Onishchouk Elia

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2019 Elia Onishchouk
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

MANIFEST.in

@@ -0,0 +1 @@
+include requirements.txt

README.md

@@ -0,0 +1,31 @@
+# Introduction to Python. Hometask
+
+RSS reader is a command-line utility which receives [RSS](wikipedia.org/wiki/RSS) URL and prints results in human-readable format.
+
+
+Utility provides the following interface:
+```shell
+usage: rss_reader.py [-h] [--version] [--json] [--verbose] [--limit LIMIT]
+                     source
+
+Pure Python command-line RSS reader.
+
+positional arguments:
+  source         RSS URL
+
+optional arguments:
+  -h, --help     show this help message and exit
+  --version      Print version info
+  --json         Print result as JSON in stdout
+  --verbose      Outputs verbose status messages
+  --limit LIMIT  Limit news topics if this parameter provided
+
+```
+
+With the argument `--json` the program converts the news into [JSON](https://en.wikipedia.org/wiki/JSON) format.(Still in progress)
+
+With the argument `--limit` the program prints given number of news.
+
+With the argument `--verbose` the program prints all logs in stdout.(Still in progress)
+
+Withe the argument `--version` the program prints in stdout it's current version and complete it's work.

rss_reader/rss_reader.py

@@ -0,0 +1,110 @@
+import argparse
+import feedparser
+import html
+from bs4 import BeautifulSoup
+import json
+from tqdm import tqdm
+
+import version
+
+class Item:
+    def __init__(self, title, date, link, description, links):
+        self.title=title
+        self.date=date
+        self.link=link
+        self.description=description
+        self.links=links
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description='Pure Python command-line RSS reader.')
+    parser.add_argument('source', type=str, help='RSS URL')
+
+    parser.add_argument('--version', action='version', version='%(prog)s v'+version.__version__, help='Print version info')
+    parser.add_argument('--json', action='store_true', help='Print result as JSON in stdout')
+    parser.add_argument('--verbose', action='store_true', help='Outputs verbose status messages')
+    parser.add_argument('--limit', type=int, default=-1, help='Limit news topics if this parameter provided')
+    args = parser.parse_args()
+    NewsFeed = feedparser.parse(args.source)
+    if args.limit==-1 :
+        args.limit=len(NewsFeed.entries)
+
+
+    d=json.dumps([{"title": "title1","description": "description1","link": "link2","pubDate": "pubDate1","source": {"url1": "url1","__url2": "url2"}}, {"title": "title2","description": "description2","link": "link2","pubDate": "pubDate2","source": {"url1": "url1","__url2": "url2"}}])
+    open("out.json","w").write(d)
+    for i in range(args.limit) :
+
+        entry = NewsFeed.entries[i]
+        soup = html.unescape(BeautifulSoup(entry['summary'], "html.parser"))
+
+        print ('Title: {0}'.format(html.unescape(entry['title'])))    
+        print ('Date: {0}'.format(entry['published']))
+        print ('Link: {0}'.format(entry['link']))
+        print ()
+
+        j=1
+        images_links=[]
+        for img in soup.findAll('img') :       
+
+            if 'alt' in img.attrs:
+                alt=img['alt']
+                if alt!='':
+                    final=' [image {0} | {1}] '.format(j,alt)
+                else:
+                    final=' [image {0}]'.format(j)    
+
+            else:
+                final=' [image {0}]'.format(j)
+            src=img['src']
+            images_links.append('[{0}]: {1}'.format(j, src))
+            j+=1
+
+            soup.find('img').replace_with(final)
+        j=1
+        href_links=[]
+        for href in soup.findAll('a'):
+            if 'href' in href.attrs:
+                link=href['href']
+                if href.text!='':
+                    final=' [link {0} | {1}] '.format(j,href.text)
+                else:
+                    final=' [link {0}] '.format(j)  
+                soup.find('a').replace_with(final)
+                href_links.append('[{0}]: {1}'.format(j, link))
+                j+=1
+        j=1
+        video_links=[]
+        for video in soup.findAll('iframe'):
+            if 'src' in video.attrs:
+                link=video['src']
+                final=' [video {0}] '.format(j)
+                soup.find('iframe').replace_with(final)
+                video_links.append('[{0}]: {1}'.format(j, link))
+                j+=1    
+        links={'images_links':images_links,'href_links':href_links,'video_links':video_links}
+        item=Item(html.unescape(entry['title']),entry['published'],entry['link'],soup.text,links)
+        print(soup.text)
+        print ()
+        print ()
+        if href_links:
+            print ('Links:')
+            for link in href_links:
+                print (link)
+        if images_links:
+            print ()
+            print ('Images:')
+            for link in images_links:
+                print (link)
+
+        if video_links:
+            print ()
+            print ('Videos:')
+            for link in video_links:
+                print (link)
+        print ()
+        print ()
+        print ()
+
+if __name__ == '__main__':
+
+    main()

rss_reader/version.py

@@ -0,0 +1 @@
+__version__="0.8"

setup.py

@@ -0,0 +1,33 @@
+import setuptools
+from rss_reader import version
+
+with open("README.md", "r") as fh:
+    long_description = fh.read()
+
+setuptools.setup(
+    name="rss-reader", 
+    version=version.__version__,
+    author="Elia Onishchouk",
+    author_email="elias0n@mail.ru",
+    description="A simple command-line RSS reader",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://github.com/el0ny/PythonHomework",
+    packages=setuptools.find_packages(),
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    entry_points={  
+
+        'console_scripts': [
+
+            'rss_reader = rss_reader.rss_reader:main',
+
+        ],
+
+    },
+    install_requires=['feedparser', 'bs4'],
+    python_requires='>=3.6',
+)