From f555f20dd5201fb186daa19080b5d6c4c7141366 Mon Sep 17 00:00:00 2001 From: Yuval Adam <_@yuv.al> Date: Mon, 24 Oct 2022 22:09:20 +0300 Subject: Implement scan and update index.html --- scan.py | 47 +++++++++++++++++++++++++++++++++++++++++++++-- templates/index.html | 19 ++++++++++++++----- 2 files changed, 59 insertions(+), 7 deletions(-) diff --git a/scan.py b/scan.py index 34c65d8..cf367f4 100644 --- a/scan.py +++ b/scan.py @@ -7,8 +7,51 @@ ROOT_PATH = Path(__file__).parent DATA_DIR = ROOT_PATH / "data" TLDS_URL = "https://data.iana.org/TLD/tlds-alpha-by-domain.txt" +MALE_NAMES_URL = "https://raw.githubusercontent.com/DictionaryHouse/EnglishName/master/top_1000_EN_%E7%94%B7%E6%80%A7names_english.txt" +FEMALE_NAMES_URL = "https://raw.githubusercontent.com/DictionaryHouse/EnglishName/master/top_1000_EN_%E5%A5%B3%E6%80%A7names_english.txt" 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.split("\n")[1:] if len(tld) < 4] - f.write("\n".join(tlds).strip()) \ No newline at end of file + 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) + +NAMES = [] + +with open(DATA_DIR / "names.txt", "w") as f: + print("Fetching female names...") + res = requests.get(FEMALE_NAMES_URL) + f.write(res.text) + NAMES += res.text.split("\n") + print("Fetching male names...") + res = requests.get(MALE_NAMES_URL) + f.write(res.text) + NAMES += res.text.split("\n") + +# print(NAMES) +# print(TLDS) + +CANDIDATES = [] + +for name in NAMES: + if name[-2:] in TLDS: + CANDIDATES.append(f"{name[:-2]}.{name[-2:]}") + if name[-3:] in TLDS: + CANDIDATES.append(f"{name[:-3]}.{name[-3:]}") + +with open(DATA_DIR / "domains.txt", "w") as f: + f.write("\n".join(CANDIDATES).strip()) + +for c in CANDIDATES: + try: + print(f"Fetching {c}...", end="") + res = requests.get(f"http://{c}", timeout=5) + if res.ok: + print(f"Found {c}!") + with open(DATA_DIR / "homepages" / f"{c}.html", "w") as f: + f.write(res.text) + else: + print("x") + except: + print("x") \ No newline at end of file diff --git a/templates/index.html b/templates/index.html index a740c34..344f50c 100644 --- a/templates/index.html +++ b/templates/index.html @@ -18,9 +18,18 @@ -
- {% for name in names %} - {{name.name}} - {{name.domain}} - {% endfor %} + +An exclusive club of nerds that own the domain hack to their name, and serve their personal homepage from it.
+ +