Archived
209 lines
6.4 KiB
Python
209 lines
6.4 KiB
Python
# Kategoriserare fokuserad på primärnischerna:
|
|
# Teen 18+, Skinny, Petite, Bondage (+ särskilda beteenden).
|
|
# Allt innehåll hålls strikt till legal adult-18+-kategorier.
|
|
|
|
import re
|
|
|
|
PRIMARY_KEYS = {
|
|
"teen18": {"keywords": ["teen", "18", "18yo", "18year", "18+", "schoolgirl",
|
|
"school", "college", "university", "firstlegal",
|
|
"brat", "bratty"],
|
|
"label": "Teen 18+"},
|
|
"petite": {"keywords": ["petite", "tiny", "slim", "slender"],
|
|
"label": "Petite"},
|
|
"skinny": {"keywords": ["skinny", "thin", "bony", "wispy", "flatchested"],
|
|
"label": "Skinny"},
|
|
"bondage": {"keywords": ["bondage", "shibari", "kinbaku", "rope", "tie",
|
|
"tied", "suspension", "shackle", "collar",
|
|
"leashed", "restrain", "handcuff", "gag",
|
|
"ballgag", "blindfold", "petplay", "hogtie",
|
|
"ropeplay", "strapped"],
|
|
"label": "Bondage"},
|
|
}
|
|
|
|
SUB_RULES = {
|
|
"teen18": [
|
|
("uniform", "Uniform"),
|
|
("school", "Skoluniform"),
|
|
("sailor", "Sjäuniform"),
|
|
("maid", "Maid"),
|
|
("nurse", "Sjuksköterska"),
|
|
("cute", "Söt"),
|
|
("spicy", "Piffig"),
|
|
("firsttime", "Första gången"),
|
|
("firstanal", "Första anal"),
|
|
("firstorgasm", "Första orgasm"),
|
|
("18", "Fyllda 18"),
|
|
("birthday", "Födelsedag"),
|
|
("highschool", "HS"),
|
|
("student", "Student"),
|
|
("aunt", "Moster"),
|
|
("teacher", "Lärare"),
|
|
("american", "Amerikansk"),
|
|
("european", "Europeisk"),
|
|
("asian", "Asiatisk"),
|
|
],
|
|
"petite": [
|
|
("stockings", "Strumpbyxor"),
|
|
("pantyhose", "Pantyhose"),
|
|
("nylons", "Nylons"),
|
|
("socks", "Sockar"),
|
|
("ankles", "Anklar"),
|
|
("waist", "Smal midja"),
|
|
("outfit", "Outfit"),
|
|
("boots", "Boots"),
|
|
("kneehigh", "Knähöga"),
|
|
("tinywaist", "Smal midja"),
|
|
],
|
|
"skinny": [
|
|
("flat", "Platt bröstkorg"),
|
|
("mini", "Mini"),
|
|
("petite", "Petite"),
|
|
("narrow", "Smal"),
|
|
("little", "Liten"),
|
|
],
|
|
"bondage": [
|
|
("shibari", "Shibari"),
|
|
("kinbaku", "Kinbaku"),
|
|
("rope", "Rep"),
|
|
("strapped", "Reger"),
|
|
("suspension", "Suspension"),
|
|
("hogtie", "Hogtie"),
|
|
("spread", "Spret"),
|
|
("anklecuffs", "Ankelko"),
|
|
("ballgag", "Ballgag"),
|
|
("gag", "Gag"),
|
|
("blindfold", "Blindfold"),
|
|
("mask", "Mask"),
|
|
("cotton", "Bomull"),
|
|
("chain", "Kedja"),
|
|
("stick", "Stick"),
|
|
("vacuum", "Vacuum"),
|
|
("mummifier", "Mummification"),
|
|
("spanking", "Spanking"),
|
|
("flog", "Flogger"),
|
|
("whip", "Whip"),
|
|
("crops", "Crops"),
|
|
("predic", "Predicament"),
|
|
("endurance", "Endurance"),
|
|
("struggl", "Struggle"),
|
|
],
|
|
}
|
|
|
|
ACTIVITY_RULES = {
|
|
"solo": ("Solo", "Solo"),
|
|
"masturb": ("Solo", "Masturbation"),
|
|
"nude": ("Nude", "Nude"),
|
|
"tease": ("Tease", "Tease"),
|
|
"strip": ("Tease", "Strip"),
|
|
"dance": ("Tease", "Dance"),
|
|
"handjob": ("Handjob", "Handjob"),
|
|
"blowjob": ("Oral", "Blowjob"),
|
|
"oral": ("Oral", "Oral"),
|
|
"deepthroat": ("Oral", "Deep throat"),
|
|
"pov": ("POV", "POV"),
|
|
"cowgirl": ("Ridning", "Cowgirl"),
|
|
"reverse": ("Ridning", "Reverse cowgirl"),
|
|
"doggy": ("Doggy", "Doggy"),
|
|
"anal": ("Anal", "Anal"),
|
|
"dp": ("Anal", "DP"),
|
|
"creampie": ("Creampie", "Creampie"),
|
|
"threesome": ("Grupp", "Threesome"),
|
|
"gangbang": ("Grupp", "Gangbang"),
|
|
"orgy": ("Grupp", "Orgi"),
|
|
"lesbian": ("Lesbian", "Lesbian"),
|
|
"cam": ("Webcam", "Webcam"),
|
|
"public": ("Public", "Public"),
|
|
"outdoor": ("Public", "Outdoor"),
|
|
"voyeur": ("Voyeur", "Voyeur"),
|
|
"hidden": ("Voyeur", "Hidden cam"),
|
|
"wet": ("Wet", "Wet"),
|
|
"lingerie": ("Lingerie", "Lingerie"),
|
|
"bikini": ("Lingerie", "Bikini"),
|
|
"cosplay": ("Cosplay", "Cosplay"),
|
|
"anime": ("Cosplay", "Anime"),
|
|
}
|
|
|
|
|
|
def _norm(s):
|
|
s = (s or "").lower()
|
|
s = re.sub(r"[^a-z0-9 ]", "", s)
|
|
s = re.sub(r"\s+", " ", s).strip()
|
|
return s
|
|
|
|
|
|
def _has_any(text, kws):
|
|
t = _norm(text)
|
|
return any(_norm(k) in t for k in kws)
|
|
|
|
|
|
def duration_bucket(duration):
|
|
if not duration:
|
|
return None
|
|
if duration < 300:
|
|
return "Längd: kort"
|
|
if duration < 2100:
|
|
return "Längd: medel"
|
|
return "Längd: lång"
|
|
|
|
|
|
def categorize(meta, height=None, duration=None, site=None):
|
|
title = _norm(meta.get("title") or "")
|
|
tags = [_norm(t) for t in (meta.get("meta_tags") or [])]
|
|
hay = f"{title} {' '.join(tags)}"
|
|
|
|
# primära nischer
|
|
primary = []
|
|
for key, spec in PRIMARY_KEYS.items():
|
|
if _has_any(hay, spec["keywords"]):
|
|
primary.append(spec["label"])
|
|
|
|
# sub-nischer (max en per primärgrupp)
|
|
subs = []
|
|
for key, rules in SUB_RULES.items():
|
|
p = PRIMARY_KEYS[key]["label"]
|
|
if p not in primary:
|
|
continue
|
|
for kw, label in rules:
|
|
if _has_any(hay, [kw]):
|
|
subs.append(f"{p} > {label}")
|
|
break
|
|
|
|
# aktivitet = endast rena akter (utan dubbel mot primärer)
|
|
acts = []
|
|
for key, (cat, label) in ACTIVITY_RULES.items():
|
|
if _has_any(hay, [key]):
|
|
acts.append(label)
|
|
# bara akter som INTE redan är en primär/sub-etikett
|
|
skip = set(primary) | {s.split(" > ")[1] for s in subs}
|
|
acts = [a for a in dict.fromkeys(acts) if a not in skip]
|
|
|
|
cats = list(dict.fromkeys(primary))
|
|
for sub in subs:
|
|
if sub not in cats:
|
|
cats.append(sub)
|
|
cats.extend(a for a in acts if a not in cats)
|
|
bucket = duration_bucket(duration)
|
|
if bucket:
|
|
cats.append(bucket)
|
|
if site:
|
|
cats.append(f"Kanal: {site}")
|
|
if height:
|
|
cats.append(f"{height}p")
|
|
|
|
# tags = alla matchnande etiketter (sub + aktivitet + primära)
|
|
t = set()
|
|
for kws in SUB_RULES.values():
|
|
for kw, label in kws:
|
|
if _has_any(hay, [kw]):
|
|
t.add(label)
|
|
for key, (cat, label) in ACTIVITY_RULES.items():
|
|
if _has_any(hay, [key]):
|
|
t.add(label)
|
|
for key, spec in PRIMARY_KEYS.items():
|
|
if _has_any(hay, spec["keywords"]):
|
|
t.add(spec["label"])
|
|
if site:
|
|
t.add(f"kanal:{site}")
|
|
|
|
return cats, sorted(t) |