Snapshot: full project state

.case-verify/leagle_search.py

@@ -0,0 +1,75 @@
+import re, subprocess, json, time, os
+
+UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0 Safari/537.36"
+CK = "/tmp/lg_c.txt"
+
+CASES = [
+    ("Littlefield", "Littlefield", "64471-3"),
+    ("Kovacs", "Kovacs", "60035-0"),
+    ("Chumbley", "Chumbley", "72539-0"),
+    ("Short", "Short", "61176-9"),
+    ("Borghi", "Gilroy", "80925-9"),
+    ("Elam", "Elam", "48219-5"),
+    ("Konzen", "Konzen", "50402-4"),
+    ("Witte", "Witte", "29341"),
+    ("Skarbek", "Skarbek", "18013-1-III"),
+    ("PearsonMaines", "Pearson-Maines", "29873-9-I"),
+    ("Olivares", "Olivares", "28758-3-I"),
+    ("Sedlock", "Sedlock", "28848-2-I"),
+    ("Glorfield", "Glorfield", "3410-1-III"),
+    ("Hadley", "Hadley", "44308"),
+    ("Mueller", "Mueller", "57592-9-I"),
+    ("White", "White", "23917-5-II"),
+    ("Schwarz", "Schwarz", "32274-2-III"),
+    ("Kraft", "Kraft", "58247-5"),
+    ("Berol", "Berol", "31379"),
+    ("Brewer", "Brewer", "66577-0"),
+    ("Brown", "Brown", "49548-3"),
+]
+
+def curl(url, cookie_file=None, write=False, get_params=None):
+    cmd = ["curl", "-s", "-m", "40", "-H", f"User-Agent: {UA}"]
+    if cookie_file:
+        cmd += ["-b", cookie_file, "-c", cookie_file]
+    if get_params:
+        cmd += ["-G"]
+        for k, v in get_params.items():
+            cmd += ["--data-urlencode", f"{k}={v}"]
+    cmd.append(url)
+    r = subprocess.run(cmd, capture_output=True, text=True, timeout=50)
+    return r.stdout
+
+def leagle_search(query):
+    h = curl("https://www.leagle.com/leaglesearch", cookie_file=CK,
+             get_params={"casen": query, "crt": "Washington"})
+    results = []
+    for m in re.finditer(r'<a href="https://www\.leagle\.com/decision/([a-z0-9]+)"[^>]*>\s*<h3>([^<]+)\(\s*<span class="dec-date">([^<]+)</span>\s*\)\s*</h3>\s*<p>(.*?)</p>', h, re.S):
+        did, name, date, info = m.group(1), m.group(2).strip(), m.group(3).strip(), m.group(4)
+        info = re.sub(r'<[^>]+>', ' ', info)
+        info = re.sub(r'\s+', ' ', info).strip()
+        results.append({"id": did, "name": name, "date": date, "info": info})
+    return results
+
+# ensure cookies
+curl("https://www.leagle.com/search", cookie_file=CK)
+time.sleep(1)
+
+all_res = {}
+for key, query, docket in CASES:
+    rs = leagle_search(query)
+    picked = None
+    # prefer docket match
+    for r in rs:
+        if docket.replace("-", "") in r["info"].replace("-", "").replace(" ", ""):
+            picked = r; break
+    if not picked:
+        for r in rs:
+            n = r["name"].lower()
+            if key.lower() in n and ("marriage" in n or "estate" in n or key.lower() == "berol"):
+                picked = r; break
+    all_res[key] = picked
+    print(key, "=>", (picked["id"], picked["date"], picked["info"][:70]) if picked else f"NOT FOUND ({len(rs)} results)")
+    time.sleep(3)
+
+json.dump(all_res, open("/Users/drjones/astraea-books/.case-verify/leagle/leagle_urls.json", "w"), indent=1)
+print("saved")