Full Code of KVignesh122/AssetNewsSentimentAnalyzer for AI

Repository: KVignesh122/AssetNewsSentimentAnalyzer
Branch: main
Commit: b3dcb02333c0
Files: 12
Total size: 37.2 KB

Directory structure:
gitextract_03kt3su7/

├── .gitignore
├── LICENSE
├── MANIFEST.in
├── README.md
├── asset_sentiment_analyzer/
│   ├── __init__.py
│   ├── apps.py
│   ├── gpt_client.py
│   ├── scrapper.py
│   ├── utils.py
│   └── websearch_funcs.py
├── requirements.txt
└── setup.py

================================================
FILE CONTENTS
================================================

================================================
FILE: .gitignore
================================================
.google-cookie
__pycache__/google1.cpython-311.pyc
__pycache__/gpt_client.cpython-311.pyc
__pycache__/scrapper.cpython-311.pyc
__pycache__/websearch.cpython-311.pyc
__pycache__/*
*.csv
oai.py
main-mine.py
websearch copy.py
plotting.py
sbc.py
*.pyc


================================================
FILE: LICENSE
================================================
                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.

      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the
      direction or management of such entity, whether by contract or
      otherwise, or (ii) ownership of fifty percent (50%) or more of the
      outstanding shares, or (iii) beneficial ownership of such entity.

      "You" (or "Your") shall mean an individual or Legal Entity
      exercising permissions granted by this License.

      "Source" form shall mean the preferred form for making modifications,
      including but not limited to software source code, documentation
      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions
      to that Work or Derivative Works thereof, that is intentionally
      submitted to Licensor for inclusion in the Work by the copyright owner
      or by an individual or Legal Entity authorized to submit on behalf of
      the copyright owner. For the purposes of this definition, "submitted"
      means any form of electronic, verbal, or written communication sent
      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise
      designated in writing by the copyright owner as "Not a Contribution."

      "Contributor" shall mean Licensor and any individual or Legal Entity
      on behalf of whom a Contribution has been received by Licensor and
      subsequently incorporated within the Work.

   2. Grant of Copyright License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      copyright license to reproduce, prepare Derivative Works of,
      publicly display, publicly perform, sublicense, and distribute the
      Work and such Derivative Works in Source or Object form.

   3. Grant of Patent License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      (except as stated in this section) patent license to make, have made,
      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a
      cross-claim or counterclaim in a lawsuit) alleging that the Work
      or a Contribution incorporated within the Work constitutes direct
      or contributory patent infringement, then any patent licenses
      granted to You under this License for that Work shall terminate
      as of the date such litigation is filed.

   4. Redistribution. You may reproduce and distribute copies of the
      Work or Derivative Works thereof in any medium, with or without
      modifications, and in Source or Object form, provided that You
      meet the following conditions:

      (a) You must give any other recipients of the Work or
          Derivative Works a copy of this License; and

      (b) You must cause any modified files to carry prominent notices
          stating that You changed the files; and

      (c) You must retain, in the Source form of any Derivative Works
          that You distribute, all copyright, patent, trademark, and
          attribution notices from the Source form of the Work,
          excluding those notices that do not pertain to any part of
          the Derivative Works; and

      (d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,
          within a display generated by the Derivative Works, if and
          wherever such third-party notices normally appear. The contents
          of the NOTICE file are for informational purposes only and
          do not modify the License. You may add Your own attribution
          notices within Derivative Works that You distribute, alongside
          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.

      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or
      for any such Derivative Works as a whole, provided Your use,
      reproduction, and distribution of the Work otherwise complies with
      the conditions stated in this License.

   5. Submission of Contributions. Unless You explicitly state otherwise,
      any Contribution intentionally submitted for inclusion in the Work
      by You to the Licensor shall be under the terms and conditions of
      this License, without any additional terms or conditions.
      Notwithstanding the above, nothing herein shall supersede or modify
      the terms of any separate license agreement you may have executed
      with Licensor regarding such Contributions.

   6. Trademarks. This License does not grant permission to use the trade
      names, trademarks, service marks, or product names of the Licensor,
      except as required for reasonable and customary use in describing the
      origin of the Work and reproducing the content of the NOTICE file.

   7. Disclaimer of Warranty. Unless required by applicable law or
      agreed to in writing, Licensor provides the Work (and each
      Contributor provides its Contributions) on an "AS IS" BASIS,
      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
      implied, including, without limitation, any warranties or conditions
      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,
      whether in tort (including negligence), contract, or otherwise,
      unless required by applicable law (such as deliberate and grossly
      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all
      other commercial damages or losses), even if such Contributor
      has been advised of the possibility of such damages.

   9. Accepting Warranty or Additional Liability. While redistributing
      the Work or Derivative Works thereof, You may choose to offer,
      and charge a fee for, acceptance of support, warranty, indemnity,
      or other liability obligations and/or rights consistent with this
      License. However, in accepting such obligations, You may act only
      on Your own behalf and on Your sole responsibility, not on behalf
      of any other Contributor, and only if You agree to indemnify,
      defend, and hold each Contributor harmless for any liability
      incurred by, or claims asserted against, such Contributor by reason
      of your accepting any such warranty or additional liability.

   END OF TERMS AND CONDITIONS

   APPENDIX: How to apply the Apache License to your work.

      To apply the Apache License to your work, attach the following
      boilerplate notice, with the fields enclosed by brackets "[]"
      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright [yyyy] [name of copyright owner]

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.
   You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License.


================================================
FILE: MANIFEST.in
================================================
include LICENSE
include requirements.txt


================================================
FILE: README.md
================================================
# Asset News Sentiment Analyzer

This application provides two sophisticated tools catering to sentiment analysis of financial assets and securities by using ChatGPT on Google search results and online news articles. You will just need an OpenAI API Key to get started and utilize the power of all the functionalities provided by this package, namely to fetch news articles, analyze their content, and produce insightful reports for investment and trading decisions.

A simple trading strategy involving daily sentiment analysis signals from this package may provide basic market traction of the target asset (We did a sample backtest on commodities over the past 100 market days):

<table>
  <tr>
    <td align="center">
      <strong>Crude Oil 100 Days</strong><br>
      <img src="images/Crude Oil.jpg" alt="Crude Oil Sample" width="500" height="300">
    </td>
    <td align="center">
      <strong>Gold 100 Days</strong><br>
      <img src="images/Gold.jpg" alt="Gold Sample" width="500" height="300">
    </td>
  </tr>
</table>

***Disclaimer: All investments and trading involve risk. This package is intended for research/academic purposes, and coding projects. It aids algorithmic/quantitative traders and researchers in their work. The reports and signals generated by this package does not constitute financial advice, and users should perform their own due diligence before making any trading decisions.***

## Contents

- [Two Main Classes](#two-main-classes)
  - [SentimentAnalyzer Tool](#1-sentimentanalyzer-tool)
  - [WebInteractor Tool](#2-webinteractor-tool)
- [Installation](#installation)
- [Contributing](#contributing)
- [License](#license)

## Two Main Classes

### 1. SentimentAnalyzer Tool

The `SentimentAnalyzer` class allows users to perform sentiment analysis on news articles related to a specific financial asset for any given date. It fetches news links, retrieves the content, and if desired, uses GPT models to generate reports and assess market sentiment.

**Usage**

```python
from asset_sentiment_analyzer import SentimentAnalyzer

# Initialize the analyzer
analyzer = SentimentAnalyzer(asset='Crude Oil', openai_key='your-openai-key')

# Get sentiment analysis as string for today or any date in the past (returns "bullish", "bearish", or "neutral")
sentiment = analyzer.get_sentiment(date='06-02-2024')
print(f"The sentiment for the asset is: {sentiment}")

# Fetch news links for any date with news_date argument in MM-dd-YYYY format.
news_links = analyzer.fetch_news_links(news_date='06-02-2024')

# Display news content
for url in news_links:
    print(analyzer.show_news_content(url))

# Generate a report
report = analyzer.produce_daily_report(date='06-02-2024', max_words=300)
print(report)

```

**API Reference**

* `SentimentAnalyzer(<asset_name>)`: Initializes the SentimentAnalyzer object with specified asset and optional OpenAI key (`openai_key` parameter) and model selection (`model` parameter).

__Available Methods:__

* `.fetch_news_links()`: Fetches news links from Google Search News tab for the specified asset on the given date. If `news_date` parameter is not assigned, it will retrieve the current day's latests news links. `nlinks` parameter denotes the number of news links to retrieve, default is `4`.
* `.show_news_content(<news_url>)`: Parses and returns main content as string for a given news URL.
* `.get_sentiment()`: Analyzes online results automatically and returns the news sentiment for asset/security on any given date. If `date` parameter is not assigned, it will return the current day's latest sentiment verdict.
* `.produce_daily_report()`: Generates a daily report returned as string with insights based on the online Google Search content for any given date. If `date` parameter is not assigned, it will generate report for the current day. The default `max_words` is `100`, but this can be adjusted as preferred.

Note: All dates must be in `MM-dd-YYYY` format or must be passed as a `datetime.datetime` object into the methods.

### 2. WebInteractor Tool

The `WebInteractor` class provides functionalities to interact with web content, perform Google searches, and retrieve content, which can then be fed into a GPT client for further interaction.

**Usage**

```python
from asset_sentiment_analyzer import WebInteractor

# Initialize the WebInteractor
web_interactor = WebInteractor()

# Perform a Google search and retrieve result links as list
search_results = web_interactor.search_google(query="Apple Stocks", nlinks=5)
print(search_results)

# Fetch the main content of a webpage
content = web_interactor.get_webpage_main_content(url="https://example.com")
print(content)

# Interact with a GPT model
my_prompt = f"""
How will this affect the latest Apple earnings report:
{content}
"""
response = web_interactor.get_llm_response(prompt=my_prompt, openai_api_key="your_openai_api_key")
print(response)

```

**API Reference**

* `WebInteractor()`: Initializes a WebInteractor object which provides functionalities for interacting with web content and performing web searches.

__Available Methods:__

* `.search_google(<query>)`: Searches Google for the specified query and retrieves a list of unique links. Parameters:
  * `query` (str): The search query.
  * `tld` (str, optional): The top-level domain for Google (eg. 'com' for Google.com).
  * `lang` (str, optional): The language setting for the Google search.
  * `date` (str, optional): The date to refine search results. (`MM-dd-YYYY` format)
  * `country` (str, optional): The country setting for Google search results.
  * `tab` (str, optional): Specifies the tab under which the search is performed, allowing for specific types of search results.
  * Possible values include:
    - `'app'` for Applications
    - `'blg'` for Blogs
    - `'bks'` for Books
    - `'dsc'` for Discussions
    - `'isch'` for Images
    - `'nws'` for News
    - `'pts'` for Patents
    - `'plcs'` for Places
    - `'rcp'` for Recipes
    - `'shop'` for Shopping
    - `'vid'` for Video
  * `nlinks` (int, optional): The number of links to retrieve.
* `.get_webpage_main_content(<url>)`: Fetches the main content of a webpage.
* `.get_llm_response(<prompt>, <openai_api_key>)`: A method to interact with a GPT language model based on a specified prompt and retrieve its response.

## Installation

Project has been published on pip

```bash
pip install asset-sentiment-analyzer
```

## Contributing

If you would like to contribute to this project, please follow the guidelines below:

- Fork the repository.
- Create a new branch (git checkout -b feature-branch).
- Make your changes.
- Commit your changes (git commit -m 'Add new feature').
- Push to the branch (git push origin feature-branch).
- Open a pull request.

## License

This project is pioneered by SkyBlue Capital (Singapore), and is licensed under the Apache-2.0 License. See the LICENSE file for details.

<img src="images/HBlack.png" alt="SBC Logo" width="190" height="55">


================================================
FILE: asset_sentiment_analyzer/__init__.py
================================================
from . import gpt_client
from . import scrapper
from . import utils
from . import websearch_funcs

from .apps import SentimentAnalyzer, WebInteractor

__all__ = [SentimentAnalyzer, WebInteractor, websearch_funcs, gpt_client, scrapper, utils]


================================================
FILE: asset_sentiment_analyzer/apps.py
================================================
import asyncio
from . import websearch_funcs

from .scrapper import get_news_links, parse_webpage
from datetime import datetime
from .gpt_client import chunk, get_gpt_response, ANALYSER_INSTR


class SentimentAnalyzer:
    def __init__(self, asset, openai_key=None, model="gpt-3.5-turbo") -> None:
        """
        Initializes the SentimentAnalyzer object.
        
        Parameters:
            asset (str): The financial asset for which sentiment analysis is to be performed.
            openai_key (str, optional): The API key for OpenAI, required for accessing GPT models.
            model (str, optional): The specific GPT model to use for generating text and analyzing sentiment.
        
        Returns:
            None
        """
        self.asset = asset
        self.oai_key = openai_key
        self.model = model

        self.date_of_interest = None
        self.news_links = None
        return

    def fetch_news_links(self, news_date=datetime.today(), nlinks=4):
        """
        Fetches a specific number of news links related to the asset on a given date.
        
        Parameters:
            news_date (datetime, optional): The date for which to fetch news links.
            nlinks (int, optional): The maximum number of news links to retrieve.
        
        Returns:
            list: A list of URLs as strings that link to news articles.
        
        Raises:
            ValueError: If 'nlinks' is not an integer.
        """
        if not isinstance(nlinks, int):
            raise ValueError("nlinks parameter value has to be an int.")
        
        if news_date == self.date_of_interest:
            assert(self.news_links is not None)
            return self.news_links
        
        self.news_links = get_news_links(self.asset, nlinks, news_date)
        self.date_of_interest = news_date
        return self.news_links
    
    def show_news_content(self, news_url):
        """
        Fetches and displays the content of a news article from a URL.
        
        Parameters:
            news_url (str): The URL of the news article to fetch content from.
        
        Returns:
            str: The content of the news article.
        """
        return asyncio.run(parse_webpage(news_url))

    async def __get_all_news_content(self, links):
        """
        Asynchronously retrieves and concatenates the content from a list of news URLs.
        
        Parameters:
            links (list): A list of news URLs to fetch content from.
        
        Returns:
            str: Concatenated content from all the news articles.
        """
        news = ''
        for idx, link in enumerate(links, start=1):
            news += f"""
                Article {idx}:
                "{await parse_webpage(link)}"
                """
        return news
    
    def __construct_report_prompt(self, max_words, news):
        return f"""Write out a short and impactful report with key insights 
                for {self.asset} from these given information:
                {news}
                Your writeup must strictly be within {max_words} words.
                """
    
    def produce_daily_report(self, date=datetime.today(), max_words=100):
        """
        Produces a short report based on the news linked to the asset for given date, using the GPT model.
        
        Parameters:
            date (datetime, optional): The date for which the report is produced.
            max_words (int, optional): The maximum number of words in the report.
        
        Returns:
            str: The generated report as a string.
        
        Raises:
            ValueError: If an OpenAI API key is not set.
        """
        if self.oai_key is None:
            raise ValueError("An OpenAI API key is required to interact with GPT models.")
        
        links = self.fetch_news_links(date)
        
        news = asyncio.run(self.__get_all_news_content(links))
        news = chunk(news)
        text = get_gpt_response(
                user_prompt=self.__construct_report_prompt(max_words, news),
                openai_key=self.oai_key,
                preferred_model=self.model
            )
        return text

    def __construct_sentiment_prompt(self, news):
        return f"""Based on all your knowlege of financial markets and textual analysis, 
            assess information from all these articles and determine if the sentiment for {self.asset} 
            is mainly bullish, bearish, or neutral:
            {news}
            Your response must strictly contain only one word string in lower case ("bullish", "bearish", 
            or "neutral") and no other words.
            """
    
    def get_sentiment(self, date=datetime.today()):
        """
        Determines the news sentiment for the asset for the given date, using the GPT model.
        
        Parameters:
            date (datetime, optional): The date for which sentiment is assessed.
        
        Returns:
            str: The determined sentiment ('bullish', 'bearish', or 'neutral').
        
        Raises:
            ValueError: If an OpenAI API key is not set.
        """
        if self.oai_key is None:
            raise ValueError("An OpenAI API key is required to interact with GPT models.")

        links = self.fetch_news_links(date)
        assert(len(links) <= 4)
        
        news = asyncio.run(self.__get_all_news_content(links))
        news = chunk(news)
        sentiment = get_gpt_response(
            user_prompt=self.__construct_sentiment_prompt(news),
            openai_key=self.oai_key,
            generation_tk_limit=10,
            preferred_model=self.model,
            system_instruction=ANALYSER_INSTR
        )
        return sentiment.lower()


class WebInteractor():
    def __init__(self) -> None:
        """
        Initializes the WebInteractor class which provides functionalities 
        for interacting with web content and performing web searches.
        """
        pass

    def search_google(self, query, tld='com', lang='en', date='0', country='', tab='', nlinks=None):
        """
        Searches Google for the specified query and retrieves a list of unique links.

        Parameters:
            query (str): The search query.
            tld (str, optional): The top-level domain for Google (e.g., 'com' for Google.com).
            lang (str, optional): The language setting for the Google search.
            date (str, optional): The date to refine search results.
            country (str, optional): The country setting for Google search results.
            tab (str, optional): Specifies the tab under which the search is performed, allowing for specific types of search results.
            Possible values include:
                - 'app' for Applications
                - 'blg' for Blogs
                - 'bks' for Books
                - 'dsc' for Discussions
                - 'isch' for Images
                - 'nws' for News
                - 'pts' for Patents
                - 'plcs' for Places
                - 'rcp' for Recipes
                - 'shop' for Shopping
                - 'vid' for Video
            nlinks (int, optional): The number of links to retrieve.

        Returns:
            list: A unique set of URLs returned from the Google search.
        """
        links =  list(websearch_funcs.search_google(
            query=query,
            tld=tld,
            lang=lang,
            tbs=websearch_funcs.get_tbs(date),
            country=country,
            tbm=tab,
            stop=nlinks
        ))
        return list(set(links))
    
    def get_webpage_main_content(self, url):
        return asyncio.run(parse_webpage(url))
    
    def get_llm_response(self, prompt, openai_api_key, generation_tk_limit=None, gpt_model="gpt-3.5-turbo", system_instruction=None):
        """
        Generates a response from a GPT language model based on a specified prompt.
        
        Parameters:
            prompt (str): The prompt to send to the language model.
            openai_api_key (str): The API key for OpenAI, required for accessing the language model.
            generation_tk_limit (int, optional): The maximum number of tokens that the language model is allowed to generate.
            gpt_model (str, optional): The specific GPT model to use for generating responses.
            system_instruction (str, optional): Additional instructions to guide the language model's response.
        
        Returns:
            str: The response generated by the language model for the user query.
        """
        return get_gpt_response(
                user_prompt=prompt,
                openai_key=openai_api_key,
                generation_tk_limit=generation_tk_limit,
                preferred_model=gpt_model,
                system_instruction=system_instruction
            )


================================================
FILE: asset_sentiment_analyzer/gpt_client.py
================================================
from openai import OpenAI
import tiktoken

ENCODING_STANDARD = "cl100k_base"
ANALYSER_INSTR = """You will be provided with a few financial/technical analysis writeups, 
news content, or opinion articles by the user. Based on these content, determine if the asset 
being requested by the user has a overall bullish, bearish, or neutral sentiment. Follow the instructions 
of the user closely.
"""


def get_tokens(text: str):
    enc = tiktoken.get_encoding(ENCODING_STANDARD)
    return enc.encode(text)


def get_token_length(text: str):
    return len(get_tokens(text))


def decode_tokens(tokens):
    enc = tiktoken.get_encoding(ENCODING_STANDARD)
    return enc.decode(tokens)


def chunk(text: str, max_token_len=3000):
    text_tk_length = get_token_length(text)
    if text_tk_length > max_token_len:
        tokenized_text = get_tokens(text)
        return decode_tokens(tokenized_text[:max_token_len])
    return text


def get_gpt_response(user_prompt: str, openai_key: str, generation_tk_limit=None, preferred_model="gpt-3.5-turbo", system_instruction=None):
    client = OpenAI(api_key=openai_key)

    if system_instruction is not None:
        gpt_prompt = [
            {"role":"system","content": system_instruction},
            {"role": "user", "content": user_prompt}
        ]
    else:
        gpt_prompt = [
            {"role": "user", "content": user_prompt}
        ]

    response = client.chat.completions.create(
        model=preferred_model,
        messages=gpt_prompt,
        max_tokens=generation_tk_limit
    )
    return response.choices[0].message.content


================================================
FILE: asset_sentiment_analyzer/scrapper.py
================================================
from bs4 import BeautifulSoup
from readability import Document
from .websearch_funcs import search_google, get_tbs
import aiohttp
import asyncio
from .utils import get_random_user_agent


async def fetch(session, url):
    headers = {'User-Agent': get_random_user_agent()}
    try:
        timeout = aiohttp.ClientTimeout(total=60)  # Increasing the total timeout to 60 seconds
        await asyncio.sleep(0.5)
        async with session.get(url, headers=headers, timeout=timeout) as response:
            return await response.text()
    except aiohttp.ClientError as e:
        print(f"Client error: {e}")
        return None
    except asyncio.TimeoutError:
        print("The request timed out")
        return None


async def parse_webpage(url_link):
    async with aiohttp.ClientSession() as session:
        html_content = await fetch(session, url_link)
        if html_content is not None:
            doc = Document(html_content)
            soup = BeautifulSoup(doc.summary(), 'html.parser')
            return soup.get_text(strip=True)
        return ''


def get_news_links(asset_name: str, nlinks: int, date=None) -> list:
    links = []
    
    additional_queries = [
        asset_name + " technical analysis",
        asset_name + " price sentiment",
        asset_name + " trading signal",
        asset_name,
    ]
    i = 0
    
    while len(links) < nlinks and i <= 3:
        articles_needed = nlinks - len(links)
        if date:
            links += list(search_google(additional_queries[i], stop=articles_needed, pause=0.5, tbm="nws", tbs=get_tbs(date)))
        else:
            links += list(search_google(additional_queries[i], stop=articles_needed, pause=0.5, tbm="nws"))
        links = list(set(links))
        i += 1
    
    return links


================================================
FILE: asset_sentiment_analyzer/utils.py
================================================
from random import choice

# List of user agents for requests
USER_AGENTS_LIST = [
    # Chrome
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36',
    'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36',
    # Firefox
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:88.0) Gecko/20100101 Firefox/88.0',
    'Mozilla/5.0 (X11; Linux x86_64; rv:88.0) Gecko/20100101 Firefox/88.0',
    # Safari
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1 Safari/605.1.15',
    'Mozilla/5.0 (iPhone; CPU iPhone OS 14_5 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0 Mobile/15E148 Safari/604.1',
    # Edge
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36 Edg/90.0.818.49',
    # Opera
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36 OPR/76.0.4017.123'
]

# Define URL templates
GOOGLE_HOMEPAGE_URL = "https://www.google.%(tld)s/"
GOOGLE_SEARCH_RESULTS_URL = "https://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&" \
             "btnG=Google+Search&tbs=%(tbs)s&safe=%(safe)s&" \
             "cr=%(country)s&tbm=%(tbm)s"


def get_random_user_agent():
    """Select a random user agent from a predefined list."""
    return choice(USER_AGENTS_LIST)


================================================
FILE: asset_sentiment_analyzer/websearch_funcs.py
================================================
import os
import time
import ssl
from http.cookiejar import LWPCookieJar
from urllib.request import Request, urlopen
from urllib.parse import quote_plus, urlparse, parse_qs
from bs4 import BeautifulSoup
from datetime import datetime, date
from . import utils

# Initialize cookie jar at script directory
current_folder = os.path.dirname(os.path.abspath(__file__))
cookie_jar_path = os.path.join(current_folder, '.google-cookie')
cookie_jar = LWPCookieJar(cookie_jar_path)
try:
    cookie_jar.load()
except Exception:
    pass  # Handle exceptions or log errors as needed


def get_tbs(preferred_date):
    """Format the tbs parameter for Google search."""
    
    if preferred_date == '0':
        return '0'
        
    preferred_date = to_date(preferred_date)
    if is_future_date(preferred_date):
        raise ValueError(f"Cannot be a future date.")
    date_str = preferred_date.strftime('%m/%d/%Y')
    return f"cdr:1,cd_min:{date_str},cd_max:{date_str}"


def to_date(input_date):
    """
    Convert a datetime.datetime object or a string containing a date
    into a datetime.date object.

    :param input_date: A datetime.datetime object or a string representing a date.
    :param date_format: A string representing the expected format of the date string (optional).
    :return: A datetime.date object.
    """
    if isinstance(input_date, datetime):
        return input_date.date()
    elif isinstance(input_date, str):
        try:
            return datetime.strptime(input_date, '%m/%d/%Y').date()
        except ValueError:
            raise ValueError(f"Date string does not match format '%m/%d/%Y'")
    else:
        raise TypeError("Input must be a datetime.datetime object or a string")


def is_future_date(input_date):
    """
    Check if a given datetime.date object is a date in the future.

    :param input_date: A datetime.date object.
    :return: True if the input_date is in the future, False otherwise.
    """
    if not isinstance(input_date, date) and not isinstance(input_date, datetime):
        raise TypeError("Input date must be a datetime.date object")
    
    today = date.today()
    return input_date > today


def get_page(url, user_agent=None, verify_ssl=True):
    """Retrieve a webpage with optional SSL verification."""
    if user_agent is None:
        user_agent = utils.get_random_user_agent()
    request = Request(url, headers={'User-Agent': user_agent})
    cookie_jar.add_cookie_header(request)
    
    context = ssl.create_default_context() if verify_ssl else ssl._create_unverified_context()
    response = urlopen(request, context=context)
    cookie_jar.extract_cookies(response, request)
    html_content = response.read()
    response.close()
    
    try:
        cookie_jar.save()
    except Exception:
        pass
    
    return html_content


def filter_result(link):
    """Filter valid links from Google search results."""
    if link.startswith('/url?'):
        link = parse_qs(urlparse(link).query)['q'][0]
    o = urlparse(link)
    if o.netloc and 'google' not in o.netloc:
        return link


def search_google(query, tld='com', lang='en', tbs='0', safe='off',
                  stop=None, pause=1.0, country='', tbm='', user_agent=None):
    """Perform a Google search and yield found URLs."""
    query = quote_plus(query)
    initial_url = utils.GOOGLE_HOMEPAGE_URL % vars()
    get_page(initial_url, user_agent)

    results = set()
    count = 0

    while not stop or count < stop:
        time.sleep(pause)  # Pause to avoid rate limiting
        search_url = utils.GOOGLE_SEARCH_RESULTS_URL % vars()
        html = get_page(search_url, user_agent)
        soup = BeautifulSoup(html, 'html.parser')
        anchors = soup.find(id='search').find_all('a') if soup.find(id='search') else soup.find_all('a')

        for anchor in anchors:
            link = anchor.get('href')
            if link and (filtered_link := filter_result(link)) and filtered_link not in results:
                results.add(filtered_link)
                yield filtered_link
                count += 1
                if stop and count >= stop:
                    break
        
        if count == len(results):
            break


================================================
FILE: requirements.txt
================================================
requests
beautifulsoup4
readability-lxml
lxml_html_clean
tiktoken
openai
aiohttp

================================================
FILE: setup.py
================================================
from setuptools import setup, find_packages

setup(
    name='asset_sentiment_analyzer',
    version='0.1.4',
    description='A sentiment analyzer package for financial assets and securities utilizing GPT models.',
    long_description=open('README.md').read(),
    long_description_content_type='text/markdown',
    url='https://github.com/KVignesh122/AssetNewsSentimentAnalyzer',
    author='Kumaravel Vignesh',
    author_email='k_vignesh@hotmail.com',
    license='Apache-2.0',
    packages=find_packages(),
    install_requires=open('requirements.txt').read().splitlines(),
    classifiers=[
        'Development Status :: 3 - Alpha',
        'Intended Audience :: Developers',
        'License :: OSI Approved :: Apache Software License',
        'Programming Language :: Python :: 3',
        'Programming Language :: Python :: 3.8',
        'Programming Language :: Python :: 3.9',
        'Programming Language :: Python :: 3.10'
    ],
    python_requires='>=3.6',
)