Compare commits
14 Commits
660832b79e
...
72d1d1916e
Author | SHA1 | Date | |
---|---|---|---|
|
72d1d1916e | ||
|
4d05f84325 | ||
|
e0094e63c3 | ||
|
fd8242e3ef | ||
|
ad01fa6cca | ||
|
2eac0fa379 | ||
|
5aee29b7ca | ||
|
df617513cc | ||
|
e1b7640587 | ||
|
6d1af4e2cf | ||
|
f5e01562b1 | ||
|
2fcb8b8c20 | ||
|
7def329f19 | ||
|
d59b83f04b |
@ -577,9 +577,11 @@ class TestJSInterpreter(unittest.TestCase):
|
||||
def test_unary_operators(self):
|
||||
jsi = JSInterpreter('function f(){return 2 - - - 2;}')
|
||||
self.assertEqual(jsi.call_function('f'), 0)
|
||||
# fails
|
||||
# jsi = JSInterpreter('function f(){return 2 + - + - - 2;}')
|
||||
# self.assertEqual(jsi.call_function('f'), 0)
|
||||
jsi = JSInterpreter('function f(){return 2 + - + - - 2;}')
|
||||
self.assertEqual(jsi.call_function('f'), 0)
|
||||
# https://github.com/ytdl-org/youtube-dl/issues/32815
|
||||
jsi = JSInterpreter('function f(){return 0 - 7 * - 6;}')
|
||||
self.assertEqual(jsi.call_function('f'), 42)
|
||||
|
||||
""" # fails so far
|
||||
def test_packed(self):
|
||||
|
@ -158,6 +158,10 @@ _NSIG_TESTS = [
|
||||
'https://www.youtube.com/s/player/b7910ca8/player_ias.vflset/en_US/base.js',
|
||||
'_hXMCwMt9qE310D', 'LoZMgkkofRMCZQ',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/590f65a6/player_ias.vflset/en_US/base.js',
|
||||
'1tm7-g_A9zsI8_Lay_', 'xI4Vem4Put_rOg',
|
||||
),
|
||||
]
|
||||
|
||||
|
||||
|
@ -3033,7 +3033,6 @@ class InfoExtractor(object):
|
||||
transform_source=transform_source, default=None)
|
||||
|
||||
def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
|
||||
|
||||
# allow passing `transform_source` through to _find_jwplayer_data()
|
||||
transform_source = kwargs.pop('transform_source', None)
|
||||
kwfind = compat_kwargs({'transform_source': transform_source}) if transform_source else {}
|
||||
|
@ -8,7 +8,7 @@ from ..compat import compat_str
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
str_or_none,
|
||||
try_get,
|
||||
traverse_obj,
|
||||
)
|
||||
|
||||
|
||||
@ -118,7 +118,8 @@ class PalcoMP3ArtistIE(PalcoMP3BaseIE):
|
||||
artist = self._call_api(artist_slug, self._ARTIST_FIELDS_TMPL)['artist']
|
||||
|
||||
def entries():
|
||||
for music in (try_get(artist, lambda x: x['musics']['nodes'], list) or []):
|
||||
for music in traverse_obj(artist, (
|
||||
'musics', 'nodes', lambda _, m: m['musicID'])):
|
||||
yield self._parse_music(music)
|
||||
|
||||
return self.playlist_result(
|
||||
@ -137,7 +138,7 @@ class PalcoMP3VideoIE(PalcoMP3BaseIE):
|
||||
'title': 'Maiara e Maraisa - Você Faz Falta Aqui - DVD Ao Vivo Em Campo Grande',
|
||||
'description': 'md5:7043342c09a224598e93546e98e49282',
|
||||
'upload_date': '20161107',
|
||||
'uploader_id': 'maiaramaraisaoficial',
|
||||
'uploader_id': '@maiaramaraisaoficial',
|
||||
'uploader': 'Maiara e Maraisa',
|
||||
}
|
||||
}]
|
||||
|
@ -5,48 +5,52 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
parse_duration,
|
||||
unsmuggle_url,
|
||||
url_or_none,
|
||||
)
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..compat import compat_parse_qs
|
||||
|
||||
|
||||
class SenateISVPIE(InfoExtractor):
|
||||
|
||||
# [committee, stream_number, stream_domain, stream_id, msl3]
|
||||
_COMM_MAP = [
|
||||
['ag', '76440', 'http://ag-f.akamaihd.net'],
|
||||
['aging', '76442', 'http://aging-f.akamaihd.net'],
|
||||
['approps', '76441', 'http://approps-f.akamaihd.net'],
|
||||
['armed', '76445', 'http://armed-f.akamaihd.net'],
|
||||
['banking', '76446', 'http://banking-f.akamaihd.net'],
|
||||
['budget', '76447', 'http://budget-f.akamaihd.net'],
|
||||
['cecc', '76486', 'http://srs-f.akamaihd.net'],
|
||||
['commerce', '80177', 'http://commerce1-f.akamaihd.net'],
|
||||
['csce', '75229', 'http://srs-f.akamaihd.net'],
|
||||
['dpc', '76590', 'http://dpc-f.akamaihd.net'],
|
||||
['energy', '76448', 'http://energy-f.akamaihd.net'],
|
||||
['epw', '76478', 'http://epw-f.akamaihd.net'],
|
||||
['ethics', '76449', 'http://ethics-f.akamaihd.net'],
|
||||
['finance', '76450', 'http://finance-f.akamaihd.net'],
|
||||
['foreign', '76451', 'http://foreign-f.akamaihd.net'],
|
||||
['govtaff', '76453', 'http://govtaff-f.akamaihd.net'],
|
||||
['help', '76452', 'http://help-f.akamaihd.net'],
|
||||
['indian', '76455', 'http://indian-f.akamaihd.net'],
|
||||
['intel', '76456', 'http://intel-f.akamaihd.net'],
|
||||
['intlnarc', '76457', 'http://intlnarc-f.akamaihd.net'],
|
||||
['jccic', '85180', 'http://jccic-f.akamaihd.net'],
|
||||
['jec', '76458', 'http://jec-f.akamaihd.net'],
|
||||
['judiciary', '76459', 'http://judiciary-f.akamaihd.net'],
|
||||
['rpc', '76591', 'http://rpc-f.akamaihd.net'],
|
||||
['rules', '76460', 'http://rules-f.akamaihd.net'],
|
||||
['saa', '76489', 'http://srs-f.akamaihd.net'],
|
||||
['smbiz', '76461', 'http://smbiz-f.akamaihd.net'],
|
||||
['srs', '75229', 'http://srs-f.akamaihd.net'],
|
||||
['uscc', '76487', 'http://srs-f.akamaihd.net'],
|
||||
['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
|
||||
['arch', '', 'http://ussenate-f.akamaihd.net/']
|
||||
['ag', '76440', 'http://ag-f.akamaihd.net', '2036803', 'agriculture'],
|
||||
['aging', '76442', 'http://aging-f.akamaihd.net', '2036801', 'aging'],
|
||||
['approps', '76441', 'http://approps-f.akamaihd.net', '2036802', 'appropriations'],
|
||||
['armed', '76445', 'http://armed-f.akamaihd.net', '2036800', 'armedservices'],
|
||||
['banking', '76446', 'http://banking-f.akamaihd.net', '2036799', 'banking'],
|
||||
['budget', '76447', 'http://budget-f.akamaihd.net', '2036798', 'budget'],
|
||||
['cecc', '76486', 'http://srs-f.akamaihd.net', '2036782', 'srs_cecc'],
|
||||
['commerce', '80177', 'http://commerce1-f.akamaihd.net', '2036779', 'commerce'],
|
||||
['csce', '75229', 'http://srs-f.akamaihd.net', '2036777', 'srs_srs'],
|
||||
['dpc', '76590', 'http://dpc-f.akamaihd.net', None, 'dpc'],
|
||||
['energy', '76448', 'http://energy-f.akamaihd.net', '2036797', 'energy'],
|
||||
['epw', '76478', 'http://epw-f.akamaihd.net', '2036783', 'environment'],
|
||||
['ethics', '76449', 'http://ethics-f.akamaihd.net', '2036796', 'ethics'],
|
||||
['finance', '76450', 'http://finance-f.akamaihd.net', '2036795', 'finance_finance'],
|
||||
['foreign', '76451', 'http://foreign-f.akamaihd.net', '2036794', 'foreignrelations'],
|
||||
['govtaff', '76453', 'http://govtaff-f.akamaihd.net', '2036792', 'hsgac'],
|
||||
['help', '76452', 'http://help-f.akamaihd.net', '2036793', 'help'],
|
||||
['indian', '76455', 'http://indian-f.akamaihd.net', '2036791', 'indianaffairs'],
|
||||
['intel', '76456', 'http://intel-f.akamaihd.net', '2036790', 'intelligence'],
|
||||
['intlnarc', '76457', 'http://intlnarc-f.akamaihd.net', None, 'internationalnarcoticscaucus'],
|
||||
['jccic', '85180', 'http://jccic-f.akamaihd.net', '2036778', 'jccic'],
|
||||
['jec', '76458', 'http://jec-f.akamaihd.net', '2036789', 'jointeconomic'],
|
||||
['judiciary', '76459', 'http://judiciary-f.akamaihd.net', '2036788', 'judiciary'],
|
||||
['rpc', '76591', 'http://rpc-f.akamaihd.net', None, 'rpc'],
|
||||
['rules', '76460', 'http://rules-f.akamaihd.net', '2036787', 'rules'],
|
||||
['saa', '76489', 'http://srs-f.akamaihd.net', '2036780', 'srs_saa'],
|
||||
['smbiz', '76461', 'http://smbiz-f.akamaihd.net', '2036786', 'smallbusiness'],
|
||||
['srs', '75229', 'http://srs-f.akamaihd.net', '2031966', 'srs_srs'],
|
||||
['uscc', '76487', 'http://srs-f.akamaihd.net', '2036781', 'srs_uscc'],
|
||||
['vetaff', '76462', 'http://vetaff-f.akamaihd.net', '2036785', 'veteransaffairs'],
|
||||
['arch', '', 'http://ussenate-f.akamaihd.net/', None, None],
|
||||
['uscp', None, '', '2043685', 'uscp'],
|
||||
['cio', None, '', '2043686', 'cio']
|
||||
]
|
||||
|
||||
_IE_NAME = 'senate.gov'
|
||||
_VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
|
||||
_TESTS = [{
|
||||
@ -54,100 +58,120 @@ class SenateISVPIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': 'judiciary031715',
|
||||
'ext': 'mp4',
|
||||
'title': 'Integrated Senate Video Player',
|
||||
'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
|
||||
'info_dict': {
|
||||
'id': 'commerce011514',
|
||||
'ext': 'mp4',
|
||||
'title': 'Integrated Senate Video Player'
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
'title': 'judiciary031715',
|
||||
'thumbnail': 'http://www.judiciary.senate.gov/themes/judiciary/images/video-poster-flash-fit.png',
|
||||
},
|
||||
'expected_warnings': ['Failed to download m3u8 information: HTTP Error 404: Not Found'],
|
||||
}, {
|
||||
'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
|
||||
# checksum differs each time
|
||||
'info_dict': {
|
||||
'id': 'intel090613',
|
||||
'ext': 'mp4',
|
||||
'title': 'Integrated Senate Video Player'
|
||||
}
|
||||
'title': 'intel090613',
|
||||
},
|
||||
'expected_warnings': ['Failed to download m3u8 information: HTTP Error 404: Not Found'],
|
||||
}, {
|
||||
# From http://www.c-span.org/video/?96791-1
|
||||
'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715',
|
||||
'only_matching': True,
|
||||
'url': 'https://www.senate.gov/isvp/?comm=govtaff&type=archv&stt=975&filename=govtaff111722&auto_play=false&poster=https%3A%2F%2Fwww%2Ehsgac%2Esenate%2Egov%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng',
|
||||
'info_dict': {
|
||||
'id': 'govtaff111722',
|
||||
'ext': 'mp4',
|
||||
'title': 'govtaff111722',
|
||||
'thumbnail': 'https://www.hsgac.senate.gov/images/video-poster-flash-fit.png',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.senate.gov/isvp/?type=arch&comm=energy&filename=energy111722&stt=00:22:30&auto_play=false&wmode=transparent&poster=https%3A%2F%2Fwww%2Eenergy%2Esenate%2Egov%2Fthemes%2Fenergy%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng',
|
||||
'info_dict': {
|
||||
'id': 'energy111722',
|
||||
'ext': 'mp4',
|
||||
'title': 'energy111722',
|
||||
'thumbnail': 'https://www.energy.senate.gov/themes/energy/images/video-poster-flash-fit.png',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.senate.gov/isvp/?comm=foreign&type=archv&stt=0&filename=foreign080322&auto_play=false&wmode=transparent&poster=https%3A%2F%2Fwww%2Eforeign%2Esenate%2Egov%2Fthemes%2Fforeign%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng',
|
||||
'info_dict': {
|
||||
'id': 'foreign080322',
|
||||
'ext': 'mp4',
|
||||
'title': 'foreign080322',
|
||||
'thumbnail': 'https://www.foreign.senate.gov/themes/foreign/images/video-poster-flash-fit.png',
|
||||
},
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
# returns url from an iframe
|
||||
def _search_iframe_url(webpage):
|
||||
mobj = re.search(
|
||||
r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
|
||||
r'''<iframe\b[^>]+\bsrc\s*=\s*(['"])(?P<url>https?://www\.senate\.gov/isvp/?\?(?:(?!\1)\S)+)''',
|
||||
webpage)
|
||||
if mobj:
|
||||
return mobj.group('url')
|
||||
|
||||
@staticmethod
|
||||
def __dictify(cm):
|
||||
return dict((row[0], (row[1:] + ['', ''])[:4]) for row in cm)
|
||||
|
||||
# returns stream_number, stream_domain, stream_id, msl3
|
||||
def _get_info_for_comm(self, committee):
|
||||
for entry in self._COMM_MAP:
|
||||
if entry[0] == committee:
|
||||
return entry[1:]
|
||||
dict = self.__dictify(self._COMM_MAP)
|
||||
return dict[committee][0:]
|
||||
|
||||
def _real_extract(self, url):
|
||||
# smuggled data may contain a forced title that should be used
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
|
||||
qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs'))
|
||||
if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
|
||||
raise ExtractorError('Invalid URL', expected=True)
|
||||
|
||||
video_id = re.sub(r'.mp4$', '', qs['filename'][0])
|
||||
# error handling for invalid URL - specify which error
|
||||
if not qs.get('filename'):
|
||||
raise ExtractorError('Invalid URL. Missing filename in query parameters', expected=True)
|
||||
if not qs.get('comm'):
|
||||
raise ExtractorError('Invalid URL. Missing committee in query parameters', expected=True)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
committee = qs.get('comm')[0]
|
||||
filename = qs.get('filename')[0]
|
||||
video_id = re.sub(r'\.mp4$', '', filename)
|
||||
|
||||
if smuggled_data.get('force_title'):
|
||||
title = smuggled_data['force_title']
|
||||
else:
|
||||
title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
|
||||
poster = qs.get('poster')
|
||||
thumbnail = poster[0] if poster else None
|
||||
# there is no point in pulling the title from the webpage since it always defaults to 'Integrated Senate Player'
|
||||
title = smuggled_data.get('force_title') or filename
|
||||
|
||||
video_type = qs['type'][0]
|
||||
committee = video_type if video_type == 'arch' else qs['comm'][0]
|
||||
stream_num, domain = self._get_info_for_comm(committee)
|
||||
stream_number, stream_domain, stream_id, msl3 = self._get_info_for_comm(committee)
|
||||
stream_number = int(stream_number)
|
||||
stream_id = int(stream_id)
|
||||
|
||||
# the possible locations for the video: only the first has been seen in use
|
||||
possible_manifest_urls = [
|
||||
'https://www-senate-gov-media-srs.akamaized.net/hls/live/%d/%s/%s/master.m3u8' % (stream_id, committee, filename),
|
||||
'https://www-senate-gov-msl3archive.akamaized.net/%s/%s_1/master.m3u8' % (msl3, filename),
|
||||
'%s/i/%s_1@%d/master.m3u8' % (stream_domain, filename, stream_number),
|
||||
'https://ussenate-f.akamaihd.net/i/%s.mp4/master.m3u8' % video_id,
|
||||
]
|
||||
|
||||
# we iterate through the possible locations until we find formats
|
||||
formats = []
|
||||
if video_type == 'arch':
|
||||
filename = video_id if '.' in video_id else video_id + '.mp4'
|
||||
formats = [{
|
||||
# All parameters in the query string are necessary to prevent a 403 error
|
||||
'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
|
||||
}]
|
||||
else:
|
||||
hdcore_sign = 'hdcore=3.1.0'
|
||||
url_params = (domain, video_id, stream_num)
|
||||
f4m_url = '%s/z/%s_1@%s/manifest.f4m?' % url_params + hdcore_sign
|
||||
m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
|
||||
for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
|
||||
# URLs without the extra param induce an 404 error
|
||||
entry.update({'extra_param_to_segment_url': hdcore_sign})
|
||||
formats.append(entry)
|
||||
for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
|
||||
mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
|
||||
for url in possible_manifest_urls:
|
||||
entries = self._extract_m3u8_formats(
|
||||
url, video_id, ext='mp4', m3u8_id='hls',
|
||||
entry_protocol='m3u8_native', fatal=False)
|
||||
|
||||
for entry in entries:
|
||||
mobj = re.search(r'(?P<tag>-[pb]).m3u8', entry['url'])
|
||||
if mobj:
|
||||
entry['format_id'] += mobj.group('tag')
|
||||
formats.append(entry)
|
||||
|
||||
if formats:
|
||||
break
|
||||
|
||||
self._sort_formats(formats)
|
||||
thumbnail = url_or_none(qs.get('poster', [None])[-1])
|
||||
start_time = parse_duration(qs.get('stt', [None])[-1])
|
||||
stop_time = parse_duration(qs.get('dur', [None])[-1])
|
||||
if stop_time is not None:
|
||||
stop_time += start_time or 0
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': thumbnail,
|
||||
'start_time': start_time,
|
||||
'stop_time': stop_time,
|
||||
}
|
||||
|
@ -14,6 +14,7 @@ from .utils import (
|
||||
remove_quotes,
|
||||
unified_timestamp,
|
||||
variadic,
|
||||
write_string,
|
||||
)
|
||||
from .compat import (
|
||||
compat_basestring,
|
||||
@ -53,15 +54,16 @@ def wraps_op(op):
|
||||
|
||||
# NB In principle NaN cannot be checked by membership.
|
||||
# Here all NaN values are actually this one, so _NaN is _NaN,
|
||||
# although _NaN != _NaN.
|
||||
# although _NaN != _NaN. Ditto Infinity.
|
||||
|
||||
_NaN = float('nan')
|
||||
_Infinity = float('inf')
|
||||
|
||||
|
||||
def _js_bit_op(op):
|
||||
|
||||
def zeroise(x):
|
||||
return 0 if x in (None, JS_Undefined, _NaN) else x
|
||||
return 0 if x in (None, JS_Undefined, _NaN, _Infinity) else x
|
||||
|
||||
@wraps_op(op)
|
||||
def wrapped(a, b):
|
||||
@ -84,7 +86,7 @@ def _js_arith_op(op):
|
||||
def _js_div(a, b):
|
||||
if JS_Undefined in (a, b) or not (a or b):
|
||||
return _NaN
|
||||
return operator.truediv(a or 0, b) if b else float('inf')
|
||||
return operator.truediv(a or 0, b) if b else _Infinity
|
||||
|
||||
|
||||
def _js_mod(a, b):
|
||||
@ -220,6 +222,42 @@ class LocalNameSpace(ChainMap):
|
||||
return 'LocalNameSpace%s' % (self.maps, )
|
||||
|
||||
|
||||
class Debugger(object):
|
||||
ENABLED = False
|
||||
|
||||
@staticmethod
|
||||
def write(*args, **kwargs):
|
||||
level = kwargs.get('level', 100)
|
||||
|
||||
def truncate_string(s, left, right=0):
|
||||
if s is None or len(s) <= left + right:
|
||||
return s
|
||||
return '...'.join((s[:left - 3], s[-right:] if right else ''))
|
||||
|
||||
write_string('[debug] JS: {0}{1}\n'.format(
|
||||
' ' * (100 - level),
|
||||
' '.join(truncate_string(compat_str(x), 50, 50) for x in args)))
|
||||
|
||||
@classmethod
|
||||
def wrap_interpreter(cls, f):
|
||||
def interpret_statement(self, stmt, local_vars, allow_recursion, *args, **kwargs):
|
||||
if cls.ENABLED and stmt.strip():
|
||||
cls.write(stmt, level=allow_recursion)
|
||||
try:
|
||||
ret, should_ret = f(self, stmt, local_vars, allow_recursion, *args, **kwargs)
|
||||
except Exception as e:
|
||||
if cls.ENABLED:
|
||||
if isinstance(e, ExtractorError):
|
||||
e = e.orig_msg
|
||||
cls.write('=> Raises:', e, '<-|', stmt, level=allow_recursion)
|
||||
raise
|
||||
if cls.ENABLED and stmt.strip():
|
||||
if should_ret or not repr(ret) == stmt:
|
||||
cls.write(['->', '=>'][should_ret], repr(ret), '<-|', stmt, level=allow_recursion)
|
||||
return ret, should_ret
|
||||
return interpret_statement
|
||||
|
||||
|
||||
class JSInterpreter(object):
|
||||
__named_object_counter = 0
|
||||
|
||||
@ -307,8 +345,7 @@ class JSInterpreter(object):
|
||||
def __op_chars(cls):
|
||||
op_chars = set(';,[')
|
||||
for op in cls._all_operators():
|
||||
for c in op[0]:
|
||||
op_chars.add(c)
|
||||
op_chars.update(op[0])
|
||||
return op_chars
|
||||
|
||||
def _named_object(self, namespace, obj):
|
||||
@ -326,9 +363,8 @@ class JSInterpreter(object):
|
||||
# collections.Counter() is ~10% slower in both 2.7 and 3.9
|
||||
counters = dict((k, 0) for k in _MATCHING_PARENS.values())
|
||||
start, splits, pos, delim_len = 0, 0, 0, len(delim) - 1
|
||||
in_quote, escaping, skipping = None, False, 0
|
||||
after_op, in_regex_char_group = True, False
|
||||
|
||||
in_quote, escaping, after_op, in_regex_char_group = None, False, True, False
|
||||
skipping = 0
|
||||
for idx, char in enumerate(expr):
|
||||
paren_delta = 0
|
||||
if not in_quote:
|
||||
@ -382,10 +418,12 @@ class JSInterpreter(object):
|
||||
return separated[0][1:].strip(), separated[1].strip()
|
||||
|
||||
@staticmethod
|
||||
def _all_operators():
|
||||
return itertools.chain(
|
||||
def _all_operators(_cached=[]):
|
||||
if not _cached:
|
||||
_cached.extend(itertools.chain(
|
||||
# Ref: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Operators/Operator_Precedence
|
||||
_SC_OPERATORS, _LOG_OPERATORS, _COMP_OPERATORS, _OPERATORS)
|
||||
_SC_OPERATORS, _LOG_OPERATORS, _COMP_OPERATORS, _OPERATORS))
|
||||
return _cached
|
||||
|
||||
def _operator(self, op, left_val, right_expr, expr, local_vars, allow_recursion):
|
||||
if op in ('||', '&&'):
|
||||
@ -416,7 +454,7 @@ class JSInterpreter(object):
|
||||
except Exception as e:
|
||||
if allow_undefined:
|
||||
return JS_Undefined
|
||||
raise self.Exception('Cannot get index {idx:.100}'.format(**locals()), expr=repr(obj), cause=e)
|
||||
raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
|
||||
|
||||
def _dump(self, obj, namespace):
|
||||
try:
|
||||
@ -438,6 +476,7 @@ class JSInterpreter(object):
|
||||
_FINALLY_RE = re.compile(r'finally\s*\{')
|
||||
_SWITCH_RE = re.compile(r'switch\s*\(')
|
||||
|
||||
@Debugger.wrap_interpreter
|
||||
def interpret_statement(self, stmt, local_vars, allow_recursion=100):
|
||||
if allow_recursion < 0:
|
||||
raise self.Exception('Recursion limit reached')
|
||||
@ -511,7 +550,6 @@ class JSInterpreter(object):
|
||||
expr = self._dump(inner, local_vars) + outer
|
||||
|
||||
if expr.startswith('('):
|
||||
|
||||
m = re.match(r'\((?P<d>[a-z])%(?P<e>[a-z])\.length\+(?P=e)\.length\)%(?P=e)\.length', expr)
|
||||
if m:
|
||||
# short-cut eval of frequently used `(d%e.length+e.length)%e.length`, worth ~6% on `pytest -k test_nsig`
|
||||
@ -693,7 +731,7 @@ class JSInterpreter(object):
|
||||
(?P<op>{_OPERATOR_RE})?
|
||||
=(?!=)(?P<expr>.*)$
|
||||
)|(?P<return>
|
||||
(?!if|return|true|false|null|undefined)(?P<name>{_NAME_RE})$
|
||||
(?!if|return|true|false|null|undefined|NaN|Infinity)(?P<name>{_NAME_RE})$
|
||||
)|(?P<indexing>
|
||||
(?P<in>{_NAME_RE})\[(?P<idx>.+)\]$
|
||||
)|(?P<attribute>
|
||||
@ -727,11 +765,12 @@ class JSInterpreter(object):
|
||||
raise JS_Break()
|
||||
elif expr == 'continue':
|
||||
raise JS_Continue()
|
||||
|
||||
elif expr == 'undefined':
|
||||
return JS_Undefined, should_return
|
||||
elif expr == 'NaN':
|
||||
return _NaN, should_return
|
||||
elif expr == 'Infinity':
|
||||
return _Infinity, should_return
|
||||
|
||||
elif md.get('return'):
|
||||
return local_vars[m.group('name')], should_return
|
||||
@ -760,17 +799,27 @@ class JSInterpreter(object):
|
||||
right_expr = separated.pop()
|
||||
# handle operators that are both unary and binary, minimal BODMAS
|
||||
if op in ('+', '-'):
|
||||
# simplify/adjust consecutive instances of these operators
|
||||
undone = 0
|
||||
while len(separated) > 1 and not separated[-1].strip():
|
||||
undone += 1
|
||||
separated.pop()
|
||||
if op == '-' and undone % 2 != 0:
|
||||
right_expr = op + right_expr
|
||||
elif op == '+':
|
||||
while len(separated) > 1 and separated[-1].strip() in self.OP_CHARS:
|
||||
right_expr = separated.pop() + right_expr
|
||||
# hanging op at end of left => unary + (strip) or - (push right)
|
||||
left_val = separated[-1]
|
||||
for dm_op in ('*', '%', '/', '**'):
|
||||
bodmas = tuple(self._separate(left_val, dm_op, skip_delims=skip_delim))
|
||||
if len(bodmas) > 1 and not bodmas[-1].strip():
|
||||
expr = op.join(separated) + op + right_expr
|
||||
if len(separated) > 1:
|
||||
separated.pop()
|
||||
right_expr = op.join((left_val, right_expr))
|
||||
else:
|
||||
separated = [op.join((left_val, right_expr))]
|
||||
right_expr = None
|
||||
break
|
||||
if right_expr is None:
|
||||
@ -797,6 +846,8 @@ class JSInterpreter(object):
|
||||
|
||||
def eval_method():
|
||||
if (variable, member) == ('console', 'debug'):
|
||||
if Debugger.ENABLED:
|
||||
Debugger.write(self.interpret_expression('[{}]'.format(arg_str), local_vars, allow_recursion))
|
||||
return
|
||||
types = {
|
||||
'String': compat_str,
|
||||
|
@ -2406,7 +2406,7 @@ class ExtractorError(YoutubeDLError):
|
||||
""" tb, if given, is the original traceback (so that it can be printed out).
|
||||
If expected is set, this is a normal error message and most likely not a bug in youtube-dl.
|
||||
"""
|
||||
|
||||
self.orig_msg = msg
|
||||
if sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
|
||||
expected = True
|
||||
if video_id is not None:
|
||||
|
Loading…
Reference in New Issue
Block a user