perplexity-webui-scraper 0.3.3__tar.gz → 0.3.4__tar.gz

{perplexity_webui_scraper-0.3.3 → perplexity_webui_scraper-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: perplexity-webui-scraper
-Version: 0.3.3
+Version: 0.3.4
 Summary: Python scraper to extract AI responses from Perplexity's web interface.
 Keywords: perplexity,ai,scraper,webui,api,client
 Author: henrique-coder
@@ -19,7 +19,7 @@ Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Internet :: WWW/HTTP
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Typing :: Typed
-Requires-Dist: curl-cffi>=0.13.0
+Requires-Dist: curl-cffi>=0.14.0
 Requires-Dist: orjson>=3.11.5
 Requires-Dist: pydantic>=2.12.5
 Requires-Python: >=3.10
@@ -52,15 +52,44 @@ uv pip install perplexity-webui-scraper
 
 ## Requirements
 
-- **Perplexity Pro subscription**
-- **Session token** (`__Secure-next-auth.session-token` cookie from browser)
+- **Perplexity Pro/Max account**
+- **Session token** (`__Secure-next-auth.session-token` cookie from your browser)
 
 ### Getting Your Session Token
 
+You can obtain your session token in two ways:
+
+#### Option 1: Automatic (CLI Tool)
+
+The package includes a CLI tool to automatically generate and save your session token:
+
+```bash
+get-perplexity-session-token
+```
+
+This interactive tool will:
+
+1. Ask for your Perplexity email
+2. Send a verification code to your email
+3. Accept either a 6-digit code or magic link
+4. Extract and display your session token
+5. Optionally save it to your `.env` file
+
+**Features:**
+
+- Secure ephemeral session (cleared on exit)
+- Automatic `.env` file management
+- Support for both OTP codes and magic links
+- Clean terminal interface with status updates
+
+#### Option 2: Manual (Browser)
+
+If you prefer to extract the token manually:
+
 1. Log in at [perplexity.ai](https://www.perplexity.ai)
-2. Open DevTools (`F12`) → Application → Cookies
-3. Copy `__Secure-next-auth.session-token` value
-4. Store in `.env`: `PERPLEXITY_SESSION_TOKEN=your_token`
+2. Open DevTools (`F12`) → Application/Storage → Cookies
+3. Copy the value of `__Secure-next-auth.session-token`
+4. Store in `.env`: `PERPLEXITY_SESSION_TOKEN="your_token"`
 
 ## Quick Start
 
@@ -117,25 +146,34 @@ conversation.ask("Latest AI research", files=["paper.pdf"])
 
 ### `Conversation.ask(query, model?, files?, citation_mode?, stream?)`
 
-| Parameter       | Type           | Default       | Description         |
-| --------------- | -------------- | ------------- | ------------------- |
-| `query`         | `str`          | —             | Question (required) |
-| `model`         | `Model`        | `Models.BEST` | AI model            |
-| `files`         | `list[str]`    | `None`        | File paths          |
-| `citation_mode` | `CitationMode` | `CLEAN`       | Citation format     |
-| `stream`        | `bool`         | `False`       | Enable streaming    |
+| Parameter       | Type                    | Default       | Description         |
+| --------------- | ----------------------- | ------------- | ------------------- |
+| `query`         | `str`                   | -             | Question (required) |
+| `model`         | `Model`                 | `Models.BEST` | AI model            |
+| `files`         | `list[str \| PathLike]` | `None`        | File paths          |
+| `citation_mode` | `CitationMode`          | `CLEAN`       | Citation format     |
+| `stream`        | `bool`                  | `False`       | Enable streaming    |
 
 ### Models
 
-| Model                          | Description       |
-| ------------------------------ | ----------------- |
-| `Models.BEST`                  | Auto-select best  |
-| `Models.RESEARCH`              | Deep research     |
-| `Models.SONAR`                 | Fast queries      |
-| `Models.GPT_51`                | OpenAI GPT-5.1    |
-| `Models.CLAUDE_45_SONNET`      | Claude 4.5 Sonnet |
-| `Models.GEMINI_3_PRO_THINKING` | Gemini 3.0 Pro    |
-| `Models.GROK_41`               | xAI Grok 4.1      |
+| Model                              | Description                                                               |
+| ---------------------------------- | ------------------------------------------------------------------------- |
+| `Models.RESEARCH`                  | Research - Fast and thorough for routine research                         |
+| `Models.LABS`                      | Labs - Multi-step tasks with advanced troubleshooting                     |
+| `Models.BEST`                      | Best - Automatically selects the most responsive model based on the query |
+| `Models.SONAR`                     | Sonar - Perplexity's fast model                                           |
+| `Models.GPT_52`                    | GPT-5.2 - OpenAI's latest model                                           |
+| `Models.GPT_52_THINKING`           | GPT-5.2 Thinking - OpenAI's latest model with thinking                    |
+| `Models.CLAUDE_45_OPUS`            | Claude Opus 4.5 - Anthropic's Opus reasoning model                        |
+| `Models.CLAUDE_45_OPUS_THINKING`   | Claude Opus 4.5 Thinking - Anthropic's Opus reasoning model with thinking |
+| `Models.GEMINI_3_PRO`              | Gemini 3 Pro - Google's newest reasoning model                            |
+| `Models.GEMINI_3_FLASH`            | Gemini 3 Flash - Google's fast reasoning model                            |
+| `Models.GEMINI_3_FLASH_THINKING`   | Gemini 3 Flash Thinking - Google's fast reasoning model with thinking     |
+| `Models.GROK_41`                   | Grok 4.1 - xAI's latest advanced model                                    |
+| `Models.GROK_41_THINKING`          | Grok 4.1 Thinking - xAI's latest reasoning model                          |
+| `Models.KIMI_K2_THINKING`          | Kimi K2 Thinking - Moonshot AI's latest reasoning model                   |
+| `Models.CLAUDE_45_SONNET`          | Claude Sonnet 4.5 - Anthropic's newest advanced model                     |
+| `Models.CLAUDE_45_SONNET_THINKING` | Claude Sonnet 4.5 Thinking - Anthropic's newest reasoning model           |
 
 ### CitationMode
 
@@ -159,6 +197,16 @@ conversation.ask("Latest AI research", files=["paper.pdf"])
 | `timezone`        | `None`        | Timezone           |
 | `coordinates`     | `None`        | Location (lat/lng) |
 
+## CLI Tools
+
+### Session Token Generator
+
+```bash
+get-perplexity-session-token
+```
+
+Interactive tool to automatically obtain your Perplexity session token via email authentication. The token can be automatically saved to your `.env` file for immediate use.
+
 ## Disclaimer
 
 This is an **unofficial** library. It uses internal APIs that may change without notice. Use at your own risk. Not for production use.

perplexity_webui_scraper-0.3.4/README.md

@@ -0,0 +1,182 @@
+<div align="center">
+
+# Perplexity WebUI Scraper
+
+Python scraper to extract AI responses from [Perplexity's](https://www.perplexity.ai) web interface.
+
+[![PyPI](https://img.shields.io/pypi/v/perplexity-webui-scraper?color=blue)](https://pypi.org/project/perplexity-webui-scraper)
+[![Python](https://img.shields.io/pypi/pyversions/perplexity-webui-scraper)](https://pypi.org/project/perplexity-webui-scraper)
+[![License](https://img.shields.io/github/license/henrique-coder/perplexity-webui-scraper?color=green)](./LICENSE)
+
+</div>
+
+---
+
+## Installation
+
+```bash
+uv pip install perplexity-webui-scraper
+```
+
+## Requirements
+
+- **Perplexity Pro/Max account**
+- **Session token** (`__Secure-next-auth.session-token` cookie from your browser)
+
+### Getting Your Session Token
+
+You can obtain your session token in two ways:
+
+#### Option 1: Automatic (CLI Tool)
+
+The package includes a CLI tool to automatically generate and save your session token:
+
+```bash
+get-perplexity-session-token
+```
+
+This interactive tool will:
+
+1. Ask for your Perplexity email
+2. Send a verification code to your email
+3. Accept either a 6-digit code or magic link
+4. Extract and display your session token
+5. Optionally save it to your `.env` file
+
+**Features:**
+
+- Secure ephemeral session (cleared on exit)
+- Automatic `.env` file management
+- Support for both OTP codes and magic links
+- Clean terminal interface with status updates
+
+#### Option 2: Manual (Browser)
+
+If you prefer to extract the token manually:
+
+1. Log in at [perplexity.ai](https://www.perplexity.ai)
+2. Open DevTools (`F12`) → Application/Storage → Cookies
+3. Copy the value of `__Secure-next-auth.session-token`
+4. Store in `.env`: `PERPLEXITY_SESSION_TOKEN="your_token"`
+
+## Quick Start
+
+```python
+from perplexity_webui_scraper import Perplexity
+
+client = Perplexity(session_token="YOUR_TOKEN")
+conversation = client.create_conversation()
+
+conversation.ask("What is quantum computing?")
+print(conversation.answer)
+
+# Follow-up
+conversation.ask("Explain it simpler")
+print(conversation.answer)
+```
+
+### Streaming
+
+```python
+for chunk in conversation.ask("Explain AI", stream=True):
+    print(chunk.answer)
+```
+
+### With Options
+
+```python
+from perplexity_webui_scraper import (
+    ConversationConfig,
+    Coordinates,
+    Models,
+    SourceFocus,
+)
+
+config = ConversationConfig(
+    model=Models.RESEARCH,
+    source_focus=[SourceFocus.WEB, SourceFocus.ACADEMIC],
+    language="en-US",
+    coordinates=Coordinates(latitude=40.7128, longitude=-74.0060),
+)
+
+conversation = client.create_conversation(config)
+conversation.ask("Latest AI research", files=["paper.pdf"])
+```
+
+## API
+
+### `Perplexity(session_token, config?)`
+
+| Parameter       | Type           | Description        |
+| --------------- | -------------- | ------------------ |
+| `session_token` | `str`          | Browser cookie     |
+| `config`        | `ClientConfig` | Timeout, TLS, etc. |
+
+### `Conversation.ask(query, model?, files?, citation_mode?, stream?)`
+
+| Parameter       | Type                    | Default       | Description         |
+| --------------- | ----------------------- | ------------- | ------------------- |
+| `query`         | `str`                   | -             | Question (required) |
+| `model`         | `Model`                 | `Models.BEST` | AI model            |
+| `files`         | `list[str \| PathLike]` | `None`        | File paths          |
+| `citation_mode` | `CitationMode`          | `CLEAN`       | Citation format     |
+| `stream`        | `bool`                  | `False`       | Enable streaming    |
+
+### Models
+
+| Model                              | Description                                                               |
+| ---------------------------------- | ------------------------------------------------------------------------- |
+| `Models.RESEARCH`                  | Research - Fast and thorough for routine research                         |
+| `Models.LABS`                      | Labs - Multi-step tasks with advanced troubleshooting                     |
+| `Models.BEST`                      | Best - Automatically selects the most responsive model based on the query |
+| `Models.SONAR`                     | Sonar - Perplexity's fast model                                           |
+| `Models.GPT_52`                    | GPT-5.2 - OpenAI's latest model                                           |
+| `Models.GPT_52_THINKING`           | GPT-5.2 Thinking - OpenAI's latest model with thinking                    |
+| `Models.CLAUDE_45_OPUS`            | Claude Opus 4.5 - Anthropic's Opus reasoning model                        |
+| `Models.CLAUDE_45_OPUS_THINKING`   | Claude Opus 4.5 Thinking - Anthropic's Opus reasoning model with thinking |
+| `Models.GEMINI_3_PRO`              | Gemini 3 Pro - Google's newest reasoning model                            |
+| `Models.GEMINI_3_FLASH`            | Gemini 3 Flash - Google's fast reasoning model                            |
+| `Models.GEMINI_3_FLASH_THINKING`   | Gemini 3 Flash Thinking - Google's fast reasoning model with thinking     |
+| `Models.GROK_41`                   | Grok 4.1 - xAI's latest advanced model                                    |
+| `Models.GROK_41_THINKING`          | Grok 4.1 Thinking - xAI's latest reasoning model                          |
+| `Models.KIMI_K2_THINKING`          | Kimi K2 Thinking - Moonshot AI's latest reasoning model                   |
+| `Models.CLAUDE_45_SONNET`          | Claude Sonnet 4.5 - Anthropic's newest advanced model                     |
+| `Models.CLAUDE_45_SONNET_THINKING` | Claude Sonnet 4.5 Thinking - Anthropic's newest reasoning model           |
+
+### CitationMode
+
+| Mode       | Output                |
+| ---------- | --------------------- |
+| `DEFAULT`  | `text[1]`             |
+| `MARKDOWN` | `text[1](url)`        |
+| `CLEAN`    | `text` (no citations) |
+
+### ConversationConfig
+
+| Parameter         | Default       | Description        |
+| ----------------- | ------------- | ------------------ |
+| `model`           | `Models.BEST` | Default model      |
+| `citation_mode`   | `CLEAN`       | Citation format    |
+| `save_to_library` | `False`       | Save to library    |
+| `search_focus`    | `WEB`         | Search type        |
+| `source_focus`    | `WEB`         | Source types       |
+| `time_range`      | `ALL`         | Time filter        |
+| `language`        | `"en-US"`     | Response language  |
+| `timezone`        | `None`        | Timezone           |
+| `coordinates`     | `None`        | Location (lat/lng) |
+
+## CLI Tools
+
+### Session Token Generator
+
+```bash
+get-perplexity-session-token
+```
+
+Interactive tool to automatically obtain your Perplexity session token via email authentication. The token can be automatically saved to your `.env` file for immediate use.
+
+## Disclaimer
+
+This is an **unofficial** library. It uses internal APIs that may change without notice. Use at your own risk. Not for production use.
+
+By using this library, you agree to Perplexity AI's Terms of Service.

{perplexity_webui_scraper-0.3.3 → perplexity_webui_scraper-0.3.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "perplexity-webui-scraper"
-version = "0.3.3"
+version = "0.3.4"
 description = "Python scraper to extract AI responses from Perplexity's web interface."
 authors = [{ name = "henrique-coder", email = "henriquemoreira10fk@gmail.com" }]
 license = "MIT"
@@ -23,18 +23,21 @@ classifiers = [
     "Typing :: Typed",
 ]
 dependencies = [
-    "curl-cffi>=0.13.0",
+    "curl-cffi>=0.14.0",
     "orjson>=3.11.5",
     "pydantic>=2.12.5",
 ]
 
 [dependency-groups]
 dev = [
+    "beautifulsoup4>=4.14.3",
+    "jsbeautifier>=1.15.4",
+    "lxml>=6.0.2",
     "python-dotenv>=1.2.1",
     "rich>=14.2.0",
 ]
 lint = [
-    "ruff>=0.14.8",
+    "ruff>=0.14.10",
 ]
 tests = [
     "pytest>=9.0.2",
@@ -98,6 +101,9 @@ line-ending = "lf"                  # Unix-style line endings
 docstring-code-format = true        # Format code examples inside docstrings
 skip-magic-trailing-comma = false   # Preserve trailing commas as formatting hints
 
+[project.scripts]
+get-perplexity-session-token = "perplexity_webui_scraper.cli.get_perplexity_session_token:get_token"
+
 [build-system]
 requires = ["uv_build"]
 build-backend = "uv_build"

{perplexity_webui_scraper-0.3.3 → perplexity_webui_scraper-0.3.4}/src/perplexity_webui_scraper/__init__.py

@@ -1,6 +1,6 @@
 """Extract AI responses from Perplexity's web interface."""
 
-from importlib.metadata import version
+from importlib import metadata
 
 from .config import ClientConfig, ConversationConfig
 from .core import Conversation, Perplexity
@@ -16,7 +16,7 @@ from .models import Model, Models
 from .types import Coordinates, Response, SearchResultItem
 
 
-__version__: str = version("perplexity-webui-scraper")
+__version__: str = metadata.version("perplexity-webui-scraper")
 __all__: list[str] = [
     "AuthenticationError",
     "CitationMode",

perplexity_webui_scraper-0.3.4/src/perplexity_webui_scraper/cli/get_perplexity_session_token.py

@@ -0,0 +1,216 @@
+"""CLI utility for secure Perplexity authentication and session extraction."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from sys import exit
+from typing import NoReturn
+
+from curl_cffi.requests import Session
+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.
+    """
+
+    path = Path(".env")
+    line_entry = f'{ENV_KEY}="{token}"'
+
+    try:
+        lines = path.read_text(encoding="utf-8").splitlines() if path.exists() else []
+        updated = False
+        new_lines = []
+
+        for line in lines:
+            if line.strip().startswith(ENV_KEY):
+                new_lines.append(line_entry)
+                updated = True
+            else:
+                new_lines.append(line)
+
+        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."""
+
+    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 = csrf_data.get("csrfToken")
+
+        if not csrf:
+            raise ValueError("Failed to obtain CSRF token.")
+
+    return session, csrf
+
+
+def _request_verification_code(session: Session, csrf: str, email: str) -> None:
+    """Send verification code to user's email."""
+
+    with console.status("[bold green]Sending verification code...", spinner="dots"):
+        r = session.post(
+            f"{BASE_URL}/api/auth/signin/email?version=2.18&source=default",
+            json={
+                "email": email,
+                "csrfToken": csrf,
+                "useNumericOtp": "true",
+                "json": "true",
+                "callbackUrl": f"{BASE_URL}/?login-source=floatingSignup",
+            },
+        )
+
+        if r.status_code != 200:
+            raise ValueError(f"Authentication request failed: {r.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."""
+
+    with console.status("[bold green]Validating...", spinner="dots"):
+        if user_input.startswith("http"):
+            return user_input
+
+        r_otp = session.post(
+            f"{BASE_URL}/api/auth/otp-redirect-link",
+            json={
+                "email": email,
+                "otp": user_input,
+                "redirectUrl": f"{BASE_URL}/?login-source=floatingSignup",
+                "emailLoginMethod": "web-otp",
+            },
+        )
+
+        if r_otp.status_code != 200:
+            raise ValueError("Invalid verification code.")
+
+        redirect_path = r_otp.json().get("redirect")
+
+        if not redirect_path:
+            raise ValueError("No redirect URL received.")
+
+        return f"{BASE_URL}{redirect_path}" if redirect_path.startswith("/") else redirect_path
+
+
+def _extract_session_token(session: Session, redirect_url: str) -> str:
+    """Extract session token from cookies after authentication."""
+
+    session.get(redirect_url)
+    token = session.cookies.get("__Secure-next-auth.session-token")
+
+    if not token:
+        raise ValueError("Authentication successful, but token not found.")
+
+    return token
+
+
+def _display_and_save_token(token: str) -> None:
+    """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")
+
+    prompt_text = f"Save token to [bold yellow].env[/bold yellow] file ({ENV_KEY})?"
+
+    if Confirm.ask(prompt_text, default=True, console=console):
+        if update_env(token):
+            console.print("[dim]Token saved to .env successfully.[/dim]")
+        else:
+            console.print("[red]Failed to save to .env file.[/red]")
+
+
+def _show_header() -> None:
+    """Display welcome header."""
+
+    console.print(
+        Panel(
+            "[bold white]Perplexity WebUI Scraper[/bold white]\n\n"
+            "Automatic session token generator via email authentication.\n"
+            "[dim]All session data will be cleared on exit.[/dim]",
+            title="🔐 Token Generator",
+            border_style="cyan",
+        )
+    )
+
+
+def _show_exit_message() -> None:
+    """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.")
+    console.input()
+
+
+def get_token() -> NoReturn:
+    """
+    Executes the authentication flow within an ephemeral terminal screen.
+
+    Handles CSRF, Email OTP/Link validation, and secure token display.
+    """
+
+    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)
+
+
+if __name__ == "__main__":
+    get_token()

{perplexity_webui_scraper-0.3.3 → perplexity_webui_scraper-0.3.4}/src/perplexity_webui_scraper/config.py

@@ -32,5 +32,5 @@ class ConversationConfig:
 class ClientConfig:
     """HTTP client settings."""
 
-    timeout: int = 1800
+    timeout: int = 3600
     impersonate: str = "chrome"

{perplexity_webui_scraper-0.3.3 → perplexity_webui_scraper-0.3.4}/src/perplexity_webui_scraper/constants.py

@@ -1,8 +1,4 @@
-"""Fixed constants and values for the Perplexity API.
-
-These are internal API values that should not be modified by users.
-They represent fixed parameters required by the Perplexity WebUI API.
-"""
+"""Constants and values for the Perplexity internal API and HTTP interactions."""
 
 from __future__ import annotations
 
@@ -10,21 +6,14 @@ from re import Pattern, compile
 from typing import Final
 
 
-# =============================================================================
 # API Configuration
-# =============================================================================
-
 API_VERSION: Final[str] = "2.18"
 """Current API version used by Perplexity WebUI."""
 
 API_BASE_URL: Final[str] = "https://www.perplexity.ai"
 """Base URL for all API requests."""
 
-
-# =============================================================================
 # API Endpoints
-# =============================================================================
-
 ENDPOINT_ASK: Final[str] = "/rest/sse/perplexity_ask"
 """SSE endpoint for sending prompts."""
 
@@ -34,54 +23,39 @@ ENDPOINT_SEARCH_INIT: Final[str] = "/search/new"
 ENDPOINT_UPLOAD: Final[str] = "/rest/uploads/batch_create_upload_urls"
 """Endpoint for file upload URL generation."""
 
-
-# =============================================================================
 # API Fixed Parameters
-# =============================================================================
-
 SEND_BACK_TEXT: Final[bool] = True
-"""Whether to receive full text in each streaming chunk.
+"""
+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).
-
-Currently must be True for the parser to work correctly.
 """
 
 USE_SCHEMATIZED_API: Final[bool] = False
-"""Whether to use the schematized API format.
-
-Currently must be False - schematized format is not supported.
-"""
+"""Whether to use the schematized API format."""
 
 PROMPT_SOURCE: Final[str] = "user"
 """Source identifier for prompts."""
 
-
-# =============================================================================
-# Regex Patterns (Pre-compiled for performance)
-# =============================================================================
-
+# 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.
+"""
+Regex pattern for matching citation markers like [1], [2], etc.
 
 Uses word boundary to avoid matching things like [123].
-Pre-compiled for performance in streaming scenarios.
 """
 
 JSON_OBJECT_PATTERN: Final[Pattern[str]] = compile(r"^\{.*\}$")
 """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.
+"""
+Default HTTP headers for API requests.
 
 Referer and Origin are added dynamically based on BASE_URL.
 """

{perplexity_webui_scraper-0.3.3 → perplexity_webui_scraper-0.3.4}/src/perplexity_webui_scraper/core.py

@@ -8,7 +8,7 @@ from pathlib import Path
 from typing import TYPE_CHECKING, Any
 from uuid import uuid4
 
-from orjson import loads
+from orjson import JSONDecodeError, loads
 
 
 if TYPE_CHECKING:
@@ -57,10 +57,12 @@ class Perplexity:
 
     def create_conversation(self, config: ConversationConfig | None = None) -> Conversation:
         """Create a new conversation."""
+
         return Conversation(self._http, config or ConversationConfig())
 
     def close(self) -> None:
         """Close the client."""
+
         self._http.close()
 
     def __enter__(self) -> Perplexity:
@@ -103,55 +105,64 @@ class Conversation:
     @property
     def answer(self) -> str | None:
         """Last response text."""
+
         return self._answer
 
     @property
     def title(self) -> str | None:
         """Conversation title."""
+
         return self._title
 
     @property
     def search_results(self) -> list[SearchResultItem]:
         """Search results from last response."""
+
         return self._search_results
 
     @property
     def uuid(self) -> str | None:
         """Conversation UUID."""
+
         return self._backend_uuid
 
     def __iter__(self) -> Generator[Response, None, None]:
         if self._stream_generator is not None:
             yield from self._stream_generator
+
             self._stream_generator = None
 
     def ask(
         self,
         query: str,
         model: Model | None = None,
-        files: list[str | PathLike[str]] | None = None,
+        files: list[str | PathLike] | None = None,
         citation_mode: CitationMode | None = None,
         stream: bool = False,
     ) -> Conversation:
         """Ask a question. Returns self for method chaining or streaming iteration."""
+
         effective_model = model or self._config.model or Models.BEST
         effective_citation = citation_mode if citation_mode is not None else self._config.citation_mode
         self._citation_mode = effective_citation
         self._execute(query, effective_model, files, stream=stream)
+
         return self
 
     def _execute(
         self,
         query: str,
         model: Model,
-        files: list[str | PathLike[str]] | None,
+        files: list[str | PathLike] | None,
         stream: bool = False,
     ) -> None:
         """Execute a query."""
+
         self._reset_response_state()
 
         # Upload files
         file_urls: list[str] = []
+
         if files:
             validated = self._validate_files(files)
             file_urls = [self._upload_file(f) for f in validated]
@@ -172,15 +183,17 @@ class Conversation:
         self._raw_data = {}
         self._stream_generator = None
 
-    def _validate_files(self, files: list[str | PathLike[str]] | None) -> list[_FileInfo]:
+    def _validate_files(self, files: list[str | PathLike] | None) -> list[_FileInfo]:
         if not files:
             return []
 
         seen: set[str] = set()
         file_list: list[Path] = []
+
         for item in files:
             if item and isinstance(item, (str, PathLike)):
                 path = Path(item).resolve()
+
                 if path.as_posix() not in seen:
                     seen.add(path.as_posix())
                     file_list.append(path)
@@ -203,11 +216,13 @@ class Conversation:
                     raise FileValidationError(file_path, "Path is not a file")
 
                 file_size = path.stat().st_size
+
                 if file_size > MAX_FILE_SIZE:
                     raise FileValidationError(
                         file_path,
                         f"File exceeds 50MB limit: {file_size / (1024 * 1024):.1f}MB",
                     )
+
                 if file_size == 0:
                     raise FileValidationError(file_path, "File is empty")
 
@@ -224,10 +239,10 @@ class Conversation:
                 )
             except FileValidationError:
                 raise
-            except (FileNotFoundError, PermissionError) as e:
-                raise FileValidationError(file_path, f"Cannot access file: {e}") from e
-            except OSError as e:
-                raise FileValidationError(file_path, f"File system error: {e}") from e
+            except (FileNotFoundError, PermissionError) as error:
+                raise FileValidationError(file_path, f"Cannot access file: {error}") from error
+            except OSError as error:
+                raise FileValidationError(file_path, f"File system error: {error}") from error
 
         return result
 
@@ -255,8 +270,8 @@ class Conversation:
                 raise FileUploadError(file_info.path, "No upload URL returned")
 
             return upload_url
-        except FileUploadError:
-            raise
+        except FileUploadError as error:
+            raise error
         except Exception as e:
             raise FileUploadError(file_info.path, str(e)) from e
 
@@ -301,6 +316,7 @@ class Conversation:
         if self._backend_uuid is not None:
             params["last_backend_uuid"] = self._backend_uuid
             params["query_source"] = "followup"
+
             if self._read_write_token:
                 params["read_write_token"] = self._read_write_token
 
@@ -312,6 +328,7 @@ class Conversation:
 
         def replacer(m: Match[str]) -> str:
             num = m.group(1)
+
             if not num.isdigit():
                 return m.group(0)
 
@@ -319,8 +336,10 @@ class Conversation:
                 return ""
 
             idx = int(num) - 1
+
             if 0 <= idx < len(self._search_results):
                 url = self._search_results[idx].url or ""
+
                 if self._citation_mode == CitationMode.MARKDOWN and url:
                     return f"[{num}]({url})"
 
@@ -330,8 +349,10 @@ class Conversation:
 
     def _parse_line(self, line: str | bytes) -> dict[str, Any] | None:
         prefix = b"data: " if isinstance(line, bytes) else "data: "
+
         if (isinstance(line, bytes) and line.startswith(prefix)) or (isinstance(line, str) and line.startswith(prefix)):
             return loads(line[6:])
+
         return None
 
     def _process_data(self, data: dict[str, Any]) -> None:
@@ -341,10 +362,25 @@ class Conversation:
         if self._read_write_token is None and "read_write_token" in data:
             self._read_write_token = data["read_write_token"]
 
-        if "text" not in data:
-            return
+        if "blocks" in data:
+            for block in data["blocks"]:
+                if block.get("intended_usage") == "web_results":
+                    diff = block.get("diff_block", {})
+
+                    for patch in diff.get("patches", []):
+                        if patch.get("op") == "replace" and patch.get("path") == "/web_results":
+                            pass
+
+        if "text" not in data and "blocks" not in data:
+            return None
+
+        try:
+            json_data = loads(data["text"])
+        except KeyError as e:
+            raise ValueError("Missing 'text' field in data") from e
+        except JSONDecodeError as e:
+            raise ValueError("Invalid JSON in 'text' field") from e
 
-        json_data = loads(data["text"])
         answer_data: dict[str, Any] = {}
 
         if isinstance(json_data, list):
@@ -359,14 +395,18 @@ class Conversation:
                         answer_data = raw_content
 
                     self._update_state(data.get("thread_title"), answer_data)
+
                     break
         elif isinstance(json_data, dict):
             self._update_state(data.get("thread_title"), json_data)
+        else:
+            raise ValueError("Unexpected JSON structure in 'text' field")
 
     def _update_state(self, title: str | None, answer_data: dict[str, Any]) -> None:
         self._title = title
 
         web_results = answer_data.get("web_results", [])
+
         if web_results:
             self._search_results = [
                 SearchResultItem(
@@ -379,10 +419,12 @@ class Conversation:
             ]
 
         answer_text = answer_data.get("answer")
+
         if answer_text is not None:
             self._answer = self._format_citations(answer_text)
 
         chunks = answer_data.get("chunks", [])
+
         if chunks:
             self._chunks = chunks
 
@@ -402,16 +444,21 @@ class Conversation:
     def _complete(self, payload: dict[str, Any]) -> None:
         for line in self._http.stream_ask(payload):
             data = self._parse_line(line)
+
             if data:
                 self._process_data(data)
+
                 if data.get("final"):
                     break
 
     def _stream(self, payload: dict[str, Any]) -> Generator[Response, None, None]:
         for line in self._http.stream_ask(payload):
             data = self._parse_line(line)
+
             if data:
                 self._process_data(data)
+
                 yield self._build_response()
+
                 if data.get("final"):
                     break

{perplexity_webui_scraper-0.3.3 → perplexity_webui_scraper-0.3.4}/src/perplexity_webui_scraper/http.py

@@ -46,6 +46,7 @@ class HTTPClient:
             "Origin": API_BASE_URL,
         }
         cookies: dict[str, str] = {SESSION_COOKIE_NAME: session_token}
+
         self._session: Session = Session(
             headers=headers,
             cookies=cookies,
@@ -101,6 +102,7 @@ class HTTPClient:
         try:
             response = self._session.get(url, params=params)
             response.raise_for_status()
+
             return response
         except Exception as e:
             self._handle_error(e, f"GET {endpoint}: ")
@@ -132,6 +134,7 @@ class HTTPClient:
         try:
             response = self._session.post(url, json=json, stream=stream)
             response.raise_for_status()
+
             return response
         except Exception as e:
             self._handle_error(e, f"POST {endpoint}: ")

{perplexity_webui_scraper-0.3.3 → perplexity_webui_scraper-0.3.4}/src/perplexity_webui_scraper/limits.py

@@ -10,11 +10,8 @@ MAX_FILES: Final[int] = 30
 """Maximum number of files that can be attached to a single prompt."""
 
 MAX_FILE_SIZE: Final[int] = 50 * 1024 * 1024  # 50 MB in bytes
-"""Maximum file size in bytes (50 MB)."""
+"""Maximum file size in bytes."""
 
 # Request Limits
 DEFAULT_TIMEOUT: Final[int] = 30 * 60  # 30 minutes in seconds
-"""Default request timeout in seconds (30 minutes).
-
-Set high to accommodate complex models that may take longer to respond.
-"""
+"""Default request timeout in seconds"""

perplexity_webui_scraper-0.3.4/src/perplexity_webui_scraper/models.py

@@ -0,0 +1,73 @@
+"""AI model definitions for Perplexity WebUI Scraper."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True, slots=True)
+class Model:
+    """AI model configuration.
+
+    Attributes:
+        identifier: Model identifier used by the API.
+        mode: Model execution mode. Default: "copilot".
+    """
+
+    identifier: str
+    mode: str = "copilot"
+
+
+class Models:
+    """Available AI models with their configurations.
+
+    All models use the "copilot" mode which enables web search.
+    """
+
+    RESEARCH = Model(identifier="pplx_alpha")
+    """Research - Fast and thorough for routine research"""
+
+    LABS = Model(identifier="pplx_beta")
+    """Labs - Multi-step tasks with advanced troubleshooting"""
+
+    BEST = Model(identifier="pplx_pro_upgraded")
+    """Best - Automatically selects the most responsive model based on the query"""
+
+    SONAR = Model(identifier="experimental")
+    """Sonar - Perplexity's fast model"""
+
+    GPT_52 = Model(identifier="gpt52")
+    """GPT-5.2 - OpenAI's latest model"""
+
+    GPT_52_THINKING = Model(identifier="gpt52_thinking")
+    """GPT-5.2 Thinking - OpenAI's latest model with thinking"""
+
+    CLAUDE_45_OPUS = Model(identifier="claude45opus")
+    """Claude Opus 4.5 - Anthropic's Opus reasoning model"""
+
+    CLAUDE_45_OPUS_THINKING = Model(identifier="claude45opusthinking")
+    """Claude Opus 4.5 Thinking - Anthropic's Opus reasoning model with thinking"""
+
+    GEMINI_3_PRO = Model(identifier="gemini30pro")
+    """Gemini 3 Pro - Google's newest reasoning model"""
+
+    GEMINI_3_FLASH = Model(identifier="gemini30flash")
+    """Gemini 3 Flash - Google's fast reasoning model"""
+
+    GEMINI_3_FLASH_THINKING = Model(identifier="gemini30flash_high")
+    """Gemini 3 Flash Thinking - Google's fast reasoning model with enhanced thinking"""
+
+    GROK_41 = Model(identifier="grok41nonreasoning")
+    """Grok 4.1 - xAI's latest advanced model"""
+
+    GROK_41_THINKING = Model(identifier="grok41reasoning")
+    """Grok 4.1 Thinking - xAI's latest reasoning model"""
+
+    KIMI_K2_THINKING = Model(identifier="kimik2thinking")
+    """Kimi K2 Thinking - Moonshot AI's latest reasoning model"""
+
+    CLAUDE_45_SONNET = Model(identifier="claude45sonnet")
+    """Claude Sonnet 4.5 - Anthropic's newest advanced model"""
+
+    CLAUDE_45_SONNET_THINKING = Model(identifier="claude45sonnetthinking")
+    """Claude Sonnet 4.5 Thinking - Anthropic's newest reasoning model"""

perplexity_webui_scraper-0.3.3/README.md

@@ -1,134 +0,0 @@
-<div align="center">
-
-# Perplexity WebUI Scraper
-
-Python scraper to extract AI responses from [Perplexity's](https://www.perplexity.ai) web interface.
-
-[![PyPI](https://img.shields.io/pypi/v/perplexity-webui-scraper?color=blue)](https://pypi.org/project/perplexity-webui-scraper)
-[![Python](https://img.shields.io/pypi/pyversions/perplexity-webui-scraper)](https://pypi.org/project/perplexity-webui-scraper)
-[![License](https://img.shields.io/github/license/henrique-coder/perplexity-webui-scraper?color=green)](./LICENSE)
-
-</div>
-
----
-
-## Installation
-
-```bash
-uv pip install perplexity-webui-scraper
-```
-
-## Requirements
-
-- **Perplexity Pro subscription**
-- **Session token** (`__Secure-next-auth.session-token` cookie from browser)
-
-### Getting Your Session Token
-
-1. Log in at [perplexity.ai](https://www.perplexity.ai)
-2. Open DevTools (`F12`) → Application → Cookies
-3. Copy `__Secure-next-auth.session-token` value
-4. Store in `.env`: `PERPLEXITY_SESSION_TOKEN=your_token`
-
-## Quick Start
-
-```python
-from perplexity_webui_scraper import Perplexity
-
-client = Perplexity(session_token="YOUR_TOKEN")
-conversation = client.create_conversation()
-
-conversation.ask("What is quantum computing?")
-print(conversation.answer)
-
-# Follow-up
-conversation.ask("Explain it simpler")
-print(conversation.answer)
-```
-
-### Streaming
-
-```python
-for chunk in conversation.ask("Explain AI", stream=True):
-    print(chunk.answer)
-```
-
-### With Options
-
-```python
-from perplexity_webui_scraper import (
-    ConversationConfig,
-    Coordinates,
-    Models,
-    SourceFocus,
-)
-
-config = ConversationConfig(
-    model=Models.RESEARCH,
-    source_focus=[SourceFocus.WEB, SourceFocus.ACADEMIC],
-    language="en-US",
-    coordinates=Coordinates(latitude=40.7128, longitude=-74.0060),
-)
-
-conversation = client.create_conversation(config)
-conversation.ask("Latest AI research", files=["paper.pdf"])
-```
-
-## API
-
-### `Perplexity(session_token, config?)`
-
-| Parameter       | Type           | Description        |
-| --------------- | -------------- | ------------------ |
-| `session_token` | `str`          | Browser cookie     |
-| `config`        | `ClientConfig` | Timeout, TLS, etc. |
-
-### `Conversation.ask(query, model?, files?, citation_mode?, stream?)`
-
-| Parameter       | Type           | Default       | Description         |
-| --------------- | -------------- | ------------- | ------------------- |
-| `query`         | `str`          | —             | Question (required) |
-| `model`         | `Model`        | `Models.BEST` | AI model            |
-| `files`         | `list[str]`    | `None`        | File paths          |
-| `citation_mode` | `CitationMode` | `CLEAN`       | Citation format     |
-| `stream`        | `bool`         | `False`       | Enable streaming    |
-
-### Models
-
-| Model                          | Description       |
-| ------------------------------ | ----------------- |
-| `Models.BEST`                  | Auto-select best  |
-| `Models.RESEARCH`              | Deep research     |
-| `Models.SONAR`                 | Fast queries      |
-| `Models.GPT_51`                | OpenAI GPT-5.1    |
-| `Models.CLAUDE_45_SONNET`      | Claude 4.5 Sonnet |
-| `Models.GEMINI_3_PRO_THINKING` | Gemini 3.0 Pro    |
-| `Models.GROK_41`               | xAI Grok 4.1      |
-
-### CitationMode
-
-| Mode       | Output                |
-| ---------- | --------------------- |
-| `DEFAULT`  | `text[1]`             |
-| `MARKDOWN` | `text[1](url)`        |
-| `CLEAN`    | `text` (no citations) |
-
-### ConversationConfig
-
-| Parameter         | Default       | Description        |
-| ----------------- | ------------- | ------------------ |
-| `model`           | `Models.BEST` | Default model      |
-| `citation_mode`   | `CLEAN`       | Citation format    |
-| `save_to_library` | `False`       | Save to library    |
-| `search_focus`    | `WEB`         | Search type        |
-| `source_focus`    | `WEB`         | Source types       |
-| `time_range`      | `ALL`         | Time filter        |
-| `language`        | `"en-US"`     | Response language  |
-| `timezone`        | `None`        | Timezone           |
-| `coordinates`     | `None`        | Location (lat/lng) |
-
-## Disclaimer
-
-This is an **unofficial** library. It uses internal APIs that may change without notice. Use at your own risk. Not for production use.
-
-By using this library, you agree to Perplexity AI's Terms of Service.

perplexity_webui_scraper-0.3.3/src/perplexity_webui_scraper/models.py

@@ -1,58 +0,0 @@
-"""AI model definitions for Perplexity WebUI Scraper."""
-
-from __future__ import annotations
-
-from dataclasses import dataclass
-
-
-@dataclass(frozen=True, slots=True)
-class Model:
-    """AI model configuration.
-
-    Attributes:
-        identifier: Model identifier used by the API.
-        mode: Model execution mode. Default: "copilot".
-    """
-
-    identifier: str
-    mode: str = "copilot"
-
-
-class Models:
-    """Available AI models with their configurations.
-
-    All models use the "copilot" mode which enables web search.
-    """
-
-    LABS = Model(identifier="pplx_beta")
-    """Create projects from scratch (turn your ideas into completed docs, slides, dashboards, and more)."""
-
-    RESEARCH = Model(identifier="pplx_alpha")
-    """Deep research on any topic (in-depth reports with more sources, charts, and advanced reasoning)."""
-
-    BEST = Model(identifier="pplx_pro")
-    """Automatically selects the best model based on the query. Recommended for most use cases."""
-
-    SONAR = Model(identifier="experimental")
-    """Perplexity's fast model. Good for quick queries."""
-
-    GPT_51 = Model(identifier="gpt51")
-    """OpenAI's latest model (GPT-5.1)."""
-
-    GPT_51_THINKING = Model(identifier="gpt51_thinking")
-    """OpenAI's latest model with extended reasoning capabilities."""
-
-    CLAUDE_45_SONNET = Model(identifier="claude45sonnet")
-    """Anthropic's Claude 4.5 Sonnet model."""
-
-    CLAUDE_45_SONNET_THINKING = Model(identifier="claude45sonnetthinking")
-    """Anthropic's Claude 4.5 Sonnet with extended reasoning capabilities."""
-
-    GEMINI_3_PRO_THINKING = Model(identifier="gemini30pro")
-    """Google's Gemini 3.0 Pro with reasoning capabilities."""
-
-    GROK_41 = Model(identifier="grok41nonreasoning")
-    """xAI's Grok 4.1 model."""
-
-    KIMI_K2_THINKING = Model(identifier="kimik2thinking")
-    """Moonshot AI's Kimi K2 reasoning model (hosted in the US)."""