Refactor

blog2epub/blog2epub_gui.py

@@ -1,5 +1,6 @@
 import logging
 import os
+import platform
 import re
 import sys
 import webbrowser
@@ -17,7 +18,6 @@
 from kivymd.uix.datatables import MDDataTable  # type: ignore
 from kivymd.uix.tab import MDTabsBase, MDTabs  # type: ignore
 from kivymd.uix.textfield import MDTextField  # type: ignore
-from kivy.utils import platform  # type: ignore
 
 from plyer import filechooser, notification, email  # type: ignore
 
@@ -65,7 +65,6 @@ def get_previous():
 
 now = datetime.now()
 date_time = now.strftime("%Y-%m-%d[%H.%M.%S]")
-
 logging_filename = os.path.join(
     str(Path.home()), ".blog2epub", f"blog2epub_{date_time}.log"
 )
@@ -406,28 +405,6 @@ def _is_int(value) -> Optional[int]:
         except ValueError:
             return None
 
-    def _get_params(self):
-        if platform == "android":
-            cache_folder = self.user_data_dir
-        else:
-            cache_folder = os.path.join(str(Path.home()), ".blog2epub")
-        destination_folder = str(Path.home())
-        return {
-            "interface": self.interface,
-            "url": self._get_url(),
-            "include_images": True,
-            "images_size": (600, 800),
-            "images_quality": 40,
-            "start": None,
-            "end": None,
-            "limit": self._is_int(self.limit_entry.text),
-            "skip": self._is_int(self.skip_entry.text),
-            "force_download": False,
-            "file_name": None,
-            "cache_folder": cache_folder,
-            "destination_folder": destination_folder,
-        }
-
     def _download_ebook(self, blog2epub: Blog2Epub):
         blog2epub.download()
         self._enable_download_button()
@@ -504,7 +481,23 @@ def download(self, instance):
         self.articles_table.update_row_data(self.articles_table, [])
         self.tab_select.disabled = True
         self.save_settings()
-        self.blog2epub = Blog2Epub(self._get_params())
+        self.blog2epub = Blog2Epub(
+            {
+                "interface": self.interface,
+                "url": self._get_url(),
+                "include_images": True,
+                "images_size": (600, 800),
+                "images_quality": 40,
+                "start": None,
+                "end": None,
+                "limit": self._is_int(self.limit_entry.text),
+                "skip": self._is_int(self.skip_entry.text),
+                "force_download": False,
+                "file_name": None,
+                "cache_folder": os.path.join(str(Path.home()), ".blog2epub"),
+                "destination_folder": str(Path.home()),
+            }
+        )
         self.download_thread = Thread(
             target=self._download_ebook,
             kwargs={"blog2epub": self.blog2epub},
@@ -578,7 +571,6 @@ def send_ebook_via_email(inst):
             orientation="horizontal",
             size_hint=(1, 0.1),
             spacing=sp(10),
-            # padding=sp(16),
         )
 
         buttons_row.add_widget(
@@ -638,12 +630,12 @@ def __init__(self):
         self.title = f"blog2epub - v. {Blog2Epub.version}"
         logging.info(self.title)
         logging.debug(f"Metrics.density = {Metrics.density}")
-        if platform == "linux":
-            self.icon = asset_path("blog2epub.svg")
-        elif platform == "win":
+        if platform.system() == "Darwin":
+            self.icon = asset_path("blog2epub.icns")
+        elif platform.system() == "Windows":
             self.icon = asset_path("blog2epub_256px.png")
         else:
-            self.icon = asset_path("blog2epub.icns")
+            self.icon = asset_path("blog2epub.svg")
 
     def build(self):
         self.theme_cls.theme_style = "Light"

blog2epub/blog2epub_main.py

@@ -1,6 +1,3 @@
-from typing import Dict
-
-from blog2epub.common.exceptions import NoCrawlerDetectedError
 from blog2epub.common.globals import VERSION
 from blog2epub.crawlers import BlogspotCrawler, WordpressCrawler
 
@@ -10,16 +7,10 @@ class Blog2Epub:
 
     version = VERSION
 
-    def __init__(self, params: Dict):
-        self.crawler = self.select_crawler(params)
-        if self.crawler is None:
-            raise NoCrawlerDetectedError("No crawler detected")
-
-    @staticmethod
-    def select_crawler(params: Dict):
-        if params["url"].find(".blogspot.") > -1:
-            return BlogspotCrawler(**params)
-        return WordpressCrawler(**params)
+    def __init__(self, **kwargs):
+        if kwargs.get("url").find(".blogspot.") > -1:
+            self.crawler = BlogspotCrawler(**kwargs)
+        self.crawler = WordpressCrawler(**kwargs)
 
     def download(self):
         self.crawler.crawl()

blog2epub/common/book.py

@@ -76,8 +76,8 @@ def __init__(
         self,
         book_data: Any,
         configuration: ConfigurationModel,
-        interface: EmptyInterface,
-        destination_folder: str,
+        interface: EmptyInterface = EmptyInterface(),
+        destination_folder: str = ".",
     ):
         self.title = book_data.title
         self.description = book_data.description

blog2epub/common/interfaces.py

@@ -1,13 +1,8 @@
-from abc import ABC, abstractmethod
-
-
-class EmptyInterface(ABC):
+class EmptyInterface:
     """Empty interface for script output."""
 
-    @abstractmethod
     def print(self, text: str):
-        pass
+        print(text)
 
-    @abstractmethod
     def exception(self, **kwargs):
-        pass
+        print(kwargs)

blog2epub/crawlers/abstract.py

@@ -1,12 +1,61 @@
+import os
 from abc import ABC, abstractmethod
-from typing import List, Optional
+from datetime import datetime
+from pathlib import Path
+from typing import List, Optional, Dict
 
-from blog2epub.models.book import ArticleModel
+from blog2epub.common.book import Book
+from blog2epub.common.interfaces import EmptyInterface
+from blog2epub.crawlers.default import Article, Downloader
+from blog2epub.models.book import ArticleModel, DirModel
+from blog2epub.models.configuration import ConfigurationModel
+from blog2epub.common.crawler import (
+    prepare_file_name,
+    prepare_port,
+    prepare_url_to_crawl,
+)
 
 
 class AbstractCrawler(ABC):
     ignore_downloads: List[str] = []
 
+    def __init__(
+        self,
+        url: str,
+        configuration: ConfigurationModel,
+        start: Optional[datetime] = None,
+        end: Optional[datetime] = None,
+        file_name: Optional[str] = None,
+        cache_folder: str = os.path.join(str(Path.home()), ".blog2epub"),
+        interface: EmptyInterface = EmptyInterface(),
+    ):
+        super().__init__()
+        self.url = url
+        self.configuration = configuration
+        self.url_to_crawl = prepare_url_to_crawl(self.url)
+        self.port = prepare_port(self.url_to_crawl)
+        self.file_name = prepare_file_name(file_name, self.url)
+        self.cache_folder = cache_folder
+        self.start = start
+        self.end = end
+        self.interface = interface
+        self.dirs = DirModel(
+            path=str(os.path.join(self.cache_folder, self.url.replace("/", "_"))),
+        )
+        self.book: Optional[Book]
+        self.title = None
+        self.subtitle = None
+        self.description = None
+        self.language: str | None = self.configuration.language
+        self.atom_feed = False
+        self.articles: List[Article] = []
+        self.article_counter = 0
+        self.images: List[str] = []
+        self.downloader = Downloader(self)
+        self.tags: Dict = {}
+        self.active = False
+        self.cancelled = False
+
     @abstractmethod
     def crawl(self):
         pass