Download canceling improvement

blog2epub/blog2epub_cli.py

@@ -4,8 +4,8 @@
 
 
 class CliInterface(EmptyInterface):
-    def print(self, text: str):
-        print(text)
+    def print(self, text: str, end: str = "\n"):
+        print(text, end=end)
 
     def exception(self, e):
         print(e)

blog2epub/crawlers/article_factory/abstract.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Optional, Callable
+from typing import Callable, Optional
 
 from lxml.html.soupparser import fromstring
 

blog2epub/crawlers/default.py

@@ -269,7 +269,7 @@ def crawl(self):
                     dirs=self.dirs,
                     language=self.language,
                     downloader=self.downloader,
-                    download_callback=self._break_the_loop
+                    download_callback=self._break_the_loop,
                 )
                 art = art_factory.process()
                 self.images = self.images + art.images

blog2epub/crawlers/zeissikonveb.py

@@ -22,7 +22,7 @@ def get_title(self) -> Optional[str]:
 
 
 class ZeissIkonVEBCrawler(DefaultCrawler):
-    """TODO: https://zeissikonveb.de"""
+    """https://zeissikonveb.de"""
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
@@ -36,7 +36,7 @@ def __init__(self, **kwargs):
             Pattern(regex=r"font-size:[\s0-9]+px\;"),
             Pattern(regex=r"line-height:[\s0-9]+\;"),
             Pattern(regex=r"font-family:Arial, Helvetica, sans-serif"),
-            Pattern(regex=r"<p\/>"),
+            Pattern(regex=r'<p (class|style)="[^"]+" (class|style)="[^"]+"><span style="[^"]+"><br><\/span><\/p>'),
         ]
         self.patterns.date = [
             Pattern(regex=r"letzte Änderung[\s:]*([0-9]{1,2})[\.\s]*([A-Za-z]+)[\.\s]*([0-9]{4})"),