Anatoli_Ageichik_3anatoliageichik@gmail.com

.gitignore

@@ -0,0 +1,13 @@
+.idea/
+final_task/dist
+*.pyc
+*.json
+*.idea'.idea'
+final_task/rss_reader/.coverage
+*.html
+*.pdf
+*.pkl
+*.idea'.idea'
+final_task/FinalTaskRssParser.egg-inf
+final_task/rss_reader/images/
+.idea/

final_task/README.md

@@ -1,3 +1,49 @@
-# Your readme here
-Some text.
-Checkout how to write this file using *markdown*.
+
+# Python RSS-reader
+Python RSS-reader is a command-line utility which receives RSS URL and prints results in human-readable format.
+
+To start Python RSS-reader run one of the following commands in command line:
+
+ ``python rss_reader.py "https://news.yahoo.com/rss/" --limit 1``
+``python rss_reader.py "https://timesofindia.indiatimes.com/rssfeedstopstories.cms" --json --limit 1``
+  7 file in my project
+  - consoleArgumemt.py this file which handles console phrases
+  - ConsoleOut.py - in this file function which handles print to console
+  - Handler.py - handles request
+  - Log.py - 
+  - rss-reader.py - main file in project
+  - RssException.py - contains exception
+  - WorkWithCache.py -  in this file function which works with cache(read and write json)
+
+### JSON structure:
+ ``` 
+{
+    "news": "news text",
+    "title": "Title of news",
+    "date": "Wed, 20 Nov 2019 02:47:47 -0500",
+    "links": [
+      "http://l1.yimg.com/uu/api/res/1.2/1KHP4ztUcOL6a98.vsEHQA--/YXBwaWQ9eXRhY2h5b247aD04Njt3PTEzMDs-/http://media.zenfs.com/en_us/News/afp.com/0dca2dadd67f7128eb881f0333640fce05a84084.jpg"
+    ],
+    "strDate": "20191120"
+
+} 
+```
+### Functional
+```
+positional arguments:
+source RSS URL
+optional arguments:
+-h, --help show this help message and exit
+--version Print version info
+--json Print result as JSON in stdout
+--verbose Outputs verbose status messages
+--limit LIMIT Limit news topics if this parameter provided
+--date - view news from cache with specified date
+```
+
+### Iteration 4
+``python rss_reader.py --date 20191122 --to_html "D:\EpamFINAL\FinalTaskRssParser\final_task\rss_reader"``
+
+``python rss_reader.py "https://news.yahoo.com/rss/" --to_pdf  "D:\EpamFINAL\FinalTaskRssParser\final_task\rss_reader"
+
+

final_task/rss_reader/ConsoleArgument.py

@@ -0,0 +1,15 @@
+import argparse
+
+
+def get_console_argument():
+    arg = argparse.ArgumentParser(description="read command of comamnd-line")
+    arg.add_argument("link", nargs='?', type=str, default="", help="Rss URL")
+    arg.add_argument('--limit', help="limit news topics if this parameter privided", type=int)
+    arg.add_argument('--verbose', help="verbose", action='store_true')
+    arg.add_argument('--json', help="print result as json in stdout", action='store_true')
+    arg.add_argument('--version', help="print version info", action='store_true')
+    arg.add_argument('--date', help="print news from cache for your date",  type=int)
+    arg.add_argument('--to-html', help="create html file with news")
+    arg.add_argument('--to-pdf', help="create pdf file with news")
+
+    return arg.parse_args()

final_task/rss_reader/ConsoleOut.py

@@ -0,0 +1,33 @@
+from pprint import pprint
+
+from Log import log_decore
+
+
+@log_decore
+def print_json(list_json):
+    for item_list in list_json:
+        pprint(item_list)
+
+
+@log_decore
+def print_array_of_news(news):
+    for item_news in news:
+        print("Title: " + item_news.title)
+        print("Date:  " + item_news.date)
+        print("Link:  " + item_news.link)
+        print("\n" + item_news.news + '\n')
+        print("Links: ")
+        for item_link in item_news.links:
+            print(item_link + "\n")
+
+
+@log_decore
+def print_array_of_dict(news):
+    for item_news in news:
+        print("Title: " + item_news["title"])
+        print("Date:  " + item_news["date"])
+        print("Link:  " + item_news["link"])
+        print("\n" + item_news["news"] + '\n')
+        print("Links: ")
+        for item_link in item_news["links"]:
+            print(item_link + "\n")

final_task/rss_reader/ConvertToHtmlAndPdf.py

@@ -0,0 +1,112 @@
+import os
+import sys
+from fpdf import FPDF
+from News import News
+from dominate.tags import html, head, meta, body, div, img, p, b, br, h1, a
+
+from WorkWithCache import correct_title
+from Log import log_decore
+from RssException import RssException
+
+@log_decore
+def convert_Dict_to_News(arr_news_dict):
+    all_news = []
+    for item_news in arr_news_dict:
+        tmp_img_link = item_news["links"]
+        tmp_link = item_news["link"]
+        tmp_news = item_news["news"]
+        tmp_title = item_news["title"]
+        tmp_date = item_news["date"]
+        tmp_date_str_date = item_news["strDate"]
+        item_of_list_news = News(tmp_news, tmp_link, tmp_title, tmp_date, tmp_img_link, tmp_date_str_date)
+        all_news.append(item_of_list_news)
+    return all_news
+
+
+
+'''create an HTML file and fill it with news'''
+@log_decore
+def create_html_news(path, News):
+    if os.path.isdir(path) is False:
+        raise RssException("Error. It isn't a folder")
+
+    path = os.path.join(path, "News.html")
+
+    news_html = html()
+    news_html.add(head(meta(charset='utf-8')))
+    news_body = news_html.add(body())
+    with news_body:
+        for item_news in News:
+            news_body = news_body.add(div())
+            news_body += h1(item_news.title)
+            news_body += p(b("Date: "), a(item_news.date))
+
+            text = item_news.news
+
+            # remove links in the text and add pictures
+            if len(item_news.links) > 0:
+                start = text.find(']', 0, len(text))
+                text = text[start + 1:]
+
+                this_dir = os.path.abspath(os.path.dirname(__file__))
+                sys.path.append(this_dir)
+                news_body += img(src=f"file:///{this_dir}/images/{correct_title(item_news.title)}.jpg")
+            else:
+                # if there are no pictures, just remove the links
+                start = text.find(']', 0, len(text))
+                text = text[start + 1:]
+
+            news_body += p(text.encode("utf-8").decode("utf-8"), br(), br())
+
+    try:
+        with open(path, 'w', encoding='utf-8') as rss_html:
+            rss_html.write(str(news_html))
+    except FileNotFoundError:
+        raise RssException('Error. No such folder\n')
+    print("file News.html created")
+
+
+
+'''create an PDF file and fill it with news'''
+@log_decore
+def create_pdf_news(path, News):
+    if os.path.isdir(path) is False:
+        raise RssException("Error. It isn't a folder")
+    path = os.path.join(path, "News.pdf")
+
+    pdf = FPDF()
+    try:
+        pdf.add_font('DejaVuSans', '', 'DejaVuSans.ttf', uni=True)
+        pdf.set_font("DejaVuSans")
+    except RuntimeError:
+        raise RssException("fonts file not found")
+    pdf.alias_nb_pages()
+    pdf.add_page()
+
+    for item_news in News:
+        text = item_news.news
+        # remove links in the text and add pictures
+
+        start = text.find(']', 0, len(text))
+        text = text[start + 1:]
+
+        pdf.set_font_size(26)
+        pdf.write(11, item_news.title + '\n\n')
+        pdf.set_font_size(14)
+        pdf.write(11, f"Date: {item_news.date}\n")
+
+        this_dir = os.path.abspath(os.path.dirname(__file__))
+        sys.path.append(this_dir)
+        if len(item_news.links) > 0:
+            try:
+                pdf.image(f'{this_dir}/images/{correct_title(item_news.title)}.jpg', w=75, h=75)
+            except RuntimeError:
+                pass
+        pdf.write(10, "\n")
+        pdf.write(10, text + "\n\n\n\n")
+    pdf.output(path, 'F')
+    try:
+        pdf.output(path, 'F')
+    except FileNotFoundError:
+        raise RssException("Error. No such folder")
+    print("file News.pdf created")

final_task/rss_reader/Handler.py

@@ -0,0 +1,124 @@
+import feedparser
+from dataclasses import asdict
+import html
+
+from Log import log_decore
+from WorkWithCache import write_json_to_cache
+from News import News
+''' convert from News class to json'''
+
+
+@log_decore
+def parse_to_json(news):
+    return asdict(news)
+
+
+
+''' In this class, we do all the news processing. 
+Here we translate the format required by the user'''
+
+
+class Handler:
+    @log_decore
+    # limit - count elements which user want see
+    def __init__(self, url, limit):
+
+        self.article = feedparser.parse(url)
+        self.numb_news = 0
+        self.parsers = []
+        # standart value if user did not indicate limit we get all news
+        if limit == -1:
+            limit = len(self.article.entries)
+        self.create_news(url, limit)
+
+    @log_decore
+    def create_news(self, url, limit):
+        # for every news, which user will see we create object
+        while self.numb_news < limit:
+            tmp_img_link = self.get_img_links(self.get_news(self.numb_news))
+            tmp_link = self.get_link(self.numb_news)
+            tmp_news = self.parse_html(self.get_news(self.numb_news))
+            tmp_title = self.get_title(self.numb_news)
+            tmp_date = self.get_date(self.numb_news)
+            tmp_date_str_date = self.get_str_date(self.numb_news)
+            item_of_list_news = News(tmp_news, tmp_link, tmp_title, tmp_date, tmp_img_link, tmp_date_str_date)
+            self.parsers.append(item_of_list_news)
+            self.numb_news += 1
+
+    @log_decore
+    def get_news(self, index):
+        try:
+            return self.article.entries[index].summary
+        except IndexError:
+            pass
+
+    @log_decore
+    def get_link(self, index):
+        return self.article.entries[index].link
+
+
+    @log_decore
+    def get_title(self, index):
+        return html.unescape(self.article.entries[index].title)
+
+    @log_decore
+    def get_date(self, index):
+        return self.article.entries[index].published
+
+    @log_decore
+    def get_str_date(self, index):
+        str_date = ""
+        str_date += str(self.article.entries[index]['published_parsed'].tm_year)
+        str_date += str(self.article.entries[index]['published_parsed'].tm_mon)
+        str_date += str(self.article.entries[index]['published_parsed'].tm_mday)
+        return str_date
+
+    @log_decore
+    def get_img_links(self, text):
+        img_links = []
+        index_start_find = 0
+        while 1:
+            start = text.find('src="', index_start_find, len(text))
+            index_start_find = start + len('src="')
+            end = text.find('"', index_start_find)
+            if start == -1 or end == -1:
+                break
+            img_links.append(text[start + len('src="'):end])
+        return img_links
+
+    @log_decore
+    def get_img_alt(self, text):
+        img_alt = []
+        index_start_find = 0
+        while 1:
+            start = text.find('alt="', index_start_find, len(text))
+            index_start_find = start + len('alt="')
+            end = text.find('"', index_start_find)
+            if start == -1 or end == -1:
+                break
+            img_alt.append(text[start + len('alt="'):end])
+        return img_alt
+
+    @log_decore
+    def parse_html(self, text):
+        news = ""
+        img_alt = self.get_img_alt(text)
+        # add imgLinks to article
+        for id, item in enumerate(img_alt):
+            news += ("[img " + str(id) + " ")
+            news += (item + "]")
+
+        # clean the news from
+        while text.count('<'):
+            text = text[:text.find('<')] + text[text.find('>') + 1:]
+        news += text
+        news = html.unescape(news)
+        return news
+
+    @log_decore
+    def get_all(self):
+        # return all news which user want see
+        for item_news in self.parsers:
+            write_json_to_cache(parse_to_json(item_news))
+
+        return self.parsers

final_task/rss_reader/Log.py

@@ -0,0 +1,11 @@
+import logging
+
+
+def log_decore(fn):
+    def wrapper(*args, **kwargs):
+        logging.info(f"function \"{fn.__name__}\"Run function")
+        res = fn(*args, **kwargs)
+        logging.info(f"function \"{fn.__name__}\"Stop function")
+        return res
+
+    return wrapper

final_task/rss_reader/News.py

@@ -0,0 +1,17 @@
+from dataclasses import dataclass
+from typing import List
+
+''' 
+    in this class, we store news in the required format and 
+    implement all the logic for processing news in the class Handler
+'''
+
+
+@dataclass
+class News:
+    news: str
+    link: str
+    title: str
+    date: str
+    links: List[str]
+    strDate: str

final_task/rss_reader/RssException.py

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