bitbot-3.11-fork/Utils.py

222 lines
6.8 KiB
Python
Raw Normal View History

import json, re, traceback, urllib.request, urllib.parse, urllib.error, ssl
2016-03-29 11:56:58 +00:00
import bs4
USER_AGENT = ("Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/49.0.2623.87 Safari/537.36")
REGEX_HTTP = re.compile("https?://", re.I)
def remove_colon(s):
if s.startswith(":"):
s = s[1:]
return s
def arbitrary(s, n):
return remove_colon(" ".join(s[n:]))
def seperate_hostmask(hostmask):
hostmask = remove_colon(hostmask)
first_delim = hostmask.find("!")
second_delim = hostmask.find("@")
nickname = username = hostname = hostmask
if first_delim > -1 and second_delim > first_delim:
nickname, username = hostmask.split("!", 1)
username, hostname = hostmask.split("@", 1)
return nickname, username, hostname
def get_url(url, **kwargs):
if not urllib.parse.urlparse(url).scheme:
2016-03-29 11:56:58 +00:00
url = "http://%s" % url
url_parsed = urllib.parse.urlparse(url)
2016-03-29 11:56:58 +00:00
method = kwargs.get("method", "GET")
get_params = kwargs.get("get_params", "")
post_params = kwargs.get("post_params", None)
headers = kwargs.get("headers", {})
if get_params:
get_params = "?%s" % urllib.parse.urlencode(get_params)
if post_params:
post_params = urllib.parse.urlencode(post_params).encode("utf8")
url = "%s%s" % (url, get_params)
try:
url.encode("latin-1")
except UnicodeEncodeError:
if kwargs.get("code"):
return 0, False
return False
2016-03-29 11:56:58 +00:00
request = urllib.request.Request(url, post_params)
request.add_header("Accept-Language", "en-US")
request.add_header("User-Agent", USER_AGENT)
for header, value in headers.items():
request.add_header(header, value)
request.method = method
try:
2017-11-03 19:20:23 +00:00
response = urllib.request.urlopen(request, timeout=5)
except urllib.error.HTTPError as e:
2016-03-29 11:56:58 +00:00
traceback.print_exc()
if kwargs.get("code"):
return e.code, False
return False
except urllib.error.URLError as e:
traceback.print_exc()
if kwargs.get("code"):
return -1, False
return False
except ssl.CertificateError as e:
traceback.print_exc()
if kwargs.get("code"):
return -1, False,
return False
2016-03-29 11:56:58 +00:00
response_content = response.read()
encoding = response.info().get_content_charset()
if kwargs.get("soup"):
return bs4.BeautifulSoup(response_content, kwargs.get("parser", "lxml"))
2016-03-29 11:56:58 +00:00
if not encoding:
soup = bs4.BeautifulSoup(response_content, kwargs.get("parser", "lxml"))
2016-03-29 11:56:58 +00:00
metas = soup.find_all("meta")
for meta in metas:
if "charset=" in meta.get("content", ""):
encoding = meta.get("content").split("charset=", 1)[1
].split(";", 1)[0]
elif meta.get("charset", ""):
encoding = meta.get("charset")
else:
continue
break
if not encoding:
for item in soup.contents:
if isinstance(item, bs4.Doctype):
if item == "html":
encoding = "utf8"
else:
encoding = "latin-1"
break
response_content = response_content.decode(encoding or "utf8")
data = response_content
if kwargs.get("json") and data:
2016-03-29 11:56:58 +00:00
try:
data = json.loads(response_content)
except json.decoder.JSONDecodeError:
traceback.print_exc()
return False
if kwargs.get("code"):
return response.code, data
else:
return data
COLOR_WHITE, COLOR_BLACK, COLOR_BLUE, COLOR_GREEN = 0, 1, 2, 3
COLOR_RED, COLOR_BROWN, COLOR_PURPLE, COLOR_ORANGE = 4, 5, 6, 7
COLOR_YELLOW, COLOR_LIGHTGREEN, COLOR_CYAN, COLOR_LIGHTCYAN = (8, 9,
10, 11)
COLOR_LIGHTBLUE, COLOR_PINK, COLOR_GREY, COLOR_LIGHTGREY = (12, 13,
14, 15)
FONT_BOLD, FONT_ITALIC, FONT_UNDERLINE, FONT_INVERT = ("\x02", "\x1D",
"\x1F", "\x16")
FONT_COLOR, FONT_RESET = "\x03", "\x0F"
def color(foreground, background=None):
foreground = str(foreground).zfill(2)
if background:
background = str(background).zfill(2)
2016-03-29 11:56:58 +00:00
return "%s%s%s" % (FONT_COLOR, foreground,
"" if not background else ",%s" % background)
TIME_SECOND = 1
TIME_MINUTE = TIME_SECOND*60
TIME_HOUR = TIME_MINUTE*60
TIME_DAY = TIME_HOUR*24
TIME_WEEK = TIME_DAY*7
def time_unit(seconds):
since = None
unit = None
if seconds >= TIME_WEEK:
since = seconds/TIME_WEEK
unit = "week"
elif seconds >= TIME_DAY:
since = seconds/TIME_DAY
unit = "day"
elif seconds >= TIME_HOUR:
since = seconds/TIME_HOUR
unit = "hour"
elif seconds >= TIME_MINUTE:
since = seconds/TIME_MINUTE
unit = "minute"
else:
since = seconds
unit = "second"
since = int(since)
if since > 1:
unit = "%ss" % unit # pluralise the unit
return [since, unit]
REGEX_PRETTYTIME = re.compile("\d+[wdhms]", re.I)
SECONDS_MINUTES = 60
SECONDS_HOURS = SECONDS_MINUTES*60
SECONDS_DAYS = SECONDS_HOURS*24
SECONDS_WEEKS = SECONDS_DAYS*7
def from_pretty_time(pretty_time):
seconds = 0
for match in re.findall(REGEX_PRETTYTIME, pretty_time):
number, unit = int(match[:-1]), match[-1].lower()
if unit == "m":
number = number*SECONDS_MINUTES
elif unit == "h":
number = number*SECONDS_HOURS
elif unit == "d":
number = number*SECONDS_DAYS
elif unit == "w":
number = number*SECONDS_WEEKS
seconds += number
if seconds > 0:
return seconds
2016-04-10 16:40:58 +00:00
2018-08-09 11:23:54 +00:00
def to_pretty_time(total_seconds):
minutes, seconds = divmod(total_seconds, 60)
hours, minutes = divmod(minutes, 60)
days, hours = divmod(hours, 24)
weeks, days = divmod(days, 7)
out = ""
if not weeks == 0:
out += "%dw" % weeks
if not days == 0:
out += "%dd" % days
if not hours == 0:
out += "%dh" % hours
if not minutes == 0:
out += "%dm" % minutes
if not seconds == 0:
out += "%ds" % seconds
return out
2016-04-10 16:40:58 +00:00
IS_TRUE = ["true", "yes", "on", "y"]
IS_FALSE = ["false", "no", "off", "n"]
def bool_or_none(s):
s = s.lower()
if s in IS_TRUE:
return True
elif s in IS_FALSE:
return False
def int_or_none(s):
stripped_s = s.lstrip("0")
if stripped_s.isdigit():
return int(stripped_s)
def get_closest_setting(event, setting, default=None):
server = event["server"]
if "channel" in event:
closest = event["channel"]
elif "target" in event and "is_channel" in event and event["is_channel"]:
closest = event["target"]
else:
closest = event["user"]
return closest.get_setting(setting, server.get_setting(setting, default))
def prevent_highlight(nickname):
return nickname[0]+"\u200b"+nickname[1:]