From 7769f837018cbfa6cab615b8ae938528f895ce8c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 18 May 2017 22:18:33 +0700 Subject: [PATCH] [jsinterp] Add support for quoted names and indexers (closes #13123, closes #13130) --- youtube_dl/jsinterp.py | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/youtube_dl/jsinterp.py b/youtube_dl/jsinterp.py index 24cdec28c..038910049 100644 --- a/youtube_dl/jsinterp.py +++ b/youtube_dl/jsinterp.py @@ -6,6 +6,7 @@ from .utils import ( ExtractorError, + remove_quotes, ) _OPERATORS = [ @@ -57,7 +58,6 @@ def interpret_statement(self, stmt, local_vars, allow_recursion=100): def interpret_expression(self, expr, local_vars, allow_recursion): expr = expr.strip() - if expr == '': # Empty expression return None @@ -121,11 +121,19 @@ def interpret_expression(self, expr, local_vars, allow_recursion): pass m = re.match( - r'(?P%s)\.(?P[^(]+)(?:\(+(?P[^()]*)\))?$' % _NAME_RE, + r'(?P%s)\[(?P.+)\]$' % _NAME_RE, expr) + if m: + val = local_vars[m.group('in')] + idx = self.interpret_expression( + m.group('idx'), local_vars, allow_recursion - 1) + return val[idx] + + m = re.match( + r'(?P%s)(?:\.(?P[^(]+)|\[(?P[^]]+)\])\s*(?:\(+(?P[^()]*)\))?$' % _NAME_RE, expr) if m: variable = m.group('var') - member = m.group('member') + member = remove_quotes(m.group('member') or m.group('member2')) arg_str = m.group('args') if variable in local_vars: @@ -173,14 +181,6 @@ def interpret_expression(self, expr, local_vars, allow_recursion): return obj[member](argvals) - m = re.match( - r'(?P%s)\[(?P.+)\]$' % _NAME_RE, expr) - if m: - val = local_vars[m.group('in')] - idx = self.interpret_expression( - m.group('idx'), local_vars, allow_recursion - 1) - return val[idx] - for op, opfunc in _OPERATORS: m = re.match(r'(?P.+?)%s(?P.+)' % re.escape(op), expr) if not m: @@ -211,21 +211,22 @@ def interpret_expression(self, expr, local_vars, allow_recursion): raise ExtractorError('Unsupported JS expression %r' % expr) def extract_object(self, objname): + _FUNC_NAME_RE = r'''(?:[a-zA-Z$0-9]+|"[a-zA-Z$0-9]+"|'[a-zA-Z$0-9]+')''' obj = {} obj_m = re.search( (r'(?([a-zA-Z$0-9]+\s*:\s*function\(.*?\)\s*\{.*?\}(?:,\s*)?)*)' + - r'\}\s*;', + r'\s*(?P(%s\s*:\s*function\(.*?\)\s*\{.*?\}(?:,\s*)?)*)' + + r'\}\s*;' % _FUNC_NAME_RE, self.code) fields = obj_m.group('fields') # Currently, it only supports function definitions fields_m = re.finditer( - r'(?P[a-zA-Z$0-9]+)\s*:\s*function' - r'\((?P[a-z,]+)\){(?P[^}]+)}', + r'(?P%s)\s*:\s*function' + r'\((?P[a-z,]+)\){(?P[^}]+)}' % _FUNC_NAME_RE, fields) for f in fields_m: argnames = f.group('args').split(',') - obj[f.group('key')] = self.build_function(argnames, f.group('code')) + obj[remove_quotes(f.group('key'))] = self.build_function(argnames, f.group('code')) return obj