feat: Prioritize Babepedia/Adult databases for image scraping and add full-name filter (ignore ambiguous single names)
This commit is contained in:
david
@@ -1504,6 +1504,11 @@
|
||||
<span>Female Only</span>
|
||||
</label>
|
||||
|
||||
<label style="font-size: 0.75rem; color: var(--text-main); display: inline-flex; align-items: center; gap: 0.35rem; cursor: pointer; user-select: none;">
|
||||
<input type="checkbox" id="toggle-stash-full-name" checked />
|
||||
<span>Full Names (First + Last)</span>
|
||||
</label>
|
||||
|
||||
<label style="font-size: 0.75rem; color: var(--text-main); display: inline-flex; align-items: center; gap: 0.35rem; cursor: pointer; user-select: none;">
|
||||
<input type="checkbox" id="toggle-stash-has-scenes" checked />
|
||||
<span>With Scenes Only (>= 1)</span>
|
||||
@@ -4901,6 +4906,7 @@ Return ONLY a valid JSON object with an array named "results":
|
||||
const btnStashStopImages = document.getElementById('btn-stash-stop-images');
|
||||
const btnCommitStashImages = document.getElementById('btn-commit-stash-images');
|
||||
const toggleStashFemaleOnly = document.getElementById('toggle-stash-female-only');
|
||||
const toggleStashFullName = document.getElementById('toggle-stash-full-name');
|
||||
const toggleStashHasScenes = document.getElementById('toggle-stash-has-scenes');
|
||||
const stashImagesSearchInput = document.getElementById('stash-images-search-input');
|
||||
const thStashImgSelectAll = document.getElementById('th-stash-img-select-all');
|
||||
@@ -4953,8 +4959,9 @@ Return ONLY a valid JSON object with an array named "results":
|
||||
const stashUrl = stashEndpointInput ? stashEndpointInput.value.trim() : '';
|
||||
const gender = toggleStashFemaleOnly && toggleStashFemaleOnly.checked ? 'FEMALE' : 'ALL';
|
||||
const hasScenes = toggleStashHasScenes && toggleStashHasScenes.checked ? 'true' : 'false';
|
||||
const fullNamesOnly = toggleStashFullName && toggleStashFullName.checked ? 'true' : 'false';
|
||||
|
||||
const res = await fetch(`/api/stash/performers/missing-images?url=${encodeURIComponent(stashUrl)}&gender=${gender}&has_scenes=${hasScenes}`);
|
||||
const res = await fetch(`/api/stash/performers/missing-images?url=${encodeURIComponent(stashUrl)}&gender=${gender}&has_scenes=${hasScenes}&full_names_only=${fullNamesOnly}`);
|
||||
if (!res.ok) {
|
||||
const err = await res.json();
|
||||
throw new Error(err.error || 'Failed to scan Stash performers');
|
||||
@@ -5390,6 +5397,7 @@ Return ONLY a valid JSON object with an array named "results":
|
||||
}
|
||||
|
||||
if (toggleStashFemaleOnly) toggleStashFemaleOnly.addEventListener('change', scanStashForMissingImages);
|
||||
if (toggleStashFullName) toggleStashFullName.addEventListener('change', scanStashForMissingImages);
|
||||
if (toggleStashHasScenes) toggleStashHasScenes.addEventListener('change', scanStashForMissingImages);
|
||||
|
||||
if (stashImagesSearchInput) {
|
||||
|
||||
@@ -384,19 +384,74 @@ def query_stash_batch(items, stash_url=None):
|
||||
|
||||
return results
|
||||
|
||||
def scrape_babepedia_images(name, limit=4):
|
||||
slug = name.strip().replace(' ', '_')
|
||||
url = f"https://www.babepedia.com/babe/{urllib.parse.quote(slug)}"
|
||||
req = urllib.request.Request(
|
||||
url,
|
||||
headers={
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36',
|
||||
'Accept-Language': 'en-US,en;q=0.9',
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'
|
||||
}
|
||||
)
|
||||
results = []
|
||||
seen = set()
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=6) as res:
|
||||
html = res.read().decode('utf-8', errors='ignore')
|
||||
m = re.search(r'id=\"profimg\"[^\>]*href=\"([^\"]+)\"', html)
|
||||
if not m:
|
||||
m = re.search(r'<img[^>]+src=[\"\'](/babeimg/[^\"\']+)[\"\']', html)
|
||||
if m:
|
||||
u = m.group(1)
|
||||
if not u.startswith('http'):
|
||||
u = 'https://www.babepedia.com' + u
|
||||
seen.add(u)
|
||||
results.append({'url': u, 'thumbnail': u, 'source': 'Babepedia'})
|
||||
|
||||
gallery = re.findall(r'href=[\"\'](/pics/[^\"\']+)[\"\']', html)
|
||||
for g in gallery:
|
||||
if not g.startswith('http'):
|
||||
g = 'https://www.babepedia.com' + g
|
||||
if g not in seen:
|
||||
seen.add(g)
|
||||
results.append({'url': g, 'thumbnail': g, 'source': 'Babepedia'})
|
||||
if len(results) >= limit:
|
||||
break
|
||||
except Exception:
|
||||
pass
|
||||
return results
|
||||
|
||||
def search_performer_candidate_images(name, aliases=None, limit=6):
|
||||
results = []
|
||||
seen = set()
|
||||
|
||||
# 1. Primary: Direct Babepedia Adult Database Scrape
|
||||
babe_imgs = scrape_babepedia_images(name, limit=4)
|
||||
for it in babe_imgs:
|
||||
if it['url'] not in seen:
|
||||
seen.add(it['url'])
|
||||
results.append(it)
|
||||
|
||||
if len(results) >= limit:
|
||||
return results
|
||||
|
||||
# 2. Secondary: Adult Database Targeted Queries on Bing
|
||||
queries = [
|
||||
f"{name} actress portrait",
|
||||
f"{name} model photoshoot",
|
||||
f"{name} portrait"
|
||||
f'"{name}" site:babepedia.com',
|
||||
f'"{name}" site:freeones.com',
|
||||
f'"{name}" site:iafd.com',
|
||||
f'"{name}" site:boobpedia.com',
|
||||
f'"{name}" adult star headshot portrait',
|
||||
f'"{name}" adult photoshoot portrait'
|
||||
]
|
||||
if aliases and isinstance(aliases, list):
|
||||
for a in aliases[:2]:
|
||||
if a and a.lower() != name.lower():
|
||||
queries.append(f"{a} actress portrait")
|
||||
queries.append(f'"{a}" site:babepedia.com')
|
||||
queries.append(f'"{a}" adult star portrait')
|
||||
|
||||
results = []
|
||||
seen = set()
|
||||
for q in queries:
|
||||
url = f"https://www.bing.com/images/search?q={urllib.parse.quote(q)}&FORM=HDRSC2"
|
||||
req = urllib.request.Request(
|
||||
@@ -413,11 +468,11 @@ def search_performer_candidate_images(name, aliases=None, limit=6):
|
||||
murls = re.findall(r'"murl":"(http[^&]+)"', html)
|
||||
turls = re.findall(r'"turl":"(http[^&]+)"', html)
|
||||
for i, u in enumerate(murls):
|
||||
clean_u = u.replace('\\/', '/')
|
||||
if clean_u not in seen:
|
||||
clean_u = u.replace(r'\/', '/')
|
||||
if clean_u not in seen and not any(bad in clean_u.lower() for bad in ['youtube.com', 'wikimedia.org', 'wikipedia.org', 'disney', 'marvel', 'cartoon', 'anime']):
|
||||
seen.add(clean_u)
|
||||
t = turls[i].replace('\\/', '/') if i < len(turls) else clean_u
|
||||
results.append({'url': clean_u, 'thumbnail': t})
|
||||
t = turls[i].replace(r'\/', '/') if i < len(turls) else clean_u
|
||||
results.append({'url': clean_u, 'thumbnail': t, 'source': 'Adult Web'})
|
||||
if len(results) >= limit:
|
||||
break
|
||||
except Exception:
|
||||
@@ -1178,6 +1233,7 @@ class RobustProxyHandler(http.server.SimpleHTTPRequestHandler):
|
||||
stash_url = params.get('url', [''])[0] or DEFAULT_STASH_URL
|
||||
gender_filter = params.get('gender', ['FEMALE'])[0].upper()
|
||||
only_scenes = params.get('has_scenes', ['true'])[0].lower() in ['true', '1']
|
||||
full_names_only = params.get('full_names_only', ['true'])[0].lower() in ['true', '1']
|
||||
|
||||
query = '''
|
||||
query {
|
||||
@@ -1205,6 +1261,13 @@ class RobustProxyHandler(http.server.SimpleHTTPRequestHandler):
|
||||
if not is_missing:
|
||||
continue
|
||||
|
||||
# Filter out ambiguous single-word names (only first names)
|
||||
p_name = (p.get('name') or '').strip()
|
||||
if full_names_only:
|
||||
name_parts = [pt for pt in re.split(r'[\s\.\-_]+', p_name) if len(pt) > 1]
|
||||
if len(name_parts) < 2:
|
||||
continue
|
||||
|
||||
p_gender = (p.get('gender') or '').upper()
|
||||
if gender_filter != 'ALL':
|
||||
if gender_filter == 'FEMALE' and p_gender not in ['FEMALE', '', 'NONE', None]:
|
||||
|
||||
Reference in New Issue
Block a user