Klimets Artyom

MANIFEST.in

@@ -0,0 +1 @@
+include rss_reader/times-new-roman.ttf

README.md

@@ -0,0 +1,6 @@
+# Command-line RSS reader
+
+Final task for the Introduction to Python Epam courses.
+
+* [Code coverage](Test_coverage.png) -- Code coverage percentage with tests
+* [Json schema](json_schema.json) -- Scheme of JSON structure

json_schema.json

@@ -0,0 +1,73 @@
+{
+  "$schema": "http://json-schema.org/draft-04/schema#",
+  "type": "object",
+  "properties": {
+    "News": {
+      "type": "array",
+      "items": [
+        {
+          "type": "object",
+          "properties": {
+            "Feed#": {
+              "type": "object",
+              "title": "Feed",
+              "properties": {
+                "Feed source": {
+                  "type": "string",
+                  "title": "Source ",
+                  "description": "Source where the news came from"
+                },
+                "Title": {
+                  "type": "string",
+                  "title": "Title",
+                  "description": "Title of the feed"
+                },
+                "Date": {
+                  "type": "string",
+                  "title": "Publication date",
+                  "description": "Date when the news was published"
+                },
+                "Link": {
+                  "type": "string",
+                  "title": "Link",
+                  "description": "News link"
+                },
+                "Description": {
+                  "type": "string",
+                  "title": "Description",
+                  "description": "A description of the feed"
+                },
+                "Media_content": {
+                  "type": "array",
+                  "title": "Image links",
+                  "description": "Array of image links", 
+                  "items": [
+                    {
+                      "type": "string"
+                      "title": "URL",
+                      "description": "URL of image"
+                    }
+                  ]
+                }
+              },
+              "required": [
+                "Feed source",
+                "Title",
+                "Date",
+                "Link",
+                "Description",
+                "Media_content"
+              ]
+            }
+          },
+          "required": [
+            "Feed0"
+          ]
+        }
+      ]
+    }
+  },
+  "required": [
+    "News"
+  ]
+}

requirements.txt

@@ -0,0 +1,7 @@
+beautifulsoup4>=4.8.0
+validator_collection>=1.3.7
+sqlalchemy>=1.2.7
+feedparser>=5.2.1
+fpdf>=1.7.2
+httplib2>=0.14.0
+Pillow>=6.2.1

rss_reader/__init__.py

@@ -0,0 +1,2 @@
+'''Package implements command-line RSS reader with some advanced features'''
+__version__ = '1.4'

rss_reader/__main__.py

@@ -0,0 +1,3 @@
+'''Module contain entry point to the package'''
+from .cli import main
+main()

rss_reader/cli.py

@@ -0,0 +1,98 @@
+'''Module implements a CLI of the application'''
+import logging
+from argparse import ArgumentParser
+from datetime import datetime
+from os import path, makedirs
+from validator_collection.checkers import is_url
+from .rssreader import RSSReader
+from collections import defaultdict
+
+
+def main():
+    '''Entry point of the app'''
+    parser = adding_arguments()
+    args = parser.parse_args()
+    init_logging(args.verbose)
+    source, date = validate_arguments(args)
+    configuration_for_conversion = mk_config_for_conversion(args.to_pdf, args.to_html)
+    rss = RSSReader(source, args.limit, date, args.json, configuration_for_conversion, args.all)
+    rss.exec()
+
+
+def adding_arguments():
+    '''Function initializes arguments of the RSS Reader'''
+    parser = ArgumentParser(description='Pure Python command-line RSS reader')
+    parser.add_argument('source', metavar='source', type=str, help='RSS URL')
+    parser.add_argument('--version', action='version', version='ver 1.4', help='Print version info')
+    parser.add_argument('--limit', metavar='LIMIT', type=int, help='Amount of news output')
+    parser.add_argument('--verbose', action='store_true', help='Print all logs in stdout')
+    parser.add_argument('--json', action='store_true', help='Print news in json format')
+    parser.add_argument('--date', type=str, help='Print news published on a given day')
+    parser.add_argument('--to-pdf', type=str, help='Conversion news to the PDF format')
+    parser.add_argument('--to-html', type=str, help='Conversion news to the HTML format')
+    parser.add_argument('--all', action='store_true', help='Getting all cached news.\
+                    Compatible with the following arguments: --verbose, --json, --to-pdf, --to-html')
+    return parser
+
+
+def init_logging(verbose):
+    '''Logging initialization'''
+    if verbose:
+        logging.basicConfig(format='%(module)s %(asctime)s  %(message)s',
+                            datefmt='%I:%M:%S', level=logging.INFO)
+
+
+def validate_arguments(args):
+    '''Function validates of all received arguments'''
+    source = validate_url(args.source)
+    date = None
+    if args.date:
+        date = validate_date(args.date)
+    if args.to_html:
+        validate_path(args.to_html)
+    if args.to_pdf:
+        validate_path(args.to_pdf)
+    return source, date
+
+
+def validate_url(source):
+    '''Function validates the URL that is the source of the news'''
+    logging.info('URL validation')
+    if not is_url(source):
+        raise ValueError('Invalid url')
+    return source
+
+
+def validate_date(date):
+    '''Function validates date'''
+    logging.info('Date validation')
+    try:
+        checked_date = datetime.strptime(date, '%Y%m%d').date()
+        return checked_date
+    except ValueError as e:
+        print('Wrong date')
+
+
+def validate_path(dir_for_save):
+    '''Function validates the path where the exported file will be saved'''
+    if path.exists(dir_for_save):
+        logging.info(f'Directory {dir_for_save} already exists')
+    else:
+        makedirs(dir_for_save)
+        logging.info(f'Create directory {dir_for_save} for saving file')
+    return dir_for_save
+
+
+def mk_config_for_conversion(pdf, html):
+    '''Function creates a dictionary which contain which type of files and where news will be saved'''
+    logging.info('Making dict with configuration of conversion')
+    dict_with_directories = defaultdict(str)
+    if pdf:
+        dict_with_directories['pdf'] = pdf
+    if html:
+        dict_with_directories['html'] = html
+    return dict_with_directories
+
+
+if __name__ == "__main__":
+    main()