From 3f9190c64de58219f6be86228aaac3cf3815f253 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sat, 23 Nov 2019 20:17:16 +0300
Subject: [PATCH 01/31] Create basic CLI with arguments parsing

Created CLI using argparse and handle all arguments from the
first iteration.
---
 final_task/rss_reader/rss_reader.py | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index e69de29..8e9b6ac 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -0,0 +1,24 @@
+import argparse
+
+
+# temp
+__version__ = "0.1"
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description="Pure Python command-line RSS reader.")
+
+    parser.add_argument("source", help="RSS URL")
+    parser.add_argument("--version", action="version", version=f"{parser.prog}s {__version__}",
+                        help="Print version info")
+    parser.add_argument("--json", action="store_true", help="Print result as JSON in stdout")
+    parser.add_argument("-v", "--verbose", action="store_true", help="Outputs verbose status messages")
+    parser.add_argument("--limit", type=int, help="Limit news topics if this parameter provided")
+
+    args = parser.parse_args()
+
+    rss_url = args.source
+
+    if args.verbose:
+        print("verbosity turned on")
+
+    limit = args.limit if args.limit is not None else 0

From 6cbe140b136b9971da8bd6d0410f09dc1f8346cd Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sat, 23 Nov 2019 20:36:30 +0300
Subject: [PATCH 02/31] Create class for RSS feed with basic parsing
 functionality

Created Feed class for parsed RSS. For now, it only stores
necessary fields from object returned by feedparser library.
---
 final_task/rss_reader/feed.py | 83 +++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)
 create mode 100644 final_task/rss_reader/feed.py

diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
new file mode 100644
index 0000000..8b55f0d
--- /dev/null
+++ b/final_task/rss_reader/feed.py
@@ -0,0 +1,83 @@
+import urllib.parse
+import html
+
+import feedparser
+
+
+class URLFormatError(ValueError):
+    pass
+
+
+class FeedNotFoundError(Exception):
+    pass
+
+
+class IncorrectRSSError(Exception):
+    pass
+
+
+class Feed:
+
+    def __init__(self, link, limit=0, *, date=None, to_json=False):
+        self.link = self._try_fix_url(link)
+        self.title = None
+        self.items = []
+
+        self.limit = int(limit)
+        self.parse_remote()
+
+    def parse_remote(self):
+        parsed_rss = feedparser.parse(self.link)
+        # Did Feedparser access feed as remote and is the HTTP status ok
+        if "status" not in parsed_rss or parsed_rss.status >= 400:
+            raise FeedNotFoundError("Could not connect or find RSS feed")
+        # Checks does parsed_feed object contain at least one main element of feed
+        if "title" not in parsed_rss.feed and "link" not in parsed_rss and len(parsed_rss.entries) < 0:
+            raise IncorrectRSSError("URL is not a correct RSS feed")
+
+        self.title = parsed_rss.feed.get("title") or parsed_rss.feed.get("link")
+
+        if self.limit < 1 or self.limit > len(parsed_rss.entries):
+            limit = len(parsed_rss.entries)
+        else:
+            limit = self.limit
+        self.items = []
+        for entry in parsed_rss.entries[:limit]:
+            item = self.parse_remote_item(entry)
+            if item is not None:
+                self.items.append(item)
+
+    def parse_remote_item(self, entry):
+        item = dict()
+        if "published_parsed" not in entry:
+            return None
+        item["date"] = entry.published
+        # item["date_str"] = self._create_date_str(entry.published_parsed)
+
+        if "title" in entry:
+            item["title"] = html.unescape(entry.title)
+        else:
+            item["title"] = None
+
+        item["link"] = entry.get("link")
+
+        if len(entry.enclosures) > 0:
+            item["enclosure"] = entry.enclosures[0]
+
+        item["description"] = entry.get("description")
+
+        return item
+
+    @staticmethod
+    def _try_fix_url(url):
+        """
+        Attempts to fix and uniform url
+        :type url: str
+        """
+        try:
+            parsed_url = urllib.parse.urlsplit(url, "https")
+        except ValueError:
+            raise URLFormatError("Error in url format")
+        else:
+            result_url = urllib.parse.urlunsplit(parsed_url)
+            return result_url if not result_url.endswith('/') else result_url[:-1]

From 7adeb983d14ea845dd096732a3201c506407850d Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sat, 23 Nov 2019 20:44:52 +0300
Subject: [PATCH 03/31] Create module for html parsing

Created module with function for parsing html, which can be in
"description" field of RSS item.
---
 final_task/rss_reader/html_to_text.py     | 43 +++++++++++++++++++++++
 final_task/rss_reader/links_collection.py | 27 ++++++++++++++
 2 files changed, 70 insertions(+)
 create mode 100644 final_task/rss_reader/html_to_text.py
 create mode 100644 final_task/rss_reader/links_collection.py

diff --git a/final_task/rss_reader/html_to_text.py b/final_task/rss_reader/html_to_text.py
new file mode 100644
index 0000000..09dc1a1
--- /dev/null
+++ b/final_task/rss_reader/html_to_text.py
@@ -0,0 +1,43 @@
+from bs4 import BeautifulSoup
+from .links_collection import LinksCollection
+
+
+def _handle_image(tag, refs):
+    if "src" in tag.attrs and tag.attrs["src"]:
+        index = refs.add(tag.attrs["src"])
+        alt_text = tag.attrs.get("alt", "no description")
+        tag.replace_with(f"[image {index}: {alt_text}][{index}]")
+
+
+def _handle_link(tag, link, refs):
+    if (
+            len(tag.get_text()) > 0 and
+            "href" in tag.attrs and
+            len(tag.attrs["href"]) > 0 and
+            tag.href != link
+    ):
+        index = refs.add(tag.attrs["href"])
+        tag.insert_after(f"[{index}]")
+
+
+def _create_refs_text(refs):
+    s = ["Links:\n"]
+    for i, r in enumerate(refs):
+        s.append(f"[{(i+1)}]: {r}\n")
+    s = "".join(s)
+    return s
+
+
+def parse(html, skip_link=None):
+    refs = LinksCollection()
+    if skip_link is not None:
+        refs.add(skip_link)
+    soup = BeautifulSoup(html, features="lxml")
+    for tag in soup.find_all(name=["img", "a"]):
+        if tag.name == 'img':
+            _handle_image(tag, refs)
+        else:
+            _handle_link(tag, skip_link, refs)
+
+    text = soup.get_text() + "\n\n" + _create_refs_text(refs)
+    return text
diff --git a/final_task/rss_reader/links_collection.py b/final_task/rss_reader/links_collection.py
new file mode 100644
index 0000000..0061e8c
--- /dev/null
+++ b/final_task/rss_reader/links_collection.py
@@ -0,0 +1,27 @@
+from collections.abc import Collection
+
+
+class LinksCollection(Collection):
+
+    def __len__(self) -> int:
+        return len(self.items_dict)
+
+    def __contains__(self, __x: object) -> bool:
+        return __x in self.items_dict
+
+    def __iter__(self):
+        return self.items_dict.__iter__()
+
+    def __init__(self, initial=None):
+        self.items_dict = dict()
+        self._next_index_ = 1
+
+        if initial is not None:
+            for element in initial:
+                self.add(element)
+
+    def add(self, item):
+        if item is not None and item not in self.items_dict:
+            self.items_dict[item] = self._next_index_
+            self._next_index_ += 1
+        return self.items_dict[item]

From 8df0ad317e22cbda10afff5fd3c8a8b67ba69cff Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sat, 23 Nov 2019 20:51:43 +0300
Subject: [PATCH 04/31] Add html parsing to Feed class

---
 final_task/rss_reader/feed.py | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index 8b55f0d..d7b3b96 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -3,6 +3,8 @@
 
 import feedparser
 
+from . import html_to_text
+
 
 class URLFormatError(ValueError):
     pass
@@ -64,8 +66,12 @@ def parse_remote_item(self, entry):
         if len(entry.enclosures) > 0:
             item["enclosure"] = entry.enclosures[0]
 
-        item["description"] = entry.get("description")
-
+        if "description" in entry:
+            item["description"] = entry.description
+            if self._is_html(entry.description_detail.type):
+                item["description_parsed"] = html_to_text.parse(item["description"], skip_link=item.get("link"))
+        else:
+            item["description"] = None
         return item
 
     @staticmethod
@@ -81,3 +87,7 @@ def _try_fix_url(url):
         else:
             result_url = urllib.parse.urlunsplit(parsed_url)
             return result_url if not result_url.endswith('/') else result_url[:-1]
+
+    @staticmethod
+    def _is_html(element_type):
+        return element_type in ["text/html", "application/xhtml+xml"]

From 9ab49d1666c6ef7d50fc886a082b000d6f3fb398 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sat, 23 Nov 2019 21:03:19 +0300
Subject: [PATCH 05/31] Add methods for generating plain text and json from RSS

Added methods for generating json and plain text with links list
to Feed class
---
 final_task/rss_reader/feed.py | 40 ++++++++++++++++++++++++++++++++++-
 1 file changed, 39 insertions(+), 1 deletion(-)

diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index d7b3b96..cd305b0 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -1,5 +1,6 @@
 import urllib.parse
 import html
+import json
 
 import feedparser
 
@@ -54,7 +55,6 @@ def parse_remote_item(self, entry):
         if "published_parsed" not in entry:
             return None
         item["date"] = entry.published
-        # item["date_str"] = self._create_date_str(entry.published_parsed)
 
         if "title" in entry:
             item["title"] = html.unescape(entry.title)
@@ -74,6 +74,44 @@ def parse_remote_item(self, entry):
             item["description"] = None
         return item
 
+    def render_text(self):
+        s = []
+
+        title = self.title or "no title"
+        s.append(title)
+        s.append("\n")
+
+        for item in self.items:
+            s.append("\n\n")
+
+            item_title = item["title"] or "no title"
+            s.append("Title: " + item_title + "\n")
+
+            s.append("Date: " + item["date"] + "\n")
+
+            item_link = item["link"] or "no link"
+            s.append("Link: " + item_link + "\n")
+
+            s.append("\n")
+            if "enclosure" in item:
+                s.append("Enclosure: " + item["enclosure"]+"\n")
+                s.append("\n")
+
+            s.append("Description: ")
+            if "description_parsed" in item:
+                s.append(item["description_parsed"])
+            else:
+                description = item["description"] or "no description"
+                s.append(description)
+
+        s = "".join(s)
+        return s
+
+    def render_json(self):
+        feed_dict = {"title": self.title, "items": self.items}
+        s = json.dumps(feed_dict, indent="\t")
+        return s
+
     @staticmethod
     def _try_fix_url(url):
         """

From 498b4f820d286dd3c6b164020bd2584911278424 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sat, 23 Nov 2019 21:06:13 +0300
Subject: [PATCH 06/31] Remove unnecessary parameter from Feed constructor

---
 final_task/rss_reader/feed.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index cd305b0..9884077 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -21,7 +21,7 @@ class IncorrectRSSError(Exception):
 
 class Feed:
 
-    def __init__(self, link, limit=0, *, date=None, to_json=False):
+    def __init__(self, link, limit=0, *, date=None):
         self.link = self._try_fix_url(link)
         self.title = None
         self.items = []

From 67ed39ce674a99054e59f5aaa7550a42aed42dae Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sat, 23 Nov 2019 21:18:09 +0300
Subject: [PATCH 07/31] Fix relative module import error

---
 final_task/rss_reader/feed.py         | 2 +-
 final_task/rss_reader/html_to_text.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index 9884077..cc9c1a2 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -4,7 +4,7 @@
 
 import feedparser
 
-from . import html_to_text
+import html_to_text
 
 
 class URLFormatError(ValueError):
diff --git a/final_task/rss_reader/html_to_text.py b/final_task/rss_reader/html_to_text.py
index 09dc1a1..3524575 100644
--- a/final_task/rss_reader/html_to_text.py
+++ b/final_task/rss_reader/html_to_text.py
@@ -1,5 +1,5 @@
 from bs4 import BeautifulSoup
-from .links_collection import LinksCollection
+from links_collection import LinksCollection
 
 
 def _handle_image(tag, refs):

From 5acb43da53f9ee9fed9f400c734bc93452ddcd50 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sat, 23 Nov 2019 21:36:26 +0300
Subject: [PATCH 08/31] Add RSS parsing and printing and handle custom
 exceptions

---
 final_task/rss_reader/rss_reader.py | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index 8e9b6ac..f47b4b7 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -1,5 +1,6 @@
 import argparse
 
+from feed import Feed, URLFormatError, FeedNotFoundError, IncorrectRSSError
 
 # temp
 __version__ = "0.1"
@@ -22,3 +23,13 @@
         print("verbosity turned on")
 
     limit = args.limit if args.limit is not None else 0
+
+    try:
+        feed = Feed(rss_url, limit)
+    except (URLFormatError, FeedNotFoundError, IncorrectRSSError) as e:
+        print("Error: " + str(e))
+    else:
+        if not args.json:
+            print(feed.render_text())
+        else:
+            print(feed.render_json())

From b93e90bcfa5cee616eee842658a1d78698deeeef Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sun, 24 Nov 2019 01:09:21 +0300
Subject: [PATCH 09/31] Add logging and implement --verbose argument

Added logging with ERROR level to display handled custom
exceptions; and INFO level to display verbose status messages if
corresponding argument is provided.
---
 final_task/rss_reader/feed.py       | 15 +++++++++++++--
 final_task/rss_reader/rss_reader.py | 12 ++++++++++--
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index cc9c1a2..281582a 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -1,7 +1,7 @@
 import urllib.parse
 import html
 import json
-
+import logging
 import feedparser
 
 import html_to_text
@@ -23,6 +23,7 @@ class Feed:
 
     def __init__(self, link, limit=0, *, date=None):
         self.link = self._try_fix_url(link)
+        logging.info(f'The link to the rss feed is "{self.link}"')
         self.title = None
         self.items = []
 
@@ -38,17 +39,23 @@ def parse_remote(self):
         if "title" not in parsed_rss.feed and "link" not in parsed_rss and len(parsed_rss.entries) < 0:
             raise IncorrectRSSError("URL is not a correct RSS feed")
 
+        logging.info("Feed successfully received")
         self.title = parsed_rss.feed.get("title") or parsed_rss.feed.get("link")
 
         if self.limit < 1 or self.limit > len(parsed_rss.entries):
             limit = len(parsed_rss.entries)
+            logging.info("Parsing items without limit")
         else:
             limit = self.limit
+            logging.info(f"Items limit is {limit}")
         self.items = []
-        for entry in parsed_rss.entries[:limit]:
+        for i, entry in enumerate(parsed_rss.entries[:limit]):
+            logging.info(f"Parsing item {(i+1)}")
             item = self.parse_remote_item(entry)
             if item is not None:
                 self.items.append(item)
+            else:
+                logging.info("Skipping invalid item")
 
     def parse_remote_item(self, entry):
         item = dict()
@@ -70,11 +77,14 @@ def parse_remote_item(self, entry):
             item["description"] = entry.description
             if self._is_html(entry.description_detail.type):
                 item["description_parsed"] = html_to_text.parse(item["description"], skip_link=item.get("link"))
+                logging.info("Item description is html and therefore converted to plain text")
         else:
             item["description"] = None
         return item
 
     def render_text(self):
+        logging.info("Generating plain text representation of feed")
+
         s = []
 
         title = self.title or "no title"
@@ -108,6 +118,7 @@ def render_text(self):
         return s
 
     def render_json(self):
+        logging.info("Generating json representation of feed")
         feed_dict = {"title": self.title, "items": self.items}
         s = json.dumps(feed_dict, indent="\t")
         return s
diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index f47b4b7..47f724c 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -1,4 +1,5 @@
 import argparse
+import logging
 
 from feed import Feed, URLFormatError, FeedNotFoundError, IncorrectRSSError
 
@@ -20,16 +21,23 @@
     rss_url = args.source
 
     if args.verbose:
-        print("verbosity turned on")
+        log_level = logging.INFO
+    else:
+        log_level = logging.WARNING
 
     limit = args.limit if args.limit is not None else 0
+    logging.basicConfig(format="%(levelname)s:%(message)s", level=log_level)
+
+    logging.info("Program starts")
 
     try:
         feed = Feed(rss_url, limit)
     except (URLFormatError, FeedNotFoundError, IncorrectRSSError) as e:
-        print("Error: " + str(e))
+        logging.error(str(e))
     else:
         if not args.json:
             print(feed.render_text())
         else:
             print(feed.render_json())
+
+    logging.info("Program finishes")

From fcbf10fe1526edc07f90965582528ed671bc4e42 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sun, 24 Nov 2019 18:57:52 +0300
Subject: [PATCH 10/31] Rename internal methods and remove incorrect docstring

---
 final_task/rss_reader/feed.py | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index 281582a..46ec6ee 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -28,9 +28,9 @@ def __init__(self, link, limit=0, *, date=None):
         self.items = []
 
         self.limit = int(limit)
-        self.parse_remote()
+        self._parse_remote()
 
-    def parse_remote(self):
+    def _parse_remote(self):
         parsed_rss = feedparser.parse(self.link)
         # Did Feedparser access feed as remote and is the HTTP status ok
         if "status" not in parsed_rss or parsed_rss.status >= 400:
@@ -51,13 +51,13 @@ def parse_remote(self):
         self.items = []
         for i, entry in enumerate(parsed_rss.entries[:limit]):
             logging.info(f"Parsing item {(i+1)}")
-            item = self.parse_remote_item(entry)
+            item = self._parse_remote_item(entry)
             if item is not None:
                 self.items.append(item)
             else:
                 logging.info("Skipping invalid item")
 
-    def parse_remote_item(self, entry):
+    def _parse_remote_item(self, entry):
         item = dict()
         if "published_parsed" not in entry:
             return None
@@ -125,10 +125,6 @@ def render_json(self):
 
     @staticmethod
     def _try_fix_url(url):
-        """
-        Attempts to fix and uniform url
-        :type url: str
-        """
         try:
             parsed_url = urllib.parse.urlsplit(url, "https")
         except ValueError:

From 914c17b34f85a26afc1e558ae37f38931de1a04e Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sun, 24 Nov 2019 20:01:16 +0300
Subject: [PATCH 11/31] Update README

---
 final_task/README.md | 33 ++++++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/final_task/README.md b/final_task/README.md
index 7af281f..c17f2c6 100644
--- a/final_task/README.md
+++ b/final_task/README.md
@@ -1,3 +1,30 @@
-# Your readme here
-Some text.
-Checkout how to write this file using *markdown*.
+# Console RSS Reader
+Cli-based RSS Reader built with Python 3.8. 
+Supports all RSS standards, can handle incorrect RSS. 
+Also partially supports Atom feeds. 
+
+## Getting Started
+### Prerequisites
+- Python 3.8
+- feedparser, lxml, beautifulsoup4
+
+```
+pip install feedparser lxml beautifulsoup4
+```
+### Usage
+The program runs from file `rss_parser.py`
+```
+usage: rss_reader.py [-h] [--version] [--json] [-v] [--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
+  -v, --verbose  Outputs verbose status messages
+  --limit LIMIT  Limit news topics if this parameter provided
+```

From 2bc74105b372499f38c3098d769a8d67409c5f05 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sun, 24 Nov 2019 21:30:24 +0300
Subject: [PATCH 12/31] Add LICENSE and update README

---
 final_task/LICENSE   | 21 +++++++++++++++++++++
 final_task/README.md |  2 ++
 2 files changed, 23 insertions(+)
 create mode 100644 final_task/LICENSE

diff --git a/final_task/LICENSE b/final_task/LICENSE
new file mode 100644
index 0000000..5450455
--- /dev/null
+++ b/final_task/LICENSE
@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2019 Denis Marfonov
+
+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.
diff --git a/final_task/README.md b/final_task/README.md
index c17f2c6..0f7f447 100644
--- a/final_task/README.md
+++ b/final_task/README.md
@@ -28,3 +28,5 @@ optional arguments:
   -v, --verbose  Outputs verbose status messages
   --limit LIMIT  Limit news topics if this parameter provided
 ```
+### Licence
+This project is licensed under the MIT License - see the LICENSE file for details.

From 24c0cc615be1d7ca71ea9c4de796388931ed8132 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sun, 24 Nov 2019 22:28:45 +0300
Subject: [PATCH 13/31] Move code to separate function

This is done in order to add main() function to 'console scripts'
in setup.py
---
 final_task/rss_reader/rss_reader.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index 47f724c..f5e095c 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -6,7 +6,8 @@
 # temp
 __version__ = "0.1"
 
-if __name__ == '__main__':
+
+def main():
     parser = argparse.ArgumentParser(description="Pure Python command-line RSS reader.")
 
     parser.add_argument("source", help="RSS URL")
@@ -41,3 +42,7 @@
             print(feed.render_json())
 
     logging.info("Program finishes")
+
+
+if __name__ == '__main__':
+    main()

From 9f214b50230c4235661f800b6b2f5dfc6d379fde Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sun, 24 Nov 2019 22:36:36 +0300
Subject: [PATCH 14/31] Make correct package from code folder and fill setup.py

Added __init__ to make correct python package.
Created __main__ to allow starting package as program
Added content to setup.py.
---
 final_task/{ => rss_reader}/__init__.py |  0
 final_task/rss_reader/__main__.py       |  3 +++
 final_task/setup.py                     | 29 +++++++++++++++++++++++++
 3 files changed, 32 insertions(+)
 rename final_task/{ => rss_reader}/__init__.py (100%)
 create mode 100644 final_task/rss_reader/__main__.py

diff --git a/final_task/__init__.py b/final_task/rss_reader/__init__.py
similarity index 100%
rename from final_task/__init__.py
rename to final_task/rss_reader/__init__.py
diff --git a/final_task/rss_reader/__main__.py b/final_task/rss_reader/__main__.py
new file mode 100644
index 0000000..9223eaf
--- /dev/null
+++ b/final_task/rss_reader/__main__.py
@@ -0,0 +1,3 @@
+from rss_reader import main
+
+main()
\ No newline at end of file
diff --git a/final_task/setup.py b/final_task/setup.py
index e69de29..48ee6b5 100644
--- a/final_task/setup.py
+++ b/final_task/setup.py
@@ -0,0 +1,29 @@
+from setuptools import setup, find_packages
+
+with open("README.md", "r") as fh:
+    long_description = fh.read()
+
+setup(
+    name='rss-reader_scarzdz',
+    version='0.1',
+    url='https://github.com/scarzdz/FinalTaskRssParser',
+    license='MIT',
+    author='Denis Marfonov',
+    author_email='marfonovdenis@gmail.com',
+    description='Cli-based RSS Reader',
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    packages=['rss_reader'],
+    classifiers=[
+        "Programming Language :: Python :: 3"
+        "Programming Language :: Python :: 3.8",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires='>=3.8',
+    entry_points={
+        'console_scripts': [
+            'rss-reader=rss_reader.rss_reader:main',
+        ],
+    },
+)

From cb62489ce21b8526fd6ab31522deaf6dabf662dd Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Sun, 24 Nov 2019 22:50:31 +0300
Subject: [PATCH 15/31] Add dependencies list and reformat file

---
 final_task/setup.py | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/final_task/setup.py b/final_task/setup.py
index 48ee6b5..5d9dd6e 100644
--- a/final_task/setup.py
+++ b/final_task/setup.py
@@ -1,29 +1,34 @@
-from setuptools import setup, find_packages
+from setuptools import setup
 
 with open("README.md", "r") as fh:
     long_description = fh.read()
 
 setup(
-    name='rss-reader_scarzdz',
-    version='0.1',
-    url='https://github.com/scarzdz/FinalTaskRssParser',
-    license='MIT',
-    author='Denis Marfonov',
-    author_email='marfonovdenis@gmail.com',
-    description='Cli-based RSS Reader',
+    name="rss-reader_scarzdz",
+    version="0.1",
+    url="https://github.com/scarzdz/FinalTaskRssParser",
+    license="MIT",
+    author="Denis Marfonov",
+    author_email="marfonovdenis@gmail.com",
+    description="Cli-based RSS Reader",
     long_description=long_description,
     long_description_content_type="text/markdown",
-    packages=['rss_reader'],
+    packages=["rss_reader"],
     classifiers=[
         "Programming Language :: Python :: 3"
         "Programming Language :: Python :: 3.8",
         "License :: OSI Approved :: MIT License",
         "Operating System :: OS Independent",
     ],
-    python_requires='>=3.8',
+    python_requires=">=3.8",
+    install_requires=[
+        "beautifulsoup4",
+        "feedparser",
+        "lxml"
+    ],
     entry_points={
-        'console_scripts': [
-            'rss-reader=rss_reader.rss_reader:main',
+        "console_scripts": [
+            "rss-reader=rss_reader.rss_reader:main",
         ],
     },
 )

From 0d63bc4145cb8572fb7d8cccdbc9a4b6472e8ff6 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 01:00:54 +0300
Subject: [PATCH 16/31] Fix typo

---
 final_task/setup.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/final_task/setup.py b/final_task/setup.py
index 5d9dd6e..aa62797 100644
--- a/final_task/setup.py
+++ b/final_task/setup.py
@@ -15,7 +15,7 @@
     long_description_content_type="text/markdown",
     packages=["rss_reader"],
     classifiers=[
-        "Programming Language :: Python :: 3"
+        "Programming Language :: Python :: 3",
         "Programming Language :: Python :: 3.8",
         "License :: OSI Approved :: MIT License",
         "Operating System :: OS Independent",

From 7c50244bc7357b600c77466b3d474a0c72f6c1d5 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 01:20:08 +0300
Subject: [PATCH 17/31] Change imports to relative

---
 final_task/rss_reader/__main__.py     | 4 ++--
 final_task/rss_reader/feed.py         | 2 +-
 final_task/rss_reader/html_to_text.py | 2 +-
 final_task/rss_reader/rss_reader.py   | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/final_task/rss_reader/__main__.py b/final_task/rss_reader/__main__.py
index 9223eaf..f8e010c 100644
--- a/final_task/rss_reader/__main__.py
+++ b/final_task/rss_reader/__main__.py
@@ -1,3 +1,3 @@
-from rss_reader import main
+from .rss_reader import main
 
-main()
\ No newline at end of file
+main()
diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index 46ec6ee..476f630 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -4,7 +4,7 @@
 import logging
 import feedparser
 
-import html_to_text
+from . import html_to_text
 
 
 class URLFormatError(ValueError):
diff --git a/final_task/rss_reader/html_to_text.py b/final_task/rss_reader/html_to_text.py
index 3524575..09dc1a1 100644
--- a/final_task/rss_reader/html_to_text.py
+++ b/final_task/rss_reader/html_to_text.py
@@ -1,5 +1,5 @@
 from bs4 import BeautifulSoup
-from links_collection import LinksCollection
+from .links_collection import LinksCollection
 
 
 def _handle_image(tag, refs):
diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index f5e095c..0cbadf8 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -1,7 +1,7 @@
 import argparse
 import logging
 
-from feed import Feed, URLFormatError, FeedNotFoundError, IncorrectRSSError
+from .feed import Feed, URLFormatError, FeedNotFoundError, IncorrectRSSError
 
 # temp
 __version__ = "0.1"

From 9ec3adec203657946f38ad02040d1c742855a082 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 01:21:56 +0300
Subject: [PATCH 18/31] Update README

---
 final_task/README.md | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/final_task/README.md b/final_task/README.md
index 0f7f447..dbb2189 100644
--- a/final_task/README.md
+++ b/final_task/README.md
@@ -1,5 +1,5 @@
-# Console RSS Reader
-Cli-based RSS Reader built with Python 3.8. 
+# RSS Reader
+Cli-based RSS reader built with Python 3.8. 
 Supports all RSS standards, can handle incorrect RSS. 
 Also partially supports Atom feeds. 
 
@@ -11,10 +11,25 @@ Also partially supports Atom feeds.
 ```
 pip install feedparser lxml beautifulsoup4
 ```
+### Installation
+```
+pip install -i https://test.pypi.org/simple/ rss-reader-scarzdz
+```
+Also you can just download source code and install using: 
+```
+$ python final_task/setup.py install
+```
+### Running
+After installation, `rss-reader` command is added to PATH.
+
+Alternatively, the application can be run from the source file:
+``` 
+$ cd final_task
+$ python -m rss_reader ...
+```
 ### Usage
-The program runs from file `rss_parser.py`
 ```
-usage: rss_reader.py [-h] [--version] [--json] [-v] [--limit LIMIT] source
+usage: rss-reader [-h] [--version] [--json] [-v] [--limit LIMIT] source
 
 Pure Python command-line RSS reader.
 

From 53e0a60377500686d651a0763d07947b13d2d42a Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 01:25:21 +0300
Subject: [PATCH 19/31] Make CLI always show correct program name

---
 final_task/rss_reader/rss_reader.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index 0cbadf8..12351af 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -5,10 +5,11 @@
 
 # temp
 __version__ = "0.1"
+PROG = "rss-reader"
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Pure Python command-line RSS reader.")
+    parser = argparse.ArgumentParser(description="Pure Python command-line RSS reader.", prog=PROG)
 
     parser.add_argument("source", help="RSS URL")
     parser.add_argument("--version", action="version", version=f"{parser.prog}s {__version__}",

From 26cf900dac80c8d4e28e20d773ff3d895915d512 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 01:36:42 +0300
Subject: [PATCH 20/31] Fill requirements.txt

---
 final_task/rss_reader/requirements.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/final_task/rss_reader/requirements.txt b/final_task/rss_reader/requirements.txt
index e69de29..5c90ddd 100644
--- a/final_task/rss_reader/requirements.txt
+++ b/final_task/rss_reader/requirements.txt
@@ -0,0 +1,3 @@
+lxml~=4.4.1
+feedparser~=5.2.1
+beautifulsoup4~=4.8.1
\ No newline at end of file

From ca5ae76db61139522ecd1e4642421e5263449370 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 01:38:47 +0300
Subject: [PATCH 21/31] Bump version number to 0.2

---
 final_task/rss_reader/rss_reader.py | 2 +-
 final_task/setup.py                 | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index 12351af..50a047a 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -4,7 +4,7 @@
 from .feed import Feed, URLFormatError, FeedNotFoundError, IncorrectRSSError
 
 # temp
-__version__ = "0.1"
+__version__ = "0.2"
 PROG = "rss-reader"
 
 
diff --git a/final_task/setup.py b/final_task/setup.py
index aa62797..f037459 100644
--- a/final_task/setup.py
+++ b/final_task/setup.py
@@ -5,7 +5,7 @@
 
 setup(
     name="rss-reader_scarzdz",
-    version="0.1",
+    version="0.2",
     url="https://github.com/scarzdz/FinalTaskRssParser",
     license="MIT",
     author="Denis Marfonov",

From 80e321b37819238bd310db9ce28f99afb61b0631 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 02:19:06 +0300
Subject: [PATCH 22/31] Add --date argument to CLI

---
 final_task/rss_reader/feed.py       |  8 +++++++-
 final_task/rss_reader/rss_reader.py | 25 ++++++++++++++++++++-----
 2 files changed, 27 insertions(+), 6 deletions(-)

diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index 476f630..31142f5 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -6,6 +6,8 @@
 
 from . import html_to_text
 
+DATE_FORMAT = "%Y%m%d"
+
 
 class URLFormatError(ValueError):
     pass
@@ -28,7 +30,11 @@ def __init__(self, link, limit=0, *, date=None):
         self.items = []
 
         self.limit = int(limit)
-        self._parse_remote()
+        if date is None:
+            self._parse_remote()
+        else:
+            pass
+
 
     def _parse_remote(self):
         parsed_rss = feedparser.parse(self.link)
diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index 50a047a..4228076 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -1,13 +1,23 @@
 import argparse
 import logging
+import time
 
-from .feed import Feed, URLFormatError, FeedNotFoundError, IncorrectRSSError
+from . import feed
 
 # temp
 __version__ = "0.2"
 PROG = "rss-reader"
 
 
+def date_str(string):
+    logging.info("Checking date argument")
+    try:
+        time.strptime(string, format=feed.DATE_FORMAT)
+    except ValueError:
+        raise argparse.ArgumentTypeError(f"Incorrect date format: {string}")
+    return string
+
+
 def main():
     parser = argparse.ArgumentParser(description="Pure Python command-line RSS reader.", prog=PROG)
 
@@ -18,6 +28,11 @@ def main():
     parser.add_argument("-v", "--verbose", action="store_true", help="Outputs verbose status messages")
     parser.add_argument("--limit", type=int, help="Limit news topics if this parameter provided")
 
+    # It is done because argparse treat '%' in parameters as old-style formatting
+    date_format_escaped = feed.DATE_FORMAT.replace("%", "%%")
+    parser.add_argument("--date", type=date_str,
+                        help=f"Load news with date ({date_format_escaped}) from cache, if this parameter provided")
+
     args = parser.parse_args()
 
     rss_url = args.source
@@ -33,14 +48,14 @@ def main():
     logging.info("Program starts")
 
     try:
-        feed = Feed(rss_url, limit)
-    except (URLFormatError, FeedNotFoundError, IncorrectRSSError) as e:
+        rss_feed = feed.Feed(rss_url, limit)
+    except (feed.URLFormatError, feed.FeedNotFoundError, feed.IncorrectRSSError) as e:
         logging.error(str(e))
     else:
         if not args.json:
-            print(feed.render_text())
+            print(rss_feed.render_text())
         else:
-            print(feed.render_json())
+            print(rss_feed.render_json())
 
     logging.info("Program finishes")
 

From 7944473d01f2d7004ff862ca581b33d3ffa6096b Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 13:00:37 +0300
Subject: [PATCH 23/31] Implement local caching using sqlite database

---
 final_task/rss_reader/database.py   | 118 ++++++++++++++++++++++++++++
 final_task/rss_reader/feed.py       |  79 ++++++++++++++-----
 final_task/rss_reader/rss_reader.py |  19 ++---
 3 files changed, 186 insertions(+), 30 deletions(-)
 create mode 100644 final_task/rss_reader/database.py

diff --git a/final_task/rss_reader/database.py b/final_task/rss_reader/database.py
new file mode 100644
index 0000000..070eb9a
--- /dev/null
+++ b/final_task/rss_reader/database.py
@@ -0,0 +1,118 @@
+import sqlite3
+import time
+import pkg_resources
+
+DATE_FORMAT = "%Y-%m-%d"
+DATETIME_FORMAT = "%Y-%m-%d %H:%M:%S"
+
+DATA_FILE = "data/rss.sqlite"
+
+
+class DBError(Exception):
+    pass
+
+
+class DB:
+    def __init__(self):
+        path = pkg_resources.resource_filename(__name__, DATA_FILE)
+        try:
+            self.conn = sqlite3.connect(path)
+        except sqlite3.OperationalError as e:
+            raise DBError(str(e))
+        self.cursor = self.conn.cursor()
+        self.feed_id = None
+
+    def _create_db(self):
+        self.cursor.execute("DROP TABLE IF EXISTS feeds")
+        self.cursor.execute("DROP TABLE IF EXISTS items")
+        self.cursor.execute('''
+            CREATE TABLE feeds(
+                id INTEGER PRIMARY KEY,
+                title TEXT,
+                link TEXT UNIQUE NOT NULL 
+            )
+        ''')
+        self.cursor.execute('''
+            CREATE TABLE items(
+                id INTEGER PRIMARY KEY,
+                feed_id INTEGER NOT NULL, 
+                published TEXT NOT NULL,
+                title TEXT,
+                link TEXT,
+                enclosure TEXT,
+                description TEXT,
+                description_parsed TEXT,
+                FOREIGN KEY (feed_id) REFERENCES feeds(id)
+            )
+        ''')
+        self.cursor.execute('''
+            CREATE UNIQUE INDEX un_items ON items(published, title, link)
+        ''')
+        self.conn.commit()
+
+    def get_feed(self, feed_link, req_date, limit=-1):
+        feed_info = self._get_feed_info_if_exists(feed_link)
+        if feed_info is not None:
+            req_date = time.strftime(DATE_FORMAT, req_date)
+
+            self.cursor.execute('''
+                select i.title, i.published, i.link, i.enclosure, i.description, i.description_parsed 
+                    from items i join feeds f on i.feed_id = f.id 
+                        where f.id=(?) and date(i.published)=date(?) limit (?)
+            ''', (feed_info[0], req_date, limit)
+            )
+
+            items = []
+            for i in self.cursor.fetchall():
+                item = dict(title=i[0], date=time.strptime(i[1], DATETIME_FORMAT), link=i[2], enclosure=i[3],
+                            description=i[4], description_parsed=i[5])
+                items.append(item)
+            return dict(title=feed_info[1], items=items)
+        else:
+
+            return None
+
+    def store_feed(self, link, title, items):
+        feed_id = self._get_feed_id_if_exists(link)
+        if feed_id is None:
+            self.cursor.execute("insert into feeds(title, link) values (?, ?)", (title, link))
+            feed_id = self.cursor.lastrowid
+            self.conn.commit()
+        self.feed_id = feed_id
+        self._store_items(items)
+
+    def _store_items(self, items):
+        for i in items:
+            item_dict = dict(
+                feed_id=self.feed_id,
+                published=time.strftime(DATETIME_FORMAT, i["date"]),
+                title=i["title"],
+                link=i["link"],
+                enclosure=i["enclosure"],
+                description=i["description"],
+                description_parsed=i["description_parsed"]
+            )
+            self.cursor.execute('''
+            insert or ignore into items(feed_id, published, title, link, enclosure, description, description_parsed) 
+                values (:feed_id, :published, :title, :link, :enclosure, :description, :description_parsed)
+            ''', item_dict)
+        self.conn.commit()
+
+    def _get_feed_id_if_exists(self, feed_link):
+        feed_info = self._get_feed_info_if_exists(feed_link)
+        if feed_info is not None:
+            return feed_info[0]
+        else:
+            return None
+
+    def _get_feed_info_if_exists(self, feed_link):
+        self.cursor.execute("select feeds.id, feeds.title from feeds where feeds.link=?", (feed_link,))
+        feed_info = self.cursor.fetchone()
+        if feed_info is not None:
+            return feed_info[0], feed_info[1]
+        return None
+
+
+if __name__ == '__main__':
+    db = DB()
+    db._create_db()
diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index 31142f5..14ab064 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -2,11 +2,11 @@
 import html
 import json
 import logging
+import time
 import feedparser
 
 from . import html_to_text
-
-DATE_FORMAT = "%Y%m%d"
+from .database import DB, DBError
 
 
 class URLFormatError(ValueError):
@@ -21,6 +21,10 @@ class IncorrectRSSError(Exception):
     pass
 
 
+class LocalCacheError(Exception):
+    pass
+
+
 class Feed:
 
     def __init__(self, link, limit=0, *, date=None):
@@ -30,13 +34,25 @@ def __init__(self, link, limit=0, *, date=None):
         self.items = []
 
         self.limit = int(limit)
+        self.date = date
+        try:
+            self.db = DB()
+        except DBError:
+            if self.date is not None:
+                raise LocalCacheError("Unable to open local cache")
+            else:
+                self.db = None
+                logging.warning("Unable to open local cache. Feed items will not be saved.")
+
         if date is None:
             self._parse_remote()
+            self._save_to_cache()
         else:
-            pass
-
+            self.date = date
+            self._load_cache()
 
     def _parse_remote(self):
+        logging.info("Parsing feed from remote source")
         parsed_rss = feedparser.parse(self.link)
         # Did Feedparser access feed as remote and is the HTTP status ok
         if "status" not in parsed_rss or parsed_rss.status >= 400:
@@ -67,7 +83,7 @@ def _parse_remote_item(self, entry):
         item = dict()
         if "published_parsed" not in entry:
             return None
-        item["date"] = entry.published
+        item["date"] = entry.published_parsed
 
         if "title" in entry:
             item["title"] = html.unescape(entry.title)
@@ -78,7 +94,10 @@ def _parse_remote_item(self, entry):
 
         if len(entry.enclosures) > 0:
             item["enclosure"] = entry.enclosures[0]
+        else:
+            item["enclosure"] = None
 
+        item["description_parsed"] = None
         if "description" in entry:
             item["description"] = entry.description
             if self._is_html(entry.description_detail.type):
@@ -88,6 +107,24 @@ def _parse_remote_item(self, entry):
             item["description"] = None
         return item
 
+    def _load_cache(self):
+        logging.info("Loading feed from cache")
+        limit = -1
+        if self.limit > 0:
+            limit = self.limit
+        db_feed = self.db.get_feed(self.link, self.date, limit)
+        if db_feed is not None:
+            logging.info("Feed successfully loaded")
+            self.title = db_feed["title"]
+            self.items = db_feed["items"]
+        else:
+            logging.warning("Feed with the specified link is not found in cache")
+
+    def _save_to_cache(self):
+        if self.db is not None:
+            self.db.store_feed(self.link, self.title, self.items)
+            logging.info("Feed saved to cache")
+
     def render_text(self):
         logging.info("Generating plain text representation of feed")
 
@@ -96,28 +133,28 @@ def render_text(self):
         title = self.title or "no title"
         s.append(title)
         s.append("\n")
+        if len(self.items) == 0:
+            s.append("\nno items to show\n")
+        else:
+            for item in self.items:
+                s.append("\n\n")
 
-        for item in self.items:
-            s.append("\n\n")
-
-            item_title = item["title"] or "no title"
-            s.append("Title: " + item_title + "\n")
+                item_title = item["title"] or "no title"
+                s.append("Title: " + item_title + "\n")
 
-            s.append("Date: " + item["date"] + "\n")
+                item_date = time.strftime("%a, %d %b %Y %H:%M:%S +0000", item["date"])
+                s.append("Date: " + item_date + "\n")
 
-            item_link = item["link"] or "no link"
-            s.append("Link: " + item_link + "\n")
+                item_link = item["link"] or "no link"
+                s.append("Link: " + item_link + "\n")
 
-            s.append("\n")
-            if "enclosure" in item:
-                s.append("Enclosure: " + item["enclosure"]+"\n")
                 s.append("\n")
+                if item["enclosure"] is not None:
+                    s.append("Enclosure: " + item["enclosure"]+"\n")
+                    s.append("\n")
 
-            s.append("Description: ")
-            if "description_parsed" in item:
-                s.append(item["description_parsed"])
-            else:
-                description = item["description"] or "no description"
+                s.append("Description: ")
+                description = item["description_parsed"] or item["description"] or "no description"
                 s.append(description)
 
         s = "".join(s)
diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index 4228076..73c8391 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -7,15 +7,16 @@
 # temp
 __version__ = "0.2"
 PROG = "rss-reader"
+DATE_FORMAT = "%Y%m%d"
 
 
 def date_str(string):
     logging.info("Checking date argument")
     try:
-        time.strptime(string, format=feed.DATE_FORMAT)
+        date = time.strptime(string, DATE_FORMAT)
     except ValueError:
         raise argparse.ArgumentTypeError(f"Incorrect date format: {string}")
-    return string
+    return date
 
 
 def main():
@@ -29,7 +30,7 @@ def main():
     parser.add_argument("--limit", type=int, help="Limit news topics if this parameter provided")
 
     # It is done because argparse treat '%' in parameters as old-style formatting
-    date_format_escaped = feed.DATE_FORMAT.replace("%", "%%")
+    date_format_escaped = DATE_FORMAT.replace("%", "%%")
     parser.add_argument("--date", type=date_str,
                         help=f"Load news with date ({date_format_escaped}) from cache, if this parameter provided")
 
@@ -48,9 +49,13 @@ def main():
     logging.info("Program starts")
 
     try:
-        rss_feed = feed.Feed(rss_url, limit)
-    except (feed.URLFormatError, feed.FeedNotFoundError, feed.IncorrectRSSError) as e:
+        if args.date is None:
+            rss_feed = feed.Feed(rss_url, limit)
+        else:
+            rss_feed = feed.Feed(rss_url, limit, date=args.date)
+    except (feed.URLFormatError, feed.FeedNotFoundError, feed.IncorrectRSSError, feed.LocalCacheError) as e:
         logging.error(str(e))
+
     else:
         if not args.json:
             print(rss_feed.render_text())
@@ -58,7 +63,3 @@ def main():
             print(rss_feed.render_json())
 
     logging.info("Program finishes")
-
-
-if __name__ == '__main__':
-    main()

From aa24f8b8d0eff2b940fb5cb8be6eeab8bb5828e8 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 18:22:59 +0300
Subject: [PATCH 24/31] Add check for db, turn main class into context manager

If db is not exist or invalid, it is (re-)created.
Feed class become context manager, it no longer contains heavy methods
in init. Also, it helps to close db connector properly.
Finally, slightly change plain text conversion.
---
 final_task/rss_reader/database.py   | 59 ++++++++++++++++++++++-------
 final_task/rss_reader/feed.py       | 33 +++++++++++-----
 final_task/rss_reader/rss_reader.py | 17 +++------
 3 files changed, 74 insertions(+), 35 deletions(-)

diff --git a/final_task/rss_reader/database.py b/final_task/rss_reader/database.py
index 070eb9a..2982337 100644
--- a/final_task/rss_reader/database.py
+++ b/final_task/rss_reader/database.py
@@ -1,6 +1,7 @@
 import sqlite3
 import time
 import pkg_resources
+import logging
 
 DATE_FORMAT = "%Y-%m-%d"
 DATETIME_FORMAT = "%Y-%m-%d %H:%M:%S"
@@ -19,10 +20,24 @@ def __init__(self):
             self.conn = sqlite3.connect(path)
         except sqlite3.OperationalError as e:
             raise DBError(str(e))
+
         self.cursor = self.conn.cursor()
         self.feed_id = None
 
+        if not self._is_db_exist():
+            self._create_db()
+
+    def _is_db_exist(self):
+        try:
+            self.cursor.execute('''SELECT count(name) FROM sqlite_master 
+                                       WHERE type='table' AND (name='items' or name='feeds')''')
+        except sqlite3.DatabaseError:
+            return False
+        # if the count is 2, then tables exists
+        return self.cursor.fetchone()[0] == 2
+
     def _create_db(self):
+        logging.info("Creating DB for local cache")
         self.cursor.execute("DROP TABLE IF EXISTS feeds")
         self.cursor.execute("DROP TABLE IF EXISTS items")
         self.cursor.execute('''
@@ -54,13 +69,15 @@ def get_feed(self, feed_link, req_date, limit=-1):
         feed_info = self._get_feed_info_if_exists(feed_link)
         if feed_info is not None:
             req_date = time.strftime(DATE_FORMAT, req_date)
-
-            self.cursor.execute('''
-                select i.title, i.published, i.link, i.enclosure, i.description, i.description_parsed 
-                    from items i join feeds f on i.feed_id = f.id 
-                        where f.id=(?) and date(i.published)=date(?) limit (?)
-            ''', (feed_info[0], req_date, limit)
-            )
+            try:
+                self.cursor.execute('''
+                    select i.title, i.published, i.link, i.enclosure, i.description, i.description_parsed 
+                        from items i join feeds f on i.feed_id = f.id 
+                            where f.id=(?) and date(i.published)=date(?) limit (?)
+                ''', (feed_info[0], req_date, limit)
+                )
+            except sqlite3.Error:
+                raise DBError("Error getting items from db")
 
             items = []
             for i in self.cursor.fetchall():
@@ -75,12 +92,19 @@ def get_feed(self, feed_link, req_date, limit=-1):
     def store_feed(self, link, title, items):
         feed_id = self._get_feed_id_if_exists(link)
         if feed_id is None:
-            self.cursor.execute("insert into feeds(title, link) values (?, ?)", (title, link))
-            feed_id = self.cursor.lastrowid
+            try:
+                self.cursor.execute("insert into feeds(title, link) values (?, ?)", (title, link))
+                feed_id = self.cursor.lastrowid
+            except sqlite3.Error:
+                self.conn.rollback()
+                raise DBError("Error adding feed to db")
             self.conn.commit()
         self.feed_id = feed_id
         self._store_items(items)
 
+    def close(self):
+        self.conn.close()
+
     def _store_items(self, items):
         for i in items:
             item_dict = dict(
@@ -92,10 +116,14 @@ def _store_items(self, items):
                 description=i["description"],
                 description_parsed=i["description_parsed"]
             )
-            self.cursor.execute('''
-            insert or ignore into items(feed_id, published, title, link, enclosure, description, description_parsed) 
-                values (:feed_id, :published, :title, :link, :enclosure, :description, :description_parsed)
-            ''', item_dict)
+            try:
+                self.cursor.execute('''
+                insert or ignore into items(feed_id, published, title, link, enclosure, description, description_parsed) 
+                    values (:feed_id, :published, :title, :link, :enclosure, :description, :description_parsed)
+                ''', item_dict)
+            except sqlite3.Error:
+                self.conn.rollback()
+                raise DBError("Error adding item to db")
         self.conn.commit()
 
     def _get_feed_id_if_exists(self, feed_link):
@@ -106,7 +134,10 @@ def _get_feed_id_if_exists(self, feed_link):
             return None
 
     def _get_feed_info_if_exists(self, feed_link):
-        self.cursor.execute("select feeds.id, feeds.title from feeds where feeds.link=?", (feed_link,))
+        try:
+            self.cursor.execute("select feeds.id, feeds.title from feeds where feeds.link=?", (feed_link,))
+        except sqlite3.Error:
+            raise DBError("Error checking Feed in db")
         feed_info = self.cursor.fetchone()
         if feed_info is not None:
             return feed_info[0], feed_info[1]
diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index 14ab064..8dea1c7 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -9,19 +9,23 @@
 from .database import DB, DBError
 
 
-class URLFormatError(ValueError):
+class FeedError(Exception):
     pass
 
 
-class FeedNotFoundError(Exception):
+class URLFormatError(FeedError, ValueError):
     pass
 
 
-class IncorrectRSSError(Exception):
+class FeedNotFoundError(FeedError):
     pass
 
 
-class LocalCacheError(Exception):
+class IncorrectRSSError(FeedError):
+    pass
+
+
+class LocalCacheError(FeedError):
     pass
 
 
@@ -32,9 +36,18 @@ def __init__(self, link, limit=0, *, date=None):
         logging.info(f'The link to the rss feed is "{self.link}"')
         self.title = None
         self.items = []
-
         self.limit = int(limit)
         self.date = date
+        self.db = None
+
+    def __enter__(self):
+        self.load()
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.close()
+
+    def load(self):
         try:
             self.db = DB()
         except DBError:
@@ -44,13 +57,15 @@ def __init__(self, link, limit=0, *, date=None):
                 self.db = None
                 logging.warning("Unable to open local cache. Feed items will not be saved.")
 
-        if date is None:
+        if self.date is None:
             self._parse_remote()
             self._save_to_cache()
         else:
-            self.date = date
             self._load_cache()
 
+    def close(self):
+        self.db.close()
+
     def _parse_remote(self):
         logging.info("Parsing feed from remote source")
         parsed_rss = feedparser.parse(self.link)
@@ -128,8 +143,7 @@ def _save_to_cache(self):
     def render_text(self):
         logging.info("Generating plain text representation of feed")
 
-        s = []
-
+        s = ["\nFeed: "]
         title = self.title or "no title"
         s.append(title)
         s.append("\n")
@@ -153,7 +167,6 @@ def render_text(self):
                     s.append("Enclosure: " + item["enclosure"]+"\n")
                     s.append("\n")
 
-                s.append("Description: ")
                 description = item["description_parsed"] or item["description"] or "no description"
                 s.append(description)
 
diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index 73c8391..926f585 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -49,17 +49,12 @@ def main():
     logging.info("Program starts")
 
     try:
-        if args.date is None:
-            rss_feed = feed.Feed(rss_url, limit)
-        else:
-            rss_feed = feed.Feed(rss_url, limit, date=args.date)
-    except (feed.URLFormatError, feed.FeedNotFoundError, feed.IncorrectRSSError, feed.LocalCacheError) as e:
+        with feed.Feed(rss_url, limit, date=args.date) as rss_feed:
+            if not args.json:
+                print(rss_feed.render_text())
+            else:
+                print(rss_feed.render_json())
+    except feed.FeedError as e:
         logging.error(str(e))
 
-    else:
-        if not args.json:
-            print(rss_feed.render_text())
-        else:
-            print(rss_feed.render_json())
-
     logging.info("Program finishes")

From 962802243221d6bf79e5283932dc5d7a171ae076 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 18:28:36 +0300
Subject: [PATCH 25/31] Add DB exceptions handle(re-raising) to main class

---
 final_task/rss_reader/feed.py | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index 8dea1c7..b4520a1 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -13,7 +13,7 @@ class FeedError(Exception):
     pass
 
 
-class URLFormatError(FeedError, ValueError):
+class URLFormatError(FeedError):
     pass
 
 
@@ -127,7 +127,10 @@ def _load_cache(self):
         limit = -1
         if self.limit > 0:
             limit = self.limit
-        db_feed = self.db.get_feed(self.link, self.date, limit)
+        try:
+            db_feed = self.db.get_feed(self.link, self.date, limit)
+        except DBError:
+            raise LocalCacheError("Unable to load items from cache")
         if db_feed is not None:
             logging.info("Feed successfully loaded")
             self.title = db_feed["title"]
@@ -137,7 +140,10 @@ def _load_cache(self):
 
     def _save_to_cache(self):
         if self.db is not None:
-            self.db.store_feed(self.link, self.title, self.items)
+            try:
+                self.db.store_feed(self.link, self.title, self.items)
+            except DBError:
+                raise LocalCacheError("Unable to save feed to cache")
             logging.info("Feed saved to cache")
 
     def render_text(self):

From 8ae5afdfffc9ae0041967352721dcc4786cfb409 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 19:41:48 +0300
Subject: [PATCH 26/31] Update README and slightly change json output

---
 final_task/README.md          | 55 ++++++++++++++++++++++++++++++++++-
 final_task/rss_reader/feed.py |  4 +--
 2 files changed, 56 insertions(+), 3 deletions(-)

diff --git a/final_task/README.md b/final_task/README.md
index dbb2189..60adc59 100644
--- a/final_task/README.md
+++ b/final_task/README.md
@@ -42,6 +42,59 @@ optional arguments:
   --json         Print result as JSON in stdout
   -v, --verbose  Outputs verbose status messages
   --limit LIMIT  Limit news topics if this parameter provided
+  --date DATE    Load news with date (%Y%m%d) from cache, if this parameter
+                 provided
 ```
-### Licence
+## Behavior
+RSS Reader can work in online or offline mode. 
+
+In **online** mode, when `--date` argument is not provided, the application loads and parses rss feed from `source` argument. 
+It is done using `feedparser` library. 
+Parsed news saved in **_sqlite database_**, which located in `rss_parser/data/rss.sqlite`. 
+If item contains _html_ markup, it converted to plain text.
+
+In **offline** mode, when `--date` argument is provided, 
+the application loads news with specified feed link and date from the database.
+
+News printed to stdout in the following format:
+
+```
+Feed: *RSS feed title*
+
+
+Title: *item 1 title*
+Date: *%a, %d %b %Y %H:%M:%S +0000* 
+Link: https://example.com/link_to_item
+
+*Item description*
+
+Links:
+[1]: *first link is always link to item*
+[2]: Others can be links parsed from  <a> or <img> tags
+
+
+Title: *item 2 title*
+Date: ...
+```
+
+News is converted to json like this:
+```
+{
+  "title": "*Feed title*",
+  "link": "*link to feed*"
+  "items": [
+    {
+      "title": "*item 1 title*",
+      "date": *time.struct_time tuple*,
+      "link": "*link to item*",
+      "enclosure": *null* or *link to eclosure*,
+      "description": "*item description*",
+      "description_parsed": "*description parsed to plain text*"  or *null* if description is text
+    },
+    ...
+  ]
+}
+```
+
+## Licence
 This project is licensed under the MIT License - see the LICENSE file for details.
diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index b4520a1..eb29605 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -181,8 +181,8 @@ def render_text(self):
 
     def render_json(self):
         logging.info("Generating json representation of feed")
-        feed_dict = {"title": self.title, "items": self.items}
-        s = json.dumps(feed_dict, indent="\t")
+        feed_dict = {"title": self.title, "link": self.link, "items": self.items}
+        s = json.dumps(feed_dict, indent=2)
         return s
 
     @staticmethod

From ef7f12a3a6b88fa3fe9bc2cea643dd03000128a2 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 19:42:56 +0300
Subject: [PATCH 27/31] Bumps version number

---
 final_task/rss_reader/rss_reader.py | 2 +-
 final_task/setup.py                 | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index 926f585..a7e2dec 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -5,7 +5,7 @@
 from . import feed
 
 # temp
-__version__ = "0.2"
+__version__ = "0.3"
 PROG = "rss-reader"
 DATE_FORMAT = "%Y%m%d"
 
diff --git a/final_task/setup.py b/final_task/setup.py
index f037459..2b3336b 100644
--- a/final_task/setup.py
+++ b/final_task/setup.py
@@ -5,7 +5,7 @@
 
 setup(
     name="rss-reader_scarzdz",
-    version="0.2",
+    version="0.3",
     url="https://github.com/scarzdz/FinalTaskRssParser",
     license="MIT",
     author="Denis Marfonov",
@@ -30,5 +30,5 @@
         "console_scripts": [
             "rss-reader=rss_reader.rss_reader:main",
         ],
-    },
+    }
 )

From 7f63ba87db2517835418c0207ad4e184d232a1bc Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 19:55:30 +0300
Subject: [PATCH 28/31] Make post-release to correct mistake

---
 final_task/setup.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/final_task/setup.py b/final_task/setup.py
index 2b3336b..0341368 100644
--- a/final_task/setup.py
+++ b/final_task/setup.py
@@ -5,7 +5,7 @@
 
 setup(
     name="rss-reader_scarzdz",
-    version="0.3",
+    version="0.3.post1",
     url="https://github.com/scarzdz/FinalTaskRssParser",
     license="MIT",
     author="Denis Marfonov",

From 4eda8c6fd11775ac16b2f6e2e53d0b5ecdc36b6b Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 22:47:29 +0300
Subject: [PATCH 29/31] Add epub and html creating

---
 final_task/rss_reader/book_gen.py   | 110 ++++++++++++++++++++++++++++
 final_task/rss_reader/feed.py       |   7 ++
 final_task/rss_reader/rss_reader.py |  17 ++++-
 3 files changed, 130 insertions(+), 4 deletions(-)
 create mode 100644 final_task/rss_reader/book_gen.py

diff --git a/final_task/rss_reader/book_gen.py b/final_task/rss_reader/book_gen.py
new file mode 100644
index 0000000..605c5e6
--- /dev/null
+++ b/final_task/rss_reader/book_gen.py
@@ -0,0 +1,110 @@
+import time
+import os.path
+import html
+
+from ebooklib import epub
+
+DATE_FORMAT = "%Y%m%d"
+
+
+def _render_document(title, items, date_str):
+    html = ["<html><head><title>"]
+    h_title = f"{date_str}"
+    html.append(h_title)
+    html.append("</title></head><body>")
+
+    html.append("<h1>")
+    html.append(title)
+    html.append("</h1>")
+
+    for i in items:
+        html.append(_render_item(i))
+
+    html = "".join(html)
+    return html
+
+
+def _render_item(item):
+    html = ["<hr>"]
+    title = item["title"] or "No Headline"
+    html.append(f"<h2>{title}</h2>")
+    date = time.strftime("%a, %d %b %Y %H:%M:%S", item["date"])
+    html.append(f"<p><i>{date}</i></p>")
+    if item["link"] is not None:
+        link = item["link"]
+        html.append(f"<p><a href='{link}'>{link}</a></p>")
+    else:
+        html.append(f"<p><a>no link</a></p>")
+    description = item["description"] or "No description"
+    html.append(f"<p>{description}</p>")
+    html = "".join(html)
+    return html
+
+
+def _gen_id(title: str, date:str) -> str:
+    """
+    generate string for book id and file name
+
+    :return: generated string
+    """
+    string = title + "_" + date
+    string = string.lower()
+    for c in r'\|/:*?"<>':
+        string.replace(c, '_')
+    if len(string) > 122:
+        string = string[:121] + "..."
+    return string
+
+
+def _create_html(book_id, bookpath, text):
+    # text = html.escape(text)
+    file = None
+    if os.path.isdir(bookpath):
+        file = open(os.path.join(bookpath, book_id + ".html"), "w", encoding="utf-8")
+    elif not os.path.exists(bookpath) or os.path.isfile(bookpath) or os.path.islink(bookpath):
+        file = open(bookpath, "w", encoding="utf-8")
+    try:
+        file.write(text)
+        file.close()
+    except (AttributeError, OSError):
+        pass
+
+
+def _create_epub(book_title, book_id, bookpath, text):
+
+    book = epub.EpubBook()
+    book.set_language('en')
+    book.set_identifier(book_id)
+    book.set_title(book_title)
+
+    content = epub.EpubHtml(title='News', file_name='content.xhtml')
+
+    content.set_content(text)
+    book.add_item(content)
+
+    book.toc = (content,)
+    book.spine = [content]
+    book.add_item(epub.EpubNcx())
+    book.add_item(epub.EpubNav())
+    if os.path.isdir(bookpath):
+        epub.write_epub(os.path.join(bookpath, book_id+".epub"), book)
+    elif not os.path.exists(bookpath) or os.path.isfile(bookpath) or os.path.islink(bookpath):
+        epub.write_epub(bookpath, book)
+
+
+def create_book(title, items, bookpath, date=None, *, html=False):
+    if date is not None:
+        date = time.strftime(DATE_FORMAT, date)
+    else:
+        date = "Latest"
+
+    if title is None:
+        title = "No Title"
+    book_title = title + " - " + date
+    text = _render_document(book_title, items, date)
+    book_id = _gen_id(title, date)
+
+    if html:
+        _create_html(book_id, bookpath, text)
+    else:
+        _create_epub(book_title, book_id, bookpath, text)
diff --git a/final_task/rss_reader/feed.py b/final_task/rss_reader/feed.py
index eb29605..99852e8 100644
--- a/final_task/rss_reader/feed.py
+++ b/final_task/rss_reader/feed.py
@@ -7,6 +7,7 @@
 
 from . import html_to_text
 from .database import DB, DBError
+from . import book_gen
 
 
 class FeedError(Exception):
@@ -185,6 +186,12 @@ def render_json(self):
         s = json.dumps(feed_dict, indent=2)
         return s
 
+    def create_html(self, path):
+        book_gen.create_book(self.title, self.items, path, self.date, html=True)
+
+    def create_epub(self, path):
+        book_gen.create_book(self.title, self.items, path, self.date)
+
     @staticmethod
     def _try_fix_url(url):
         try:
diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index a7e2dec..c0fa3c6 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -1,6 +1,7 @@
 import argparse
 import logging
 import time
+import os.path
 
 from . import feed
 
@@ -21,11 +22,15 @@ def date_str(string):
 
 def main():
     parser = argparse.ArgumentParser(description="Pure Python command-line RSS reader.", prog=PROG)
+    group = parser.add_mutually_exclusive_group()
+    group.add_argument("--json", action="store_true", help="Print result as JSON in stdout")
+    group.add_argument("--html", type=str, help="Generate html book on path", metavar='PATH')
+    group.add_argument("--epub", type=str, help="Generate epub book an path", metavar='PATH')
 
     parser.add_argument("source", help="RSS URL")
     parser.add_argument("--version", action="version", version=f"{parser.prog}s {__version__}",
                         help="Print version info")
-    parser.add_argument("--json", action="store_true", help="Print result as JSON in stdout")
+    # parser.add_argument("--json", action="store_true", help="Print result as JSON in stdout")
     parser.add_argument("-v", "--verbose", action="store_true", help="Outputs verbose status messages")
     parser.add_argument("--limit", type=int, help="Limit news topics if this parameter provided")
 
@@ -50,10 +55,14 @@ def main():
 
     try:
         with feed.Feed(rss_url, limit, date=args.date) as rss_feed:
-            if not args.json:
-                print(rss_feed.render_text())
-            else:
+            if args.json:
                 print(rss_feed.render_json())
+            elif args.epub is not None:
+                rss_feed.create_epub(args.epub)
+            elif args.html is not None:
+                rss_feed.create_html(args.html)
+            else:
+                print(rss_feed.render_text())
     except feed.FeedError as e:
         logging.error(str(e))
 

From 665e65bdc1c80b4a5c965e6537e375d0454a17b7 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 22:49:00 +0300
Subject: [PATCH 30/31] Update README

---
 final_task/README.md | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/final_task/README.md b/final_task/README.md
index 60adc59..1808c1b 100644
--- a/final_task/README.md
+++ b/final_task/README.md
@@ -29,7 +29,9 @@ $ python -m rss_reader ...
 ```
 ### Usage
 ```
-usage: rss-reader [-h] [--version] [--json] [-v] [--limit LIMIT] source
+usage: rss-reader [-h] [--json | --html PATH | --epub PATH] [--version] [-v]
+                  [--limit LIMIT] [--date DATE]
+                  source
 
 Pure Python command-line RSS reader.
 
@@ -38,8 +40,10 @@ positional arguments:
 
 optional arguments:
   -h, --help     show this help message and exit
-  --version      Print version info
   --json         Print result as JSON in stdout
+  --html PATH    Generate html book on path
+  --epub PATH    Generate epub book an path
+  --version      Print version info
   -v, --verbose  Outputs verbose status messages
   --limit LIMIT  Limit news topics if this parameter provided
   --date DATE    Load news with date (%Y%m%d) from cache, if this parameter

From 8553cf45c22440c35c2b5b0d60db03f2ea86b260 Mon Sep 17 00:00:00 2001
From: scarzdz <scar.zdz@gmail.com>
Date: Mon, 25 Nov 2019 22:53:29 +0300
Subject: [PATCH 31/31] Bump version number and add new requirement

---
 final_task/rss_reader/requirements.txt | 3 ++-
 final_task/rss_reader/rss_reader.py    | 2 +-
 final_task/setup.py                    | 5 +++--
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/final_task/rss_reader/requirements.txt b/final_task/rss_reader/requirements.txt
index 5c90ddd..ccccda4 100644
--- a/final_task/rss_reader/requirements.txt
+++ b/final_task/rss_reader/requirements.txt
@@ -1,3 +1,4 @@
 lxml~=4.4.1
 feedparser~=5.2.1
-beautifulsoup4~=4.8.1
\ No newline at end of file
+beautifulsoup4~=4.8.1
+ebooklib~=0.17.1
\ No newline at end of file
diff --git a/final_task/rss_reader/rss_reader.py b/final_task/rss_reader/rss_reader.py
index c0fa3c6..0d652fe 100644
--- a/final_task/rss_reader/rss_reader.py
+++ b/final_task/rss_reader/rss_reader.py
@@ -6,7 +6,7 @@
 from . import feed
 
 # temp
-__version__ = "0.3"
+__version__ = "0.4"
 PROG = "rss-reader"
 DATE_FORMAT = "%Y%m%d"
 
diff --git a/final_task/setup.py b/final_task/setup.py
index 0341368..7ab1d7f 100644
--- a/final_task/setup.py
+++ b/final_task/setup.py
@@ -5,7 +5,7 @@
 
 setup(
     name="rss-reader_scarzdz",
-    version="0.3.post1",
+    version="0.4",
     url="https://github.com/scarzdz/FinalTaskRssParser",
     license="MIT",
     author="Denis Marfonov",
@@ -24,7 +24,8 @@
     install_requires=[
         "beautifulsoup4",
         "feedparser",
-        "lxml"
+        "lxml",
+        "ebooklib"
     ],
     entry_points={
         "console_scripts": [