Anna_Gonchar_raphaelkyzy@gmail.com

.gitignore

@@ -0,0 +1,17 @@
+# Editors
+.idea/
+
+# Environments
+venv/
+
+# Byte-compiled / optimized
+__pycache__/
+*.py[cod]
+
+*.log
+
+# Distribution / packaging
+*.egg-info/
+build/
+develop-eggs/
+dist/

final_task/README.md

@@ -1,3 +1,53 @@
-# Your readme here
-Some text.
-Checkout how to write this file using *markdown*.
+# RSS reader
+RSS reader is a command-line utility which receives RSS URL and prints results in human-readable
+format.
+
+[The source for this project is available here](https://github.com/AnnaPotter/FinalTaskRssParser).
+
+
+### Installation
+$ pip install rss-reader-Anna-Gonchar
+
+### Usage
+$ rss-reader (-h | --help)
+
+    Show help message and exit
+
+$ rss-reader <RSS-SOURCE-LINK>
+
+    Print rss feeds in human-readable format
+
+$ rss-reader --version
+
+    Print version info
+
+$ rss-reader --json
+
+    Print result as JSON in stdout
+
+$ rss-reader.py --verbose
+
+    Outputs verbose status messages
+
+$ rss-reader.py --limit LIMIT
+
+    Limit news topics, if this parameter provided
+
+$ rss-reader.py --date DATE
+
+    Gets a date in %Y%m%d format. Print news from the specified date
+    and source (<RSS-SOURCE-LINK>), if it specified
+
+$ rss-reader.py --to-pdf PATH_TO_PDF
+
+    Gets file path. Convert news to pdf and save them to pdf file on the specified path
+
+$ rss-reader.py --to-html PATH_TO_HTML
+
+    Gets file path. Convert news to html and save them to html file on the specified path
+
+### Storage
+All the pieces of news received from the source are saved to the binary file.
+Shelve module is used for this. It saves object with the specific key to the file.
+The key is the rss news publication date, the value is the news.
+

final_task/rss_reader/README.md

@@ -0,0 +1,26 @@
+#JSON structure:
+
+{
+
+     [
+
+               {      
+                 "feed_title": feed title,
+                 "feed_language": feed language,            
+                 "title": news title,
+                 "summary": news content,
+                 "date": news publication date,
+                 "link": news link },
+
+               {  
+                 "feed_title": feed title,
+                 "feed_language": feed language, 
+                 "title": news title,
+                 "summary": news content,
+                 "date": news publication date,
+                 "link": news link },
+
+               ...
+
+     ]
+}

final_task/rss_reader/__init__.py

@@ -0,0 +1 @@
+

final_task/rss_reader/action_functions.py

@@ -0,0 +1,179 @@
+""" Module of creation functions and action functions.
+
+    Functions:
+    create_logger(com_line_args) -> logger
+    get_com_line_args() -> com_line_args
+    get_news(command_line_args, logger) -> news_collection
+    print_news_stdout(news_collection) -> None
+    print_news_json(news_collection) -> None
+    print_news(news_collection, com_line_args, logger) -> None
+    print_cache_news(news_collection, logger) -> None
+    print_cache_news_json(news_collection, logger) -> None
+    convert_date(date_str, logger) -> str_date
+    clean_str(string) -> clean_string """
+
+import feedparser
+from bs4 import BeautifulSoup
+import html
+import argparse
+import json
+import logging
+from datetime import datetime
+from exceptions import Error
+from models import NewsEntry
+from dataclasses import asdict
+from validation_functions import check_limit_arg
+
+
+def create_logger(com_line_args):
+    """Create logger function.
+
+       Creates a logger considering the --verbose argument. """
+    # Create a logger
+    logger = logging.getLogger("rss_reader_logger")
+    logger.setLevel(logging.DEBUG)
+
+    # Create handlers
+    c_handler = logging.StreamHandler()
+    f_handler = logging.FileHandler("file.log")
+
+    # Check --verbose argument
+    if com_line_args.verbose:
+        c_handler.setLevel(logging.DEBUG)
+    else:
+        c_handler.setLevel(logging.ERROR)
+
+    # Create formatters and add it to handlers
+    c_format = logging.Formatter('%(name)s - %(levelname)s - %(message)s')
+    f_format = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+    c_handler.setFormatter(c_format)
+    f_handler.setFormatter(f_format)
+
+    # Add handlers to the logger
+    logger.addHandler(f_handler)
+    logger.addHandler(c_handler)
+
+    return logger
+
+
+def get_com_line_args():
+    """ Function to get command line arguments. """
+    parser = argparse.ArgumentParser(description="Pure Python command-line RSS reader.", add_help=True)
+    parser.add_argument("--date", type=convert_date,
+                        help="Gets a date in %%Y%%m%%d format. Print news from the specified date.")
+    parser.add_argument("--to-html", type=str,
+                        help="Gets file path. Convert news to html and save them to html file.")
+    parser.add_argument("--to-pdf", type=str,
+                        help="Gets file path. Convert news to pdf and save them to pdf file.")
+    parser.add_argument("--version", action="store_true", 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, help="Limit news topics if this parameter provided")
+    parser.add_argument("source", type=str, nargs="?", help="RSS URL")
+
+    return parser.parse_args()
+
+
+def get_limit_news_collection(news_collection, com_line_args, logger):
+    if not check_limit_arg(com_line_args, logger):
+        limit = len(news_collection)
+    else:
+        limit = com_line_args.limit
+
+    if len(news_collection) < limit:
+        logger.warning("The number of news is less than the value of the argument limit.")
+        return news_collection
+    else:
+        return news_collection[:limit]
+
+
+def get_news(command_line_args, logger):
+    """ Get news function.
+
+        Uses feedparser library to receive news,
+        and BeautifulSoup library to converting news in readable format.  """
+    logger.info("Getting news.")
+    news_feed = feedparser.parse(command_line_args.source)
+
+    feed = {"title": clean_str(news_feed.feed.get("title", "")),
+            "language": news_feed.feed.get("language", "")}
+    news_collection = []
+    source = command_line_args.source
+
+    for entry in news_feed.entries:
+        news_entry = NewsEntry()
+        news_entry.feed_title = feed["title"]
+        news_entry.feed_language = feed["language"]
+
+        news_entry.source = source
+        news_entry.title = clean_str(entry.get("title", ""))
+        news_entry.date = entry.get("published", "")
+        news_entry.link = entry.get("link", "")
+
+        # get rid of html tags
+        soup = BeautifulSoup(entry.get("summary", ""), "html.parser")
+        news_entry.summary = clean_str(soup.text)
+        # get images links
+        images = soup.findAll("img")
+
+        for img in images:
+            if img["src"]:
+                news_entry.image_links.append(img["src"])
+
+        news_collection.append(news_entry)
+
+    return news_collection
+
+
+def print_news_stdout(news_collection):
+    """ Function for print news to stdout in text format. """
+    if news_collection:
+        for entry in news_collection:
+            entry.print_entry()
+
+
+def print_news_json(news_collection):
+    """ Function for print news to stdout in json format. """
+    news_collection_for_json = []
+
+    for entry in news_collection:
+        entry_for_json = asdict(entry)
+        news_collection_for_json.append(entry_for_json)
+
+    print(json.dumps(news_collection_for_json, indent=4))
+
+
+def print_news(news_collection, com_line_args, logger):
+    """ Function for print news to stdout,
+        that take account of json argument. """
+
+    # news_collection already get valid limit argument
+    logger.info("Printing news.")
+    if com_line_args.date:
+        logger.info("Printing cache news.")
+    else:
+        logger.info("Printing news.")
+
+    if com_line_args.json:
+        logger.info("Printing news in json format.")
+        print_news_json(news_collection)
+    else:
+        logger.info("Printing news stdout.")
+        print_news_stdout(news_collection)
+
+
+def convert_date(date_str):
+    """  Converting date function.  """
+    try:
+        datetime_obj = datetime.strptime(date_str, '%Y%m%d')
+        str_date = datetime_obj.strftime("%d %b %Y")
+        if str_date[0] == '0':
+            str_date = str_date[1:]
+        return str_date
+    except ValueError as e:
+        raise Error("Invalid date argument. Please, check your input.")
+
+
+def clean_str(string):
+    clean_string = html.unescape(string).encode('ascii', 'ignore').decode("utf-8")
+    return clean_string

final_task/rss_reader/caching_functions.py

@@ -0,0 +1,65 @@
+"""  Module of caching functions.
+
+      Functions:
+      cache_news(news_collection, logger) -> None
+      get_cached_news(com_line_args, logger) -> cached_news_collection   """
+
+import shelve
+from os import path
+
+from validation_functions import check_limit_arg
+from exceptions import EmptyFileError, EmptyCollectionError
+
+DIRECTORY = path.abspath(path.dirname(__file__))
+
+
+def cache_news(news_collection, logger):
+    """ Caching news function. """
+    logger.info("Collecting news to cache file.")
+    with shelve.open(path.join(DIRECTORY, '.cache_rss_news')) as news_dict:
+        for news in news_collection:
+            hash_date = news.date
+            news_dict[hash_date] = news
+    logger.info("News was cached successfully.")
+
+
+def get_cached_news(com_line_args, logger):
+    logger.info("Getting cache news.")
+    date = com_line_args.date
+    source = com_line_args.source
+
+    news_collection = []
+
+    with shelve.open(path.join(DIRECTORY, '.cache_rss_news')) as news_dict:
+        if not news_dict:
+            raise EmptyFileError("Cache file is empty. Please, retrieve news from internet. ")
+
+        if not check_limit_arg(com_line_args, logger):
+            limit = len(news_dict)
+        else:
+            limit = min(com_line_args.limit, len(news_dict))
+
+        if source:
+            for hash_date_key in news_dict:
+                if date in hash_date_key:
+                    if hash_date_key.split()[1] == date.partition(' ')[0]:
+                        news = news_dict[hash_date_key]
+                        if source == news.source:
+                            news_collection.append(news)
+
+        else:
+            for hash_date_key in news_dict:
+                if date in hash_date_key:
+                    if hash_date_key.split()[1] == date.partition(' ')[0]:
+                        news = news_dict[hash_date_key]
+                        news_collection.append(news)
+
+    if not news_collection:
+        if source:
+            raise EmptyCollectionError("There are no news in cache file on specified date and source.")
+        else:
+            raise EmptyCollectionError("There are no news in cache file on specified date.")
+
+    else:
+        logger.info("Successfully get news from cache.")
+        return news_collection[:limit]