Skip to content

Free, open-source Google Maps scraper for lead generation (Python, no API key, no Docker). Exports name, phone, email, website, rating and Instagram/Facebook/LinkedIn/TikTok/YouTube/X links to CSV. 100 places with emails in 44 s; --grid beats Google's 120 cap. MX email check, ad-pixel detection. Skill for Claude Code, Codex and Cursor.

Merge branch 'feat/preset-search' into fix/v2-parity

Mahan Jafari828cf0b515f7
diff --cc engine/serve.py
index 1646933,1540485..696bb33
--- a/engine/serve.py
+++ b/engine/serve.py
@@@ -15,7 -15,7 +15,7 @@@ Google Maps, for email or socials jobs
to Google's public DNS (dns.google), nothing else.
Standard library only.
"""
- import argparse, csv, hmac, html, io, json, os, re, secrets, signal, socket, socketserver, sqlite3, sys, threading, unicodedata
-import argparse, csv, gzip, hmac, html, io, json, os, re, secrets, signal, socket, socketserver, sys, threading, unicodedata
++import argparse, csv, gzip, hmac, html, io, json, os, re, secrets, signal, socket, socketserver, sqlite3, sys, threading, unicodedata
import urllib.parse
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
@@@ -59,14 -61,48 +61,52 @@@ def file_name(job, jid)
return (re.sub(r"[^a-z0-9]+", "-", s).strip("-")[:60] or "results") + "-" + jid[:8]
+ FOLD = str.maketrans({"ł": "l", "ø": "o", "đ": "d", "ı": "i", "ß": "ss", "æ": "ae", "œ": "oe", "þ": "th"})
+
+
+ def fold(s):
+ """"sao paulo sp br" for "São Paulo, SP, BR": accents dropped (also ł, ø, ı...), lower case, punctuation
+ as single spaces."""
+ s = "".join(c for c in unicodedata.normalize("NFKD", s.lower().translate(FOLD)) if not unicodedata.combining(c))
+ return " ".join(re.sub(r"[\W_]+", " ", s).split())
+
+
+ def cities():
+ """Every city as one "folded label<TAB>label<TAB>lat<TAB>lon<TAB>country" line, biggest first. Read on the
+ first lookup, then kept (about 35 MB)."""
+ global _cities
+ with _cities_lock:
+ if _cities is None:
+ rows = []
+ with gzip.open(os.path.join(PRESETS, "cities.tsv.gz"), "rt", encoding="utf-8") as f:
+ for line in f:
+ name, admin, cc, lat, lon = line.rstrip("\n").split("\t")
+ label = ", ".join([name] + ([admin] if admin and admin != name else []) + [cc])
+ rows.append("\t".join((fold(label), label, lat, lon, cc)))
+ _cities = rows
+ return _cities
+
+
+ def find_cities(q, limit=20):
+ """The biggest cities whose "name, region, country" starts with q; with no q, the biggest in the US."""
+ q, out = fold(q), []
+ for row in cities(): # ponytail: a linear scan, about 30 ms; a prefix index if lookups ever lag
+ if row.startswith(q) if q else row.endswith("\tUS"):
+ _, label, lat, lon, cc = row.split("\t")
+ out.append({"label": label, "lat": lat, "lon": lon, "country": cc})
+ if len(out) == limit:
+ break
+ return out
+
+
def log(msg):
- """One line on stderr with a UTC timestamp and its offset. Counts only, never scraped values."""
+ """One line on stderr with a UTC timestamp and its offset. Counts only, never scraped values.
+ A log that cannot be written (full disk, closed stderr) is dropped, never raised."""
with _log_lock:
- print(f"{jobs.utc_now()} {msg}", file=sys.stderr, flush=True)
+ try:
+ print(f"{jobs.utc_now()} {msg}", file=sys.stderr, flush=True)
+ except (OSError, ValueError):
+ pass
def env_value(v):