fixed pypi, enabled cli usage w/ 0.0.4, changed package name, using poetry

Author: paulpierre

README.md

@@ -4,12 +4,12 @@
  |   |   |  (   |       (     |     (   |  \ \  \ /   |   __/  |    
 _|  _|  _| \__._|      \___| _|    \__._|   \_/\_/   _| \___| _|    
 
-----------------------------
-md_crawler.py by @paulpierre
-----------------------------
+---------------------------------
+markdown_crawler - by @paulpierre
+---------------------------------
 A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page
 https://github.com/paulpierre
-https://x.com/paulpierre                                                           
+https://x.com/paulpierre                                                        
 ```
 <br><br>
 
@@ -39,23 +39,23 @@ If you wish to simply use it in the CLI, you can run the following command:
 
 Install the package
 ```
-pip install md_crawler
+pip install markdown-crawler
 ```
 
 Execute the CLI
 ```
-md_crawler -t 5 -d 3 -b ./markdown https://en.wikipedia.org/wiki/Morty_Smith
+markdown-crawler -t 5 -d 3 -b ./markdown https://en.wikipedia.org/wiki/Morty_Smith
 ```
 
 To run from the github repo, once you have it checked out:
 ```
-pip install -r requirements.txt
-python3 md_crawler.py -t 5 -d 3 -b ./markdown https://en.wikipedia.org/wiki/Morty_Smith
+pip install .
+markdown-crawler -t 5 -d 3 -b ./markdown https://en.wikipedia.org/wiki/Morty_Smith
 ```
 
 Or use the library in your own code:
 ```
-from md_crawler import md_crawl
+from markdown_crawler import md_crawl
 url = 'https://en.wikipedia.org/wiki/Morty_Smith'
 md_crawl(url, max_depth=3, num_threads=5, base_path='markdown')
 ```
@@ -73,7 +73,7 @@ md_crawl(url, max_depth=3, num_threads=5, base_path='markdown')
 
 The following arguments are supported
 ```
-usage: md_crawler [-h] [--max-depth MAX_DEPTH] [--num-threads NUM_THREADS] [--base-path BASE_PATH] [--debug DEBUG]
+usage: markdown-crawler [-h] [--max-depth MAX_DEPTH] [--num-threads NUM_THREADS] [--base-path BASE_PATH] [--debug DEBUG]
                   [--target-content TARGET_CONTENT] [--target-links TARGET_LINKS] [--valid-paths VALID_PATHS]
                   [--domain-match DOMAIN_MATCH] [--base-path-match BASE_PATH_MATCH]
                   base-url
@@ -82,7 +82,7 @@ usage: md_crawler [-h] [--max-depth MAX_DEPTH] [--num-threads NUM_THREADS] [--ba
 <br><br>
 
 # 📝 Example
-Take a look at [example.py](https://github.com/paulpierre/md_crawler/blob/main/example.py) for an example
+Take a look at [example.py](https://github.com/paulpierre/markdown-crawler/blob/main/example.py) for an example
 implementation of the library. In this configuration we set:
 - `max_depth` to 3. We will crawl the base URL and 3 levels of children
 - `num_threads` to 5. We will use 5 parallel(ish) threads to crawl the website
@@ -95,13 +95,13 @@ implementation of the library. In this configuration we set:
 
 And when we run it we can view the progress
 <br>
-> ![cli](https://github.com/paulpierre/md_crawler/blob/main/img/ss_crawler.png?raw=true)
+> ![cli](https://github.com/paulpierre/markdown-crawler/blob/main/img/ss_crawler.png?raw=true)
 
 We can see the progress of our files in the `markdown` directory locally
-> ![md](https://github.com/paulpierre/md_crawler/blob/main/img/ss_dir.png?raw=true)
+> ![md](https://github.com/paulpierre/markdown-crawler/blob/main/img/ss_dir.png?raw=true)
 
 And we can see the contents of the HTML converted to markdown
-> ![md](https://github.com/paulpierre/md_crawler/blob/main/img/ss_markdown.png?raw=true)
+> ![md](https://github.com/paulpierre/markdown-crawler/blob/main/img/ss_markdown.png?raw=true)
 
 <br><br>
 # ❤️ Thanks 
@@ -134,4 +134,4 @@ SOFTWARE.
 <br><br>
 
 ###  html2text credits
-`md_crawler` makes use of html2text by the late and legendary [Aaron Swartz]([email protected]). The original source code can be found [here](http://www.aaronsw.com/2002/html2text). A modification was implemented to make it compatible with Python 3.x. It is licensed under GNU General Public License (GPL).
+`markdown_crawler` makes use of html2text by the late and legendary [Aaron Swartz]([email protected]). The original source code can be found [here](http://www.aaronsw.com/2002/html2text). A modification was implemented to make it compatible with Python 3.x. It is licensed under GNU General Public License (GPL).

dist/markdown-crawler-0.0.4.tar.gz

@@ -1,4 +1,4 @@
-from md_crawler import md_crawl
+from markdown_crawler import md_crawl
 url = 'https://rickandmorty.fandom.com/wiki/Evil_Morty'
 print(f'🕸️ Starting crawl of {url}')
 md_crawl(

dist/markdown_crawler-0.0.4-py3-none-any.whl

@@ -1,9 +1,8 @@
 from bs4 import BeautifulSoup
 import urllib.parse
 import threading
-from md_crawler import html2text
+from markdown_crawler import html2text
 import requests
-import argparse
 import logging
 import queue
 import time
@@ -291,7 +290,7 @@ def md_crawl(
         logging.basicConfig(level=logging.DEBUG)
         logger.debug('🐞 Debugging enabled')
 
-    logger.info(f'{BANNER}\n\n🕸️ Crawling {base_url} at ⏬ depth {max_depth} with 🧵 {num_threads} threads')
+    logger.info(f'🕸️ Crawling {base_url} at ⏬ depth {max_depth} with 🧵 {num_threads} threads')
 
     # Validate the base URL
     if not is_valid_url(base_url):
@@ -336,44 +335,4 @@ def md_crawl(
     for t in threads:
         t.join()
 
-    logger.info('🏁 All threads have finished')
-
-
-def main():
-    arg_parser = argparse.ArgumentParser()
-    arg_parser.description = 'A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page'
-    arg_parser.add_argument('--max-depth', '-d', required=False, default=3, type=int)
-    arg_parser.add_argument('--num-threads', '-t', required=False, default=5, type=int)
-    arg_parser.add_argument('--base-dir', '-b', required=False, default='markdown', type=str)
-    arg_parser.add_argument('--debug', '-e', required=False, type=bool, default=False)
-    arg_parser.add_argument('--target-content', '-c', required=False, type=str, default=None)
-    arg_parser.add_argument('--target-links', '-l', required=False, type=str, default=DEFAULT_TARGET_LINKS)
-    arg_parser.add_argument('--valid-paths', '-v', required=False, type=str, default=None)
-    arg_parser.add_argument('--domain-match', '-m', required=False, type=bool, default=True)
-    arg_parser.add_argument('--base-path-match', '-p', required=False, type=bool, default=True)
-    arg_parser.add_argument('base_url', type=str)
-
-    # ----------------
-    # Parse target arg
-    # ----------------
-    args = arg_parser.parse_args()
-
-    md_crawl(
-        args.base_url,
-        max_depth=args.max_depth,
-        num_threads=args.num_threads,
-        base_dir=args.base_path,
-        target_content=args.target_content.split(',') if args.target_content and ',' in args.target_content else None,
-        target_links=args.target_links.split(',') if args.target_links and ',' in args.target_links else [args.target_links],
-        valid_paths=args.valid_paths.split(',') if args.valid_paths and ',' in args.valid_paths else None,
-        is_domain_match=args.domain_match,
-        is_base_path_match=args.base_match,
-        is_debug=args.debug
-    )
-
-
-# --------------
-# CLI entrypoint
-# --------------
-if __name__ == '__main__':
-    main()
+    logger.info('🏁 All threads have finished')

example.py

@@ -0,0 +1,47 @@
+import argparse
+from markdown_crawler import (
+    md_crawl,
+    DEFAULT_TARGET_LINKS,
+    BANNER
+)
+
+def main():
+    print(BANNER)
+    arg_parser = argparse.ArgumentParser()
+    arg_parser.add_argument('--max-depth', '-d', required=False, default=3, type=int, help='Max depth of child links to crawl')
+    arg_parser.add_argument('--num-threads', '-t', required=False, default=5, type=int, help='Number of threads to use for crawling')
+    arg_parser.add_argument('--base-dir', '-b', required=False, default='markdown', type=str, help='Base directory to save markdown files in')
+    arg_parser.add_argument('--debug', '-e', required=False, type=bool, default=False, help='Enable debug mode')
+    arg_parser.add_argument('--target-content', '-c', required=False, type=str, default=None, help='CSS target path of the content to extract from each page')
+    arg_parser.add_argument('--target-links', '-l', required=False, type=str, default=DEFAULT_TARGET_LINKS, help='CSS target path containing the links to crawl')
+    arg_parser.add_argument('--valid-paths', '-v', required=False, type=str, default=None, help='Comma separated list of valid relative paths to crawl, (ex. /wiki,/categories,/help')
+    arg_parser.add_argument('--domain-match', '-m', required=False, type=bool, default=True, help='Crawl only links that match the base domain')
+    arg_parser.add_argument('--base-path-match', '-p', required=False, type=bool, default=True, help='Crawl only links that match the base path of the base_url specified in CLI')
+    arg_parser.add_argument('base_url', type=str, help='Base URL to crawl (ex. 🐍🎷 https://rickandmorty.fandom.com/wiki/Evil_Morty')
+    if len(arg_parser.parse_args().__dict__.keys()) == 0:
+        arg_parser.print_help()
+        return
+    # ----------------
+    # Parse target arg
+    # ----------------
+    args = arg_parser.parse_args()
+
+    md_crawl(
+        args.base_url,
+        max_depth=args.max_depth,
+        num_threads=args.num_threads,
+        base_dir=args.base_path,
+        target_content=args.target_content.split(',') if args.target_content and ',' in args.target_content else None,
+        target_links=args.target_links.split(',') if args.target_links and ',' in args.target_links else [args.target_links],
+        valid_paths=args.valid_paths.split(',') if args.valid_paths and ',' in args.valid_paths else None,
+        is_domain_match=args.domain_match,
+        is_base_path_match=args.base_match,
+        is_debug=args.debug
+    )
+
+
+# --------------
+# CLI entrypoint
+# --------------
+if __name__ == '__main__':
+    main()

md_crawler/__init__.py renamed to markdown_crawler/__init__.py

@@ -0,0 +1,27 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+
+[project]
+name = "markdown-crawler"
+version = "0.0.4"
+authors = [
+  { name="Paul Pierre", email="[email protected]" },
+]
+description = "A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page"
+readme = "README.md"
+requires-python = ">=3.4"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/paulpierre/markdown-crawler"
+"Bug Tracker" = "https://github.com/paulpierre/markdown-crawler/issues"
+"Twitter" = "https://twitter.com/paulpierre"
+
+[project.scripts]
+markdown-crawler = "markdown_crawler.cli:main"