def _generate_timecode(self, sequence, timecode):
match = re.match(self._TIMECODE, timecode, flags=re.U)
if match:
start, end = (
self._fix_timecode(
timecode=re.sub(r"[\.,]", ",", match.group("appeartime"))
),
self._fix_timecode(
timecode=re.sub(r"[\.,]", ",", match.group("disappertime"))
),
)
return "{seq}\r\n{appeartime} --> {disappertime}\r\n".format(
seq=sequence, appeartime=start, disappertime=end
)
return ""
def fix_kv(m):
v = m.group(0)
if v in ("true", "false", "null"):
return v
elif 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],
)
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 '"%s"' % v
def to_configs(username="",
password="",
cookies="",
quality="",
output="",
language=""):
configs = load_configs()
fname = ".udemy-dl.conf"
fmode = "w"
if configs:
cfu = configs.get("username")
cfp = configs.get("password")
cfc = configs.get("cookies")
cfq = configs.get("quality")
cfl = configs.get("language")
cfo = configs.get("output")
if cfo:
cfo = re.sub(r'"', "", cfo.strip())
if username and cfu != username:
configs.update({"username": username})
if password and cfp != password:
configs.update({"password": password})
if cookies and cfc != cookies:
configs.update({"cookies": cookies})
if quality and cfq != quality:
configs.update({"quality": quality})
if language and cfl != language:
configs.update({"language": language})
if output and cfo != output:
output = re.sub(r'"', "", output.strip())
configs.update({"output": output})
with open(fname, fmode) as fd:
json.dump(configs, fd, indent=4)
if not configs:
if output:
output = re.sub(r'"', "", output.strip())
creds = {
"username": username,
"password": password,
"quality": quality,
"output": output,
"language": language,
"cookies": cookies,
}
with open(fname, fmode) as fd:
json.dump(creds, fd, indent=4)
return "cached"
def to_filepath(base, name):
base = re.sub(r'"', "", base.strip())
filepath = os.path.join(base, name)
try:
os.makedirs(filepath)
except:
pass
return filepath
def set_log_filepath(self, course_path):
course_path = re.sub(r'"', "", course_path.strip())
if os.path.exists(course_path):
self._log_filepath = os.path.join(course_path, "udemy-dl.log")
file_handler = logging.FileHandler(self._log_filepath)
logging.basicConfig(
format="[%(asctime)s][%(name)s] %(levelname)-5.5s %(message)s",
level=logging.INFO,
handlers=[file_handler],
)
def hidden_inputs(html):
html = re.sub(r"<!--(?:(?!<!--).)*-->", "", html)
hidden_inputs = {} # pylint: disable=W
for entry in re.findall(r"(?i)(<input[^>]+>)", html):
attrs = extract_attributes(entry)
if not entry:
continue
if attrs.get("type") not in ("hidden", "submit"):
continue
name = attrs.get("name") or attrs.get("id")
value = attrs.get("value")
if name and value is not None:
hidden_inputs[name] = value
return hidden_inputs
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.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],
)
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 '"%s"' % v
return re.sub(
r"""(?sx)
"(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^"\\]*"|
'(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'|
{comment}|,(?={skip}[\]}}])|
[a-zA-Z_][.a-zA-Z_0-9]*|
\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 _clean(self, text):
ok = re.compile(r'[^\\/:*?"<>|]')
text = "".join(x if ok.match(x) else "_" for x in text)
text = re.sub(r"\.+$", "", text.strip())
return text
