perplexity-webui-scraper 0.3.7__py3-none-any.whl → 0.4.1__py3-none-any.whl

perplexity_webui_scraper/__init__.py

@@ -1,30 +1,51 @@
-"""
-Extract AI responses from Perplexity's web interface.
-"""
+"""Extract AI responses from Perplexity's web interface."""
 
 from importlib import metadata
 
 from .config import ClientConfig, ConversationConfig
 from .core import Conversation, Perplexity
 from .enums import CitationMode, LogLevel, SearchFocus, SourceFocus, TimeRange
+from .exceptions import (
+    AuthenticationError,
+    FileUploadError,
+    FileValidationError,
+    HTTPError,
+    PerplexityError,
+    RateLimitError,
+    ResearchClarifyingQuestionsError,
+    ResponseParsingError,
+    StreamingError,
+)
 from .models import Model, Models
 from .types import Coordinates, Response, SearchResultItem
 
 
+ConversationConfig.model_rebuild()
+
+
 __version__: str = metadata.version("perplexity-webui-scraper")
 __all__: list[str] = [
+    "AuthenticationError",
     "CitationMode",
     "ClientConfig",
     "Conversation",
     "ConversationConfig",
     "Coordinates",
+    "FileUploadError",
+    "FileValidationError",
+    "HTTPError",
     "LogLevel",
     "Model",
     "Models",
     "Perplexity",
+    "PerplexityError",
+    "RateLimitError",
+    "ResearchClarifyingQuestionsError",
     "Response",
+    "ResponseParsingError",
     "SearchFocus",
     "SearchResultItem",
     "SourceFocus",
+    "StreamingError",
     "TimeRange",
 ]

perplexity_webui_scraper/cli/get_perplexity_session_token.py

@@ -1,6 +1,4 @@
-"""
-CLI utility for secure Perplexity authentication and session extraction.
-"""
+"""CLI utility for secure Perplexity authentication and session extraction."""
 
 from __future__ import annotations
 
@@ -9,26 +7,20 @@ from sys import exit
 from typing import NoReturn
 
 from curl_cffi.requests import Session
+from orjson import loads
 from rich.console import Console
 from rich.panel import Panel
 from rich.prompt import Confirm, Prompt
 
 
-# Constants
 BASE_URL: str = "https://www.perplexity.ai"
 ENV_KEY: str = "PERPLEXITY_SESSION_TOKEN"
 
-
-# Initialize console on stderr to ensure secure alternate screen usage
 console = Console(stderr=True, soft_wrap=True)
 
 
 def update_env(token: str) -> bool:
-    """
-    Securely updates the .env file with the session token.
-
-    Preserves existing content and comments.
-    """
+    """Securely updates the .env file with the session token."""
 
     path = Path(".env")
     line_entry = f'{ENV_KEY}="{token}"'
@@ -48,26 +40,23 @@ def update_env(token: str) -> bool:
         if not updated:
             if new_lines and new_lines[-1] != "":
                 new_lines.append("")
-
             new_lines.append(line_entry)
 
         path.write_text("\n".join(new_lines) + "\n", encoding="utf-8")
-
         return True
+
     except Exception:
         return False
 
 
 def _initialize_session() -> tuple[Session, str]:
-    """
-    Initialize session and obtain CSRF token.
-    """
+    """Initialize session and obtain CSRF token."""
 
     session = Session(impersonate="chrome", headers={"Referer": BASE_URL, "Origin": BASE_URL})
 
     with console.status("[bold green]Initializing secure connection...", spinner="dots"):
         session.get(BASE_URL)
-        csrf_data = session.get(f"{BASE_URL}/api/auth/csrf").json()
+        csrf_data = loads(session.get(f"{BASE_URL}/api/auth/csrf").content)
         csrf = csrf_data.get("csrfToken")
 
         if not csrf:
@@ -77,12 +66,10 @@ def _initialize_session() -> tuple[Session, str]:
 
 
 def _request_verification_code(session: Session, csrf: str, email: str) -> None:
-    """
-    Send verification code to user's email.
-    """
+    """Send verification code to user's email."""
 
     with console.status("[bold green]Sending verification code...", spinner="dots"):
-        r = session.post(
+        response = session.post(
             f"{BASE_URL}/api/auth/signin/email?version=2.18&source=default",
             json={
                 "email": email,
@@ -93,20 +80,18 @@ def _request_verification_code(session: Session, csrf: str, email: str) -> None:
             },
         )
 
-        if r.status_code != 200:
-            raise ValueError(f"Authentication request failed: {r.text}")
+        if response.status_code != 200:
+            raise ValueError(f"Authentication request failed: {response.text}")
 
 
 def _validate_and_get_redirect_url(session: Session, email: str, user_input: str) -> str:
-    """
-    Validate user input (OTP or magic link) and return redirect URL.
-    """
+    """Validate user input (OTP or magic link) and return redirect URL."""
 
     with console.status("[bold green]Validating...", spinner="dots"):
         if user_input.startswith("http"):
             return user_input
 
-        r_otp = session.post(
+        response_otp = session.post(
             f"{BASE_URL}/api/auth/otp-redirect-link",
             json={
                 "email": email,
@@ -116,10 +101,10 @@ def _validate_and_get_redirect_url(session: Session, email: str, user_input: str
             },
         )
 
-        if r_otp.status_code != 200:
+        if response_otp.status_code != 200:
             raise ValueError("Invalid verification code.")
 
-        redirect_path = r_otp.json().get("redirect")
+        redirect_path = loads(response_otp.content).get("redirect")
 
         if not redirect_path:
             raise ValueError("No redirect URL received.")
@@ -128,9 +113,7 @@ def _validate_and_get_redirect_url(session: Session, email: str, user_input: str
 
 
 def _extract_session_token(session: Session, redirect_url: str) -> str:
-    """
-    Extract session token from cookies after authentication.
-    """
+    """Extract session token from cookies after authentication."""
 
     session.get(redirect_url)
     token = session.cookies.get("__Secure-next-auth.session-token")
@@ -142,9 +125,7 @@ def _extract_session_token(session: Session, redirect_url: str) -> str:
 
 
 def _display_and_save_token(token: str) -> None:
-    """
-    Display token and optionally save to .env file.
-    """
+    """Display token and optionally save to .env file."""
 
     console.print("\n[bold green]✅ Token generated successfully![/bold green]")
     console.print(f"\n[bold white]Your session token:[/bold white]\n[green]{token}[/green]\n")
@@ -159,9 +140,7 @@ def _display_and_save_token(token: str) -> None:
 
 
 def _show_header() -> None:
-    """
-    Display welcome header.
-    """
+    """Display welcome header."""
 
     console.print(
         Panel(
@@ -175,9 +154,7 @@ def _show_header() -> None:
 
 
 def _show_exit_message() -> None:
-    """
-    Display security note and wait for user to exit.
-    """
+    """Display security note and wait for user to exit."""
 
     console.print("\n[bold yellow]⚠️ Security Note:[/bold yellow]")
     console.print("Press [bold white]ENTER[/bold white] to clear screen and exit.")
@@ -185,46 +162,37 @@ def _show_exit_message() -> None:
 
 
 def get_token() -> NoReturn:
-    """
-    Executes the authentication flow within an ephemeral terminal screen.
-
-    Handles CSRF, Email OTP/Link validation, and secure token display.
-    """
+    """Executes the authentication flow within an ephemeral terminal screen."""
 
     with console.screen():
         try:
             _show_header()
 
-            # Step 1: Initialize session and get CSRF token
             session, csrf = _initialize_session()
 
-            # Step 2: Get email and request verification code
             console.print("\n[bold cyan]Step 1: Email Verification[/bold cyan]")
             email = Prompt.ask("  Enter your Perplexity email", console=console)
             _request_verification_code(session, csrf, email)
 
-            # Step 3: Get and validate user input (OTP or magic link)
             console.print("\n[bold cyan]Step 2: Verification[/bold cyan]")
             console.print("  Check your email for a [bold]6-digit code[/bold] or [bold]magic link[/bold].")
             user_input = Prompt.ask("  Enter code or paste link", console=console).strip()
             redirect_url = _validate_and_get_redirect_url(session, email, user_input)
 
-            # Step 4: Extract session token
             token = _extract_session_token(session, redirect_url)
 
-            # Step 5: Display and optionally save token
             _display_and_save_token(token)
 
-            # Step 6: Exit
             _show_exit_message()
 
             exit(0)
+
         except KeyboardInterrupt:
             exit(0)
+
         except Exception as error:
             console.print(f"\n[bold red]⛔ Error:[/bold red] {error}")
             console.input("[dim]Press ENTER to exit...[/dim]")
-
             exit(1)
 
 

perplexity_webui_scraper/config.py

@@ -1,27 +1,24 @@
-"""
-Configuration classes.
-"""
+"""Configuration classes."""
 
 from __future__ import annotations
 
-from dataclasses import dataclass
+from os import PathLike  # noqa: TC003
 from typing import TYPE_CHECKING
 
+from pydantic import BaseModel, ConfigDict
+
 from .enums import CitationMode, LogLevel, SearchFocus, SourceFocus, TimeRange
 
 
 if TYPE_CHECKING:
-    from pathlib import Path
-
     from .models import Model
     from .types import Coordinates
 
 
-@dataclass(slots=True)
-class ConversationConfig:
-    """
-    Default settings for a conversation. Can be overridden per message.
-    """
+class ConversationConfig(BaseModel):
+    """Default settings for a conversation."""
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     model: Model | None = None
     citation_mode: CitationMode = CitationMode.CLEAN
@@ -34,24 +31,10 @@ class ConversationConfig:
     coordinates: Coordinates | None = None
 
 
-@dataclass(frozen=True, slots=True)
-class ClientConfig:
-    """
-    HTTP client settings.
+class ClientConfig(BaseModel):
+    """HTTP client settings."""
 
-    Attributes:
-        timeout: Request timeout in seconds.
-        impersonate: Browser to impersonate (e.g., "chrome", "edge", "safari").
-        max_retries: Maximum retry attempts for failed requests.
-        retry_base_delay: Initial delay in seconds before first retry.
-        retry_max_delay: Maximum delay between retries.
-        retry_jitter: Random jitter factor (0-1) to add to delays.
-        requests_per_second: Rate limit for requests (0 to disable).
-        rotate_fingerprint: Whether to rotate browser fingerprint on retries.
-        logging_level: Logging verbosity level. Default is DISABLED.
-        log_file: Optional file path for persistent logging. If set, logs go to file only.
-                  If None, logs go to console. All logs are appended.
-    """
+    model_config = ConfigDict(frozen=True)
 
     timeout: int = 3600
     impersonate: str = "chrome"
@@ -62,4 +45,4 @@ class ClientConfig:
     requests_per_second: float = 0.5
     rotate_fingerprint: bool = True
     logging_level: LogLevel = LogLevel.DISABLED
-    log_file: str | Path | None = None
+    log_file: str | PathLike[str] | None = None

perplexity_webui_scraper/constants.py

@@ -1,6 +1,4 @@
-"""
-Constants and values for the Perplexity internal API and HTTP interactions.
-"""
+"""Constants and values for the Perplexity internal API."""
 
 from __future__ import annotations
 
@@ -8,77 +6,41 @@ from re import Pattern, compile
 from typing import Final
 
 
-# API Configuration
 API_VERSION: Final[str] = "2.18"
-"""
-Current API version used by Perplexity WebUI.
-"""
+"""Current API version used by Perplexity WebUI."""
 
 API_BASE_URL: Final[str] = "https://www.perplexity.ai"
-"""
-Base URL for all API requests.
-"""
+"""Base URL for all API requests."""
 
-# API Endpoints
 ENDPOINT_ASK: Final[str] = "/rest/sse/perplexity_ask"
-"""
-SSE endpoint for sending prompts.
-"""
+"""SSE endpoint for sending prompts."""
 
 ENDPOINT_SEARCH_INIT: Final[str] = "/search/new"
-"""
-Endpoint to initialize a search session.
-"""
+"""Endpoint to initialize a search session."""
 
 ENDPOINT_UPLOAD: Final[str] = "/rest/uploads/batch_create_upload_urls"
-"""
-Endpoint for file upload URL generation.
-"""
+"""Endpoint for file upload URL generation."""
 
-# API Fixed Parameters
 SEND_BACK_TEXT: Final[bool] = True
-"""
-Whether to receive full text in each streaming chunk.
-
-True = API sends complete text each chunk (replace mode).
-False = API sends delta chunks only (accumulate mode).
-"""
+"""Whether to receive full text in each streaming chunk (replace mode)."""
 
 USE_SCHEMATIZED_API: Final[bool] = False
-"""
-Whether to use the schematized API format.
-"""
+"""Whether to use the schematized API format."""
 
 PROMPT_SOURCE: Final[str] = "user"
-"""
-Source identifier for prompts.
-"""
+"""Source identifier for prompts."""
 
-# Regex Patterns (Pre-compiled for performance in streaming parsing)
 CITATION_PATTERN: Final[Pattern[str]] = compile(r"\[(\d{1,2})\]")
-"""
-Regex pattern for matching citation markers like [1], [2], etc.
-
-Uses word boundary to avoid matching things like [123].
-"""
+"""Regex pattern for matching citation markers like [1], [2]."""
 
 JSON_OBJECT_PATTERN: Final[Pattern[str]] = compile(r"^\{.*\}$")
-"""
-Pattern to detect JSON object strings.
-"""
+"""Pattern to detect JSON object strings."""
 
-# HTTP Headers
 DEFAULT_HEADERS: Final[dict[str, str]] = {
     "Accept": "text/event-stream, application/json",
     "Content-Type": "application/json",
 }
-"""
-Default HTTP headers for API requests.
-
-Referer and Origin are added dynamically based on BASE_URL.
-"""
+"""Default HTTP headers for API requests."""
 
 SESSION_COOKIE_NAME: Final[str] = "__Secure-next-auth.session-token"
-"""
-Name of the session cookie used for authentication.
-"""
+"""Name of the session cookie used for authentication."""