg and the # subprocess.run would send the SIGKILL signal to ffmpeg and the
# mp4 file couldn't be played, but if we ask ffmpeg to quit it # mp4 file couldn't be played, but if we ask ffmpeg to quit it
# produces a file that is playable (this is mostly useful for live # produces a file that is playable (this is mostly useful for live
# streams). Note that Windows is not affected and produces playable # streams). Note that Windows is not affected and produces playable
# files (see https://github.com/ytdl-org/youtube-dl/issues/8300). # files (see https://github.com/ytdl-org/youtube-dl/issues/8300).
if sys.platform != 'win32': if isinstance(e, KeyboardInterrupt) and sys.platform != 'win32':
proc.communicate(b'q') process_communicate_or_kill(proc, b'q')
else:
proc.kill()
proc.wait()
raise raise
return retval return retval

View File

@ -89,11 +89,13 @@ class RtmpFD(FileDownloader):
self.to_screen('') self.to_screen('')
cursor_in_new_line = True cursor_in_new_line = True
self.to_screen('[rtmpdump] ' + line) self.to_screen('[rtmpdump] ' + line)
finally:
proc.wait()
if not cursor_in_new_line: if not cursor_in_new_line:
self.to_screen('') self.to_screen('')
return proc.returncode return proc.wait()
except BaseException: # Including KeyboardInterrupt
proc.kill()
proc.wait()
raise
url = info_dict['url'] url = info_dict['url']
player_url = info_dict.get('player_url') player_url = info_dict.get('player_url')

View File

@ -16,6 +16,7 @@ from ..utils import (
ExtractorError, ExtractorError,
get_exe_version, get_exe_version,
is_outdated_version, is_outdated_version,
process_communicate_or_kill,
std_headers, std_headers,
) )
@ -226,7 +227,7 @@ class PhantomJSwrapper(object):
self.exe, '--ssl-protocol=any', self.exe, '--ssl-protocol=any',
self._TMP_FILES['script'].name self._TMP_FILES['script'].name
], stdout=subprocess.PIPE, stderr=subprocess.PIPE) ], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
out, err = p.communicate() out, err = process_communicate_or_kill(p)
if p.returncode != 0: if p.returncode != 0:
raise ExtractorError( raise ExtractorError(
'Executing JS failed\n:' + encodeArgument(err)) 'Executing JS failed\n:' + encodeArgument(err))

View File

@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import itertools import itertools
@ -23,7 +24,7 @@ from ..utils import (
class XHamsterIE(InfoExtractor): class XHamsterIE(InfoExtractor):
_DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com)' _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com|xhday\.com)'
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
https?:// https?://
(?:.+?\.)?%s/ (?:.+?\.)?%s/
@ -34,7 +35,7 @@ class XHamsterIE(InfoExtractor):
''' % _DOMAINS ''' % _DOMAINS
_TESTS = [{ _TESTS = [{
'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445', 'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
'md5': '98b4687efb1ffd331c4197854dc09e8f', 'md5': '34e1ab926db5dc2750fed9e1f34304bb',
'info_dict': { 'info_dict': {
'id': '1509445', 'id': '1509445',
'display_id': 'femaleagent-shy-beauty-takes-the-bait', 'display_id': 'femaleagent-shy-beauty-takes-the-bait',
@ -43,6 +44,7 @@ class XHamsterIE(InfoExtractor):
'timestamp': 1350194821, 'timestamp': 1350194821,
'upload_date': '20121014', 'upload_date': '20121014',
'uploader': 'Ruseful2011', 'uploader': 'Ruseful2011',
'uploader_id': 'ruseful2011',
'duration': 893, 'duration': 893,
'age_limit': 18, 'age_limit': 18,
}, },
@ -72,6 +74,7 @@ class XHamsterIE(InfoExtractor):
'timestamp': 1454948101, 'timestamp': 1454948101,
'upload_date': '20160208', 'upload_date': '20160208',
'uploader': 'parejafree', 'uploader': 'parejafree',
'uploader_id': 'parejafree',
'duration': 72, 'duration': 72,
'age_limit': 18, 'age_limit': 18,
}, },
@ -117,6 +120,9 @@ class XHamsterIE(InfoExtractor):
}, { }, {
'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx', 'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://xhday.com/videos/strapless-threesome-xhh7yVf',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -245,6 +251,7 @@ class XHamsterIE(InfoExtractor):
else: else:
categories = None categories = None
uploader_url = url_or_none(try_get(video, lambda x: x['author']['pageURL']))
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
@ -253,6 +260,8 @@ class XHamsterIE(InfoExtractor):
'timestamp': int_or_none(video.get('created')), 'timestamp': int_or_none(video.get('created')),
'uploader': try_get( 'uploader': try_get(
video, lambda x: x['author']['name'], compat_str), video, lambda x: x['author']['name'], compat_str),
'uploader_url': uploader_url,
'uploader_id': uploader_url.split('/')[-1] if uploader_url else None,
'thumbnail': video.get('thumbURL'), 'thumbnail': video.get('thumbURL'),
'duration': int_or_none(video.get('duration')), 'duration': int_or_none(video.get('duration')),
'view_count': int_or_none(video.get('views')), 'view_count': int_or_none(video.get('views')),
@ -261,7 +270,7 @@ class XHamsterIE(InfoExtractor):
'dislike_count': int_or_none(try_get( 'dislike_count': int_or_none(try_get(
video, lambda x: x['rating']['dislikes'], int)), video, lambda x: x['rating']['dislikes'], int)),
'comment_count': int_or_none(video.get('views')), 'comment_count': int_or_none(video.get('views')),
'age_limit': age_limit, 'age_limit': age_limit if age_limit is not None else 18,
'categories': categories, 'categories': categories,
'formats': formats, 'formats': formats,
} }
@ -352,6 +361,7 @@ class XHamsterIE(InfoExtractor):
'description': description, 'description': description,
'upload_date': upload_date, 'upload_date': upload_date,
'uploader': uploader, 'uploader': uploader,
'uploader_id': uploader.lower() if uploader else None,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'duration': duration, 'duration': duration,
'view_count': view_count, 'view_count': view_count,
@ -420,6 +430,9 @@ class XHamsterUserIE(InfoExtractor):
'id': 'firatkaan', 'id': 'firatkaan',
}, },
'playlist_mincount': 1, 'playlist_mincount': 1,
}, {
'url': 'https://xhday.com/users/mobhunter',
'only_matching': True,
}] }]
def _entries(self, user_id): def _entries(self, user_id):

View File

@ -499,7 +499,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$', r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$', r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
) )
_SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt') _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
_GEO_BYPASS = False _GEO_BYPASS = False

View File

@ -13,8 +13,9 @@ from ..utils import (
encodeFilename, encodeFilename,
PostProcessingError, PostProcessingError,
prepend_extension, prepend_extension,
process_communicate_or_kill,
replace_extension, replace_extension,
shell_quote shell_quote,
) )
@ -109,7 +110,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
self._downloader.to_screen('[debug] AtomicParsley command line: %s' % shell_quote(cmd)) self._downloader.to_screen('[debug] AtomicParsley command line: %s' % shell_quote(cmd))
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
stdout, stderr = p.communicate() stdout, stderr = process_communicate_or_kill(p)
if p.returncode != 0: if p.returncode != 0:
msg = stderr.decode('utf-8', 'replace').strip() msg = stderr.decode('utf-8', 'replace').strip()

View File

@ -16,6 +16,7 @@ from ..utils import (
is_outdated_version, is_outdated_version,
PostProcessingError, PostProcessingError,
prepend_extension, prepend_extension,
process_communicate_or_kill,
shell_quote, shell_quote,
subtitles_filename, subtitles_filename,
dfxp2srt, dfxp2srt,
@ -180,7 +181,7 @@ class FFmpegPostProcessor(PostProcessor):
handle = subprocess.Popen( handle = subprocess.Popen(
cmd, stderr=subprocess.PIPE, cmd, stderr=subprocess.PIPE,
stdout=subprocess.PIPE, stdin=subprocess.PIPE) stdout=subprocess.PIPE, stdin=subprocess.PIPE)
stdout_data, stderr_data = handle.communicate() stdout_data, stderr_data = process_communicate_or_kill(handle)
expected_ret = 0 if self.probe_available else 1 expected_ret = 0 if self.probe_available else 1
if handle.wait() != expected_ret: if handle.wait() != expected_ret:
return None return None
@ -228,7 +229,7 @@ class FFmpegPostProcessor(PostProcessor):
if self._downloader.params.get('verbose', False): if self._downloader.params.get('verbose', False):
self._downloader.to_screen('[debug] ffmpeg command line: %s' % shell_quote(cmd)) self._downloader.to_screen('[debug] ffmpeg command line: %s' % shell_quote(cmd))
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE) p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
stdout, stderr = p.communicate() stdout, stderr = process_communicate_or_kill(p)
if p.returncode != 0: if p.returncode != 0:
stderr = stderr.decode('utf-8', 'replace') stderr = stderr.decode('utf-8', 'replace')
msgs = stderr.strip().split('\n') msgs = stderr.strip().split('\n')

View File

@ -2212,6 +2212,15 @@ def unescapeHTML(s):
r'&([^&;]+;)', lambda m: _htmlentity_transform(m.group(1)), s) r'&([^&;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
def process_communicate_or_kill(p, *args, **kwargs):
try:
return p.communicate(*args, **kwargs)
except BaseException: # Including KeyboardInterrupt
p.kill()
p.wait()
raise
def get_subprocess_encoding(): def get_subprocess_encoding():
if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5: if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
# For subprocess calls, encode with locale encoding # For subprocess calls, encode with locale encoding
@ -3788,7 +3797,8 @@ def check_executable(exe, args=[]):
""" Checks if the given binary is installed somewhere in PATH, and returns its name. """ Checks if the given binary is installed somewhere in PATH, and returns its name.
args can be a list of arguments for a short output (like -version) """ args can be a list of arguments for a short output (like -version) """
try: try:
subprocess.Popen([exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate() process_communicate_or_kill(subprocess.Popen(
[exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE))
except OSError: except OSError:
return False return False
return exe return exe
@ -3802,10 +3812,10 @@ def get_exe_version(exe, args=['--version'],
# STDIN should be redirected too. On UNIX-like systems, ffmpeg triggers # STDIN should be redirected too. On UNIX-like systems, ffmpeg triggers
# SIGTTOU if youtube-dl is run in the background. # SIGTTOU if youtube-dl is run in the background.
# See https://github.com/ytdl-org/youtube-dl/issues/955#issuecomment-209789656 # See https://github.com/ytdl-org/youtube-dl/issues/955#issuecomment-209789656
out, _ = subprocess.Popen( out, _ = process_communicate_or_kill(subprocess.Popen(
[encodeArgument(exe)] + args, [encodeArgument(exe)] + args,
stdin=subprocess.PIPE, stdin=subprocess.PIPE,
stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate() stdout=subprocess.PIPE, stderr=subprocess.STDOUT))
except OSError: except OSError:
return False return False
if isinstance(out, bytes): # Python 2.x if isinstance(out, bytes): # Python 2.x
@ -5744,7 +5754,7 @@ def write_xattr(path, key, value):
cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE) cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
except EnvironmentError as e: except EnvironmentError as e:
raise XAttrMetadataError(e.errno, e.strerror) raise XAttrMetadataError(e.errno, e.strerror)
stdout, stderr = p.communicate() stdout, stderr = process_communicate_or_kill(p)
stderr = stderr.decode('utf-8', 'replace') stderr = stderr.decode('utf-8', 'replace')
if p.returncode != 0: if p.returncode != 0:
raise XAttrMetadataError(p.returncode, stderr) raise XAttrMetadataError(p.returncode, stderr)