1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
|
import json
import requests
from pathlib import Path
from os import makedirs, listdir
ROOT_PATH = Path(__file__).parents[1]
DATA_DIR = ROOT_PATH / "data"
TLDS_URL = "https://data.iana.org/TLD/tlds-alpha-by-domain.txt"
NAMES_ENDPOINT = "https://nameberry.com/nameberry/api/v1/search"
class NameScanner:
def fetch_tlds(self):
with open(DATA_DIR / "tlds.txt", "w") as f:
print("Fetching TLDs...")
res = requests.get(TLDS_URL)
tlds = [
tld.lower() for tld in res.text.strip().split("\n")[1:] if len(tld) < 4
]
f.write("\n".join(tlds).strip())
TLDS = set(tlds)
def fetch_homepage(self, domain):
print(f"Fetching {domain}...", end="")
res = requests.get(f"http://{domain}", timeout=5)
if res.ok:
print(f"Found {domain}!")
with open(DATA_DIR / "homepages" / f"{domain}.html", "w") as f:
f.write(res.text)
else:
print("x")
def fetch_names(self, suffix, count=5000):
res = requests.post(
NAMES_ENDPOINT,
json={
"starts_with": "",
"ends_with": suffix,
"contains": "",
"syllables": "",
"origin_id": "",
"derivation": "",
"page": 1,
"per_page": count,
},
)
if res.ok:
j = res.json()
print(f"found {j['advanced_name_count']}")
makedirs(DATA_DIR / "names", exist_ok=True)
with open(DATA_DIR / "names" / f"{suffix}.json", "w") as f:
f.write(res.text)
def fetch_all(self):
with open(DATA_DIR / "tlds.txt", "r") as f:
for line in f:
d = line.strip()
print(f"Fetching {d}...", end="")
self.fetch_names(d)
ns = NameScanner()
ns.fetch_names()
|
