├── MANIFEST.in ├── requirements.txt ├── Yirabot Request Process.png ├── .gitignore ├── .github ├── workflows │ └── bandit-analysis.yml ├── ISSUE_TEMPLATE │ ├── documentation-improvement.md │ ├── bug_report.md │ ├── feature_request.md │ └── performance-issue.md └── PULL_REQUEST_TEMPLATE.md ├── setup.py ├── yirabot ├── saving_functions.py ├── help.py ├── errors.py ├── yirabot.py ├── display_functions.py ├── helper_functions.py ├── data_extraction_functions.py ├── __init__.py ├── seo_functions.py └── crawling_functions.py ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── SECURITY.md ├── README.md └── LICENSE /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include LICENSE 2 | include README.md -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | beautifulsoup4==4.12.3 2 | Requests==2.31.0 3 | rich==13.7.0 4 | html5lib==1.1 5 | -------------------------------------------------------------------------------- /Yirabot Request Process.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/OwenOrcan/YiraBot-Crawler/HEAD/Yirabot Request Process.png -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | __pycache__/ 2 | .idea/ 3 | *.iml 4 | .vscode/ 5 | build/ 6 | dist/ 7 | YiraBot.egg-info/ 8 | env/ 9 | 10 | -------------------------------------------------------------------------------- /.github/workflows/bandit-analysis.yml: -------------------------------------------------------------------------------- 1 | name: Python Security Check with Bandit 2 | 3 | on: 4 | push: 5 | branches: 6 | - master 7 | pull_request: 8 | branches: 9 | - master 10 | 11 | jobs: 12 | bandit-scan: 13 | runs-on: ubuntu-latest 14 | steps: 15 | - name: Check out repository 16 | uses: actions/checkout@v3 17 | 18 | - name: Set up Python 19 | uses: actions/setup-python@v3 20 | with: 21 | python-version: 3.8 22 | 23 | - name: Install Bandit 24 | run: pip install bandit 25 | 26 | - name: Run Bandit security checks 27 | continue-on-error: true 28 | run: bandit -r ./yirabot -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup, find_packages 2 | 3 | setup( 4 | name='YiraBot', 5 | version='1.0.9.2', 6 | packages=find_packages(), 7 | install_requires=open('requirements.txt').readlines(), 8 | author='Owen Orcan', 9 | author_email='owenorcan@gmail.com', 10 | url='https://github.com/OwenOrcan/Yirabot-Crawler', 11 | license='GNU General Public License (Version 3)', 12 | description="YiraBot: Simplifying Web Scraping for All. A user-friendly tool for developers and enthusiasts, offering command-line ease and Python integration. Ideal for research, SEO, and data collection.", 13 | long_description=open('README.md').read(), 14 | long_description_content_type='text/markdown', 15 | 16 | entry_points={ 17 | 'console_scripts': [ 18 | 'yirabot=yirabot.yirabot:main', 19 | ], 20 | }, 21 | ) 22 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/documentation-improvement.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: Documentation Improvement 3 | about: Suggest improvements or report issues in YiraBot's documentation 4 | title: '' 5 | labels: documentation 6 | assignees: OwenOrcan 7 | 8 | --- 9 | 10 | ## Documentation Issue/Improvement 11 | 12 | 13 | ## Relevant Page/Section 14 | 15 | 16 | ## Suggested Changes 17 | 18 | 19 | ## Additional Information 20 | 21 | 22 | ## Screenshots/Examples 23 | 24 | 25 | ## Would you like to contribute to the documentation update? 26 | - [ ] Yes 27 | - [ ] No 28 | -------------------------------------------------------------------------------- /.github/PULL_REQUEST_TEMPLATE.md: -------------------------------------------------------------------------------- 1 | # Pull Request Template 2 | 3 | ## Description 4 | 5 | 6 | ## Related Issue 7 | 8 | 9 | ## Type of Change: 10 | 11 | - [ ] Bug fix. 12 | - [ ] Feature addition or improvement. 13 | - [ ] Documentation update. 14 | - [ ] Other: 15 | 16 | ## Checklist: 17 | 18 | - [ ] I have read the CONTRIBUTING document. 19 | - [ ] My code follows the code style of this project. 20 | - [ ] I have added tests to cover my changes. 21 | - [ ] All new and existing tests passed. 22 | - [ ] My changes generate no new warnings. 23 | - [ ] I have made corresponding changes to the documentation. 24 | - [ ] Any dependent changes have been merged and published. 25 | 26 | ## Additional Information 27 | 28 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/bug_report.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: Bug report 3 | about: Create a report to help us improve 4 | title: '' 5 | labels: bug 6 | assignees: OwenOrcan 7 | 8 | --- 9 | 10 | ## Description 11 | 12 | 13 | ## Steps to Reproduce 14 | 15 | 1. 16 | 2. 17 | 3. 18 | 4. 19 | 20 | ## Expected Behavior 21 | 22 | 23 | ## Actual Behavior 24 | 25 | 26 | ## Environment 27 | 28 | - Version used: 29 | - Operating System and version: 30 | - Browser and version: 31 | 32 | ## Additional Context 33 | 34 | 35 | ## Possible Solution 36 | 37 | 38 | ## Logs 39 | 40 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature_request.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: Feature request 3 | about: Suggest an idea or enhancement for YiraBot 4 | title: '' 5 | labels: enhancement 6 | assignees: OwenOrcan 7 | 8 | --- 9 | 10 | ## Feature Description 11 | 12 | 13 | ## Problem and Motivation 14 | 15 | 16 | ## Proposed Solution 17 | 18 | 19 | ## Alternatives Considered 20 | 21 | 22 | ## Additional Context 23 | 24 | 25 | ## Impact 26 | 27 | 28 | ## Possible Implementation 29 | 30 | 31 | ## Anything else? 32 | 33 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/performance-issue.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: Performance Issue 3 | about: Report a performance problem in YiraBot 4 | title: '' 5 | labels: enhancement 6 | assignees: OwenOrcan 7 | 8 | --- 9 | 10 | ## Performance Issue Description 11 | 12 | 13 | ## Steps to Reproduce 14 | 15 | 1. 16 | 2. 17 | 3. 18 | 4. 19 | 20 | ## Expected Behavior 21 | 22 | 23 | ## Actual Behavior 24 | 25 | 26 | ## Environment 27 | 28 | - YiraBot Version: 29 | - Operating System and version: 30 | - Hardware Configuration: 31 | 32 | ## Possible Causes/Solutions 33 | 34 | 35 | ## Additional Context 36 | 37 | 38 | ## Profiling Data/Screenshots 39 | 40 | -------------------------------------------------------------------------------- /yirabot/saving_functions.py: -------------------------------------------------------------------------------- 1 | from datetime import datetime 2 | from rich import print 3 | from .helper_functions import write_to_file 4 | 5 | 6 | def save_crawl_data(data, url, extract, extract_json): 7 | """ 8 | Saves the crawled data to files in specified formats based on the parameters. 9 | The filename is derived from the URL and the current timestamp. 10 | 11 | Args: 12 | data (dict): The data to be saved, expected to be a dictionary. 13 | url (str): The URL of the crawled site, used to generate part of the filename. 14 | extract (bool): If True, saves the data in text format. 15 | extract_json (bool): If True, saves the data in JSON format. 16 | 17 | Returns: 18 | None: The function outputs files and does not return any value. 19 | """ 20 | # Sanitize the URL to create a safe filename 21 | safe_url = url.replace("https://", "").replace("http://", "").replace("/", "_") 22 | timestamp = datetime.now().strftime("%Y-%m-%d") 23 | filename = f"{safe_url}.{timestamp}" 24 | 25 | # Save data in text format 26 | if extract: 27 | write_to_file(data, f"{filename}.txt") 28 | print("YiraBot: Text file created.") 29 | 30 | # Save data in JSON format 31 | if extract_json: 32 | write_to_file(data, f"{filename}.json", jsonify=True) 33 | print("YiraBot: JSON file created.") -------------------------------------------------------------------------------- /yirabot/help.py: -------------------------------------------------------------------------------- 1 | RED = "\033[31m" 2 | MAGENTA = "\033[35m" 3 | WHITE = "\033[37m" 4 | CYAN = "\033[36m" 5 | LIGHTBLUE_EX = "\033[94m" 6 | RESET = "\033[0m" 7 | 8 | def help(): 9 | help_message = RED + """ 10 | YiraBot Web Crawler v1.0.9 11 | ---------------------------------- 12 | Command Line Web Crawling, Web Scraping and SEO Analysis Tool""" + MAGENTA + """ 13 | 14 | Usage: 15 | yirabot [command] [flag] """ + WHITE + """ 16 | 17 | Commands:""" + CYAN + """ 18 | 19 | crawl 20 | - Crawl: Performs a standard crawl of the specified URL. 21 | - Flags: 22 | -file: Saves data to a text file. 23 | -json: Saves data to a JSON file. 24 | -mobile: Uses a mobile User Agent to crawl 25 | 26 | seo 27 | - SEO Analysis: Analyzes SEO-related elements of the specified URL. 28 | 29 | scrape 30 | - Scrape: Extracts main content from the specified URL. 31 | - Flags: 32 | -file: Saves content data to a text file. 33 | -json: Saves content data to a JSON file. 34 | -mobile: Uses a mobile User Agent to scrape 35 | 36 | get-html 37 | - HTML Copy: Downloads and saves the complete HTML of the specified URL. 38 | 39 | session 40 | - Protected Crawl: Starts a session for crawling authenticated pages. 41 | 42 | """ + LIGHTBLUE_EX + """ 43 | For detailed documentation and examples, visit: 44 | https://github.com/OwenOrcan/YiraBot-Crawler 45 | """ + RESET 46 | print(help_message) 47 | -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- 1 | # YiraBot Code of Conduct 2 | ![YiraBot Logo](https://github.com/OwenOrcan/YiraBot-Crawler/assets/144565916/a62073bb-2cf0-40d5-9383-95eba7b06423) 3 | 4 | 5 | ## Responsible Usage 6 | 7 | 1. **Compliance with Laws and Policies**: 8 | - Users must ensure that all activities conducted with YiraBot comply with the applicable laws and regulations of their jurisdiction. 9 | - Respect website terms of service. If a website prohibits scraping in its terms, users should not use YiraBot to scrape that website. 10 | 11 | 2. **Respecting Robots.txt**: 12 | - YiraBot will respect the directives in the `robots.txt` file of websites. Users should not attempt to bypass these restrictions. 13 | 14 | 3. **Data Privacy**: 15 | - Handle any data collected with YiraBot responsibly. 16 | - Do not use YiraBot to collect sensitive personal information. 17 | 18 | 4. **Reducing Server Load**: 19 | - Avoid excessive requests that could burden server resources. YiraBot is equipped with features to regulate request rates – these should not be circumvented. 20 | 21 | 5. **Intellectual Property Rights**: 22 | - Respect intellectual property rights. Do not use YiraBot to infringe upon copyrights or to duplicate content without permission. 23 | 24 | ## User Conduct 25 | 26 | 1. **No Malicious Use**: 27 | - YiraBot should not be used for any malicious activities such as hacking, spreading malware, or phishing. 28 | 29 | 2. **Transparency**: 30 | - Be transparent about the use of YiraBot when collecting data. If required, inform the website owners about your scraping activities. 31 | 32 | 3. **Ethical Considerations**: 33 | - Consider the ethical implications of your scraping project. Avoid projects that could have negative consequences on individuals or groups. 34 | 35 | ## Liability 36 | 37 | - Users are solely responsible for their actions while using YiraBot. The creators of YiraBot are not liable for any misuse or damage caused by the tool. 38 | 39 | ## Amendments 40 | 41 | - This Code of Conduct may be amended as necessary, and users are expected to keep themselves updated with any changes. 42 | 43 | ## Agreement 44 | 45 | By using YiraBot, users agree to abide by this Code of Conduct and all applicable laws and regulations. 46 | -------------------------------------------------------------------------------- /yirabot/errors.py: -------------------------------------------------------------------------------- 1 | class HTTPError(Exception): 2 | """Exception raised for HTTP errors.""" 3 | 4 | def __init__(self, code): 5 | """Initializes the exception with an HTTP status code. 6 | 7 | Args: 8 | code (int): The HTTP status code that caused the error. 9 | """ 10 | self.code = code 11 | self.message = f"HTTP Error Occurred: {self.code}" 12 | super().__init__(self.message) 13 | 14 | 15 | class ConnectionError(Exception): 16 | """Exception raised for errors in establishing a connection.""" 17 | 18 | def __init__(self, url): 19 | """Initializes the exception with the URL that failed to connect. 20 | 21 | Args: 22 | url (str): The URL connection to which failed. 23 | """ 24 | self.url = url 25 | self.message = f"Connection Error Occurred: {self.url}" 26 | super().__init__(self.message) 27 | 28 | 29 | class TimeoutError(Exception): 30 | """Exception raised for timeout errors.""" 31 | 32 | def __init__(self, url): 33 | """Initializes the exception with the URL that timed out. 34 | 35 | Args: 36 | url (str): The URL that experienced a timeout. 37 | """ 38 | self.url = url 39 | self.message = f"Timeout Error Occurred: {self.url}" 40 | super().__init__(self.message) 41 | 42 | 43 | class RequestError(Exception): 44 | """Exception raised for errors during a request.""" 45 | 46 | def __init__(self, url): 47 | """Initializes the exception with the URL where the request error occurred. 48 | 49 | Args: 50 | url (str): The URL that experienced a request error. 51 | """ 52 | self.url = url 53 | self.message = f"Request Error Occurred: {self.url}" 54 | super().__init__(self.message) 55 | 56 | 57 | class RobotsError(Exception): 58 | """Exception raised for robots.txt blocking errors.""" 59 | 60 | def __init__(self, url): 61 | """Initializes the exception with the URL blocked by robots.txt. 62 | 63 | Args: 64 | url (str): The URL that is blocked by robots.txt. 65 | """ 66 | self.url = url 67 | self.message = f"{self.url} Does Not Allow Crawling (Blocked By robots.txt)" 68 | super().__init__(self.message) 69 | -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | # YiraBot Project Policy 2 | ![yirabot_favicon_bigger](https://github.com/OwenOrcan/YiraBot-Crawler/assets/144565916/f797bc72-73e3-415e-9a03-cfc1be452881) 3 | 4 | ## Introduction 5 | 6 | Welcome to the YiraBot project! This policy outlines guidelines, rules, and expectations for contributors, users, and maintainers of the YiraBot open-source project. By participating in this project, you agree to adhere to these policies. 7 | 8 | ## Contribution Guidelines 9 | 10 | ### Code Contributions 11 | 12 | - Follow the project's coding style and conventions. 13 | - Ensure code quality by writing clear, well-documented, and tested code. 14 | - Submit contributions via pull requests (PRs) and provide descriptive commit messages. 15 | 16 | ### Issue Reporting 17 | 18 | - Report bugs, issues, or feature requests using the project's issue tracker. 19 | - Clearly describe the problem or enhancement you're addressing. 20 | - Include relevant information such as operating system, Python version, and YiraBot version. 21 | 22 | ### Review Process 23 | 24 | - Contributions will be reviewed by project maintainers. 25 | - Be responsive to feedback and make necessary changes in a timely manner. 26 | - Once a PR is approved, it will be merged by a maintainer. 27 | 28 | ## Licensing 29 | 30 | YiraBot is open-source software released under the [MIT License](link_to_license.md). Contributors must agree to license their contributions under the same terms. 31 | 32 | ## Release Policy 33 | 34 | - Releases will be tagged and documented following [semantic versioning](https://semver.org/). 35 | - Each release will include release notes detailing changes, bug fixes, and enhancements. 36 | 37 | ## Security 38 | 39 | - Report any security vulnerabilities or concerns to the project maintainers privately ([email address or contact information]). 40 | - Vulnerabilities will be addressed promptly, and updates will be released as necessary. 41 | 42 | ## Governance 43 | 44 | The YiraBot project is maintained by Owen Orcan. Major project decisions, such as roadmap changes and governance adjustments, will be made collaboratively among maintainers and contributors. 45 | 46 | ## Conclusion 47 | 48 | Thank you for being a part of the YiraBot community. Your contributions and collaboration are essential to the project's success. By following these guidelines and policies, we can work together to create a vibrant and welcoming open-source project. 49 | 50 | If you have any questions or need clarification on any aspect of this policy, please feel free to reach out to the project maintainers. 51 | -------------------------------------------------------------------------------- /SECURITY.md: -------------------------------------------------------------------------------- 1 | # Security Policy for YiraBot 2 | 3 | ## Introduction 4 | 5 | At YiraBot, we take the security of our software and the trust of our users seriously. The purpose of this policy is to provide guidelines on reporting security vulnerabilities and to describe how we address these concerns. 6 | 7 | ## Supported Versions 8 | 9 | Security updates and patches will be applied only to the most recent version of YiraBot. The following table outlines which versions are currently receiving security updates: 10 | 11 | | Version | Supported | 12 | | ------- | ------------------ | 13 | | > 1.0.7 | :white_check_mark: | 14 | | < 1.0.7 | :x: | 15 | 16 | ## Reporting a Vulnerability 17 | 18 | If you believe you have found a security vulnerability in YiraBot, please follow these steps: 19 | 20 | 1. **Do Not Publish the Vulnerability Publicly**: 21 | - Please do not report security vulnerabilities through public GitHub issues, forums, or other public channels. 22 | 23 | 2. **Send a Detailed Report**: 24 | - Email your security findings to [Owen Orcan](mailto:owenorcan@gmail.com) 25 | - Include detailed information about the issue, steps to reproduce, and any other information that might be helpful for understanding and resolving the vulnerability. 26 | 27 | 3. **Wait for Response**: 28 | - After submitting your report, please give us a reasonable amount of time to respond and address the issue before disclosing it to others. 29 | 30 | 4. **Disclosure Handling**: 31 | - Once the vulnerability has been evaluated and addressed, we may discuss it publicly to inform our user base. We will coordinate any public announcement with you to ensure that accurate information is released. 32 | 33 | ## Security Update Process 34 | 35 | Upon receiving a report of a security vulnerability, our team will follow this process: 36 | 37 | 1. **Confirmation and Evaluation**: 38 | - Confirm the issue and assess its impact and severity. 39 | 40 | 2. **Fixing the Issue**: 41 | - Develop a security patch or workaround to address the vulnerability. 42 | 43 | 3. **Releasing an Update**: 44 | - Release an updated version of YiraBot that resolves the issue. 45 | 46 | 4. **Notifying Users**: 47 | - Inform users about the vulnerability and encourage them to update to the latest version. 48 | 49 | 5. **Post-release Analysis**: 50 | - Conduct a post-incident review to learn from the vulnerability and improve future security practices. 51 | 52 | ## Commitment 53 | 54 | We are committed to ensuring the security and privacy of our users. We appreciate your help in keeping YiraBot safe and secure. 55 | 56 | Thank you for supporting YiraBot and its security. 57 | -------------------------------------------------------------------------------- /yirabot/yirabot.py: -------------------------------------------------------------------------------- 1 | from .help import help 2 | from .crawling_functions import * 3 | 4 | 5 | def main(): 6 | """ 7 | Main function to handle command line arguments and orchestrate the execution 8 | of commands based on user input. 9 | """ 10 | if len(sys.argv) < 2: 11 | help() 12 | elif len(sys.argv) > 5: 13 | sys.exit("YiraBot: Too many arguments!") if "-mobile" not in sys.argv else None 14 | else: 15 | command = sys.argv[1].lower() 16 | argument = sys.argv[2] if len(sys.argv) > 2 else None 17 | process_command(command, argument) 18 | 19 | 20 | def process_command(command, argument): 21 | """ 22 | Processes the given command with an optional argument, directing to the appropriate action. 23 | """ 24 | if command == "session": 25 | crawl_protected_page() 26 | elif command in ["get-html", "seo"]: 27 | process_url_command(command, argument) 28 | elif command in ["crawl", "scrape"]: 29 | process_crawl_command(command, argument) 30 | else: 31 | print("YiraBot: Unknown command.") 32 | 33 | 34 | def process_url_command(command, argument): 35 | """ 36 | Handles commands that operate on a single URL, such as downloading HTML or performing SEO analysis. 37 | """ 38 | if not argument: 39 | sys.exit("YiraBot: A URL is required for this command.") 40 | try: 41 | url = validate_url(argument) 42 | if command == "get-html": 43 | get_html(url) 44 | elif command == "seo": 45 | seo_error_analysis(url) 46 | except Exception as e: 47 | sys.exit(f"YiraBot: Error occurred: {e}") 48 | 49 | 50 | def process_crawl_command(command, argument): 51 | """ 52 | Processes commands related to crawling or scraping, handling optional flags for output format and mobile user-agent. 53 | """ 54 | if not argument: 55 | sys.exit("YiraBot: A URL is required for this command.") 56 | url = validate_url(argument) 57 | 58 | # Define the expected options 59 | expected_options = {"-mobile", "-file", "-json"} 60 | 61 | # Extract the actual options (excluding the script name and the primary command) 62 | actual_options = set( 63 | sys.argv[3:]) 64 | 65 | # Check for unexpected arguments 66 | if len(sys.argv) > 4: # Adjusted to account for the primary command and at least one option 67 | # Identify any arguments that are not in the list of expected options 68 | unexpected_args = [arg for arg in actual_options if arg not in expected_options] 69 | 70 | # Proceed only if there are no unexpected arguments and at least one expected option is present 71 | if unexpected_args or not any(option in sys.argv for option in expected_options): 72 | sys.exit("YiraBot: Unexpected argument(s) {}".format(', '.join(unexpected_args))) 73 | 74 | extract = True if "-file" in sys.argv else False 75 | extract_json = True if "-json" in sys.argv else False 76 | mobile = True if "-mobile" in sys.argv else False 77 | 78 | if command == "crawl": 79 | crawl(url, extract=extract, extract_json=extract_json, mobile=mobile) 80 | elif command == "scrape": 81 | crawl_content(url, extract=extract, extract_json=extract_json) 82 | 83 | 84 | def validate_url(url): 85 | """ 86 | Ensures the URL starts with a proper scheme (http or https) and prepends "https://" if missing. 87 | """ 88 | if not url.startswith(("http://", "https://")): 89 | return "https://" + url 90 | return url 91 | 92 | 93 | if __name__ == '__main__': 94 | main() 95 | -------------------------------------------------------------------------------- /yirabot/display_functions.py: -------------------------------------------------------------------------------- 1 | import textwrap 2 | from rich.console import Console 3 | from rich.table import Table 4 | 5 | 6 | def display_crawl_data(data): 7 | """ 8 | Displays the crawled data in a structured table format using Rich library. 9 | 10 | Parameters: 11 | - data (dict): The data to be displayed, expected to be a dictionary with keys 12 | representing data categories and values being the corresponding data. 13 | 14 | Returns: 15 | - None: This function outputs to the console and returns nothing. 16 | """ 17 | console = Console() 18 | table = Table(show_header=True, header_style="bold blue") 19 | table.add_column("Key", style="dim", width=22) 20 | table.add_column("Value", overflow="fold") 21 | 22 | # Add data to the table, wrapping text for the 'Value' column 23 | for key, value in data.items(): 24 | value_str = ', '.join(value) if isinstance(value, list) else str(value) 25 | table.add_row(key.capitalize(), textwrap.fill(value_str, width=80)) 26 | console.print(table) 27 | 28 | 29 | def display_seo_results(title_length, title_status, meta_desc_length, meta_desc_status, keyword_results, headings, 30 | heading_structure_status, images_without_alt, is_responsive, responsiveness_message, 31 | social_media_integration, website_language): 32 | """ 33 | Displays the results of an SEO analysis in a structured table format. Each aspect of the analysis 34 | is represented as a row in the table, detailing the SEO performance and recommendations. 35 | 36 | Parameters: 37 | - title_length (int): Length of the title tag. 38 | - title_status (str): Status of the title tag (e.g., "Good", "Too Short", "Too Long"). 39 | - meta_desc_length (int): Length of the meta description. 40 | - meta_desc_status (str): Status of the meta description (e.g., "Good", "Too Short", "Too Long"). 41 | - keyword_results (dict): A dictionary of top keywords and their occurrences. 42 | - headings (dict): A dictionary of heading tags (e.g., H1, H2) and their count. 43 | - heading_structure_status (str): Status of the heading structure (e.g., "Good", "Improvable"). 44 | - images_without_alt (list): List of images without alt text. 45 | - is_responsive (bool): Indicates if the website is mobile responsive. 46 | - responsiveness_message (str): Descriptive message about the website's responsiveness. 47 | - social_media_integration (dict): A dictionary indicating the presence of social media integration. 48 | - website_language (str): Language of the website. 49 | 50 | Returns: 51 | - None: Outputs to the console. 52 | """ 53 | console = Console() 54 | table = Table(title="SEO Analysis Results", show_header=True, header_style="bold blue") 55 | 56 | table.add_column("Aspect", style="dim", width=20) 57 | table.add_column("Details/Length", justify="right") 58 | table.add_column("Status/Value", overflow="fold") 59 | 60 | table.add_row("Title Tag", str(title_length), title_status) 61 | table.add_row("Meta Description", str(meta_desc_length), meta_desc_status) 62 | 63 | keywords_display = ', '.join([f"{word} ({count})" for word, count in keyword_results]) 64 | table.add_row("Top Keywords", "N/A", keywords_display) 65 | 66 | headings_display = ', '.join([f"{tag}: {count}" for tag, count in headings.items()]) 67 | table.add_row("Headings", "N/A", headings_display if headings else "No Headers") 68 | 69 | no_alt_display = ', '.join(images_without_alt) if images_without_alt else "All images have alt text" 70 | table.add_row("Images without Alt Text", str(len(images_without_alt)), no_alt_display) 71 | 72 | table.add_row("Mobile Responsiveness", "N/A", responsiveness_message) 73 | 74 | social_media_str = ", ".join([platform for platform, integrated in social_media_integration.items() if integrated]) 75 | social_media_str = social_media_str if social_media_str else "No Social Media Integration Detected" 76 | table.add_row("Social Media Integration", "N/A", social_media_str) 77 | 78 | table.add_row("Website Language", "N/A", website_language) 79 | 80 | console.print(table) 81 | -------------------------------------------------------------------------------- /yirabot/helper_functions.py: -------------------------------------------------------------------------------- 1 | import json 2 | import re 3 | import sys 4 | import time 5 | import urllib.robotparser 6 | from bs4 import Tag 7 | from rich import print 8 | import secrets 9 | 10 | USER_AGENTS = [ 11 | "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3", 12 | "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0.3 Safari/605.1.15", 13 | "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0", 14 | "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko", 15 | "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/7046A194A", 16 | "Mozilla/5.0 (iPad; CPU OS 8_4 like Mac OS X) AppleWebKit/600.1.4 (KHTML, like Gecko) Version/8.0 Mobile/12H143 Safari/600.1.4", 17 | "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36", 18 | "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:62.0) Gecko/20100101 Firefox/62.0", 19 | "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Trident/6.0)", 20 | "Opera/9.80 (Windows NT 6.1; WOW64) Presto/2.12.388 Version/12.18", 21 | "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.93 Safari/537.36", 22 | "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36", 23 | ] 24 | 25 | MOBILE_USER_AGENTS = [ 26 | "Mozilla/5.0 (Linux; Android 10; SM-G975F) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.92 Mobile Safari/537.36", 27 | "Mozilla/5.0 (iPhone; CPU iPhone OS 12_0 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/16A366", 28 | ] 29 | 30 | 31 | def extract_domain(url): 32 | """ 33 | Extracts the domain from a given URL using regex pattern matching. 34 | 35 | Args: 36 | url (str): The URL from which to extract the domain. 37 | 38 | Returns: 39 | str: The extracted domain or None if the domain could not be extracted. 40 | """ 41 | pattern = r"https?://([A-Za-z0-9.-]+)" 42 | match = re.search(pattern, url) 43 | return match.group(1) if match else None 44 | 45 | 46 | def is_allowed_by_robots_txt(url): 47 | """ 48 | Determines if crawling the given URL is allowed by the site's robots.txt file. 49 | 50 | Args: 51 | url (str): The URL to check against the robots.txt file. 52 | 53 | Returns: 54 | bool: True if crawling is allowed, False otherwise. 55 | """ 56 | rp = urllib.robotparser.RobotFileParser() 57 | rp.set_url(url + "/robots.txt") 58 | rp.read() 59 | return rp.can_fetch("*", url) 60 | 61 | 62 | def dynamic_delay(response, script=False): 63 | """ 64 | Implements a dynamic delay between requests based on server response to avoid overwhelming the server. 65 | 66 | Args: 67 | response: The HTTP response object from a request. 68 | script (bool): Flag indicating if delay messages should be suppressed. Default is False. 69 | 70 | Returns: 71 | None 72 | """ 73 | try: 74 | if response.status_code == 429: 75 | retry_after = int(response.headers.get("Retry-After", 10)) 76 | print("YiraBot: Website Server Is Overwhelmed, Waiting Before Starting Crawl.") if not script else None 77 | time.sleep(retry_after) 78 | else: 79 | print("YiraBot: Starting Crawl.") if not script else None 80 | time.sleep(1) # Default delay for non-429 responses 81 | except (KeyboardInterrupt, EOFError): 82 | sys.exit("YiraBot: Crawl Aborted") 83 | 84 | 85 | def login_successful(response, expected_response): 86 | """ 87 | Checks if a login request was successful by comparing the response URL to an expected URL. 88 | 89 | Args: 90 | response: The HTTP response object from the login request. 91 | expected_response (str): The URL expected after a successful login. 92 | 93 | Returns: 94 | bool: True if the login was successful, False otherwise. 95 | """ 96 | return response.url == expected_response 97 | 98 | 99 | def write_to_file(data, filename, jsonify=False, html=False): 100 | """ 101 | Writes data to a file in either plain text, JSON, or HTML format. 102 | 103 | Args: 104 | data: The data to write to the file. 105 | filename (str): The name of the file to write to. 106 | jsonify (bool): If True, writes data in JSON format. Default is False. 107 | html (bool): If True, writes data in HTML format. Default is False. 108 | 109 | Returns: 110 | None 111 | """ 112 | with open(filename, 'w') as file: 113 | if html: 114 | file.write(data) 115 | elif jsonify: 116 | json.dump(data, file, indent=4) 117 | else: 118 | for key, value in data.items(): 119 | file.write(f"{key.upper()}\n{'-' * (len(key) + 10)}\n") 120 | if isinstance(value, list): 121 | file.write('\n'.join(f" - {item}" for item in value)) 122 | elif isinstance(value, Tag): 123 | file.write(str(value)) 124 | else: 125 | file.write(value) 126 | file.write("\n\n") 127 | 128 | 129 | def get_random_user_agent(mobile=False): 130 | """ 131 | Returns a random user agent string from a predefined list, with an option for mobile user agents. 132 | 133 | Args: 134 | mobile (bool): If True, selects a user agent from the mobile list. Default is False. 135 | 136 | Returns: 137 | str: A randomly selected user agent string. 138 | """ 139 | return secrets.choice(MOBILE_USER_AGENTS if mobile else USER_AGENTS) 140 | -------------------------------------------------------------------------------- /yirabot/data_extraction_functions.py: -------------------------------------------------------------------------------- 1 | from urllib.parse import urljoin 2 | import requests 3 | from bs4 import BeautifulSoup 4 | 5 | 6 | def extract_crawl_data(soup, url): 7 | """ 8 | Extracts data from a BeautifulSoup object created from a crawled URL, including metadata, 9 | social media tags, links, and images. 10 | 11 | Parameters: 12 | - soup (BeautifulSoup): BeautifulSoup object of the crawled page. 13 | - url (str): The URL being crawled. 14 | 15 | Returns: 16 | - dict: A dictionary with the extracted data, including favicon, meta description, title, 17 | open graph tags, Twitter card tags, canonical URL, internal and external links, image URLs, 18 | and sitemap URLs. 19 | """ 20 | # Extract favicon, meta description, and title 21 | favicon_tag = soup.find("link", {"rel": "icon"}) 22 | meta_description_tag = soup.find("meta", {"name": "description"}) 23 | title_tag = soup.find("title") 24 | 25 | # Extract Open Graph and Twitter card tags 26 | og_tags = [str(tag) for tag in soup.find_all("meta", property=lambda x: x and x.startswith("og:"))] 27 | twitter_tags = [str(tag) for tag in soup.find_all("meta", attrs={"name": lambda x: x and x.startswith("twitter:")})] 28 | 29 | # Extract canonical URL 30 | canonical_tag = soup.find("link", {"rel": "canonical"}) 31 | 32 | # Extract internal and external links 33 | internal_links, external_links = extract_links(soup, url) 34 | 35 | # Extract image URLs 36 | images = [img['src'] for img in soup.find_all('img', src=True)] 37 | 38 | # Compile extracted data into a dictionary 39 | extracted_data = { 40 | 'favicon': favicon_tag.get("href") if favicon_tag else None, 41 | 'meta_description': meta_description_tag.get("content") if meta_description_tag else None, 42 | 'title': title_tag.get_text() if title_tag else None, 43 | 'open_graph_tags': og_tags, 44 | 'twitter_card_tags': twitter_tags, 45 | 'canonical_url': canonical_tag.get("href") if canonical_tag else None, 46 | 'internal_links': internal_links, 47 | 'external_links': external_links, 48 | 'image_urls': images, 49 | 'sitemap_urls': parse_sitemap(url) 50 | } 51 | 52 | return extracted_data 53 | 54 | 55 | def extract_content_data(soup): 56 | """ 57 | Extracts main content data from a BeautifulSoup object, including titles, paragraphs, 58 | headings, and lists. 59 | 60 | Parameters: 61 | - soup (BeautifulSoup): BeautifulSoup object of the crawled page. 62 | 63 | Returns: 64 | - dict: A dictionary with the extracted main content data. 65 | """ 66 | # Extract title, paragraphs, headings, and lists 67 | title_tag = soup.find("title") 68 | paragraphs = [p.get_text().strip() for p in soup.find_all('p')] 69 | headings = [h.get_text().strip() for h in soup.find_all(['h1', 'h2', 'h3', 'h4', 'h5', 'h6'])] 70 | lists = [ul.get_text().strip() for ul in soup.find_all(['ul', 'ol'])] 71 | 72 | # Compile extracted content into a dictionary 73 | content_data = { 74 | 'title': title_tag.get_text() if title_tag else None, 75 | 'paragraphs': paragraphs, 76 | 'headings': headings, 77 | 'lists': lists 78 | } 79 | 80 | return content_data 81 | 82 | 83 | def extract_links(soup, base_url): 84 | """ 85 | Extracts all internal and external links from a BeautifulSoup object and categorizes them. 86 | 87 | Parameters: 88 | - soup (BeautifulSoup): BeautifulSoup object of the crawled page. 89 | - base_url (str): The base URL for resolving relative links. 90 | 91 | Returns: 92 | - tuple: A tuple containing two lists, the first with internal links and the second with external links. 93 | """ 94 | internal_links = [] 95 | external_links = [] 96 | 97 | # Normalize the base URL to prevent duplication issues 98 | base_url = base_url.rstrip('/') + '/' 99 | 100 | for link in soup.find_all('a', href=True): 101 | href = link['href'].split('#')[0] # Remove URL fragments 102 | href = href.split('?')[0] # Remove URL query parameters 103 | 104 | # Categorize and normalize links 105 | if href.startswith('/'): 106 | full_link = urljoin(base_url, href.lstrip('/')) 107 | internal_links.append(full_link) 108 | elif href.startswith('http') or href.startswith('https'): 109 | external_links.append(href) 110 | 111 | return internal_links, external_links 112 | 113 | 114 | def parse_sitemap(url, script=False): 115 | """ 116 | Parses the sitemap of a given URL to extract and return all contained URLs. 117 | If 'script' is True, the 'url' parameter is treated as the full sitemap link. 118 | 119 | Parameters: 120 | - url (str): The URL to the sitemap if 'script' is True, or the base URL whose sitemap is to be parsed. 121 | - script (bool): Indicates whether the provided URL is the direct link to the sitemap. 122 | 123 | Returns: 124 | - list: A list of URLs found in the sitemap. If no sitemap is found, returns an 125 | appropriate message. 126 | """ 127 | if script: 128 | # Directly use the provided URL for the sitemap 129 | try: 130 | response = requests.get(url, timeout=10) 131 | if response.status_code == 200: 132 | soup = BeautifulSoup(response.content, 'xml') 133 | return [element.text for element in soup.find_all("loc")] 134 | except requests.exceptions.RequestException: 135 | return [] 136 | else: 137 | # Standard sitemap URLs 138 | sitemap_urls = [url + "/sitemap.xml", url + "/static/sitemap.xml"] 139 | 140 | # Attempt to parse standard sitemaps 141 | for sitemap_url in sitemap_urls: 142 | try: 143 | response = requests.get(sitemap_url, timeout=10) 144 | if response.status_code == 200: 145 | soup = BeautifulSoup(response.content, 'xml') 146 | return [element.text for element in soup.find_all("loc")] 147 | except requests.exceptions.RequestException: 148 | continue # Proceed to next URL on failure 149 | 150 | return [] 151 | -------------------------------------------------------------------------------- /yirabot/__init__.py: -------------------------------------------------------------------------------- 1 | from . import errors 2 | from .seo_functions import * 3 | from .helper_functions import * 4 | from .data_extraction_functions import * 5 | from urllib.error import HTTPError 6 | from requests import RequestException, Timeout 7 | from bs4 import BeautifulSoup 8 | from .data_extraction_functions import parse_sitemap 9 | 10 | 11 | # noinspection PyUnboundLocalVariable 12 | class Yirabot: 13 | def __init__(self): 14 | self.urls = None 15 | self.sitemap_url = None 16 | 17 | def seo_analysis(self, url, session=None): 18 | """ 19 | Performs SEO analysis on the given URL, extracting and analyzing various SEO factors. 20 | """ 21 | headers = {'User-Agent': get_random_user_agent()} 22 | try: 23 | response = session.get(url, headers=headers) if session else requests.get(url, headers=headers, timeout=10) 24 | response.raise_for_status() 25 | 26 | soup = BeautifulSoup(response.content, 'html.parser') 27 | data = { 28 | 'title_length': analyze_title(soup), 29 | 'meta_desc_length': analyze_meta_description(soup), 30 | 'headings': analyze_headings(soup), 31 | 'images_without_alt': analyze_images_for_alt_text(soup), 32 | 'keyword_results': keyword_analysis(get_combined_text(soup)), 33 | 'is_responsive': check_mobile_responsiveness(url), 34 | 'social_media_integration': check_social_media_integration(url), 35 | 'website_language': check_website_language(url), 36 | } 37 | return data 38 | 39 | except ConnectionError: 40 | raise errors.ConnectionError(url) 41 | except Timeout: 42 | raise errors.TimeoutError(url) 43 | except HTTPError: 44 | raise errors.HTTPError(response.status_code) 45 | except RequestException: 46 | raise errors.RequestError(url) 47 | 48 | def crawl(self, url, session=None, force=False): 49 | headers = {'User-Agent': get_random_user_agent()} 50 | try: 51 | if not force: 52 | if not is_allowed_by_robots_txt(url): 53 | raise errors.RobotsError(url) 54 | 55 | response = session.get(url, headers=headers) if session else requests.get(url, headers=headers, timeout=10) 56 | dynamic_delay(response, script=True) 57 | response.raise_for_status() 58 | soup = BeautifulSoup(response.text, features="html5lib") 59 | 60 | meta_description_tag = soup.find("meta", {"name": "description"}) 61 | favicon_tag = soup.find("link", {"rel": "icon"}) 62 | title_tag = soup.find("title") 63 | og_tags = [str(tag) for tag in soup.find_all("meta", property=lambda x: x and x.startswith("og:"))] 64 | twitter_tags = [str(tag) for tag in 65 | soup.find_all("meta", attrs={"name": lambda x: x and x.startswith("twitter:")})] 66 | canonical_tag = soup.find("link", {"rel": "canonical"}) 67 | internal_links, external_links = extract_links(soup, url) 68 | images = [img['src'] for img in soup.find_all('img', src=True)] 69 | 70 | data = { 71 | 'favicon': favicon_tag.get("href") if favicon_tag else None, 72 | 'meta_description': meta_description_tag.get("content") if meta_description_tag else None, 73 | 'title': title_tag.get_text() if title_tag else None, 74 | 'open_graph_tags': og_tags, 75 | 'twitter_card_tags': twitter_tags, 76 | 'canonical_url': canonical_tag.get("href") if canonical_tag else None, 77 | 'internal_links': internal_links, 78 | 'external_links': external_links, 79 | 'image_urls': images, 80 | 'sitemap_urls': parse_sitemap(url) 81 | } 82 | if type(data) is None: 83 | self.crawl(url, session, force) # sometimes the function returns none, when that happens, call that shit again. 84 | else: 85 | return data 86 | 87 | except HTTPError: 88 | raise errors.HTTPError(response.status_code) 89 | except ConnectionError: 90 | raise errors.ConnectionError(url) 91 | except Timeout: 92 | raise errors.TimeoutError(url) 93 | except RequestException: 94 | raise errors.RequestError(url) 95 | 96 | def scrape(self, url, session=None, force=False): 97 | """ 98 | Specifically crawls a URL for its main content like paragraphs, headings, and lists. 99 | Parameters: 100 | url (str): The URL to be crawled for content. 101 | session (Session, optional): Requests session for authenticated crawling. 102 | Returns: 103 | Data: Dict 104 | """ 105 | headers = {'User-Agent': get_random_user_agent()} 106 | try: 107 | if not force: 108 | if not is_allowed_by_robots_txt(url): 109 | raise errors.RobotsError(url) 110 | 111 | response = session.get(url, headers=headers) if session else requests.get(url, headers=headers, timeout=10) 112 | dynamic_delay(response, script=True) 113 | response.raise_for_status() 114 | 115 | soup = BeautifulSoup(response.text, features="html5lib") 116 | 117 | title_tag = soup.find("title") 118 | paragraphs = [p.get_text().strip() for p in soup.find_all('p')] 119 | headings = [h.get_text().strip() for h in soup.find_all(['h1', 'h2', 'h3', 'h4', 'h5', 'h6'])] 120 | lists = [ul.get_text().strip() for ul in soup.find_all(['ul', 'ol'])] 121 | 122 | data = { 123 | 'title': title_tag.get_text() if title_tag else None, 124 | 'paragraphs': paragraphs, 125 | 'headings': headings, 126 | 'lists': lists 127 | } 128 | if type(data) is None: 129 | print("Server did not response, trying again.") 130 | self.scrape(url, session, force) 131 | else: 132 | return data 133 | 134 | except HTTPError: 135 | raise errors.HTTPError 136 | except ConnectionError: 137 | raise errors.ConnectionError 138 | except Timeout: 139 | raise errors.TimeoutError 140 | except RequestException: 141 | raise errors.RequestError 142 | 143 | def validate(self, sitemap_url): 144 | self.sitemap_url = sitemap_url 145 | try: 146 | self.urls = parse_sitemap(self.sitemap_url, script=True) 147 | except ConnectionError: 148 | raise errors.ConnectionError(sitemap_url) 149 | except HTTPError: 150 | raise errors.HTTPError(sitemap_url) 151 | except TimeoutError: 152 | raise errors.TimeoutError(sitemap_url) 153 | except RequestException: 154 | raise errors.RequestError(sitemap_url) 155 | responses = {} 156 | 157 | for url in self.urls: 158 | response = requests.head(url, allow_redirects=True, timeout=10) 159 | response_code = response.status_code 160 | responses[url] = response_code 161 | return responses 162 | -------------------------------------------------------------------------------- /yirabot/seo_functions.py: -------------------------------------------------------------------------------- 1 | import re 2 | from collections import Counter, defaultdict 3 | from urllib.parse import unquote 4 | import requests 5 | from bs4 import BeautifulSoup 6 | from rich import print 7 | from .display_functions import display_seo_results 8 | 9 | # ============================================================ 10 | # SEO ANALYSIS FUNCTIONS 11 | # Functions dedicated to performing SEO analysis. 12 | # ============================================================ 13 | STOPWORDS = set( 14 | ["a", "an", "the", "and", "or", "in", "of", "by", "for", "with", "on", "at", "to", "from", "up", "down", "in", 15 | "out", "on", "off", "over", "under", "again", "further", "then", "once", "here", "there", "when", "where", "why", 16 | "how", "all", "any", "both", "each", "few", "more", "most", "other", "some", "such", "no", "nor", "not", "only", 17 | "own", "same", "so", "than", "too", "very", "your", "that"]) 18 | 19 | 20 | def check_website_language(url): 21 | try: 22 | response = requests.get(url, timeout=10) 23 | soup = BeautifulSoup(response.content, 'html.parser') 24 | 25 | html_tag = soup.find('html') 26 | if html_tag and 'lang' in html_tag.attrs: 27 | language = html_tag.attrs['lang'] 28 | return language 29 | else: 30 | return "Language attribute not found" 31 | except requests.exceptions.RequestException as e: 32 | return f"Error occurred: {e}" 33 | 34 | 35 | def check_social_media_integration(url): 36 | try: 37 | response = requests.get(url, timeout=10) 38 | soup = BeautifulSoup(response.content, 'html.parser') 39 | 40 | social_media = { 41 | "Facebook": False, 42 | "Twitter": False, 43 | "Instagram": False, 44 | "LinkedIn": False, 45 | "YouTube": False 46 | } 47 | 48 | for link in soup.find_all('a', href=True): 49 | href = link['href'] 50 | if "facebook.com" in href: 51 | social_media["Facebook"] = True 52 | elif "twitter.com" in href: 53 | social_media["Twitter"] = True 54 | elif "instagram.com" in href: 55 | social_media["Instagram"] = True 56 | elif "linkedin.com" in href: 57 | social_media["LinkedIn"] = True 58 | elif "youtube.com" in href: 59 | social_media["YouTube"] = True 60 | 61 | return social_media 62 | except requests.exceptions.RequestException as e: 63 | return {"Error": str(e)} 64 | 65 | 66 | def check_mobile_responsiveness(url): 67 | try: 68 | response = requests.get(url,timeout=10) 69 | soup = BeautifulSoup(response.content, 'html.parser') 70 | viewport_meta = soup.find("meta", {"name": "viewport"}) 71 | 72 | if viewport_meta and "width=device-width" in viewport_meta.get("content", ""): 73 | return True, "Mobile Responsive" 74 | else: 75 | return False, "Not Mobile Responsive" 76 | except requests.exceptions.RequestException as e: 77 | return False, f"Error occurred: {e}" 78 | 79 | 80 | def check_link_status(url, session=None): 81 | """ 82 | Checks the status of a link. 83 | Returns a tuple of (is_broken, status_code, reason). 84 | """ 85 | try: 86 | response = session.head(url, allow_redirects=True, timeout=10) if session else requests.head(url, allow_redirects=True, timeout=10) 87 | if response.status_code == 404: 88 | return True, 404, "Not Found" 89 | elif 300 <= response.status_code < 400: 90 | return True, response.status_code, "Unexpected Redirect" 91 | return False, response.status_code, "OK" 92 | except requests.RequestException as e: 93 | return True, None, f"Error: {e}" 94 | 95 | 96 | def keyword_analysis(text): 97 | """ 98 | Analyzes the text for the most frequent non-stopwords. 99 | """ 100 | words = re.findall(r'\w+', text.lower()) 101 | filtered_words = [word for word in words if word not in STOPWORDS] 102 | word_counts = Counter(filtered_words) 103 | return word_counts.most_common(5) 104 | 105 | 106 | def is_seo_friendly_url(url): 107 | """ 108 | Determines if the given URL is SEO-friendly based on common best practices. 109 | Returns a tuple (is_friendly, reason). 110 | """ 111 | decoded_url = unquote(url) 112 | 113 | if len(decoded_url) > 75: 114 | return False, "URL is too long (>75 characters)" 115 | if '_' in decoded_url: 116 | return False, "URL contains underscores instead of hyphens" 117 | 118 | if not re.match(r'^[a-z0-9\.-]+[a-z0-9/-]*$', decoded_url): 119 | return False, "URL contains invalid characters" 120 | 121 | if '?' in decoded_url or '&' in decoded_url: 122 | return False, "URL contains excessive parameters" 123 | 124 | return True, "SEO-friendly" 125 | 126 | 127 | def analyze_title(soup): 128 | title_tag = soup.find('title') 129 | title_length = len(title_tag.get_text()) if title_tag else 0 130 | if title_length == 0: 131 | return 0, "Missing or Empty" 132 | return title_length, "Too Long (Max 60)" if title_length > 60 else "OK" 133 | 134 | 135 | def analyze_meta_description(soup): 136 | meta_description_tag = soup.find("meta", {"name": "description"}) 137 | meta_desc_length = len(meta_description_tag.get("content")) if meta_description_tag else 0 138 | if meta_desc_length == 0: 139 | return 0, "Missing or Empty" 140 | return meta_desc_length, "Too Long (Max 300)" if meta_desc_length > 300 else "OK" 141 | 142 | 143 | def analyze_headings(soup): 144 | headings = defaultdict(int) 145 | heading_sequence = [] 146 | for heading in soup.find_all(['h1', 'h2', 'h3', 'h4', 'h5', 'h6']): 147 | headings[heading.name] += 1 148 | heading_sequence.append(heading.name) 149 | 150 | return headings, evaluate_heading_structure(headings, heading_sequence) 151 | 152 | 153 | def evaluate_heading_structure(headings, heading_sequence): 154 | if 'h1' not in headings or headings['h1'] > 1: 155 | return "Improper Usage of H1 Tags" 156 | 157 | last_heading_level = 0 158 | for heading in heading_sequence: 159 | current_level = int(heading[1]) 160 | if current_level > last_heading_level + 1: 161 | return f"Jump in heading levels detected at {heading}" 162 | last_heading_level = current_level 163 | 164 | return "OK" 165 | 166 | 167 | def analyze_images_for_alt_text(soup): 168 | images = soup.find_all('img') 169 | return [img['src'] for img in images if img.get('alt') is None] 170 | 171 | 172 | def seo_error_analysis(url, session=None): 173 | try: 174 | print("YiraBot: Starting SEO Analysis") 175 | response = session.get(url, timeout=10) if session else requests.get(url, timeout=10) 176 | soup = BeautifulSoup(response.content, 'html.parser') 177 | 178 | title_length, title_status = analyze_title(soup) 179 | meta_desc_length, meta_desc_status = analyze_meta_description(soup) 180 | headings, heading_structure_status = analyze_headings(soup) 181 | images_without_alt = analyze_images_for_alt_text(soup) 182 | 183 | # Combine texts for keyword analysis 184 | combined_text = get_combined_text(soup) 185 | keyword_results = keyword_analysis(combined_text) 186 | 187 | # Mobile Responsiveness Check 188 | is_responsive, responsiveness_message = check_mobile_responsiveness(url) 189 | 190 | # Social Media Integration Check 191 | social_media_integration = check_social_media_integration(url) 192 | 193 | # Language Check 194 | website_language = check_website_language(url) 195 | 196 | # Display results 197 | display_seo_results( 198 | title_length, title_status, 199 | meta_desc_length, meta_desc_status, 200 | keyword_results, 201 | headings, heading_structure_status, 202 | images_without_alt, 203 | is_responsive, responsiveness_message, 204 | social_media_integration, 205 | website_language 206 | ) 207 | 208 | except requests.exceptions.RequestException as e: 209 | print(f"Error occurred during SEO analysis: {e}") 210 | 211 | 212 | def get_combined_text(soup): 213 | title_text = soup.find('title').get_text() if soup.find('title') else "" 214 | meta_description_text = soup.find("meta", {"name": "description"}).get("content", "") if soup.find("meta", { 215 | "name": "description"}) else "" 216 | headings_text = ' '.join([h.get_text() for h in soup.find_all(['h1', 'h2', 'h3', 'h4', 'h5', 'h6'])]) 217 | return title_text + " " + meta_description_text + " " + headings_text 218 | -------------------------------------------------------------------------------- /yirabot/crawling_functions.py: -------------------------------------------------------------------------------- 1 | from getpass import getpass 2 | from requests.exceptions import HTTPError, ConnectionError, Timeout, RequestException 3 | from .data_extraction_functions import * 4 | from .display_functions import * 5 | from .helper_functions import * 6 | from .saving_functions import * 7 | from .seo_functions import * 8 | 9 | 10 | # ============================================================ 11 | # CRAWLING AND ANALYSIS FUNCTIONS 12 | # Core functions for crawling web pages and specific analyses. 13 | # ============================================================ 14 | 15 | 16 | def crawl(url, extract=False, extract_json=False, session=None, mobile=False): 17 | """ 18 | Crawls a given URL, extracting various information like metadata, links, and images, 19 | and optionally saves the data to a file in text or JSON format. 20 | 21 | Args: 22 | url (str): The URL to be crawled. 23 | extract (bool): If True, saves extracted data in text format. Defaults to False. 24 | extract_json (bool): If True, saves extracted data in JSON format. Defaults to False. 25 | session (Session, optional): A session object for authenticated requests. 26 | mobile (bool): If True, uses a mobile user agent for the request. 27 | 28 | Returns: 29 | None: Outputs to the console or files, based on parameters. 30 | """ 31 | # Set user agent based on the 'mobile' flag 32 | headers = {'User-Agent': get_random_user_agent(mobile=mobile)} 33 | 34 | try: 35 | # Check if crawling is allowed by robots.txt 36 | if not is_allowed_by_robots_txt(url): 37 | print("YiraBot: Crawling forbidden by robots.txt") 38 | return 39 | 40 | # Make the request using a session if provided, else use requests.get 41 | response = session.get(url, headers=headers) if session else requests.get(url, headers=headers, timeout=10) 42 | 43 | # Handle server-induced delays 44 | dynamic_delay(response) 45 | 46 | print("YiraBot: Using Mobile User Agent") if mobile else None 47 | time.sleep(1) if mobile else None 48 | 49 | # Raise an exception for bad responses 50 | response.raise_for_status() 51 | 52 | # Parse the response content with BeautifulSoup 53 | soup = BeautifulSoup(response.text, features="html5lib") 54 | 55 | # Extract data from the parsed HTML 56 | data = extract_crawl_data(soup, url) 57 | 58 | # Save or display the extracted data 59 | if extract or extract_json: 60 | save_crawl_data(data, url, extract, extract_json) 61 | else: 62 | display_crawl_data(data) 63 | 64 | except (HTTPError, ConnectionError, Timeout, RequestException) as e: 65 | print(f"YiraBot: Error occurred: {e}") 66 | except Exception as e: 67 | print(f"YiraBot: An unexpected error occurred: {e}") 68 | 69 | 70 | def crawl_content(url, extract=False, extract_json=False, session=None, mobile=False): 71 | """ 72 | Crawls a URL specifically for its main content, such as paragraphs, headings, and lists, 73 | and optionally saves the data in text or JSON format. 74 | 75 | Args: 76 | url (str): The URL to be crawled for content. 77 | extract (bool): If True, saves extracted data in text format. Defaults to False. 78 | extract_json (bool): If True, saves extracted data in JSON format. Defaults to False. 79 | session (requests.Session, optional): A session object for authenticated requests. 80 | 81 | Returns: 82 | None: Outputs to the console or files, based on parameters. 83 | """ 84 | headers = {'User-Agent': get_random_user_agent(mobile=mobile)} 85 | 86 | try: 87 | # Check if the URL is allowed by robots.txt 88 | if not is_allowed_by_robots_txt(url): 89 | print("YiraBot: Crawling forbidden by robots.txt") 90 | return 91 | 92 | # Perform the request with the provided session or a new session 93 | response = session.get(url, headers=headers, timeout=10) if session else requests.get(url, headers=headers, timeout=10) 94 | 95 | # Handle server-induced delays 96 | dynamic_delay(response) 97 | 98 | print("YiraBot: Using Mobile User Agent") if mobile else None 99 | time.sleep(1) if mobile else None 100 | 101 | # Check for successful response 102 | response.raise_for_status() 103 | 104 | # Parse the response content 105 | soup = BeautifulSoup(response.text, features="html5lib") 106 | 107 | # Extract content data from the parsed HTML 108 | data = extract_content_data(soup) 109 | 110 | # Decide whether to save or display the extracted data 111 | if extract or extract_json: 112 | save_crawl_data(data, url, extract, extract_json) 113 | else: 114 | display_crawl_data(data) 115 | 116 | except (HTTPError, ConnectionError, Timeout, RequestException) as e: 117 | print(f"YiraBot: Error occurred: {e}") 118 | except Exception as e: 119 | print(f"YiraBot: An unexpected error occurred: {e}") 120 | 121 | 122 | def crawl_protected_page(): 123 | """ 124 | Handles the crawling of protected web pages by facilitating user authentication 125 | and offering a choice of crawling methods for protected content. 126 | """ 127 | try: 128 | session = requests.Session() 129 | print("YiraBot: Session Started.") 130 | 131 | def login(): 132 | """ 133 | Prompts the user for login details and constructs the credentials payload. 134 | """ 135 | login_url = input("Enter the login page URL: ").strip() 136 | if not login_url.startswith("https://"): 137 | sys.exit("YiraBot: Secure HTTPS connection required for login.") 138 | 139 | expected_response = input("Enter the success redirect URL: ").strip() 140 | if not expected_response.startswith("https://"): 141 | expected_response = "https://" + expected_response 142 | 143 | credentials = { 144 | input("Enter the username form input name: ").strip(): input("Enter your username: ").strip(), 145 | input("Enter the password form input name: ").strip(): getpass("Enter your password: ").strip() 146 | } 147 | 148 | return login_url, expected_response, credentials 149 | 150 | login_url, expected_response, credentials = login() 151 | response = session.post(login_url, data=credentials, timeout=10) 152 | response.raise_for_status() 153 | 154 | if not login_successful(response, expected_response): 155 | print("Login failed, please check your credentials.") 156 | return 157 | 158 | print(f"YiraBot: Successfully logged into {extract_domain(login_url)}") 159 | 160 | while True: 161 | protected_url = input("Enter the URL of the protected page: ").strip() 162 | if not protected_url.startswith("https://"): 163 | print("YiraBot: Secure HTTPS connection required.") 164 | continue 165 | 166 | crawl_choice = input("Select Crawl Method:\n1: Crawl\n2: Scrape\n3: SEO\nInput: ") 167 | try: 168 | crawl_choice = int(crawl_choice) 169 | if crawl_choice == 1: 170 | crawl(protected_url, session=session) 171 | elif crawl_choice == 2: 172 | crawl_content(protected_url, session=session) 173 | elif crawl_choice == 3: 174 | seo_error_analysis(protected_url, session=session) 175 | else: 176 | print("YiraBot: Invalid input, please enter a number from the choices.") 177 | except ValueError: 178 | print("YiraBot: Please enter a valid number for the crawl choice.") 179 | except KeyboardInterrupt: 180 | print("\nYiraBot: Session Stopped") 181 | 182 | 183 | def get_html(url): 184 | """ 185 | Downloads the complete HTML content of the specified URL and saves it as an HTML file. 186 | 187 | Args: 188 | url (str): The URL of the webpage to download. 189 | 190 | Returns: 191 | None: The function saves the HTML content to a file and outputs the file name. 192 | """ 193 | try: 194 | response = requests.get(url, timeout=10) 195 | response.raise_for_status() # Ensure the request was successful 196 | html = response.text 197 | 198 | # Create a safe filename from the URL and current timestamp 199 | safe_url = url.replace("https://", "").replace("http://", "").replace("/", "_") 200 | timestamp = datetime.now().strftime("%Y-%m-%d") 201 | filename = f"{safe_url}.{timestamp}.html" 202 | 203 | # Use the write_to_file function, assuming it supports HTML content 204 | write_to_file(html, filename, html=True) 205 | 206 | print(f"YiraBot: HTML file '{filename}' created.") 207 | 208 | except requests.exceptions.HTTPError as e: 209 | print(f"YiraBot Error: HTTP error occurred while trying to get HTML. {e}") 210 | except requests.exceptions.ConnectionError: 211 | print("YiraBot Error: Connection error occurred while trying to get HTML.") 212 | except requests.exceptions.Timeout: 213 | print("YiraBot Error: Timeout occurred while trying to get HTML.") 214 | except requests.exceptions.RequestException as e: 215 | print(f"YiraBot Error: An error occurred while trying to get HTML. {e}") 216 | except Exception as e: 217 | print(f"YiraBot Error: An unexpected error occurred. {e}") 218 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 2 | ![YiraBot ](https://github.com/OwenOrcan/YiraBot-Crawler/assets/144565916/54cfd22f-9bc8-4505-b3fe-ad6dd0de83d4) 3 | 4 | # [📰 Read the Latest Release Notes](https://github.com/OwenOrcan/YiraBot-Crawler/releases) 5 | 6 | 7 | 8 | 9 | 10 | Buy Me A Coffee 11 | [![PyPI - Version](https://img.shields.io/pypi/v/YiraBot?style=for-the-badge&logo=PyPI)](https://pypi.org/project/YiraBot/) 12 | [![PyPI - Downloads](https://img.shields.io/pypi/dm/YiraBot?style=for-the-badge)](https://pypistats.org/packages/yirabot) 13 | [![GitHub Repo stars](https://img.shields.io/github/stars/OwenOrcan/YiraBot-Crawler?style=for-the-badge&logo=github&color=pink)](https://github.com/OwenOrcan/YiraBot-Crawler/stargazers) 14 | 15 | 16 | 17 | # YiraBot README 18 | 19 | ## Introduction 20 | YiraBot is a versatile Python package designed for crawling, scraping, and analyzing web pages. It provides a range of functionalities from basic webpage crawling to detailed SEO analysis, mobile responsiveness checks, and social media integration verification. This document serves as a comprehensive guide to using YiraBot, including installation, usage examples, and an explanation of its core features. 21 | 22 | ## Installation 23 | 24 | Before you can use YiraBot, you need to ensure Python is installed on your system. YiraBot is compatible with Python 3.6 and above. You can install YiraBot using pip: 25 | 26 | ```bash 27 | pip install yirabot 28 | ``` 29 | 30 | ## Features 31 | 32 | YiraBot offers a range of functionalities, including: 33 | 34 | - **Web Crawling and Scraping**: Crawls web pages to extract metadata, links, images, and specific content. 35 | - **SEO Analysis**: Performs SEO checks on web pages, including title, meta descriptions, headings, and keyword analysis. 36 | - **Mobile Responsiveness Check**: Verifies if a web page is mobile responsive. 37 | - **Social Media Integration Check**: Checks for the presence of social media platform integration on a web page. 38 | - **Protected Page Crawling**: Supports crawling of pages that require authentication. 39 | 40 | ## Usage 41 | 42 | ### Command Line Interface 43 | 44 | YiraBot can be invoked directly from the command line with various commands and options: 45 | 46 | ```bash 47 | yirabot [options] 48 | ``` 49 | 50 | #### Commands 51 | 52 | - `crawl`: Crawls a given URL to extract data. 53 | - `scrape`: Specifically extracts main content from a URL. 54 | - `seo`: Performs an SEO analysis of the specified web page. 55 | - `get-html`: Downloads and saves the complete HTML content of a web page. 56 | 57 | #### Options 58 | 59 | - `-mobile`: Uses a mobile user agent for requests. 60 | - `-file`: Saves the extracted data in text format. 61 | - `-json`: Saves the extracted data in JSON format. 62 | 63 | ### Examples 64 | 65 | **Crawling a Web Page** 66 | 67 | To crawl a web page and display extracted data: 68 | 69 | ```bash 70 | yirabot crawl example.com 71 | ``` 72 | 73 | **Saving Crawled Data** 74 | 75 | To crawl a web page and save the extracted data in JSON format: 76 | 77 | ```bash 78 | yirabot crawl example.com -json 79 | ``` 80 | 81 | **Performing SEO Analysis** 82 | 83 | To perform an SEO analysis on a web page: 84 | 85 | ```bash 86 | yirabot seo example.com 87 | ``` 88 | 89 | **Checking Mobile Responsiveness** 90 | 91 | Mobile responsiveness is part of the SEO analysis. To check if a page is mobile responsive: 92 | 93 | ```bash 94 | yirabot seo example.com 95 | ``` 96 | 97 | Look for the "Mobile Responsiveness" section in the output. 98 | 99 | **Crawling Protected Pages** 100 | 101 | YiraBot also supports crawling pages that require authentication. This process is more involved and requires setting up a session: 102 | 103 | ```bash 104 | yirabot session 105 | ``` 106 | 107 | Follow the interactive prompts to enter login details and choose the crawling method. 108 | 109 | ## Understanding Command Flags and Their Impact 110 | 111 | When using YiraBot from the command line, you can modify its behavior with various flags. These flags allow you to tailor the crawling and analysis process to your specific needs. Here’s how the functionality changes with different flags: 112 | 113 | - **-mobile**: Simulates a mobile user agent, which is essential for testing mobile responsiveness and seeing how a site presents itself on mobile devices. 114 | - **-file**: Saves the extracted data in a text file. This is useful for documentation purposes or further analysis. 115 | - **-json**: Saves the extracted data in a JSON file, offering a structured format that's easy to integrate with other tools and systems. 116 | 117 | Each flag is designed to offer flexibility and control over the crawling and analysis process, ensuring that you can obtain the data you need in the format that best suits your project. 118 | 119 | YiraBot is a powerful tool for developers, SEO specialists, and anyone interested in web page analysis. By following this guide, you should be able to install YiraBot, understand its capabilities, and start using it for your web crawling and analysis needs. 120 | 121 | 122 | # YiraBot Python Module 123 | ![Yirabot Request Process](https://github.com/OwenOrcan/YiraBot-Crawler/assets/144565916/840a5c52-9bc2-443d-aa9b-4043db62a4c2) 124 | 125 | 126 | ## Core Functionalities 127 | 128 | ### 1. SEO Analysis (`seo_analysis`) 129 | 130 | - **Description**: Performs an in-depth SEO analysis on a given URL. 131 | - **Key Features**: 132 | - Analyzes various SEO factors such as title length, meta description length, headings usage, images without alt text, keyword analysis, mobile responsiveness, social media integration, and website language. 133 | - Utilizes a user-agent from `get_random_user_agent()` for requests, simulating different browser types for more accurate SEO testing. 134 | 135 | ### 2. Crawling (`crawl`) 136 | 137 | - **Description**: Crawls a given URL to collect comprehensive data about the page. 138 | - **Key Features**: 139 | - Extracts information such as favicon, meta description, title, Open Graph tags, Twitter card tags, canonical URL, internal and external links, and image URLs. 140 | - Optionally bypasses robots.txt restrictions with the `force` parameter. 141 | - Includes a `dynamic_delay` mechanism to adjust request timing based on the server's response, simulating more natural browsing behavior. 142 | 143 | ### 3. Scraping (`scrape`) 144 | 145 | - **Description**: Targets the main content of a webpage, extracting paragraphs, headings, and lists. 146 | - **Key Features**: 147 | - Designed to scrape content while optionally ignoring robots.txt restrictions through the `force` parameter. 148 | - Focuses on extracting textual content critical for content analysis or SEO purposes. 149 | 150 | ### 4. Sitemap Validation (`validate`) 151 | 152 | - **Description**: Validates URLs found in a specified sitemap. 153 | - **Key Features**: 154 | - Parses the sitemap URL to extract all contained URLs, then checks each URL for accessibility, capturing their HTTP response status. 155 | - Useful for ensuring that all URLs in a sitemap are accessible and do not lead to errors. 156 | 157 | ## Advanced Features 158 | 159 | - **Session Management**: Supports the use of sessions via the requests library for more efficient HTTP requests by reusing TCP connections. 160 | - **User-Agent Randomization**: Mimics different browsers by setting a random user-agent for each request, improving the likelihood of obtaining accurate website content as seen by users. 161 | - **Dynamic Request Delay**: Implements a `dynamic_delay` function to adjust the frequency of requests dynamically, reducing the risk of being blocked by the target server. 162 | - **Robots.txt Respect**: By default, respects robots.txt policies for crawling and scraping, unless overridden, ensuring ethical web scraping practices. 163 | - **Recursive Error Handling**: For methods like crawl and scrape, there's a mechanism to retry the operation in certain failure scenarios, aiming to improve data retrieval success rates. 164 | 165 | ## Usage Scenarios 166 | 167 | - **SEO Audits**: Yirabot can be used to conduct SEO audits on web pages, analyzing critical factors that influence search engine rankings. 168 | - **Content Extraction**: Ideal for extracting specific content from web pages, such as text, images, and links, for analysis or repurposing. 169 | - **Website Health Checks**: Validates sitemaps and checks the accessibility of URLs, which is crucial for website maintenance and SEO. 170 | 171 | ## Implementation Notes 172 | 173 | To use Yirabot, instantiate the class and call the desired method with appropriate parameters. For SEO analysis and content scraping, pass the target URL and, if available, a session object for authenticated requests. 174 | 175 | When performing actions that might be restricted by robots.txt, consider the ethical implications and the legality of bypassing such restrictions with the `force` parameter. 176 | 177 | This class serves as a versatile tool for developers, SEO specialists, and content managers looking to automate the process of web data extraction and analysis, enhancing SEO strategies and website maintenance practices. 178 | 179 | # Examples Using YiraBot Class 180 | ## SEO Analysis 181 | ```python 182 | from yirabot import Yirabot 183 | 184 | bot = Yirabot() 185 | url = "https://example.com" 186 | seo_data = bot.seo_analysis(url) 187 | 188 | # Example of processing SEO data 189 | print("Title Length:", seo_data['title_length']) 190 | print("Meta Description Length:", seo_data['meta_desc_length']) 191 | print("Responsive:", "Yes" if seo_data['is_responsive'] else "No") 192 | ``` 193 | ## Crawling 194 | ```python 195 | url = "https://example.com" 196 | crawl_data = bot.crawl(url, force=True) #Only use force in ethical situations 197 | 198 | # Displaying some extracted data 199 | print("Page Title:", crawl_data['title']) 200 | print("Number of Internal Links:", len(crawl_data['internal_links'])) 201 | print("Number of External Links:", len(crawl_data['external_links'])) 202 | ``` 203 | ## Scraping 204 | ```python 205 | url = "https://example.com/blog" 206 | content_data = bot.scrape(url) 207 | 208 | # Displaying the first paragraph and heading 209 | print("First Paragraph:", content_data['paragraphs'][0]) 210 | print("First Heading:", content_data['headings'][0]) 211 | ``` 212 | ## Sitemap Validation 213 | ```python 214 | sitemap_url = "https://example.com/sitemap.xml" 215 | validation_results = bot.validate(sitemap_url) 216 | 217 | # Checking and printing inaccessible URLs 218 | inaccessible_urls = {url: status for url, status in validation_results.items() if status != 200} 219 | print("Inaccessible URLs:", inaccessible_urls) 220 | ``` 221 | 222 | 223 | ## Contributions 224 | 225 | Contributions to the YiraBot project are welcomed. Feel free to fork the repository, make your changes, and submit pull requests. 226 | 227 | All contributors must follow the [Contribution Policy](https://github.com/OwenOrcan/YiraBot-Crawler/blob/master/CONTRIBUTING.md) to ensure a smooth and collaborative development process. 228 | 229 | ### License 230 | YiraBot is open-sourced software licensed under the [GNU General Public License (Version 3)](LICENSE) 231 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | YiraBot is a Command Line Tool and Python Module for Web Scraping, Crawling and SEO Analysis 635 | Copyright (C) 2024 Owen Orcan 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | YiraBot Copyright (C) 2024 Owen Orcan 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | --------------------------------------------------------------------------------