Fixing empty content bug

bohdanbobrowski · Sep 6, 2024 · daf8086 · daf8086
1 parent 643cc54
commit daf8086
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 17 deletions.
diff --git a/blog2epub/blog2epub_gui.py b/blog2epub/blog2epub_gui.py
@@ -13,7 +13,6 @@
 from urllib import parse
 from urllib.error import URLError
 
-import pkg_resources
 from kivy.uix.anchorlayout import AnchorLayout  # type: ignore
 from kivy.uix.boxlayout import BoxLayout  # type: ignore
 from kivymd.uix.datatables import MDDataTable  # type: ignore
@@ -305,19 +304,6 @@ def _update_tab_generate(self):
         else:
             self.generate_button.disabled = True
 
-    def _print_packages(self):
-        installed_packages = pkg_resources.working_set
-        installed_packages_list = sorted(
-            ["%s==%s" % (i.key, i.version) for i in installed_packages]
-        )
-        if hasattr(self, "interface"):
-            self.interface.clear()
-            for pkg in installed_packages_list:
-                self.interface.print(pkg)
-        else:
-            for pkg in installed_packages_list:
-                logging.info(pkg)
-
     def _define_tab_about(self):
         self.tab_about = Tab(
             title="About",
@@ -331,7 +317,6 @@ def _define_tab_about(self):
             allow_stretch=True,
             size_hint=(1, 0.7),
         )
-        logo_image.bind(on_triple_tap=self._print_packages)
         self.tab_about.add_widget(logo_image)
         self.tab_about.add_widget(
             MDLabel(

diff --git a/blog2epub/crawlers/abstract.py b/blog2epub/crawlers/abstract.py
@@ -6,6 +6,7 @@
 import re
 
 from lxml.html.soupparser import fromstring
+from lxml.etree import tostring
 
 from blog2epub.common.downloader import Downloader
 import dateutil
@@ -221,8 +222,7 @@ def replace_images(self):
     def get_content(self):
         self.content = self.tree.xpath(self.content_xpath)
         if len(self.content) == 1:
-            self.content = self.content[0]
-            self.content = str(self.content)
+            self.content = tostring(self.content[0]).decode("utf-8")
             self.content = re.sub('style="[^"]*"', "", self.content)
             self.content = re.sub('class="[^"]*"', "", self.content)
             for src in re.findall('<iframe.+? src="([^?= ]*)', self.content):