introduction-to-python-bsuir-2019 · Archeex · Nov 10, 2019 · Nov 17, 2019 · Nov 17, 2019 · Nov 17, 2019
diff --git a/README.md b/README.md
@@ -0,0 +1,29 @@
+# Pure Python RSS Reader [PythonHomework]
+
+Python version: v3.8
+
+Current version: v0.5
+
+Code checking: Code correspond to pep8
+#### Usage:
+```shell
+usage: __main__.py [-h] [--version] [--json] [--verbose] [--limit LIMIT] [--date DATE] [--to-pdf] [--to-html] 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
+  --verbose      Outputs verbose status messages
+  --limit LIMIT  Limit news topics if this parameter provided
+  --date DATE    Show cached news by input date
+  --to-pdf       Convert news to pdf format
+  --to-html      Convert news to html format
+  ```
+  JSON scheme is described in `json_schema.json`.
+
+  News cache in json file `cached_news.json` in root application directory.
diff --git a/json_schema.json b/json_schema.json
@@ -0,0 +1,31 @@
+{
+    "$schema": "http://json-schema.org/schema#",
+    "title": "feed",
+    "type": "object",
+    "required": ["title", "date", "text", "link", "hrefs"],
+    "properties": {
+      "title": {
+        "type": "string",
+        "description": "News title"
+      },
+      "date": {
+        "type": "date",
+        "description": "News published date"
+      },
+      "text": {
+        "type": "string",
+        "description": "News text"
+      },
+      "link": {
+        "type": "string",
+        "description": "News static link"
+      },
+      "hrefs": {
+        "type": "array",
+        "items": {
+          "type": "string",
+          "description": "News hrefs"
+        }
+      }
+    }
+  }
diff --git a/requirements.txt b/requirements.txt
@@ -0,0 +1,6 @@
+feedparser==5.2.1
+requests==2.22.0
+tldextract==2.2.2
+fpdf==1.7.2
+colorama==0.4.1
+lxml==4.4.2
diff --git a/rss_reader/FreeSans.ttf b/rss_reader/FreeSans.ttf
diff --git a/rss_reader/__init__.py b/rss_reader/__init__.py
diff --git a/rss_reader/__main__.py b/rss_reader/__main__.py
@@ -0,0 +1,43 @@
+"""Main module"""
+
+import argparse
+import logging
+
+from colorama import init
+
+from .rss_reader import NewsReader
+
+
+def main():
+    init()  # colorama init
+    args = parse_args()
+
+    if args.verbose:
+        logging.basicConfig(format="%(levelname)s: %(message)s", level=logging.INFO)
+    else:
+        logging.basicConfig(format="%(levelname)s: %(message)s")
+
+    reader = NewsReader(args.source, args.limit, args.json, args.date, args.to_pdf, args.to_html, args.colorize)
+    reader.parse_url()
+
+    reader.print_news()
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Pure Python command-line RSS reader.')
+
+    parser.add_argument('source', help='RSS URL')
+    parser.add_argument('--version', help='Print version info', action='version', version='%(prog)s 0.4')
+    parser.add_argument('--json', help='Print result as JSON in stdout', action='store_true')
+    parser.add_argument('--verbose', help='Outputs verbose status messages', action='store_true')
+    parser.add_argument('--limit', help='Limit news topics if this parameter provided', type=int)
+    parser.add_argument('--date', help='Show cached news by input date', type=str)
+    parser.add_argument('--to-pdf', help='Convert news to pdf format', action='store_true')
+    parser.add_argument('--to-html', help='Convert news to html format', action='store_true')
+    parser.add_argument('--colorize', help='Colorize output text', action='store_true')
+
+    return parser.parse_args()
+
+
+if __name__ == '__main__':
+    main()
diff --git a/rss_reader/date_validation.py b/rss_reader/date_validation.py
@@ -0,0 +1,8 @@
+from datetime import datetime
+
+def is_valid_date(date, pattern):
+    try:
+        datetime.strptime(date, pattern)
+        return True
+    except ValueError:
+        return False
diff --git a/rss_reader/html_converter.py b/rss_reader/html_converter.py
@@ -0,0 +1,35 @@
+"""HTML converter module"""
+
+import logging
+
+
+class HTMLConverter:
+    def __init__(self, data, file_name):
+        self.data = data
+        self.file_name = file_name
+
+    def dump(self):
+        """Create and fill HTML-file"""
+        logging.info("Create and fill HTML-file")
+
+        html_code = f'<html>\n<head>\n<title>{self.file_name}</title>\n<meta http-equiv="Content-Type" \
+            content="text/html; charset=utf-8">\n</head>\n<body>\n'
+
+        for element in self.data:
+            html_code += f'<b><p align="center", style="font-family:\'Segoe UI\', Tahoma, Geneva, Verdana, \
+                sans-serif; color:green; font-size: 26px">{element["title"]}</p></b>\n'
+            html_code += f'<p align="center", style="font-family:\'Segoe UI\', Tahoma, Geneva, Verdana, \
+                sans-serif; color:rgb(25, 92, 25); font-size: 14px">{element["date"]}</p>\n'
+            html_code += f'<p align="center", style="font-family:\'Segoe UI\', Tahoma, Geneva, Verdana, \
+                sans-serif; color:rgb(25, 92, 25); font-size: 14px"><a href="{element["link"]}">{element["link"]} \
+                </a></p>\n'
+            html_code += f'<p style="font-family:\'Segoe UI\', Tahoma, Geneva, Verdana, sans-serif; \
+                color:rgb(24, 24, 24); font-size: 18px">{element["text"]}</p>\n'
+
+            for href in element["hrefs"]:
+                html_code += f'<p style="text-align:center"><img src="{href}" height="200"></p>\n'
+
+        html_code += '</body>\n</html>'
+
+        with open(f'{self.file_name}.html', 'w+', encoding='utf-8') as html_file:
+            html_file.write(html_code)
diff --git a/rss_reader/json_formatter.py b/rss_reader/json_formatter.py
@@ -0,0 +1,33 @@
+"""Module with tools for working with Json"""
+
+import json
+import logging
+
+
+class NewsJsonFormatter:
+    def __init__(self):
+        self.data = {}
+
+    def __str__(self):
+        """Compute json-file for print news to console in json-format"""
+        logging.info('Compute json-file for print news to console in json-format')
+
+        return json.dumps(self.data, ensure_ascii=False, indent=4)
+
+    def write_to_file(self):
+        """Write json-data to file"""
+        logging.info('Write json-data to file')
+
+        with open('data.json', 'w', encoding='utf-8') as outfile:
+            json.dump(self.data, outfile, ensure_ascii=False, indent=4)
+
+    def format(self, news):
+        """Format data to json appereance"""
+        logging.info('Format data to json appereance')
+
+        self.data = {
+            'feed': []
+        }
+
+        for element in news:
+            self.data['feed'].append(element)
diff --git a/rss_reader/news_cacher.py b/rss_reader/news_cacher.py
@@ -0,0 +1,60 @@
+"""News cacher module"""
+
+import logging
+import json
+
+from datetime import datetime
+from os.path import abspath, getsize, exists
+
+from .json_formatter import NewsJsonFormatter
+
+
+class NewsCacher:
+    def __init__(self, file_name, source):
+        self.file_name = file_name
+        self.source = source
+        self.date = datetime.now().strftime('%Y%m%d')
+        self.data = None
+
+    def get_cached_news(self, date, limit):
+        """Get cached news from json file"""
+        logging.info("Get cached news from json file")
+
+        with open(self.file_name, 'r', encoding='utf-8') as json_file:
+            self.data = json.load(json_file)
+
+        try:
+            return self.data[self.source][date][:limit]
+        except (KeyError, TypeError):
+            raise ValueError
+
+    def cache(self, json_object):
+        """Cache news to json file"""
+        logging.info("Cache news to json file")
+
+        self.data = {
+            self.source: {
+                self.date: []
+            }
+        }
+
+        if not exists(abspath(self.file_name)):
+            open(self.file_name, 'w').close()
+
+        file_size = getsize(abspath(self.file_name))
+
+        if file_size != 0:
+            with open(self.file_name, 'r', encoding='utf-8') as json_file:
+                self.data = json.load(json_file)
+
+        if self.source not in self.data:
+            self.data.update({self.source: {}})
+        if self.date not in self.data[self.source]:
+            self.data[self.source].update({self.date: []})
+
+        for element in json_object:
+            if element not in self.data[self.source][self.date]:
+                self.data[self.source][self.date].append(element)
+
+        with open(self.file_name, 'w', encoding='utf-8') as outfile:
+            json.dump(self.data, outfile, ensure_ascii=False, indent=4)
diff --git a/rss_reader/pdf_converter.py b/rss_reader/pdf_converter.py
@@ -0,0 +1,67 @@
+"""PDF converter module"""
+
+import logging
+import requests
+
+from fpdf import SYSTEM_TTFONTS, FPDF
+
+SYSTEM_TTFONTS = ''
+
+
+class PDFConverter:
+    def __init__(self, data, file_name):
+        self.data = data
+        self.file_name = file_name
+        self.pdf = FPDF(orientation='P', unit='mm', format='A4')
+
+    def dump(self):
+        """Create and fill PDF-file"""
+        logging.info("Create and fill PDF-file")
+
+        margin = 5
+
+        self.pdf.add_page()
+        self.pdf.set_auto_page_break(True, 10 * margin)
+
+        for element in self.data:
+            self.pdf.add_font('FreeSans', '', 'FreeSans.ttf', uni=True)
+            self.pdf.set_fill_color(62, 147, 96)
+
+            self.pdf.set_text_color(255, 255, 255)
+            self.pdf.set_font("FreeSans", size=14)
+            self.pdf.multi_cell(0, 8, txt=element["title"], align="C", fill=1)
+            self.pdf.set_fill_color(90, 167, 120)
+            self.pdf.set_font("FreeSans", size=10)
+            self.pdf.multi_cell(0, 5, txt=element["date"], align="R", fill=1)
+            self.pdf.set_font("FreeSans", size=10)
+            self.pdf.multi_cell(0, 5, txt=element["link"], align="R", fill=1)
+
+            self.pdf.set_fill_color(229, 229, 229)
+            self.pdf.set_text_color(0, 0, 0)
+            self.pdf.set_font("FreeSans", size=12)
+            self.pdf.multi_cell(0, 6, txt=element["text"], align="J", fill=1)
+
+            self.pdf.set_fill_color(242, 242, 242)
+            self.pdf.set_text_color(0, 0, 0)
+            self.pdf.set_font("FreeSans", size=10)
+
+            self.pdf.ln(margin)
+
+            for href in element["hrefs"]:
+                page_height = 300
+                image_height = 50
+
+                try:
+                    if page_height - self.pdf.get_y() < image_height + margin:
+                        self.pdf.add_page()
+
+                    if href[-4:] == '.png':
+                        self.pdf.image(href, x=self.pdf.get_x() + image_height + margin, y=self.pdf.get_y(),
+                                       h=image_height)
+                        self.pdf.ln(image_height + margin)
+                except Exception:
+                    logging.error('Cant get an image from url')
+
+            self.pdf.multi_cell(0, margin, txt="", align="J")
+
+        self.pdf.output(f'{self.file_name}.pdf')