Kirill_Stepanishin_kirill.stpn.by@gmail.com

final_task/README.md

@@ -1,3 +1,63 @@
-# Your readme here
-Some text.
-Checkout how to write this file using *markdown*.
+# Pyhton RSS reader
+
+## How to install:
+**1st way**
+* You need to have git installed. Run:
+> $ git clone https://github.com/kirill-stp/FinalTaskRssParser.git
+* when you are in your workspace folder. Then run:
+> $ python setup.py install
+* when you are in **final task** folder
+**2nd way:**
+* To install this package, you must have Python added to your user environment.
+* Download the distribution archive
+* run $ pip install ./python_rss_reader-1.0.tar.gz  
+
+## Usage:
+This app provide following interface:
+```shell
+usage: rss_reader.py [-h] [--version] [--json] [--verbose] [--limit LIMIT]
+                     [--date DATE]
+                     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
+  --limit LIMIT  Limit news topics
+  --date DATE    Read news from given date (YMD)
+```
+for example:
+> $ python3 rss_reader.py https://news.yahoo.com/rss --date 20191120 --limit 2 --verbose --json
+
+## JSON structure:
+```shell
+{'Article 1': {'date':time.struct_time,
+               'images': {'image desription': 'url'},
+               'link': '',
+               'summary': '',
+               'title': ''},
+ 'Article 2': {date': time.struct_time,
+               'images': {'image desription': 'url'},
+               'link': '',
+               'summary': '',
+               'title': ''},
+ 'Feed': 'Feeds from 'url'',
+ 'Link': 'rss link'}
+
+```
+## Local news storage:
+When **--date** argument is not provided, the news that you received will be saved to the database, if it wasn’t there yet.
+Cached data stored in rss_reder/cached_feeds.db file using **shelve**. Database stores dictionary-like object, where the key is the publication date and the value is instance of **Article** class.
+
+## HTML and PDF converting:
+You can use **--to-html** and **--to-pdf** to save feed in given format. If there is no internet connection, it will paste image links (clickable in pdf). If we have internet connection, then program will download images and paste it to the file. Titles in pdf also clickable.
+
+## Colorizing
+This program can colorize normal and json output, using **termcolor**. To add some color to your life, use **--colorize** argument
+

final_task/rss_reader/args_creater.py

@@ -0,0 +1,17 @@
+import argparse
+
+
+def arguments():
+    """create command line arguments"""
+
+    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 1.0', 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')
+    parser.add_argument('--limit', type=int, help='Limit news topics')
+    parser.add_argument('--date', type=str, help='Read news from given date')
+    parser.add_argument('--to-html', action='store_true', help='Save feed in html format')
+    parser.add_argument('--to-pdf', action='store_true', help='Save feed in pdf format')
+    parser.add_argument('--colorize', action='store_true', help='Print result in colorize mode')
+    return parser.parse_args()

final_task/rss_reader/article.py

@@ -0,0 +1,87 @@
+from string_operations import *
+import logging
+import datetime
+from termcolor import colored
+
+
+
+class Article:
+    """single article class"""
+
+    def __init__(self, parsed, source):
+        """receive parsed article and extracts data from it"""
+        self.title = make_string_readable(parsed.title)
+        self.link = parsed.link
+        self.feed_link = source
+        self.published = extract_date(parsed)
+        summary_ = extract_topic_info_from_summary(parsed.summary)
+        self.summary = make_string_readable(summary_)
+        self.media = parsed.media_content
+
+        description_ = extract_image_info_from_summary(parsed.summary)
+        self.media_description = make_string_readable(description_)
+
+    def print_readable_article(self, is_colored):
+        """print article to stdout in human-readable format"""
+        print( "_" * 79)
+        date = self.published
+        date_for_print = f'{date.tm_year}/{date.tm_mon}/{date.tm_mday}, {date.tm_hour}:{date.tm_min}:{date.tm_sec}\n'
+        if is_colored:
+            print(colored(date_for_print, 'red'))
+        else:
+            print(date_for_print)
+
+        cutted_title = cut_string_to_length_with_space(self.title, 77)
+        for str_number, string in enumerate(cutted_title):
+            if str_number + 1 == len(cutted_title):
+                if is_colored:
+                    print(colored(string + '[1]', 'red'))
+                else:
+                    print(string + '[1]')
+            else:
+                if is_colored:
+                    print(colored(string, 'red'))
+                else:
+                    print(string)
+
+        # images description and their links numbers (like [2] - [5])
+        str_number_of_img = ' '
+        if len(self.media) > 1:
+            str_number_of_img = f' - [{len(self.media) + 1}]'
+        images_and_link_numbers = f'\n\nImages:\n{self.media_description} [2] - {str_number_of_img}\n'
+        if is_colored:
+            print(colored(images_and_link_numbers, 'blue'))
+        else:
+            print(images_and_link_numbers)
+
+
+        cutted_summary = cut_string_to_length_with_space(self.summary, 79)
+        for string in cutted_summary:
+            if is_colored:
+                print(colored(string, 'cyan'))
+            else:
+                print(string)
+
+        # Links of article and images
+        if is_colored:
+            print(colored('\n\nLinks:\n[1]' + self.link, 'green'))
+        else:
+            print('\n\nLinks:\n[1]', self.link)
+        for number, img in enumerate(self.media):
+            if is_colored:
+                print(colored(f'[{number+2}] ' + img['url'], 'green'))
+            else:
+                print(f'[{number+2}]', img['url'])
+
+        print("_" * 79)
+
+    def make_article_json(self):
+        """convert article data in json format"""
+        json = {
+            'images': {self.media_description: img['url'] for img in self.media},
+            'link': self.link,
+            'summary': self.summary,
+            'date': self.published,
+            'title': self.title,
+        }
+        return json

final_task/rss_reader/check_func.py

@@ -0,0 +1,14 @@
+import requests
+import exceptions as ex
+
+
+def internet_connection_check():
+    url = 'http://www.google.com/'
+    timeout = 5
+    is_internet = True
+    try:
+        requests.get(url, timeout=timeout)
+    except requests.ConnectionError:
+        is_internet = False
+    finally:
+        return is_internet

final_task/rss_reader/exceptions.py

@@ -0,0 +1,17 @@
+class InvalidURLAddress(Exception):
+    pass
+
+
+class NoInternetConnection(Exception):
+    pass
+
+
+class EmptyDataBase(Exception):
+    pass
+
+
+class DateNotInDatabase(Exception):
+    pass
+
+class PathError(Exception):
+    pass