[cleanup] Misc fixes (see desc)

* [tvver] Fix bug in 6837633a4a - Closes #4054
* [rumble] Fix tests - Closes #3976
* [make] Remove `cat` abuse - Closes #3989
* [make] Revert #3684 - Closes #3814
* [utils] Improve `get_elements_by_class` - Closes #3993
* [utils] Inherit `Namespace` from `types.SimpleNamespace`
* [utils] Use `re.fullmatch` for matching filters
* [jsinterp] Handle quotes in `_separate`
* [make_readme] Allow overshooting last line

Authored by: pukkandan, kwconder, MrRawes, Lesmiscore

yt_dlp/YoutubeDL.py

@@ -576,7 +576,7 @@ class YoutubeDL:
         )
         self._allow_colors = Namespace(**{
             type_: not self.params.get('no_color') and supports_terminal_sequences(stream)
-            for type_, stream in self._out_files if type_ != 'console'
+            for type_, stream in self._out_files.items_ if type_ != 'console'
         })
 
         if sys.version_info < (3, 6):
@@ -3671,7 +3671,7 @@ class YoutubeDL:
             sys.getfilesystemencoding(),
             self.get_encoding(),
             ', '.join(
-                f'{key} {get_encoding(stream)}' for key, stream in self._out_files
+                f'{key} {get_encoding(stream)}' for key, stream in self._out_files.items_
                 if stream is not None and key != 'console')
         )
 

yt_dlp/downloader/common.py

@@ -302,7 +302,7 @@ class FileDownloader:
     )
 
     def _report_progress_status(self, s, default_template):
-        for name, style in self.ProgressStyles:
+        for name, style in self.ProgressStyles.items_:
             name = f'_{name}_str'
             if name not in s:
                 continue

yt_dlp/extractor/rumble.py

@@ -24,6 +24,11 @@ class RumbleEmbedIE(InfoExtractor):
             'title': 'WMAR 2 News Latest Headlines | October 20, 6pm',
             'timestamp': 1571611968,
             'upload_date': '20191020',
+            'channel_url': 'https://rumble.com/c/WMAR',
+            'channel': 'WMAR',
+            'thumbnail': 'https://sp.rmbl.ws/s8/1/5/M/z/1/5Mz1a.OvCc-small-WMAR-2-News-Latest-Headline.jpg',
+            'duration': 234,
+            'uploader': 'WMAR',
         }
     }, {
         'url': 'https://rumble.com/embed/vslb7v',
@@ -38,6 +43,7 @@ class RumbleEmbedIE(InfoExtractor):
             'channel': 'CTNews',
             'thumbnail': 'https://sp.rmbl.ws/s8/6/7/i/9/h/7i9hd.OvCc.jpg',
             'duration': 901,
+            'uploader': 'CTNews',
         }
     }, {
         'url': 'https://rumble.com/embed/ufe9n.v5pv5f',
@@ -96,6 +102,7 @@ class RumbleEmbedIE(InfoExtractor):
             'channel': author.get('name'),
             'channel_url': author.get('url'),
             'duration': int_or_none(video.get('duration')),
+            'uploader': author.get('name'),
         }
 
 

yt_dlp/jsinterp.py

@@ -24,6 +24,7 @@ _ASSIGN_OPERATORS.append(('=', (lambda cur, right: right)))
 _NAME_RE = r'[a-zA-Z_$][a-zA-Z_$0-9]*'
 
 _MATCHING_PARENS = dict(zip('({[', ')}]'))
+_QUOTES = '\'"'
 
 
 class JS_Break(ExtractorError):
@@ -69,12 +70,17 @@ class JSInterpreter:
             return
         counters = {k: 0 for k in _MATCHING_PARENS.values()}
         start, splits, pos, delim_len = 0, 0, 0, len(delim) - 1
+        in_quote, escaping = None, False
         for idx, char in enumerate(expr):
             if char in _MATCHING_PARENS:
                 counters[_MATCHING_PARENS[char]] += 1
             elif char in counters:
                 counters[char] -= 1
-            if char != delim[pos] or any(counters.values()):
+            elif not escaping and char in _QUOTES and in_quote in (char, None):
+                in_quote = None if in_quote else char
+            escaping = not escaping and in_quote and char == '\\'
+
+            if char != delim[pos] or any(counters.values()) or in_quote:
                 pos = 0
                 continue
             elif pos != delim_len:

yt_dlp/utils.py

@@ -34,6 +34,7 @@ import sys
 import tempfile
 import time
 import traceback
+import types
 import urllib.parse
 import xml.etree.ElementTree
 import zlib
@@ -397,14 +398,14 @@ def get_element_html_by_attribute(attribute, value, html, **kargs):
 def get_elements_by_class(class_name, html, **kargs):
     """Return the content of all tags with the specified class in the passed HTML document as a list"""
     return get_elements_by_attribute(
-        'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
+        'class', r'[^\'"]*(?<=[\'"\s])%s(?=[\'"\s])[^\'"]*' % re.escape(class_name),
         html, escape_value=False)
 
 
 def get_elements_html_by_class(class_name, html):
     """Return the html of all tags with the specified class in the passed HTML document as a list"""
     return get_elements_html_by_attribute(
-        'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
+        'class', r'[^\'"]*(?<=[\'"\s])%s(?=[\'"\s])[^\'"]*' % re.escape(class_name),
         html, escape_value=False)
 
 
@@ -3404,16 +3405,15 @@ def _match_one(filter_part, dct, incomplete):
     else:
         is_incomplete = lambda k: k in incomplete
 
-    operator_rex = re.compile(r'''(?x)\s*
+    operator_rex = re.compile(r'''(?x)
         (?P<key>[a-z_]+)
         \s*(?P<negation>!\s*)?(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
         (?:
             (?P<quote>["\'])(?P<quotedstrval>.+?)(?P=quote)|
             (?P<strval>.+?)
         )
-        \s*$
         ''' % '|'.join(map(re.escape, COMPARISON_OPERATORS.keys())))
-    m = operator_rex.search(filter_part)
+    m = operator_rex.fullmatch(filter_part.strip())
     if m:
         m = m.groupdict()
         unnegated_op = COMPARISON_OPERATORS[m['op']]
@@ -3449,11 +3449,10 @@ def _match_one(filter_part, dct, incomplete):
         '': 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*
+    operator_rex = re.compile(r'''(?x)
         (?P<op>%s)\s*(?P<key>[a-z_]+)
-        \s*$
         ''' % '|'.join(map(re.escape, UNARY_OPERATORS.keys())))
-    m = operator_rex.search(filter_part)
+    m = operator_rex.fullmatch(filter_part.strip())
     if m:
         op = UNARY_OPERATORS[m.group('op')]
         actual_value = dct.get(m.group('key'))
@@ -5395,23 +5394,15 @@ class classproperty:
         return self.func(cls)
 
 
-class Namespace:
+class Namespace(types.SimpleNamespace):
     """Immutable namespace"""
 
-    def __init__(self, **kwargs):
-        self._dict = kwargs
-
-    def __getattr__(self, attr):
-        return self._dict[attr]
-
-    def __contains__(self, item):
-        return item in self._dict.values()
-
     def __iter__(self):
-        return iter(self._dict.items())
+        return iter(self.__dict__.values())
 
-    def __repr__(self):
-        return f'{type(self).__name__}({", ".join(f"{k}={v}" for k, v in self)})'
+    @property
+    def items_(self):
+        return self.__dict__.items()
 
 
 # Deprecated