Change to html5lib parser

This parser keeps the whitespace characters in `span` elements which fixes code block rendering.
cjoy · Mar 29, 2022 · 4b4c715 · 4b4c715
1 parent 46c7707
commit 4b4c715
Show file tree

Hide file tree

Showing 4 changed files with 138 additions and 67 deletions.
diff --git a/loconotion/modules/notionparser.py b/loconotion/modules/notionparser.py
@@ -272,7 +272,7 @@ def parse_page(self, url: str):
         self.open_toggle_blocks(self.args["timeout"])
 
         # creates soup from the page to start parsing
-        soup = BeautifulSoup(self.driver.page_source, "html.parser")
+        soup = BeautifulSoup(self.driver.page_source, "html5lib")
 
         self.clean_up(soup)
         self.set_custom_meta_tags(url, soup)

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -13,6 +13,7 @@ cssutils = "^1.0.2"
 requests = "^2.23.0"
 selenium = "^3.141.0"
 toml = "^0.10.1"
+html5lib = "^1.1"
 
 [tool.poetry.dev-dependencies]
 black = "^19.10b0"