Refactor

bohdanbobrowski · bohdanbobrowski · commit b3f6fb360e27 · 2023-10-25T10:52:48.000+02:00
diff --git a/.github/workflows/pylint.yml b/.github/workflows/pylint.yml
@@ -21,4 +21,4 @@ jobs:
         pip install -r requirements.txt
     - name: Analysing the code with pylint
       run: |
-        pylint --fail-under=8 --ignore-long-lines $(git ls-files '*.py')
+        pylint --fail-under=9 $(git ls-files '*.py')
diff --git a/.pylintrc b/.pylintrc
@@ -0,0 +1,6 @@
+[MASTER]
+disable=
+    C0114, # missing-module-docstring
+    C0115, # missing-class-docstring
+    C0116, # missing-function-docstring
+    C0301, # line-too-long
diff --git a/blog2epub/__init__.py b/blog2epub/__init__.py
@@ -0,0 +1,6 @@
+from blog2epub.blog2epub_main import VERSION, Blog2Epub
+
+__all__ = [
+    "VERSION",
+    "Blog2Epub",
+]
diff --git a/blog2epub/blog2epub_cli.py b/blog2epub/blog2epub_cli.py
@@ -1,7 +1,8 @@
 import sys
 from urllib import parse
 
-from blog2epub.Blog2Epub import BadUrlException, Blog2Epub, NotEnoughCommandsException
+from blog2epub import Blog2Epub
+from blog2epub.common.exceptions import BadUrlException, NotEnoughCommandsException
 from blog2epub.common.interfaces import EmptyInterface
 
 
diff --git a/blog2epub/blog2epub_kivy.py b/blog2epub/blog2epub_kivy.py
@@ -10,8 +10,6 @@
 from typing import Dict, Optional
 from urllib import parse
 
-from blog2epub.common.crawler import prepare_url
-
 if sys.__stdout__ is None or sys.__stderr__ is None:
     os.environ["KIVY_NO_CONSOLELOG"] = "1"
 
@@ -28,10 +26,13 @@
 from kivy.uix.popup import Popup
 from kivy.uix.textinput import TextInput
 
-from blog2epub.Blog2Epub import BadUrlException, Blog2Epub
-from common.assets import asset_path
+from blog2epub import Blog2Epub
+from blog2epub.common.assets import asset_path
+from blog2epub.common.crawler import prepare_url
+from blog2epub.common.exceptions import BadUrlException
 from blog2epub.common.interfaces import EmptyInterface
 
+
 SIZE = 3 / Metrics.density / Metrics.density
 F_SIZE = 3 / Metrics.density
 
@@ -230,7 +231,7 @@ def about_url_click(inst):
 
 class AboutPopupLabel(Label):
     def __init__(self, **kwargs):
-        super(AboutPopupLabel, self).__init__(**kwargs)
+        Label.__init__(self, **kwargs)
         self.font_size = dp(8 * F_SIZE)
         self.font_name = "RobotoMono-Regular"
         self.size_hint = (1, 0.1)
@@ -320,7 +321,7 @@ def get(self, key):
 
 class Blog2EpubKivy(App):
     def __init__(self, **kwargs):
-        super(Blog2EpubKivy, self).__init__(**kwargs)
+        App.__init__(self, **kwargs)
         self.title = f"blog2epub - v. {Blog2Epub.version}"
         if platform.system() == "Darwin":
             self.icon = asset_path("blog2epub.icns")
diff --git a/blog2epub/blog2epub_main.py b/blog2epub/blog2epub_main.py
@@ -1,23 +1,12 @@
 from typing import Dict
 
-from blog2epub.crawlers.CrawlerBlogspot import Crawler, CrawlerBlogspot
-from blog2epub.crawlers.CrawlerWordpress import CrawlerWordpress
+from blog2epub.common.exceptions import NoCrawlerDetectedError
+from blog2epub.crawlers.blogspot import CrawlerBlogspot
+from blog2epub.crawlers.wordpress import CrawlerWordpress
 
 VERSION = "1.2.4"
 
 
-class NoCrawlerDetectedError(Exception):
-    pass
-
-
-class BadUrlException(Exception):
-    pass
-
-
-class NotEnoughCommandsException(Exception):
-    pass
-
-
 class Blog2Epub:
     """Main Blog2Epub class."""
 
@@ -29,7 +18,7 @@ def __init__(self, params: Dict):
             raise NoCrawlerDetectedError("No crawler detected")
 
     @staticmethod
-    def select_crawler(params: Dict) -> Crawler:
+    def select_crawler(params: Dict):
         if params["url"].find(".blogspot.") > -1:
             return CrawlerBlogspot(**params)
         return CrawlerWordpress(**params)
diff --git a/blog2epub/common/assets.py b/blog2epub/common/assets.py
@@ -9,6 +9,5 @@ def asset_path(filename: str) -> str:
         base_path = os.path.abspath("./assets/")
     if os.path.isfile(os.path.join(base_path, filename)):
         return os.path.join(base_path, filename)
-    else:
-        # if there is no given file i'm guessing that blog2epub is run from sources
-        return os.path.join(os.path.abspath("../assets/"), filename)
+    # if there is no given file i'm guessing that blog2epub is run from sources
+    return os.path.join(os.path.abspath("../assets/"), filename)
diff --git a/blog2epub/common/book.py b/blog2epub/common/book.py
@@ -5,7 +5,7 @@
 
 from ebooklib import epub
 
-from blog2epub.Cover import Cover
+from blog2epub.common.cover import Cover
 
 
 class Book:
diff --git a/blog2epub/common/cover.py b/blog2epub/common/cover.py
@@ -2,10 +2,9 @@
 from pathlib import Path
 from random import shuffle
 
+from blog2epub.common.assets import asset_path
 from PIL import Image, ImageDraw, ImageFont
 
-from common.assets import asset_path
-
 
 class Cover:
     """
diff --git a/blog2epub/common/crawler.py b/blog2epub/common/crawler.py
@@ -12,8 +12,9 @@ def prepare_file_name(file_name: str, url: str) -> str:
 
 
 def prepare_url_to_crawl(url: str) -> str:
-    r = request.urlopen("https://" + url)
-    return r.geturl()
+    with request.urlopen("https://" + url) as r:
+        response = r.geturl()
+    return response
 
 
 def prepare_port(url):
diff --git a/blog2epub/common/exceptions.py b/blog2epub/common/exceptions.py
@@ -0,0 +1,10 @@
+class NoCrawlerDetectedError(Exception):
+    pass
+
+
+class BadUrlException(Exception):
+    pass
+
+
+class NotEnoughCommandsException(Exception):
+    pass
diff --git a/blog2epub/common/interfaces.py b/blog2epub/common/interfaces.py
@@ -2,7 +2,7 @@ class EmptyInterface:
     """Empty interface for script output."""
 
     @staticmethod
-    def print(self):
+    def print(content):
         pass
 
     @staticmethod
diff --git a/blog2epub/crawlers/blogspot.py b/blog2epub/crawlers/blogspot.py
@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -*- coding : utf-8 -*-
-from blog2epub.crawlers.Crawler import Crawler
+from blog2epub.crawlers.crawler import Crawler
 
 
 class CrawlerBlogspot(Crawler):
diff --git a/blog2epub/crawlers/crawler.py b/blog2epub/crawlers/crawler.py
@@ -4,15 +4,14 @@
 import hashlib
 import html
 import imghdr
+import logging
 import os
 import re
 import time
-import logging
 from datetime import datetime
 from http.cookiejar import CookieJar
 from pathlib import Path
 from typing import Optional
-from urllib import request
 
 import atoma
 import dateutil.parser
@@ -21,13 +20,12 @@
 from lxml.html.soupparser import fromstring
 from PIL import Image
 
-import blog2epub
-from blog2epub.Book import Book
+from blog2epub.common.book import Book
 from blog2epub.common.crawler import (
+    prepare_file_name,
+    prepare_port,
     prepare_url,
     prepare_url_to_crawl,
-    prepare_port,
-    prepare_file_name,
 )
 from blog2epub.common.interfaces import EmptyInterface
 
@@ -294,10 +292,6 @@ def __init__(self, cache_folder, name):
         self.html = os.path.join(self.path, "html")
         self.images = os.path.join(self.path, "images")
         self.originals = os.path.join(self.path, "originals")
-        self.assets = os.path.join(
-            str(os.path.realpath(blog2epub.__file__).replace("__init__.py", "")),
-            "assets",
-        )
         self.prepare_directories()
 
 
@@ -349,10 +343,9 @@ def file_download(self, url: str, filepath: str) -> str:
 
     def image_download(self, url: str, filepath: str) -> bool:
         self.dirs.prepare_directories()
-        f = open(filepath, "wb")
-        response = self.session.get(url, cookies=self.cookies, headers=self.headers)
-        f.write(response.content)
-        f.close()
+        with open(filepath, "wb") as f:
+            response = self.session.get(url, cookies=self.cookies, headers=self.headers)
+            f.write(response.content)
         time.sleep(1)
         return True
 
@@ -411,8 +404,7 @@ def download_image(self, img: str) -> Optional[str]:
             picture.save(resized_fn, format="JPEG", quality=self.images_quality)
             os.remove(original_fn)
             return img_hash + ".jpg"
-        else:
-            return None
+        return None
 
 
 class Article:
@@ -624,7 +616,7 @@ def get_comments(self):
         tag = "h6"
         for c in comments_in_article:
             c = c.strip()
-            if c != "Odpowiedz" and c != "Usuń":
+            if c not in ("Odpowiedz", "Usuń"):
                 self.comments = self.comments + "<" + tag + ">" + c + "</" + tag + ">"
                 if tag == "h6":
                     tag = "p"
diff --git a/blog2epub/crawlers/wordpress.py b/blog2epub/crawlers/wordpress.py
@@ -8,7 +8,7 @@
 from lxml.ElementInclude import etree
 from lxml.html.soupparser import fromstring
 
-from blog2epub.crawlers.Crawler import Article, Crawler
+from blog2epub.crawlers.crawler import Article, Crawler
 
 
 class CrawlerWordpress(Crawler):
@@ -23,7 +23,7 @@ class CrawlerWordpress(Crawler):
     articles_regex = r"<h3 class=\'post-title entry-title\' itemprop=\'name\'>[\s]*<a href=\'([^\']*)\'>([^>^<]*)</a>[\s]*</h3>"
 
     def __init__(self, **kwargs):
-        super(CrawlerWordpress, self).__init__(**kwargs)
+        Crawler.__init__(**kwargs)
 
     def _get_atom_content(self, page=1):
         url = "https://" + self.url + "/feed/atom/"
diff --git a/blog2epubcli.py b/blog2epubcli.py
@@ -2,6 +2,6 @@
 # -*- coding : utf-8 -*-
 # Author: Bohdan Bobrowski
 
-from blog2epub import Blog2EpubCli
+from blog2epub import blog2epub_cli
 
-Blog2EpubCli.main()
+blog2epub_cli.main()
diff --git a/blog2epubkivy.py b/blog2epubkivy.py
@@ -2,6 +2,6 @@
 # -*- coding : utf-8 -*-
 # Author: Bohdan Bobrowski
 
-from blog2epub import Blog2EpubKivy
+from blog2epub import blog2epub_kivy
 
-Blog2EpubKivy.main()
+blog2epub_kivy.main()
diff --git a/setup.py b/setup.py
@@ -4,7 +4,7 @@
 
 from distutils.core import setup
 
-from blog2epub.Blog2Epub import VERSION
+from blog2epub.blog2epub_main import VERSION
 
 setup(
     name="blog2epub",
