Victoria_Kondrat'eva_sam.kondrateva@gmail.com

.gitignore

@@ -0,0 +1,52 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+bin/
+build/
+develop-eggs/
+dist/
+eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+.tox/
+.coverage
+.cache
+nosetests.xml
+coverage.xml
+
+# Translations
+*.mo
+
+# Mr Developer
+.mr.developer.cfg
+.project
+.pydevproject
+
+# Rope
+.ropeproject
+
+# Django stuff:
+*.log
+*.pot
+
+# Sphinx documentation
+docs/_build/
+
+Test_file.json

final_task/README.md

@@ -1,3 +1,110 @@
-# Your readme here
-Some text.
-Checkout how to write this file using *markdown*.
+#The best RSS-reader!
+Program is named rss_reader.py.
+##Instalation
+The recommended way to install rss-reader is with pip:
+* pip install rss_reader-5.0.tar.gz - for Windows
+* sudo pip install rss_reader-5.0.tar.gz - for Linux and Mac
+
+##Description and Functions
+```
+usage: rss_reader.py [-h] [--limit LIMIT] [--version] [--json] [--verbose]
+                     [--date DATE] [--to_pdf TO_PDF] [--to_epub TO_EPUB]
+                     [--colorize]
+                     [source]
+
+Pure Python command-line RSS reader.
+
+positional arguments:
+  source             RSS URL
+
+optional arguments:
+  -h, --help         show this help message and exit
+  --limit LIMIT      Limit news topics if this parameter provided
+  --version          Print version info
+  --json             Print result as JSON in stdout
+  --verbose          Outputs verbose status messages
+  --date DATE        Return news from cache with that date
+  --to_pdf TO_PDF    Conversion of news in the pdf format
+  --to_epub TO_EPUB  Conversion of news in the epub format
+  --colorize         Print news in colorized mode in stdout
+```
+
+To run the program from the command line, you must write the file name and string with URL-address of news site.
+
+It's print a brief description of the news information that appeared on the news site in human-readable
+format and save them in cache. 
+
+Example:
+```python rss_reader.py "https://news.yahoo.com/rss/" --limit 1
+
+Feed: Yahoo News - Latest News & Headlines
+
+Updated: Sun, 24 Nov 2019 21:19:04 GMT
+
+Version: rss20
+--------------------------------------------------------
+Title: Ukraine's President Zelensky said he didn't feel pressured by Trump. Here
+'s why that's bogus.
+Date: Sat, 23 Nov 2019 08:57:00 -0500
+Link: https://news.yahoo.com/ukraines-president-zelensky-said-didnt-135700678.ht
+ml
+Summary:  [Image: Ukraine's President Zelensky said he didn't feel pressured by
+Trump. Here's why that's bogus.] The US government's assistance to Ukraine is vi
+tal as it contends with an ongoing conflict with pro-Russian separatists in the
+Donbas region.
+Source of image: http://l2.yimg.com/uu/api/res/1.2/3h5JxcDjAP1pHR6KUD2JMQ--/YXBw
+aWQ9eXRhY2h5b247aD04Njt3PTEzMDs-/https://media.zenfs.com/en-US/business_insider_
+articles_888/7a21ff2ee09c3b4285094c4e64e9602c
+```
+###Nice features
+To please the eyes you can read news from console in a colorful format.
+For this enter such parameter like --colorize and enjoy.
+
+But this parameter work only for MAC and Linux console.
+
+###How to read saving news:
+If you want to read saved news of a certain date, you must enter a --date in %Y%m%d format and the program will work
+without any connecting to the Internet.
+
+It is also possible to select news from a specific source of a certain date, for this you must enter the url-address
+and --date that you want.
+
+###What formats can you convert to? How to do it.
+Program can convert news in ```--to_pdf``` and ```--to_epub``` format. 
+Specify the path to the file yourself. Also program convert news in ```--json``` format
+but print result as JSON in stdout.
+
+JSON format example:
+```json
+[
+    {
+        "Feed": "Yahoo",
+        "Updated": "Fri, 08 Nov 2019 17:04:06 GMT",
+        "Version": "rss20"
+    },
+    {
+        "Title": "Some title",
+        "Date": "Thu, 07 Nov 2019 09:59:52 -0500",
+        "Summary": "Some summary",
+        "Link": "Link to news",
+        "Image": "Some image information"
+    }
+]
+```
+#####Ways for converting:
+- *You can convert from cache*
+
+For this case news conversion is not depend on internet.
+With ```rss_reader.py --date 20191117 --limit 1 --to_pdf /folder1/folder2/file_name.pdf``` one news for the specified day
+would be converted (the same with ```--to_epub```) and would be generated or overwritten file 'file_name.pdf'
+in folder what you choose.
+
+- *You can convert news from the Internet*
+
+For this case Internet is required.
+With ```rss_reader.py https://news.yahoo.com/rss/ --limit 1 --to_pdf /folder1/folder2/file_name.pdf``` one news
+from specified link would be converted (the same with ```--to_epub```)and would be generated or overwritten
+file 'file_name.epub' in folder what you choose.
+
+
+

final_task/rss_reader/NewsCache.py

@@ -0,0 +1,49 @@
+import json
+import os.path
+import logging
+
+
+class NewsCache:
+    """Class which create json-file with cached news,
+    saved all fresh news and return them with certain date
+    and from certain url-address if such url will be introduced."""
+
+    def __init__(self, file_name):
+        self.logger = logging.getLogger(__name__)
+        self.file_name = file_name
+        self.logger.info("Check for cache file...")
+        if os.path.isfile(file_name):
+            try:
+                with open(file_name, "r") as json_file:
+                    self.cache_news = json.load(json_file)
+                    self.logger.info("Reading cache file...")
+            except Exception as ex:
+                self.logger.error("Error reading file: {} {}".format(type(ex), ex))
+                self.cache_news = {}
+        else:
+            self.logger.warning("Warning! Caching file is not found!")
+            self.cache_news = {}
+
+    def caching(self, all_news, url):
+        """Function which create JSON-file
+        and save news."""
+        for dictionary in all_news:
+            date_in_news = dictionary.pop('Date key')
+            title = dictionary['Title']
+            self.cache_news.setdefault(date_in_news, {}).setdefault(url, {}).setdefault(title, dictionary)
+        with open(self.file_name, "w") as file_to_write:
+            self.logger.info("News caching...")
+            file_to_write.write(json.dumps(self.cache_news))
+
+    def returning(self, desired_date, desired_url=None):
+        """Function which return news from cache-file with certain date
+        and from certain url-address if such url will be introduced."""
+        self.logger.info('News search in cache...')
+        caching_news_list = []
+        if desired_url is not None:
+            caching_news_list = list(self.cache_news.get(desired_date, {}).get(desired_url, {}).values())
+        else:
+            answer = self.cache_news.get(desired_date, {})
+            for title in answer.values():
+                caching_news_list += title.values()
+        return caching_news_list

final_task/rss_reader/RSSReader.py

@@ -0,0 +1,126 @@
+import datetime
+import feedparser
+import logging
+from bs4 import BeautifulSoup
+from RSSReaderException import RSSReaderException
+from NewsCache import NewsCache
+from unidecode import unidecode
+from output import get_output_function
+
+CACHE_FILE_NAME = "Cache file.json"
+
+
+class RSSReader:
+
+    def __init__(self, date, url, limit, is_json, pdf_file_name, epub_file_name, color):
+        self.cache = NewsCache(CACHE_FILE_NAME)
+        self.date = date
+        self.url = url
+        self.is_json = is_json
+        self.limit = limit
+        self.pdf_file_name = pdf_file_name
+        self.epub_file_name = epub_file_name
+        self.color = color
+        self.logger = logging.getLogger(__name__)
+
+    def url_parsing(self):
+        parsed_url = feedparser.parse(self.url)
+        if parsed_url.status != 200:  # URL-access check
+            self.logger.error("Can't load RSS feed.")
+            raise RSSReaderException('RSS-reader failed. Status: {}.'.format(parsed_url.status))
+        else:
+            self.logger.info('RSS parsed successfully!')
+            return parsed_url
+
+    def information_about_site(self, parsed_url):
+        """Function which make dictionary with data of website"""
+        date = parsed_url.get('updated', str(datetime.datetime.now()))
+        return {
+            'Feed': unidecode(parsed_url['feed']['title']),
+            'Updated': date,
+            'Version': unidecode(parsed_url['version']),
+        }
+
+    def make_news_data(self, news):
+        """
+        Function which parsed HTML summary of news and make dictionary with all the necessary news data.
+        :return dictionary
+        """
+        image_link = 'No image'
+        if 'summary' in news:
+            # convert_to_epub(news['summary'])
+            bs = BeautifulSoup(news['summary'], 'html.parser')
+            img = bs.find_all('img')
+            if img:
+                image_description = unidecode(img[0].get('alt', 'no description'))
+                image_link = img[0].get('src')
+                img[0].replaceWith(f' [Image: {image_description}] ')
+            summary = unidecode(str(bs.text))
+        else:
+            summary = news['title']
+        date_info = news['published_parsed'] if 'published' in news else news['updated_parsed']
+        date_key = str("{}{}{}".format(date_info.tm_year, date_info.tm_mon, date_info.tm_mday))
+        news_summary = {
+            'Title': unidecode(news['title']),
+            'Date': news['published'] if 'published' in news else news['updated'],
+            'Link': news['link'],
+            'Summary': summary,
+            'Source of image': image_link,
+            'Date key': date_key
+        }
+        return news_summary
+
+    def news_data_collection(self, parsed_url):
+        """Function that collects data from all news by calling make_news_data.
+        :return string of dictionaries
+        """
+        all_information_about_news = parsed_url['entries']
+        # amount_of_news = len(parsed_url.entries)
+        all_news = []
+        self.logger.info('News gathering')
+        for news in all_information_about_news[:self.limit]:
+            try:  # Exception when news is failed
+                dictionary_of_news_data = self.make_news_data(news)
+            except Exception as ex:
+                self.logger.error("Error processing news: {} {}".format(type(ex), ex))
+            else:
+                all_news.append(dictionary_of_news_data)  # make list of dictionaries of news data for optional output
+        return all_news
+
+    def get_news(self):
+        """Get news!"""
+        if self.date is None:
+            if self.url is None:
+                self.logger.error("URL is not provided.")
+                return
+            self.logger.info('Start parsing...')
+            try:
+                parsed_url = self.url_parsing()
+                about_website = self.information_about_site(parsed_url)
+            except Exception as ex:  # for any exception after website parsing
+                self.logger.error("Error reading site data: {}, {}.".format(type(ex), ex))
+                return
+            string_of_news_dictionaries = self.news_data_collection(parsed_url)
+            self.cache.caching(string_of_news_dictionaries, self.url)
+        else:
+            string_of_news_dictionaries = self.cache.returning(self.date, self.url)[:self.limit]
+            about_website = None
+        if not string_of_news_dictionaries:
+            self.logger.error('There is no news.')
+            return
+        file_name = None
+        if self.is_json:
+            converter = 'json'
+        elif self.pdf_file_name:
+            converter = 'pdf'
+            file_name = self.pdf_file_name
+        elif self.epub_file_name:
+            converter = 'epub'
+            file_name = self.epub_file_name
+        elif self.color:
+            converter = 'color'
+        else:
+            self.logger.info('Output news')
+            converter = 'text'
+        output = get_output_function(converter)
+        output(self.logger, string_of_news_dictionaries, about_website, file_name)

final_task/rss_reader/RSSReaderException.py

@@ -0,0 +1,2 @@
+class RSSReaderException(Exception):
+    pass