def get_element_by_class(class_name, html):
- return get_element_by_attribute(
+ """Return the content of the first tag with the specified class in the passed HTML document"""
+ retval = get_elements_by_class(class_name, html)
+ return retval[0] if retval else None
+
+
+def get_element_by_attribute(attribute, value, html, escape_value=True):
+ retval = get_elements_by_attribute(attribute, value, html, escape_value)
+ return retval[0] if retval else None
+
+
+def get_elements_by_class(class_name, html):
+ """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),
html, escape_value=False)
-def get_element_by_attribute(attribute, value, html, escape_value=True):
+def get_elements_by_attribute(attribute, value, html, escape_value=True):
"""Return the content of the tag with the specified attribute in the passed HTML document"""
value = re.escape(value) if escape_value else value
- m = re.search(r'''(?xs)
+ retlist = []
+ for m in re.finditer(r'''(?xs)
<([a-zA-Z0-9:._-]+)
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
\s+%s=['"]?%s['"]?
\s*>
(?P<content>.*?)
</\1>
- ''' % (re.escape(attribute), value), html)
+ ''' % (re.escape(attribute), value), html):
+ res = m.group('content')
- if not m:
- return None
- res = m.group('content')
+ if res.startswith('"') or res.startswith("'"):
+ res = res[1:-1]
- if res.startswith('"') or res.startswith("'"):
- res = res[1:-1]
+ retlist.append(unescapeHTML(res))
- return unescapeHTML(res)
+ return retlist
class HTMLAttributeParser(compat_HTMLParser):
libc = ctypes.cdll.LoadLibrary('libc.so.6')
except OSError:
return
+ except TypeError:
+ # LoadLibrary in Windows Python 2.7.13 only expects
+ # a bytestring, but since unicode_literals turns
+ # every string into a unicode string, it fails.
+ return
title_bytes = title.encode('utf-8')
buf = ctypes.create_string_buffer(len(title_bytes))
buf.value = title_bytes
s = s.strip()
days, hours, mins, secs, ms = [None] * 5
- m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?$', s)
+ m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?Z?$', s)
if m:
days, hours, mins, secs, ms = m.groups()
else:
)?
(?:
(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*s(?:ec(?:ond)?s?)?\s*
- )?$''', s)
+ )?Z?$''', s)
if m:
days, hours, mins, secs, ms = m.groups()
else:
- m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)$', s)
+ m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)Z?$', s)
if m:
hours, mins = m.groups()
else:
def js_to_json(code):
+ COMMENT_RE = r'/\*(?:(?!\*/).)*?\*/|//[^\n]*'
+ SKIP_RE = r'\s*(?:{comment})?\s*'.format(comment=COMMENT_RE)
+ INTEGER_TABLE = (
+ (r'(?s)^(0[xX][0-9a-fA-F]+){skip}:?$'.format(skip=SKIP_RE), 16),
+ (r'(?s)^(0+[0-7]+){skip}:?$'.format(skip=SKIP_RE), 8),
+ )
+
def fix_kv(m):
v = m.group(0)
if v in ('true', 'false', 'null'):
return v
- elif v.startswith('/*') or v == ',':
+ elif v.startswith('/*') or v.startswith('//') or v == ',':
return ""
if v[0] in ("'", '"'):
'\\x': '\\u00',
}.get(m.group(0), m.group(0)), v[1:-1])
- INTEGER_TABLE = (
- (r'^(0[xX][0-9a-fA-F]+)\s*:?$', 16),
- (r'^(0+[0-7]+)\s*:?$', 8),
- )
-
for regex, base in INTEGER_TABLE:
im = re.match(regex, v)
if im:
return re.sub(r'''(?sx)
"(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^"\\]*"|
'(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'|
- /\*.*?\*/|,(?=\s*[\]}])|
+ {comment}|,(?={skip}[\]}}])|
[a-zA-Z_][.a-zA-Z_0-9]*|
- \b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:\s*:)?|
- [0-9]+(?=\s*:)
- ''', fix_kv, code)
+ \b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:{skip}:)?|
+ [0-9]+(?={skip}:)
+ '''.format(comment=COMMENT_RE, skip=SKIP_RE), fix_kv, code)
def qualities(quality_ids):