bas-http 1.0.0__py3-none-any.whl

bas/curl_parser.py

@@ -0,0 +1,267 @@
+"""
+Parse curl commands into bas requests.
+
+The workflow:
+  1. Open browser DevTools -> Network tab
+  2. Right-click a request -> "Copy as cURL"
+  3. Paste into bas
+
+bas parses it and gives you a ready-to-go Session with all
+headers, cookies, and settings extracted.
+
+Handles both Windows (^") and Unix (\') escaping, and escaped quotes
+inside header values like sec-ch-ua.
+"""
+
+import re
+from typing import Optional
+from .cookies import Cookie, CookieJar
+from .models import Headers
+
+
+def _tokenize_curl(cmd: str) -> list[str]:
+    """
+    Tokenize a curl command string, handling:
+      - Double-quoted strings with escaped quotes inside (\")
+      - Single-quoted strings
+      - Unquoted tokens
+      - Windows ^" escaping
+      - Windows ^ line continuations
+    """
+    # Normalize Windows line continuations
+    cmd = re.sub(r'\s*\^\s*\n', ' ', cmd)
+    # Windows caret-quote: ^" -> "
+    cmd = cmd.replace('^"', '"').replace('^"', '"')
+    # Windows ^$ -> $
+    cmd = cmd.replace('^$', '$')
+
+    tokens = []
+    i = 0
+    while i < len(cmd):
+        # Skip whitespace
+        if cmd[i].isspace():
+            i += 1
+            continue
+
+        if cmd[i] == '"':
+            # Double-quoted string — handle escaped quotes \"
+            i += 1  # skip opening quote
+            buf = []
+            while i < len(cmd):
+                if cmd[i] == '\\' and i + 1 < len(cmd) and cmd[i + 1] == '"':
+                    buf.append('"')
+                    i += 2
+                elif cmd[i] == '"':
+                    i += 1  # skip closing quote
+                    break
+                else:
+                    buf.append(cmd[i])
+                    i += 1
+            tokens.append(''.join(buf))
+
+        elif cmd[i] == "'":
+            # Single-quoted string — no escaping
+            i += 1
+            buf = []
+            while i < len(cmd):
+                if cmd[i] == "'":
+                    i += 1
+                    break
+                else:
+                    buf.append(cmd[i])
+                    i += 1
+            tokens.append(''.join(buf))
+
+        else:
+            # Unquoted token
+            buf = []
+            while i < len(cmd) and not cmd[i].isspace():
+                buf.append(cmd[i])
+                i += 1
+            tokens.append(''.join(buf))
+
+    return tokens
+
+
+def parse_curl(curl_cmd: str) -> dict:
+    """
+    Parse a curl command string into its components.
+
+    Handles Windows (^"), Unix (\'), and escaped quotes inside values.
+
+    Returns:
+        {
+            "method": "GET" | "POST" | "PUT" | ...,
+            "url": "https://...",
+            "headers": {"key": "value", ...},
+            "cookies": {"name": "value", ...},
+            "cookie_header": "raw cookie string",
+            "data": "post body" or None,
+            "user_agent": "...",
+            "referer": "...",
+            "origin": "...",
+        }
+    """
+    result = {
+        "method": "GET",
+        "url": "",
+        "headers": {},
+        "cookies": {},
+        "cookie_header": "",
+        "data": None,
+        "user_agent": "",
+        "referer": "",
+        "origin": "",
+    }
+
+    tokens = _tokenize_curl(curl_cmd)
+
+    # Skip "curl" token
+    start = 0
+    if tokens and tokens[0].lower() == "curl":
+        start = 1
+
+    # First non-flag token is the URL
+    i = start
+    while i < len(tokens):
+        if tokens[i].startswith("-"):
+            # It's a flag, skip for now to find URL
+            if tokens[i] in ("-H", "-b", "-d", "-X", "-A", "-e", "--data"):
+                i += 2  # skip flag + value
+            else:
+                i += 1
+        else:
+            # It's the URL
+            result["url"] = tokens[i]
+            i += 1
+            break
+
+    # Now parse flags
+    while i < len(tokens):
+        token = tokens[i]
+
+        if token == "-H" and i + 1 < len(tokens):
+            val = tokens[i + 1]
+            if ":" in val:
+                key, _, value = val.partition(":")
+                key = key.strip()
+                value = value.strip()
+                result["headers"][key] = value
+
+                lk = key.lower()
+                if lk == "user-agent":
+                    result["user_agent"] = value
+                elif lk == "referer":
+                    result["referer"] = value
+                elif lk == "origin":
+                    result["origin"] = value
+            i += 2
+
+        elif token in ("-b", "--cookie") and i + 1 < len(tokens):
+            cookie_str = tokens[i + 1]
+            result["cookie_header"] = cookie_str
+            for pair in cookie_str.split(";"):
+                pair = pair.strip()
+                if "=" in pair:
+                    name, _, value = pair.partition("=")
+                    name = name.strip()
+                    value = value.strip()
+                    if name:
+                        result["cookies"][name] = value
+            i += 2
+
+        elif token in ("-d", "--data", "--data-raw") and i + 1 < len(tokens):
+            result["data"] = tokens[i + 1]
+            if "content-type" not in {k.lower(): v for k, v in result["headers"].items()}:
+                result["headers"]["Content-Type"] = "application/x-www-form-urlencoded"
+            i += 2
+
+        elif token == "-X" and i + 1 < len(tokens):
+            result["method"] = tokens[i + 1].upper()
+            i += 2
+
+        elif token in ("-A", "--user-agent") and i + 1 < len(tokens):
+            result["headers"]["User-Agent"] = tokens[i + 1]
+            result["user_agent"] = tokens[i + 1]
+            i += 2
+
+        elif token in ("-e", "--referer") and i + 1 < len(tokens):
+            result["headers"]["Referer"] = tokens[i + 1]
+            result["referer"] = tokens[i + 1]
+            i += 2
+
+        elif token == "--compressed":
+            i += 1
+
+        elif token == "-k":
+            i += 1
+
+        elif token.startswith("-"):
+            # Unknown flag, skip it and its value if it looks like it takes one
+            i += 1
+            if i < len(tokens) and not tokens[i].startswith("-"):
+                i += 1
+        else:
+            i += 1
+
+    if result["data"] and result["method"] == "GET":
+        result["method"] = "POST"
+
+    return result
+
+
+def curl_to_session(curl_cmd: str, **kwargs):
+    """
+    Parse a curl command and return a pre-configured Session.
+
+    Usage:
+        >>> s = curl_to_session('''curl "https://example.com" -H "User-Agent: ..." -b "cookie=value"''')
+        >>> r = s.get("https://example.com/other-page")
+    """
+    from .simple_session import Session
+
+    parsed = parse_curl(curl_cmd)
+
+    s = Session(**kwargs)
+    s.headers.update(parsed["headers"])
+
+    url = parsed["url"]
+    if url:
+        from urllib.parse import urlparse
+        domain = urlparse(url).hostname or ""
+        for name, value in parsed["cookies"].items():
+            s.set_cookie(name, value, domain=domain, path="/")
+
+    return s
+
+
+def print_curl_summary(curl_cmd: str) -> None:
+    """Print a human-readable summary of a curl command."""
+    parsed = parse_curl(curl_cmd)
+
+    print("=" * 60)
+    print("CURL COMMAND SUMMARY")
+    print("=" * 60)
+    print(f"  Method:  {parsed['method']}")
+    print(f"  URL:     {parsed['url']}")
+    print(f"  Headers: {len(parsed['headers'])}")
+    print(f"  Cookies: {len(parsed['cookies'])}")
+
+    if parsed["data"]:
+        data_preview = parsed["data"][:80] + ("..." if len(parsed["data"]) > 80 else "")
+        print(f"  Body:    {data_preview}")
+
+    print()
+    print("Headers:")
+    for key, value in parsed["headers"].items():
+        preview = value[:60] + ("..." if len(value) > 60 else "")
+        print(f"  {key}: {preview}")
+
+    if parsed["cookies"]:
+        print()
+        print("Cookies:")
+        for name, value in parsed["cookies"].items():
+            preview = value[:40] + ("..." if len(value) > 40 else "")
+            print(f"  {name} = {preview}")
+
+    print("=" * 60)

bas/impersonate.py

@@ -0,0 +1,424 @@
+"""
+Browser impersonation profiles.
+
+This module provides browser fingerprint profiles that override HTTP/2
+settings and headers to mimic real browsers. When curl-impersonate is
+available, it also enables TLS fingerprint mimicry.
+
+Unlike curlcffi which bundles impersonation in a single enum, bas
+separates the concerns:
+  - TLS impersonation (requires curl-impersonate library)
+  - HTTP/2 fingerprinting (works with standard libcurl)
+  - Header ordering and values (always works)
+"""
+
+from typing import Optional
+
+
+class BrowserProfile:
+    """
+    Defines how to mimic a specific browser.
+
+    Attributes:
+        name: Human-readable browser name
+        h2_settings: HTTP/2 SETTINGS frame parameters
+        h2_weight: HTTP/2 priority stream weight
+        h2_depends_on: HTTP/2 priority stream dependency
+        h2_exclusive: HTTP/2 priority stream exclusive flag
+        tls_version: Minimum TLS version to advertise
+        http_headers: Headers to send (in order)
+        pseudo_headers: HTTP/2 pseudo-headers order
+        header_order: Header order (True = use defined order)
+    """
+
+    def __init__(
+        self,
+        name: str,
+        h2_settings: Optional[dict] = None,
+        h2_weight: int = 1,
+        h2_depends_on: int = 0,
+        h2_exclusive: bool = False,
+        tls_version: str = "1.3",
+        http_headers: Optional[dict] = None,
+        pseudo_headers: Optional[list] = None,
+        header_order: bool = True,
+        curl_impersonate: Optional[str] = None,
+    ):
+        self.name = name
+        self.h2_settings = h2_settings or {}
+        self.h2_weight = h2_weight
+        self.h2_depends_on = h2_depends_on
+        self.h2_exclusive = h2_exclusive
+        self.tls_version = tls_version
+        self.http_headers = http_headers or {}
+        self.pseudo_headers = pseudo_headers or []
+        self.header_order = header_order
+        self.curl_impersonate = curl_impersonate  # curl-impersonate profile name
+
+    def __repr__(self):
+        return f"BrowserProfile({self.name!r})"
+
+
+# ── Pre-defined browser profiles ─────────────────────────────────────────────
+
+CHROME131 = BrowserProfile(
+    name="chrome131",
+    curl_impersonate="chrome131",
+    h2_settings={
+        "HEADER_TABLE_SIZE": 65536,
+        "MAX_CONCURRENT_STREAMS": 1000,
+        "INITIAL_WINDOW_SIZE": 6291456,
+        "MAX_FRAME_SIZE": 16384,
+        "MAX_HEADER_LIST_SIZE": 262144,
+    },
+    h2_weight=256,
+    http_headers={
+        "User-Agent": (
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+            "AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/131.0.0.0 Safari/537.36"
+        ),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+        "Accept-Language": "en-US,en;q=0.9",
+        "Accept-Encoding": "gzip, deflate, br, zstd",
+        "Sec-Ch-Ua": '"Chromium";v="131", "Not_A Brand";v="24"',
+        "Sec-Ch-Ua-Mobile": "?0",
+        "Sec-Ch-Ua-Platform": '"Windows"',
+        "Sec-Fetch-Dest": "document",
+        "Sec-Fetch-Mode": "navigate",
+        "Sec-Fetch-Site": "none",
+        "Sec-Fetch-User": "?1",
+        "Upgrade-Insecure-Requests": "1",
+    },
+)
+
+CHROME124 = BrowserProfile(
+    name="chrome124",
+    curl_impersonate="chrome124",
+    h2_settings={
+        "HEADER_TABLE_SIZE": 65536,
+        "MAX_CONCURRENT_STREAMS": 1000,
+        "INITIAL_WINDOW_SIZE": 6291456,
+        "MAX_FRAME_SIZE": 16384,
+        "MAX_HEADER_LIST_SIZE": 262144,
+    },
+    http_headers={
+        "User-Agent": (
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+            "AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/124.0.0.0 Safari/537.36"
+        ),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+        "Accept-Language": "en-US,en;q=0.9",
+        "Accept-Encoding": "gzip, deflate, br",
+        "Sec-Ch-Ua": '"Chromium";v="124", "Google Chrome";v="124", "Not-A.Brand";v="99"',
+        "Sec-Ch-Ua-Mobile": "?0",
+        "Sec-Ch-Ua-Platform": '"Windows"',
+        "Sec-Fetch-Dest": "document",
+        "Sec-Fetch-Mode": "navigate",
+        "Sec-Fetch-Site": "none",
+        "Sec-Fetch-User": "?1",
+        "Upgrade-Insecure-Requests": "1",
+    },
+)
+
+CHROME120 = BrowserProfile(
+    name="chrome120",
+    curl_impersonate="chrome120",
+    h2_settings={
+        "HEADER_TABLE_SIZE": 65536,
+        "MAX_CONCURRENT_STREAMS": 1000,
+        "INITIAL_WINDOW_SIZE": 6291456,
+        "MAX_FRAME_SIZE": 16384,
+        "MAX_HEADER_LIST_SIZE": 262144,
+    },
+    http_headers={
+        "User-Agent": (
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+            "AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/120.0.0.0 Safari/537.36"
+        ),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+        "Accept-Language": "en-US,en;q=0.9",
+        "Accept-Encoding": "gzip, deflate, br",
+        "Sec-Ch-Ua": '"Not_A Brand";v="8", "Chromium";v="120", "Google Chrome";v="120"',
+        "Sec-Ch-Ua-Mobile": "?0",
+        "Sec-Ch-Ua-Platform": '"Windows"',
+        "Sec-Fetch-Dest": "document",
+        "Sec-Fetch-Mode": "navigate",
+        "Sec-Fetch-Site": "none",
+        "Sec-Fetch-User": "?1",
+        "Upgrade-Insecure-Requests": "1",
+    },
+)
+
+CHROME110 = BrowserProfile(
+    name="chrome110",
+    curl_impersonate="chrome110",
+    h2_settings={
+        "HEADER_TABLE_SIZE": 65536,
+        "MAX_CONCURRENT_STREAMS": 1000,
+        "INITIAL_WINDOW_SIZE": 6291456,
+        "MAX_FRAME_SIZE": 16384,
+        "MAX_HEADER_LIST_SIZE": 262144,
+    },
+    http_headers={
+        "User-Agent": (
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+            "AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/110.0.0.0 Safari/537.36"
+        ),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+        "Accept-Language": "en-US,en;q=0.9",
+        "Accept-Encoding": "gzip, deflate, br",
+        "Sec-Ch-Ua": '"Chromium";v="110", "Not A(Brand";v="24", "Google Chrome";v="110"',
+        "Sec-Ch-Ua-Mobile": "?0",
+        "Sec-Ch-Ua-Platform": '"Windows"',
+        "Sec-Fetch-Dest": "document",
+        "Sec-Fetch-Mode": "navigate",
+        "Sec-Fetch-Site": "none",
+        "Sec-Fetch-User": "?1",
+        "Upgrade-Insecure-Requests": "1",
+    },
+)
+
+FIREFOX133 = BrowserProfile(
+    name="firefox133",
+    curl_impersonate="firefox133",
+    h2_settings={
+        "HEADER_TABLE_SIZE": 65536,
+        "MAX_CONCURRENT_STREAMS": 1000,
+        "INITIAL_WINDOW_SIZE": 131072,
+        "MAX_FRAME_SIZE": 16384,
+        "MAX_HEADER_LIST_SIZE": 262144,
+    },
+    http_headers={
+        "User-Agent": (
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:133.0) "
+            "Gecko/20100101 Firefox/133.0"
+        ),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
+        "Accept-Language": "en-US,en;q=0.5",
+        "Accept-Encoding": "gzip, deflate, br",
+        "Sec-Fetch-Dest": "document",
+        "Sec-Fetch-Mode": "navigate",
+        "Sec-Fetch-Site": "none",
+        "Sec-Fetch-User": "?1",
+        "Upgrade-Insecure-Requests": "1",
+    },
+)
+
+FIREFOX131 = BrowserProfile(
+    name="firefox131",
+    curl_impersonate="firefox131",
+    h2_settings={
+        "HEADER_TABLE_SIZE": 65536,
+        "MAX_CONCURRENT_STREAMS": 1000,
+        "INITIAL_WINDOW_SIZE": 131072,
+        "MAX_FRAME_SIZE": 16384,
+        "MAX_HEADER_LIST_SIZE": 262144,
+    },
+    http_headers={
+        "User-Agent": (
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:131.0) "
+            "Gecko/20100101 Firefox/131.0"
+        ),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
+        "Accept-Language": "en-US,en;q=0.5",
+        "Accept-Encoding": "gzip, deflate, br",
+        "Sec-Fetch-Dest": "document",
+        "Sec-Fetch-Mode": "navigate",
+        "Sec-Fetch-Site": "none",
+        "Sec-Fetch-User": "?1",
+        "Upgrade-Insecure-Requests": "1",
+    },
+)
+
+FIREFOX120 = BrowserProfile(
+    name="firefox120",
+    curl_impersonate="firefox120",
+    h2_settings={
+        "HEADER_TABLE_SIZE": 65536,
+        "MAX_CONCURRENT_STREAMS": 1000,
+        "INITIAL_WINDOW_SIZE": 131072,
+        "MAX_FRAME_SIZE": 16384,
+        "MAX_HEADER_LIST_SIZE": 262144,
+    },
+    http_headers={
+        "User-Agent": (
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:120.0) "
+            "Gecko/20100101 Firefox/120.0"
+        ),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
+        "Accept-Language": "en-US,en;q=0.5",
+        "Accept-Encoding": "gzip, deflate, br",
+        "Sec-Fetch-Dest": "document",
+        "Sec-Fetch-Mode": "navigate",
+        "Sec-Fetch-Site": "none",
+        "Sec-Fetch-User": "?1",
+        "Upgrade-Insecure-Requests": "1",
+    },
+)
+
+SAFARI18_0 = BrowserProfile(
+    name="safari18_0",
+    h2_settings={
+        "HEADER_TABLE_SIZE": 65536,
+        "MAX_CONCURRENT_STREAMS": 100,
+        "INITIAL_WINDOW_SIZE": 4194304,
+        "MAX_FRAME_SIZE": 16384,
+        "MAX_HEADER_LIST_SIZE": 262144,
+    },
+    http_headers={
+        "User-Agent": (
+            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
+            "AppleWebKit/605.1.15 (KHTML, like Gecko) "
+            "Version/18.0 Safari/605.1.15"
+        ),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+        "Accept-Language": "en-US,en;q=0.9",
+        "Accept-Encoding": "gzip, deflate, br",
+    },
+)
+
+SAMSUNG_ANDROID = BrowserProfile(
+    name="samsung_android",
+    curl_impersonate="samsung_android",
+    h2_settings={
+        "HEADER_TABLE_SIZE": 65536,
+        "MAX_CONCURRENT_STREAMS": 100,
+        "INITIAL_WINDOW_SIZE": 65536,
+        "MAX_FRAME_SIZE": 16384,
+        "MAX_HEADER_LIST_SIZE": 262144,
+    },
+    http_headers={
+        "User-Agent": (
+            "Mozilla/5.0 (Linux; Android 13; SM-S911B) "
+            "AppleWebKit/537.36 (KHTML, like Gecko) "
+            "SamsungBrowser/23.0 Chrome/115.0.0.0 Mobile Safari/537.36"
+        ),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
+        "Accept-Language": "en-US,en;q=0.9",
+        "Accept-Encoding": "gzip, deflate, br",
+    },
+)
+
+EDGE131 = BrowserProfile(
+    name="edge131",
+    curl_impersonate="edge131",
+    h2_settings={
+        "HEADER_TABLE_SIZE": 65536,
+        "MAX_CONCURRENT_STREAMS": 1000,
+        "INITIAL_WINDOW_SIZE": 6291456,
+        "MAX_FRAME_SIZE": 16384,
+        "MAX_HEADER_LIST_SIZE": 262144,
+    },
+    http_headers={
+        "User-Agent": (
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+            "AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/131.0.0.0 Safari/537.36 Edg/131.0.0.0"
+        ),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+        "Accept-Language": "en-US,en;q=0.9",
+        "Accept-Encoding": "gzip, deflate, br",
+        "Sec-Ch-Ua": '"Chromium";v="131", "Microsoft Edge";v="131", "Not_A Brand";v="24"',
+        "Sec-Ch-Ua-Mobile": "?0",
+        "Sec-Ch-Ua-Platform": '"Windows"',
+        "Sec-Fetch-Dest": "document",
+        "Sec-Fetch-Mode": "navigate",
+        "Sec-Fetch-Site": "none",
+        "Sec-Fetch-User": "?1",
+        "Upgrade-Insecure-Requests": "1",
+    },
+)
+
+# ── Profile registry ─────────────────────────────────────────────────────────
+
+PROFILES: dict[str, BrowserProfile] = {
+    "chrome131": CHROME131,
+    "chrome124": CHROME124,
+    "chrome120": CHROME120,
+    "chrome110": CHROME110,
+    "firefox133": FIREFOX133,
+    "firefox131": FIREFOX131,
+    "firefox120": FIREFOX120,
+    "safari18.0": SAFARI18_0,
+    "samsung_android": SAMSUNG_ANDROID,
+    "edge131": EDGE131,
+}
+
+# Aliases for curlcffi compatibility
+CHROME_ALIASES = {
+    "chrome": CHROME131,
+    "chrome99": CHROME131,  # closest available
+    "chrome100": CHROME131,
+    "chrome101": CHROME131,
+    "chrome104": CHROME131,
+    "chrome107": CHROME131,
+    "chrome110": CHROME110,
+    "chrome116": CHROME120,
+    "chrome119": CHROME120,
+    "chrome120": CHROME120,
+    "chrome123": CHROME124,
+    "chrome124": CHROME124,
+    "chrome131": CHROME131,
+}
+
+FIREFOX_ALIASES = {
+    "firefox": FIREFOX133,
+    "firefox99": FIREFOX120,
+    "firefox100": FIREFOX120,
+    "firefox102": FIREFOX120,
+    "firefox109": FIREFOX120,
+    "firefox117": FIREFOX120,
+    "firefox119": FIREFOX120,
+    "firefox120": FIREFOX120,
+    "firefox131": FIREFOX131,
+    "firefox133": FIREFOX133,
+}
+
+ALL_ALIASES = {**CHROME_ALIASES, **FIREFOX_ALIASES}
+
+
+def get_profile(name: str) -> BrowserProfile:
+    """
+    Get a browser profile by name.
+
+    Supports both exact names and curlcffi-compatible aliases.
+
+    Args:
+        name: Profile name (e.g., "chrome131", "firefox120", "chrome")
+
+    Returns:
+        BrowserProfile instance
+
+    Raises:
+        ValueError: If profile name is not recognized
+    """
+    # Normalize: strip "chrome" prefix variations
+    normalized = name.lower().strip()
+
+    # Check direct match first
+    if normalized in PROFILES:
+        return PROFILES[normalized]
+
+    # Check aliases
+    if normalized in ALL_ALIASES:
+        return ALL_ALIASES[normalized]
+
+    # Try fuzzy match
+    for profile_name, profile in PROFILES.items():
+        if profile_name in normalized or normalized in profile_name:
+            return profile
+
+    available = ", ".join(sorted(set(list(PROFILES.keys()) + list(ALL_ALIASES.keys()))))
+    raise ValueError(
+        f"Unknown browser profile: {name!r}. "
+        f"Available profiles: {available}"
+    )
+
+
+def list_profiles() -> list[str]:
+    """List all available profile names."""
+    return sorted(set(list(PROFILES.keys()) + list(ALL_ALIASES.keys())))