Unify scripts/ directory (#52)

* Unify scripts/ directory

* Keep build.py in root for simplicity

2 files changed, 82 insertions, 0 deletions

diff --git a/scripts/ghpr.py b/scripts/ghpr.py
new file mode 100644
index 0000000..4e9a124
--- /dev/null
+++ b/scripts/ghpr.py
@@ -0,0 +1,25 @@
+import sys
+
+from pathlib import Path
+from subprocess import run
+
+ROOT_PATH = Path(__file__).parent
+
+path = sys.argv[1]
+
+with open(path, "r") as f:
+    for line in f:
+        l = line.strip().split(",")
+        domain, handle, name = [x.strip() for x in l]
+
+        fn = domain.replace(".", "")
+        with open(ROOT_PATH / "names" / f"{fn}.yml", "w") as out:
+            s = f"domain: {domain}\nname: {name}\ngithub: {handle}\n"
+            out.write(s)
+
+        run(["git", "checkout", "-b", domain])
+        run(["git", "add", f"names/{fn}.yml"])
+        run(["git", "commit", "-m", f"Add {domain}"])
+        run(["git", "push", "-u", "origin", domain])
+        run(["gh", "pr", "create", "-t", f"Add {domain}", "-b", f"Hey @{handle}, would you like to merge this PR adding you to https://namehack.club?"])
+        run(["git", "checkout", "main"])
diff --git a/scripts/scan.py b/scripts/scan.py
new file mode 100644
index 0000000..cf367f4
--- /dev/null
+++ b/scripts/scan.py
@@ -0,0 +1,57 @@
+import requests
+
+from pathlib import Path
+
+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.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