audioarxiv 0.1.0rc46.post1__py3-none-any.whl

audioarxiv/__init__.py

@@ -0,0 +1,169 @@
+"""
+audioarxiv
+==========
+
+audioarxiv is a Python package designed to make staying up to date with the latest research more accessible and
+convenient.
+It allows you to fetch research papers directly from `arXiv <https://arxiv.org>`_ and converts them into speech,
+so you can listen to them on the go—whether you're commuting, working out, or simply prefer auditory learning.
+With support for customizable text-to-speech settings and a streamlined interface, audioarxiv offers researchers,
+students, and enthusiasts a hands-free way to engage with scientific literature.
+
+**Please note**: the package is still in its early stages of development,
+and some features may be limited or not fully mature yet.
+"""
+from __future__ import annotations
+
+import json
+import logging
+import subprocess
+import sys
+from pathlib import Path
+
+from pandas import DataFrame
+
+from . import audio, preprocess, resources
+
+__version__ = "0.1.0-rc46-post1"
+
+
+def get_version_information() -> str:
+    """Version information.
+
+    Returns:
+        str: Version information.
+    """
+    return __version__
+
+
+def setup_logger(logger_: logging.Logger, outdir='.', label=None, log_level='INFO', print_version=False):
+    """ Setup logging output: call at the start of the script to use
+
+    Args:
+        logger_ (logging.Logger): The logger instance to be configured.
+        outdir (str): If supplied, write the logging output to outdir/label.log
+        label (str): If supplied, write the logging output to outdir/label.log
+        log_level (str, optional): ['debug', 'info', 'warning']
+        Either a string from the list above, or an integer as specified
+        in https://docs.python.org/2/library/logging.html#logging-levels
+        print_version (bool): If true, print version information
+    """
+    if isinstance(log_level, str):
+        try:
+            level = getattr(logging, log_level.upper())
+        except AttributeError as exc:
+            raise ValueError(f'log_level {log_level} not understood') from exc
+    else:
+        level = int(log_level)
+
+    logger_.propagate = False
+    logger_.setLevel(level)
+
+    if not any(isinstance(h, logging.StreamHandler) for h in logger_.handlers):
+        stream_handler = logging.StreamHandler()
+        stream_handler.setFormatter(logging.Formatter(
+            '%(asctime)s %(name)s %(levelname)-8s: %(message)s', datefmt='%H:%M'))
+        stream_handler.setLevel(level)
+        logger_.addHandler(stream_handler)
+
+    if not any(isinstance(h, logging.FileHandler) for h in logger_.handlers):
+        if label:
+            Path(outdir).mkdir(parents=True, exist_ok=True)
+            log_file = f'{outdir}/{label}.log'
+            file_handler = logging.FileHandler(log_file)
+            file_handler.setFormatter(logging.Formatter(
+                '%(asctime)s %(levelname)-8s: %(message)s', datefmt='%H:%M'))
+
+            file_handler.setLevel(level)
+            logger_.addHandler(file_handler)
+
+    for handler in logger_.handlers:
+        handler.setLevel(level)
+
+    if print_version:
+        version = get_version_information()
+        logger_.info('Running audioarxiv version: %s', version)
+
+
+def loaded_modules_dict() -> dict:
+    """Get the modules and the versions.
+
+    Returns:
+        dict: A dictionary of the modules and the versions.
+    """
+    module_names = list(sys.modules.keys())
+    vdict = {}
+    for key in module_names:
+        if "." not in str(key):
+            vdict[key] = str(getattr(sys.modules[key], "__version__", "N/A"))
+    return vdict
+
+
+def env_package_list(as_dataframe: bool = False) -> list | DataFrame:
+    """Get the list of packages installed in the system prefix.
+
+    If it is detected that the system prefix is part of a Conda environment,
+    a call to ``conda list --prefix {sys.prefix}`` will be made, otherwise
+    the call will be to ``{sys.executable} -m pip list installed``.
+
+    Args:
+        as_dataframe (bool): return output as a `pandas.DataFrame`
+
+    Returns:
+    Union[list, DataFrame]:
+    If ``as_dataframe=False`` is given, the output is a `list` of `dict`,
+    one for each package, at least with ``'name'`` and ``'version'`` keys
+    (more if `conda` is used).
+    If ``as_dataframe=True`` is given, the output is a `DataFrame`
+    created from the `list` of `dicts`.
+    """
+    prefix = sys.prefix
+    pkgs = []
+    # if a conda-meta directory exists, this is a conda environment, so
+    # use conda to print the package list
+    conda_detected = (Path(prefix) / "conda-meta").is_dir()
+    if conda_detected:
+        try:
+            pkgs = json.loads(subprocess.check_output([
+                "conda",
+                "list",
+                "--prefix", prefix,
+                "--json"
+            ]))
+        except (FileNotFoundError, subprocess.CalledProcessError):
+            # When a conda env is in use but conda is unavailable
+            conda_detected = False
+
+    # otherwise try and use Pip
+    if not conda_detected:
+        try:
+            import pip  # noqa: F401 # pylint: disable=unused-import, import-outside-toplevel
+        except ModuleNotFoundError:  # no pip?
+            # not a conda environment, and no pip, so just return
+            # the list of loaded modules
+            modules = loaded_modules_dict()
+            pkgs = [{"name": x, "version": y} for x, y in modules.items()]
+        else:
+            pkgs = json.loads(subprocess.check_output([
+                sys.executable,
+                "-m", "pip",
+                "list", "installed",
+                "--format", "json",
+            ]))
+
+    # convert to recarray for storage
+    if as_dataframe:
+        return DataFrame(pkgs)
+    return pkgs
+
+
+logger = logging.getLogger('audioarxiv')
+setup_logger(logger)
+
+__all__ = [
+    'audio',
+    'preprocess',
+    'resources',
+    'logger',
+    '__version__'
+]

audioarxiv/audio/__init__.py

@@ -0,0 +1,12 @@
+"""
+Handles text-to-speech conversion using various engines to read research papers aloud.
+"""
+from __future__ import annotations
+
+from . import base
+from .base import Audio
+
+__all__ = [
+    'base',
+    'Audio',
+]

audioarxiv/audio/base.py

@@ -0,0 +1,172 @@
+"""
+A base class for audio.
+"""
+from __future__ import annotations
+
+import logging
+import time
+
+import pyttsx3
+
+from ..preprocess import get_sentences
+
+logger = logging.getLogger('audioarxiv')
+
+
+def validate_audio_arguments(rate: float, volume: float, voice: int | str | None, pause_seconds: float) -> dict:
+    """Validate the arguments for Audio.
+
+    Args:
+        rate (float): Number of words per minute.
+        volume (float): Volume.
+        voice (int | str | None): If it is int, it is interpreted as the index of the available voices.
+            If it is str, it is interpreted as the ID of the voice.
+            The available voice ids can be found with `list_voices()`.
+        pause_seconds (float): Duration of pause between sentences.
+
+    Returns:
+        dict: rate, volume, voice, pause_seconds
+    """
+    engine = pyttsx3.init()
+    available_voices = engine.getProperty('voices')
+    rate = max(50, min(500, rate))
+    volume = max(0.0, min(1.0, volume))
+    if isinstance(voice, int):
+        if 0 <= voice < len(available_voices):
+            voice = available_voices[voice].id
+        else:
+            voice = None
+            logger.error('Invalid voice index = %s. Keeping current voice.', voice)
+    elif isinstance(voice, str):
+        if voice not in [v.id for v in available_voices]:
+            voice = None
+            logger.error('Invalid voice ID = %s. Keeping current voice.', voice)
+    elif voice is not None:
+        logger.error('Unsupported datatype of voice = %s. It must be either int or str.', type(voice))
+    if pause_seconds < 0:
+        pause_seconds = 0.1
+        logger.error('pause = %s must be non-negative. Keeping the current pause.', pause_seconds)
+    return {'rate': rate,
+            'volume': volume,
+            'voice': voice,
+            'pause_seconds': pause_seconds}
+
+
+class Audio:
+    """A class to generate audio from text.
+    """
+    def __init__(self, rate: float = 140,  # noqa: R0913,E1120,E501 # pylint: disable=too-many-arguments,too-many-positional-arguments,C0301
+                 volume: float = 0.9,
+                 voice: str | None = None,
+                 pause_seconds: float = 0.1,
+                 validate_arguments: bool = True):
+        """A class to configure the audio.
+
+        Args:
+            rate (float, optional): Number of words per minute. Defaults to 140.
+            volume (float, optional): Volume. Defaults to 0.9.
+            voice (Optional[str], optional): Voice id.
+                The available voice ids can be found with `list_voices()`.
+                Defaults to None.
+            pause_seconds (float, optional): Duration of pause between sentences. Defaults to 0.1.
+            validate_arguments (bool): If True, validate the arguments.
+        """
+        if validate_arguments:
+            arguments = validate_audio_arguments(rate=rate,
+                                                 volume=volume,
+                                                 voice=voice,
+                                                 pause_seconds=pause_seconds)
+            rate = arguments['rate']
+            volume = arguments['volume']
+            voice = arguments['voice']
+            pause_seconds = arguments['pause_seconds']
+        self.engine = pyttsx3.init()
+        if rate is not None:
+            self.engine.setProperty('rate', rate)
+        if volume is not None:
+            self.engine.setProperty('volume', volume)
+        if voice is not None:
+            self.engine.setProperty('voice', voice)
+        self.pause_seconds = pause_seconds
+
+    @property
+    def available_voices(self) -> list:
+        """Get the available voices.
+
+        Returns:
+            list: The available voices.
+        """
+        return self.engine.getProperty('voices')
+
+    @property
+    def pause_seconds(self) -> float:
+        """The duration of pause between sentences.
+
+        Returns:
+            float: Duration of pause between sentences in second.
+        """
+        return self._pause_seconds
+
+    @pause_seconds.setter
+    def pause_seconds(self, value: float):
+        """Set the duration of pause between sentences.
+
+        Args:
+            value (float): Duration of pause between sentences.
+        """
+        if value < 0:
+            logger.error('pause = %s must be non-negative. Keeping the current pause.', value)
+            return
+        self._pause_seconds = value
+
+    def list_voices(self):
+        """Print available voices with their index and details."""
+        for i, voice in enumerate(self.available_voices):
+            logger.info("Index %s: %s (ID: %s)", i, voice.name, voice.id)
+
+    def clean_text(self, text: str) -> str:
+        """Clean the text for smoother reading.
+
+        '\\n' is replaced with a white space.
+
+        Args:
+            text (str): Text.
+
+        Returns:
+            str: Cleaned text.
+        """
+        return " ".join(text.split()).replace('\n', ' ').strip()
+
+    def read_article(self,
+                     article: str):
+        """Read the article aloud, splitting it into sentences.
+
+        Args:
+            article (str): Article.
+        """
+        if not isinstance(article, str):
+            logger.warning('article = %s is not str. Skipping.', article)
+            return
+        cleaned_text = self.clean_text(article)
+        sentences = get_sentences(cleaned_text)
+        for sentence in sentences:
+            self.engine.say(sentence)
+            self.engine.runAndWait()
+            time.sleep(self.pause_seconds)
+
+    def save_article(self,
+                     filename: str,
+                     article: str):
+        """Save the article to an audio file.
+
+        Args:
+            filename (str): File name.
+            article (str): Article.
+        """
+        cleaned_text = self.clean_text(article)
+        self.engine.save_to_file(cleaned_text, filename)
+        self.engine.runAndWait()
+
+    def stop(self):
+        """Stop the current speech."""
+        self.engine.stop()

audioarxiv/preprocess/__init__.py

@@ -0,0 +1,13 @@
+"""
+Processes and cleans the extracted text from papers,
+including sentence segmentation, symbol handling, and formatting for better audio output.
+"""
+from __future__ import annotations
+
+from .article import get_sentences
+from .math_equation import process_math_equations
+
+__all__ = [
+    'get_sentences',
+    'process_math_equations',
+]

audioarxiv/preprocess/article.py

@@ -0,0 +1,22 @@
+"""
+Functions to preprocess articles.
+"""
+from __future__ import annotations
+
+import nltk
+from nltk.tokenize import sent_tokenize
+
+# Download tokenizer if needed
+nltk.download('punkt_tab')
+
+
+def get_sentences(text: str) -> list:
+    """Get the sentences from the text.
+
+    Args:
+        text (str): Text.
+
+    Returns:
+        list: A list of sentences.
+    """
+    return sent_tokenize(text)

audioarxiv/preprocess/math_equation.py

@@ -0,0 +1,36 @@
+"""
+Functions to preprocess math equations.
+"""
+from __future__ import annotations
+
+import re
+
+from sympy import srepr
+from sympy.parsing.sympy_parser import parse_expr
+
+
+def process_math_equations(text: str) -> str:
+    """Detects LaTeX-style math symbols and converts them to a readable format.
+
+    Args:
+        text (str): Text.
+
+    Returns:
+        str: Text with the processed math equations.
+    """
+
+    def replace_math(match: re.Match) -> str:
+        raw_expr = match.group(1)
+        try:
+            parsed = parse_expr(raw_expr)
+            return f"Math: {srepr(parsed)}"
+        except Exception:
+            return f"Equation: {raw_expr}"
+
+    # First replace block math ($$...$$)
+    text = re.sub(r"\$\$(.+?)\$\$", replace_math, text)
+
+    # Then replace inline math, match $...$ only if it's surrounded by non-digit characters (to avoid $5)
+    text = re.sub(r"(?<!\w)\$(.+?)\$(?!\w)", replace_math, text)
+
+    return text

audioarxiv/resources/__init__.py

@@ -0,0 +1,10 @@
+"""
+Fetches research papers and metadata from arXiv using the arXiv API.
+"""
+from __future__ import annotations
+
+from .paper import Paper
+
+__all__ = [
+    'Paper',
+]

audioarxiv/resources/paper.py

@@ -0,0 +1,204 @@
+"""
+A class to fetch papers from arXiv.
+"""
+from __future__ import annotations
+
+import logging
+import re
+import tempfile
+from datetime import datetime
+
+import arxiv
+import fitz
+
+logger = logging.getLogger('audioarxiv')
+
+
+def validate_paper_arguments(page_size: int,
+                             delay_seconds: float,
+                             num_retries: int) -> dict:
+    """Validate the arguments for Paper.
+
+    Args:
+        page_size (int, optional): Maximum number of results fetched in a single API request. Smaller pages can
+            be retrieved faster, but may require more round-trips. The API's limit is 2000 results per page.
+            Defaults to 100.
+        delay_seconds (float, optional): Number of seconds to wait between API requests.
+            `arXiv's Terms of Use <https://arxiv.org/help/api/tou>`_ ask that you "make no
+            more than one request every three seconds."
+            Defaults to 3.0.
+        num_retries (int, optional): Number of times to retry a failing API request before raising an Exception.
+            Defaults to 3.
+
+    Returns:
+        dict: paper_size, delay_seconds, num_retries
+    """
+    return {'page_size': page_size,
+            'delay_seconds': delay_seconds,
+            'num_retries': num_retries}
+
+
+class Paper:
+    """A class to fetch papers from arXiv.
+    """
+    def __init__(self, page_size: int = 100, delay_seconds: float = 3.0, num_retries: int = 3,
+                 validate_arguments: bool = True):
+        """An arXiv paper.
+
+        Args:
+            page_size (int, optional): Maximum number of results fetched in a single API request. Smaller pages can
+                be retrieved faster, but may require more round-trips. The API's limit is 2000 results per page.
+                Defaults to 100.
+            delay_seconds (float, optional): Number of seconds to wait between API requests.
+                `arXiv's Terms of Use <https://arxiv.org/help/api/tou>`_ ask that you "make no
+                more than one request every three seconds."
+                Defaults to 3.0.
+            num_retries (int, optional): Number of times to retry a failing API request before raising an Exception.
+                Defaults to 3.
+            validate_arguments (bool, optional): If True, validate the arguments. Defaults to True.
+        """
+        if validate_arguments:
+            arguments = validate_paper_arguments(page_size=page_size,
+                                                 delay_seconds=delay_seconds,
+                                                 num_retries=num_retries)
+            page_size = arguments['page_size']
+            delay_seconds = arguments['delay_seconds']
+            num_retries = arguments['num_retries']
+        self._client = arxiv.Client(page_size=page_size,
+                                    delay_seconds=delay_seconds,
+                                    num_retries=num_retries)
+        self._sections = []
+        self.paper = None
+
+    @property
+    def client(self) -> arxiv.Client:
+        """Get the arxiv client.
+
+        Returns:
+            arxiv.Client: arxiv client.
+        """
+        return self._client
+
+    @property
+    def title(self) -> str | None:
+        """Title of the paper.
+
+        Returns:
+            str | None: Title of the paper. None if paper is None.
+        """
+        if self.paper is not None:
+            return self.paper.title
+        logger.error('paper is None.')
+        return None
+
+    @property
+    def abstract(self) -> str | None:
+        """Abstract.
+
+        Returns:
+            str | None: Abstract. None if paper is None.
+        """
+        if self.paper is not None:
+            return self.paper.summary
+        logger.error('paper is None.')
+        return None
+
+    @property
+    def authors(self) -> list | None:
+        """List of authors.
+
+        Returns:
+            list | None: List of authors. None if paper is None.
+        """
+        if self.paper is not None:
+            return [author.name for author in self.paper.authors]
+        logger.error('paper is None.')
+        return None
+
+    @property
+    def published(self) -> datetime | None:
+        """Published date.
+
+        Returns:
+            datetime: Published date. None if paper is None.
+        """
+        if self.paper is not None:
+            return self.paper.published
+        logger.error('paper is None.')
+        return None
+
+    @property
+    def updated(self) -> datetime | None:
+        """Updated date.
+
+        Returns:
+            datetime | None: Updated date. None if paper is None.
+        """
+        if self.paper is not None:
+            return self.paper.updated
+        logger.error('paper is None.')
+        return None
+
+    def search_by_arxiv_id(self, arxiv_id: str):
+        """Search paper by arXiv ID.
+
+        Args:
+            arxiv_id (str): arXiv ID.
+        """
+        self.paper = next(self.client.results(arxiv.Search(id_list=[arxiv_id])))
+
+    def download_pdf(self,
+                     dirpath: str = './',
+                     filename: str = '') -> str | None:
+        """Download the PDF.
+
+        Args:
+            dirpath (str, optional): Path to the directory. Defaults to './'.
+            filename (str, optional): Name of the file. Defaults to ''.
+
+        Returns:
+            str | None: Path of the output PDF. None if paper is None.
+        """
+        if self.paper is not None:
+            return self.paper.download_pdf(dirpath=dirpath, filename=filename)
+        logger.error('Paper is None. Cannot download PDF.')
+        return None
+
+    @property
+    def sections(self) -> list:
+        """Get the sections of the paper.
+
+        Returns:
+            list: A list of sections. Each section is a dict with the header as the key and the content as the value.
+        """
+        if len(self._sections) == 0:
+            with tempfile.NamedTemporaryFile() as tmp:
+                filename = tmp.name
+                self.download_pdf(filename=filename)
+
+                doc = fitz.open(filename)
+
+                current_section = {"header": None, "content": []}
+
+                for page in doc:
+                    blocks = page.get_text("blocks")  # Extract text blocks # type: ignore[attr-defined]
+
+                    for block in blocks:
+                        text = block[4].strip()
+
+                        # Detect section headers using common patterns (uppercase, numbered, bold)
+                        if (text.isupper() or re.match(r"^\d+(\.\d+)*\s+\w+", text) or text.endswith(":")):
+
+                            # Store previous section before switching
+                            if current_section["header"] or current_section["content"]:
+                                self._sections.append(current_section)
+
+                            current_section = {"header": text, "content": []}  # New section
+                        else:
+                            current_section["content"].append(text)
+
+                # Append the last section
+                if current_section["header"] or current_section["content"]:
+                    self._sections.append(current_section)
+
+        return self._sections

audioarxiv/tools/__init__.py

@@ -0,0 +1,3 @@
+"""
+Command line tools.
+"""

audioarxiv/tools/main.py

@@ -0,0 +1,194 @@
+"""
+A command line tool to fetch arXiv papers and read aloud.
+"""
+from __future__ import annotations
+
+import json
+import logging
+import os
+import signal
+import sys
+import time
+
+import configargparse
+from platformdirs import user_config_dir
+
+from ..audio.base import Audio, validate_audio_arguments
+from ..resources.paper import Paper, validate_paper_arguments
+
+logger = logging.getLogger('audioarxiv')
+
+
+def handle_exit(sig_num: int , frame: object):  # noqa: ARG001 # pylint: disable=unused-argument
+    """Handle the exit.
+
+    Args:
+        sig_num (int): Signal number.
+        frame (object): A frame object.
+    """
+    logger.info("\nReceived signal %s. Exiting cleanly.", sig_num)
+    sys.exit(0)
+
+
+def save_settings(config_path: str, settings: dict):
+    """Save the settings to file.
+
+    Args:
+        config_path (str): Path to the configuration file.
+        settings (dict): Dictionary of the settings.
+    """
+    try:
+        with open(config_path, 'w', encoding="utf-8") as f:
+            json.dump(settings, f, indent=4)
+    except Exception as e:
+        logger.error('Error saving settings: %s', e)
+
+
+def initialize_configuration(args: configargparse.Namespace) -> tuple:
+    """Initialize the configuration.
+
+    Args:
+        args (configargparse.Namespace): Arguments.
+
+    Returns:
+        tuple: settings, config_path
+    """
+    config_dir = user_config_dir('audioarxiv')
+    os.makedirs(config_dir, exist_ok=True)
+    config_file = 'config.json'
+    config_path = os.path.join(config_dir, config_file)
+
+    # Default settings.
+    settings = {
+        'audio': {
+            'rate': 140,
+            'volume': 0.9,
+            'voice': None,
+            'pause_seconds': 0.1
+        },
+        'paper': {
+            'page_size': 100,
+            'delay_seconds': 3.0,
+            'num_retries': 3
+        }
+    }
+
+    # Validate the default settings.
+    if os.path.exists(config_path):
+        # Load the settings from the config file.
+        try:
+            with open(config_path, encoding="utf-8") as f:
+                loaded_settings = json.load(f)
+                settings.update(loaded_settings)
+                settings['audio'] = validate_audio_arguments(**settings['audio'])
+                settings['paper'] = validate_paper_arguments(**settings['paper'])
+        except Exception as e:
+            logger.error('Error loading settings: %s. Using defaults.', e)
+    else:
+        logger.info('Saving default settings to %s...', config_path)
+        settings['audio'] = validate_audio_arguments(**settings['audio'])
+        settings['paper'] = validate_paper_arguments(**settings['paper'])
+        save_settings(config_path, settings)
+
+    # Check audio properties
+    audio_properties = list(settings['audio'].keys())
+    audio_settings_changed = False
+    for prop in audio_properties:
+        value = getattr(args, prop)
+        if value is not None:
+            # Compare with the existing setting
+            if value != settings['audio'][prop]:
+                settings['audio'][prop] = value
+                audio_settings_changed = True
+    if audio_settings_changed:
+        settings['audio'] = validate_audio_arguments(**settings['audio'])
+
+    # Check paper properties
+    paper_properties = list(settings['paper'].keys())
+    paper_settings_changed = False
+    for prop in paper_properties:
+        value = getattr(args, prop)
+        if value is not None:
+            # Compare with the existing setting
+            if value != settings['paper'][prop]:
+                settings['paper'][prop] = value
+                paper_settings_changed = True
+    if paper_settings_changed:
+        settings['paper'] = validate_paper_arguments(**settings['paper'])
+
+    # Write the settings to file if there are changes.
+    if audio_settings_changed or paper_settings_changed:
+        logger.info('Saving updated settings to %s...', config_path)
+        save_settings(config_path=config_path, settings=settings)
+    return settings, config_path
+
+
+def main():
+    """Main function.
+    """
+    signal.signal(signal.SIGINT, handle_exit)
+    signal.signal(signal.SIGTERM, handle_exit)
+
+    parser = configargparse.ArgParser()
+    parser.add_argument('--id', help='arXiv paper ID.')
+    parser.add_argument('--output', type=str, help='Output to audio file if provided.')
+    parser.add_argument('--rate', type=float, help='Number of words per minute between 50 and 500.')
+    parser.add_argument('--volume', type=float, help='Volume between 0 and 1.')
+    parser.add_argument('--voice', type=str, help='Voice.')
+    parser.add_argument('--pause-seconds', type=float, help='Duration of pause between sentences in second.')
+    parser.add_argument('--page-size', type=int, help='Maximum number of results fetched in a single API request.')
+    parser.add_argument('--delay-seconds', type=float, help='Number of seconds to wait between API requests.')
+    parser.add_argument('--num-retries', type=int, help=('Number of times to retry a failing API request before raising'
+                                                         'an Exception.'))
+    parser.add_argument('--list-voices', action='store_true', help='List the available voices.')
+
+    args = parser.parse_args()
+
+    if args.list_voices:
+        audio = Audio()
+        audio.list_voices()
+        return
+
+    # Get the settings
+    settings, config_path = initialize_configuration(args)
+
+    # The Audio instance.
+    audio = Audio(**settings['audio'])
+
+    # Load the paper.
+    paper = Paper(**settings['paper'])
+
+    # Search the paper.
+    if args.id is not None:
+        # Print the information
+        logger.info('Configuration file: %s', config_path)
+        logger.info('Audio settings')
+        for key, value in settings['audio'].items():
+            logger.info('%s: %s', key, value)
+
+        logger.info('Paper settings')
+        for key, value in settings['paper'].items():
+            logger.info('%s: %s', key, value)
+
+        logger.info('Searching arxiv: %s...', args.id)
+        paper.search_by_arxiv_id(arxiv_id=args.id)
+        # Get the sections
+        sections = paper.sections
+        if args.output is None:
+            for section in sections:
+                audio.read_article(section['header'])
+                time.sleep(1)
+                for content in section['content']:
+                    audio.read_article(content)
+                    time.sleep(1)
+        else:
+            article = []
+            for section in sections:
+                if section['header'] is not None:
+                    article.append(section['header'])
+                if section['content'] is not None:
+                    article += section['content']
+            article = " ".join(article)
+            logger.info('Saving audio...')
+            audio.save_article(filename=args.output, article=article)
+            logger.info('Audio is saved to %s.', args.output)

audioarxiv-0.1.0rc46.post1.dist-info/METADATA

@@ -0,0 +1,114 @@
+Metadata-Version: 2.4
+Name: audioarxiv
+Version: 0.1.0rc46.post1
+Summary: Sample Python Project for creating a new Python Module
+Author-email: "Isaac C. F. Wong" <isaac.cf.wong@gmail.com>
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+License-File: LICENSE
+Requires-Dist: configargparse
+Requires-Dist: arxiv
+Requires-Dist: pyttsx3
+Requires-Dist: pymupdf
+Requires-Dist: sympy
+Requires-Dist: nltk
+Requires-Dist: pandas
+Requires-Dist: platformdirs
+Requires-Dist: pyspark>=3.0.0 ; extra == "spark"
+Requires-Dist: bandit[toml]==1.8.3 ; extra == "test"
+Requires-Dist: black==25.1.0 ; extra == "test"
+Requires-Dist: check-manifest==0.50 ; extra == "test"
+Requires-Dist: flake8-bugbear==24.12.12 ; extra == "test"
+Requires-Dist: flake8-docstrings ; extra == "test"
+Requires-Dist: flake8-formatter_junit_xml ; extra == "test"
+Requires-Dist: flake8 ; extra == "test"
+Requires-Dist: flake8-pyproject ; extra == "test"
+Requires-Dist: pre-commit==4.2.0 ; extra == "test"
+Requires-Dist: pylint==3.3.6 ; extra == "test"
+Requires-Dist: pylint_junit ; extra == "test"
+Requires-Dist: pytest-cov==6.1.1 ; extra == "test"
+Requires-Dist: pytest-mock<3.14.1 ; extra == "test"
+Requires-Dist: pytest-runner ; extra == "test"
+Requires-Dist: pytest==8.3.5 ; extra == "test"
+Requires-Dist: pytest-github-actions-annotate-failures ; extra == "test"
+Requires-Dist: shellcheck-py==0.10.0.1 ; extra == "test"
+Project-URL: Documentation, https://isaac-cf-wong.github.io/audioarxiv
+Project-URL: Source, https://github.com/isaac-cf-wong/audioarxiv
+Project-URL: Tracker, https://github.com/isaac-cf-wong/audioarxiv/issues
+Provides-Extra: spark
+Provides-Extra: test
+
+# 🎧 audioarxiv
+
+[![PyPI version](https://badge.fury.io/py/audioarxiv.svg)](https://pypi.org/project/audioarxiv/)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+[![Build](https://img.shields.io/github/actions/workflow/status/isaac-cf-wong/audioarxiv/CI.yml?branch=main)](https://github.com/isaac-cf-wong/audioarxiv/actions)
+[![Python Version](https://img.shields.io/pypi/pyversions/audioarxiv)](https://pypi.org/project/audioarxiv/)
+[![Security: bandit](https://img.shields.io/badge/security-bandit-yellow.svg)](https://github.com/PyCQA/bandit)
+[![Documentation Status](https://img.shields.io/badge/documentation-online-brightgreen)](https://isaac-cf-wong.github.io/audioarxiv/)
+
+📚 **Documentation**: [https://isaac-cf-wong.github.io/audioarxiv/](https://isaac-cf-wong.github.io/audioarxiv/)
+
+**Turn arXiv papers into audio.**
+`audioarxiv` lets you fetch the research papers from arXiv and read them aloud.
+
+---
+
+## 🚀 Features
+
+- 🔍 Search and retrieve papers using the arXiv API
+- 📄 Extract and parse the content from PDF (excluding title/abstract)
+- 🗣️ Convert text to speech with natural voice output
+- 🧠 Great for passive learning while commuting or doing chores
+
+---
+
+## 📦 Installation
+
+Install from [PyPI](https://pypi.org/project/audioarxiv/):
+
+```bash
+pip install audioarxiv
+```
+
+Install from [Conda](https://anaconda.org/conda-forge/audioarxiv):
+
+```bash
+conda install -c conda-forge audioarxiv
+```
+
+---
+
+## 🛠 Usage
+
+```bash
+audioarxiv --id "<arxiv id>"
+```
+
+### 🎙️ Text-to-Speech Options
+
+You can customize the voice engine using `pyttsx3` by specifying the speaking rate, volume, voice, and pause between sentences.
+
+```bash
+audioarxiv --id "<arxiv id>" --rate <rate> --volume <volume> --voice "<voice>" --pause-seconds <pause-seconds>
+```
+
+- `rate`: Number of words per minutes. Defaults to 140.
+- `volume`: Volume of the audio. Defaults to 0.9.
+- `voice`: Voice of the audio. Defaults to the pyttsx3 default voice.
+- `pause-seconds`: Number of seconds to pause between sentences.
+
+The settings are saved, so you only need to provide your preferred settings once.
+
+## Contributing
+
+This project welcomes contributions and suggestions. For details, visit the repository's [Contributor License Agreement (CLA)](https://cla.opensource.microsoft.com) and [Code of Conduct](https://opensource.microsoft.com/codeofconduct/) pages.
+

audioarxiv-0.1.0rc46.post1.dist-info/RECORD

@@ -0,0 +1,15 @@
+audioarxiv/__init__.py,sha256=XIOQIggB9Lhdm1TolfKniYg7pEHZNnz4WqChpVcPaw0,5807
+audioarxiv/audio/__init__.py,sha256=UZx3AkhC8NZFXwQbW_sU4sQ1uGeEIRXCPDghXvZy8rY,214
+audioarxiv/audio/base.py,sha256=tQOby6-12r5lInbAQChMxsQNSQT7_od4_tZ7G8hsDKE,5984
+audioarxiv/preprocess/__init__.py,sha256=NUCDDLpSwpWTBaPNdLWUVK2FhtwMPsFvXczTE21_UvU,338
+audioarxiv/preprocess/article.py,sha256=d9nV2DEH4mvKsgUpJ3WB256rt8k5O7YvNTBUp5YOUbs,394
+audioarxiv/preprocess/math_equation.py,sha256=ulkeMZFJKxU8BH1QzNyW4BZ-UjWfDDMp1C-cqoRGyls,945
+audioarxiv/resources/__init__.py,sha256=KCZm9Hq0O9oCCtfpyKVDGo_qX-PU2qS8aJe1NgvmR7Q,166
+audioarxiv/resources/paper.py,sha256=s9XT3xuzntR_0_Np29F66muou0q409jocD4sU2dtgDM,7161
+audioarxiv/tools/__init__.py,sha256=7X5vtxzvCY9URWo0p3zvM11J6whGFeDPF7XU0dt1Qcw,28
+audioarxiv/tools/main.py,sha256=sAh7izIdGmfQZiI3tBKn-zLMhQgAQvLGu4OmYnYLsAc,6884
+audioarxiv-0.1.0rc46.post1.dist-info/entry_points.txt,sha256=d_K6uTNuC8-f9XUQ_enFBgssiK2lVV57EHCEloriVY4,57
+audioarxiv-0.1.0rc46.post1.dist-info/licenses/LICENSE,sha256=ws_MuBL-SCEBqPBFl9_FqZkaaydIJmxHrJG2parhU4M,1141
+audioarxiv-0.1.0rc46.post1.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
+audioarxiv-0.1.0rc46.post1.dist-info/METADATA,sha256=OJI4px0ymhXa8WIUf3cse9LusAcXqCKAlQmqfUHJb_o,4445
+audioarxiv-0.1.0rc46.post1.dist-info/RECORD,,

audioarxiv-0.1.0rc46.post1.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: flit 3.12.0
+Root-Is-Purelib: true
+Tag: py3-none-any

audioarxiv-0.1.0rc46.post1.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+audioarxiv=audioarxiv.tools.main:main
+

audioarxiv-0.1.0rc46.post1.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+    MIT License
+
+    Copyright (c) Microsoft Corporation.
+
+    Permission is hereby granted, free of charge, to any person obtaining a copy
+    of this software and associated documentation files (the "Software"), to deal
+    in the Software without restriction, including without limitation the rights
+    to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+    copies of the Software, and to permit persons to whom the Software is
+    furnished to do so, subject to the following conditions:
+
+    The above copyright notice and this permission notice shall be included in all
+    copies or substantial portions of the Software.
+
+    THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+    IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+    FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+    AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+    LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+    OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+    SOFTWARE