projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
[openload] Improve ext extraction
[youtube-dl]
/
youtube_dl
/
utils.py
diff --git
a/youtube_dl/utils.py
b/youtube_dl/utils.py
index a21455f707e5cb9dc51c1f5611963c5f58fc3863..6a3199fb992b72e70b6588d3999e9c6ec0a87890 100644
(file)
--- a/
youtube_dl/utils.py
+++ b/
youtube_dl/utils.py
@@
-1211,6
+1211,11
@@
def unified_timestamp(date_str, day_first=True):
if m:
date_str = date_str[:-len(m.group('tz'))]
if m:
date_str = date_str[:-len(m.group('tz'))]
+ # Python only supports microseconds, so remove nanoseconds
+ m = re.search(r'^([0-9]{4,}-[0-9]{1,2}-[0-9]{1,2}T[0-9]{1,2}:[0-9]{1,2}:[0-9]{1,2}\.[0-9]{6})[0-9]+$', date_str)
+ if m:
+ date_str = m.group(1)
+
for expression in date_formats(day_first):
try:
dt = datetime.datetime.strptime(date_str, expression) - timezone + datetime.timedelta(hours=pm_delta)
for expression in date_formats(day_first):
try:
dt = datetime.datetime.strptime(date_str, expression) - timezone + datetime.timedelta(hours=pm_delta)
@@
-1223,7
+1228,7
@@
def unified_timestamp(date_str, day_first=True):
def determine_ext(url, default_ext='unknown_video'):
def determine_ext(url, default_ext='unknown_video'):
- if url is None:
+ if url is None
or '.' not in url
:
return default_ext
guess = url.partition('?')[0].rpartition('.')[2]
if re.match(r'^[A-Za-z0-9]+$', guess):
return default_ext
guess = url.partition('?')[0].rpartition('.')[2]
if re.match(r'^[A-Za-z0-9]+$', guess):
@@
-2220,6
+2225,20
@@
def try_get(src, getter, expected_type=None):
return v
return v
+def merge_dicts(*dicts):
+ merged = {}
+ for a_dict in dicts:
+ for k, v in a_dict.items():
+ if v is None:
+ continue
+ if (k not in merged or
+ (isinstance(v, compat_str) and v and
+ isinstance(merged[k], compat_str) and
+ not merged[k])):
+ merged[k] = v
+ return merged
+
+
def encode_compat_str(string, encoding=preferredencoding(), errors='strict'):
return string if isinstance(string, compat_str) else compat_str(string, encoding, errors)
def encode_compat_str(string, encoding=preferredencoding(), errors='strict'):
return string if isinstance(string, compat_str) else compat_str(string, encoding, errors)
@@
-2253,7
+2272,10
@@
def parse_age_limit(s):
return int(m.group('age'))
if s in US_RATINGS:
return US_RATINGS[s]
return int(m.group('age'))
if s in US_RATINGS:
return US_RATINGS[s]
- return TV_PARENTAL_GUIDELINES.get(s)
+ m = re.match(r'^TV[_-]?(%s)$' % '|'.join(k[3:] for k in TV_PARENTAL_GUIDELINES), s)
+ if m:
+ return TV_PARENTAL_GUIDELINES['TV-' + m.group(1)]
+ return None
def strip_jsonp(code):
def strip_jsonp(code):
@@
-2569,8
+2591,8
@@
def _match_one(filter_part, dct):
return op(actual_value, comparison_value)
UNARY_OPERATORS = {
return op(actual_value, comparison_value)
UNARY_OPERATORS = {
- '': lambda v:
v is not None
,
- '!': lambda v:
v is None
,
+ '': lambda v:
(v is True) if isinstance(v, bool) else (v is not None)
,
+ '!': lambda v:
(v is False) if isinstance(v, bool) else (v is None)
,
}
operator_rex = re.compile(r'''(?x)\s*
(?P<op>%s)\s*(?P<key>[a-z_]+)
}
operator_rex = re.compile(r'''(?x)\s*
(?P<op>%s)\s*(?P<key>[a-z_]+)
@@
-2645,6
+2667,7
@@
def dfxp2srt(dfxp_data):
]
_x = functools.partial(xpath_with_ns, ns_map={
]
_x = functools.partial(xpath_with_ns, ns_map={
+ 'xml': 'http://www.w3.org/XML/1998/namespace',
'ttml': 'http://www.w3.org/ns/ttml',
'tts': 'http://www.w3.org/ns/ttml#styling',
})
'ttml': 'http://www.w3.org/ns/ttml',
'tts': 'http://www.w3.org/ns/ttml#styling',
})
@@
-2736,7
+2759,9
@@
def dfxp2srt(dfxp_data):
repeat = False
while True:
for style in dfxp.findall(_x('.//ttml:style')):
repeat = False
while True:
for style in dfxp.findall(_x('.//ttml:style')):
- style_id = style.get('id')
+ style_id = style.get('id') or style.get(_x('xml:id'))
+ if not style_id:
+ continue
parent_style_id = style.get('style')
if parent_style_id:
if parent_style_id not in styles:
parent_style_id = style.get('style')
if parent_style_id:
if parent_style_id not in styles:
@@
-3515,10
+3540,13
@@
class GeoUtils(object):
}
@classmethod
}
@classmethod
- def random_ipv4(cls, code):
- block = cls._country_ip_map.get(code.upper())
- if not block:
- return None
+ def random_ipv4(cls, code_or_block):
+ if len(code_or_block) == 2:
+ block = cls._country_ip_map.get(code_or_block.upper())
+ if not block:
+ return None
+ else:
+ block = code_or_block
addr, preflen = block.split('/')
addr_min = compat_struct_unpack('!L', socket.inet_aton(addr))[0]
addr_max = addr_min | (0xffffffff >> int(preflen))
addr, preflen = block.split('/')
addr_min = compat_struct_unpack('!L', socket.inet_aton(addr))[0]
addr_max = addr_min | (0xffffffff >> int(preflen))