[extractor/iq] Increase phantomjs timeout

[yt-dlp.git] / yt_dlp / utils.py

diff --git a/yt_dlp/utils.py b/yt_dlp/utils.py
index 5a88a928d6ac8f4452e5d01df717e0d2dc3c4d88..adb7c0e8c5d4686a4e0e5b3b9c669331e293ab8f 100644 (file)
--- a/yt_dlp/utils.py
+++ b/yt_dlp/utils.py
@@ -2574,7 +2574,9 @@ def strftime_or_none(timestamp, date_format, default=None):
     datetime_object = None
     try:
         if isinstance(timestamp, (int, float)):  # unix timestamp
-            datetime_object = datetime.datetime.utcfromtimestamp(timestamp)
+            # Using naive datetime here can break timestamp() in Windows
+            # Ref: https://github.com/yt-dlp/yt-dlp/issues/5185, https://github.com/python/cpython/issues/94414
+            datetime_object = datetime.datetime.fromtimestamp(timestamp, datetime.timezone.utc)
         elif isinstance(timestamp, str):  # assume YYYYMMDD
             datetime_object = datetime.datetime.strptime(timestamp, '%Y%m%d')
         date_format = re.sub(  # Support %s on windows
@@ -3273,6 +3275,8 @@ def strip_jsonp(code):
 
 def js_to_json(code, vars={}, *, strict=False):
     # vars is a dict of var, val pairs to substitute
+    STRING_QUOTES = '\'"'
+    STRING_RE = '|'.join(rf'{q}(?:\\.|[^\\{q}])*{q}' for q in STRING_QUOTES)
     COMMENT_RE = r'/\*(?:(?!\*/).)*?\*/|//[^\n]*\n'
     SKIP_RE = fr'\s*(?:{COMMENT_RE})?\s*'
     INTEGER_TABLE = (
@@ -3280,6 +3284,15 @@ def js_to_json(code, vars={}, *, strict=False):
         (fr'(?s)^(0+[0-7]+){SKIP_RE}:?$', 8),
     )
 
+    def process_escape(match):
+        JSON_PASSTHROUGH_ESCAPES = R'"\bfnrtu'
+        escape = match.group(1) or match.group(2)
+
+        return (Rf'\{escape}' if escape in JSON_PASSTHROUGH_ESCAPES
+                else R'\u00' if escape == 'x'
+                else '' if escape == '\n'
+                else escape)
+
     def fix_kv(m):
         v = m.group(0)
         if v in ('true', 'false', 'null'):
@@ -3287,28 +3300,25 @@ def fix_kv(m):
         elif v in ('undefined', 'void 0'):
             return 'null'
         elif v.startswith('/*') or v.startswith('//') or v.startswith('!') or v == ',':
-            return ""
-
-        if v[0] in ("'", '"'):
-            v = re.sub(r'(?s)\\.|"', lambda m: {
-                '"': '\\"',
-                "\\'": "'",
-                '\\\n': '',
-                '\\x': '\\u00',
-            }.get(m.group(0), m.group(0)), v[1:-1])
-        else:
-            for regex, base in INTEGER_TABLE:
-                im = re.match(regex, v)
-                if im:
-                    i = int(im.group(1), base)
-                    return '"%d":' % i if v.endswith(':') else '%d' % i
+            return ''
+
+        if v[0] in STRING_QUOTES:
+            escaped = re.sub(r'(?s)(")|\\(.)', process_escape, v[1:-1])
+            return f'"{escaped}"'
+
+        for regex, base in INTEGER_TABLE:
+            im = re.match(regex, v)
+            if im:
+                i = int(im.group(1), base)
+                return f'"{i}":' if v.endswith(':') else str(i)
+
+        if v in vars:
+            return json.dumps(vars[v])
 
-            if v in vars:
-                return json.dumps(vars[v])
-            if strict:
-                raise ValueError(f'Unknown value: {v}')
+        if not strict:
+            return f'"{v}"'
 
-        return '"%s"' % v
+        raise ValueError(f'Unknown value: {v}')
 
     def create_map(mobj):
         return json.dumps(dict(json.loads(js_to_json(mobj.group(1) or '[]', vars=vars))))
@@ -3318,15 +3328,14 @@ def create_map(mobj):
         code = re.sub(r'new Date\((".+")\)', r'\g<1>', code)
         code = re.sub(r'new \w+\((.*?)\)', lambda m: json.dumps(m.group(0)), code)
 
-    return re.sub(r'''(?sx)
-        "(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^"\\]*"|
-        '(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'|
-        {comment}|,(?={skip}[\]}}])|
+    return re.sub(rf'''(?sx)
+        {STRING_RE}|
+        {COMMENT_RE}|,(?={SKIP_RE}[\]}}])|
         void\s0|(?:(?<![0-9])[eE]|[a-df-zA-DF-Z_$])[.a-zA-Z_$0-9]*|
-        \b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:{skip}:)?|
-        [0-9]+(?={skip}:)|
+        \b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:{SKIP_RE}:)?|
+        [0-9]+(?={SKIP_RE}:)|
         !+
-        '''.format(comment=COMMENT_RE, skip=SKIP_RE), fix_kv, code)
+        ''', fix_kv, code)
 
 
 def qualities(quality_ids):
@@ -5499,7 +5508,8 @@ def jwt_encode_hs256(payload_data, key, headers={}):
 # can be extended in future to verify the signature and parse header and return the algorithm used if it's not HS256
 def jwt_decode_hs256(jwt):
     header_b64, payload_b64, signature_b64 = jwt.split('.')
-    payload_data = json.loads(base64.urlsafe_b64decode(payload_b64))
+    # add trailing ='s that may have been stripped, superfluous ='s are ignored
+    payload_data = json.loads(base64.urlsafe_b64decode(f'{payload_b64}==='))
     return payload_data