Merge remote-tracking branch 'origin/master'

README.md

@@ -100,6 +100,9 @@ name = "Notion Test Site"
 # of the generated site, and loconotion will parse all sub-pages present on the page
 page = "https://www.notion.so/Loconotion-Example-Page-03c403f4fdc94cc1b315b9469a8950ef"
 
+# optionally apply notion's dark mode, remove the line below to use the default light mode
+theme = "dark"
+
 ## Global Site Settings ##
 # this [site] table defines override settings for the whole site
 # later on we will see how to define settings for a single page

bundles/loconotion.css

@@ -34,6 +34,12 @@ div[role="button"]:not(.notion-record-icon):hover {
   padding-right: unset !important;
 }
 
+/* pull alias arrows back inline */
+svg.alias {
+  display: inline-block !important;
+  height: auto !important;
+}
+
 @media only screen and (max-width: 960px) {
   /* normalizes banner / page title width */
   .notion-scroller > div:not([class]),

docker/Dockerfile

@@ -14,7 +14,7 @@ RUN apt-get install -y google-chrome-stable
 # RUN wget https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb
 # RUN dpkg -i google-chrome-stable_current_amd64.deb; apt-get -fy install
 # Set up Chromedriver Environment variables
-ENV CHROMEDRIVER_VERSION 85.0.4183.38
+ENV CHROMEDRIVER_VERSION 87.0.4280.88
 ENV CHROMEDRIVER_DIR /chromedriver
 RUN mkdir $CHROMEDRIVER_DIR
 # Download and install Chromedriver

loconotion/notionparser.py

@@ -264,6 +264,11 @@ class Parser:
             )
             return
 
+        # light theme is on by default
+        # enable dark mode based on https://fruitionsite.com/ dark mode hack
+        if self.config.get('theme') == 'dark':
+            self.driver.execute_script("__console.environment.ThemeStore.setState({ mode: 'dark' });")
+
         # scroll at the bottom of the notion-scroller element to load all elements
         # continue once there are no changes in height after a timeout
         # don't do this if the page has a calendar databse on it or it will load forever
@@ -345,6 +350,10 @@ class Parser:
         for vendors_css in soup.find_all("link", href=lambda x: x and "vendors~" in x):
             vendors_css.decompose()
 
+        # collection selectors (List, Gallery, etc.) don't work, so remove them
+        for collection_selector in soup.findAll("div", {"class": "notion-collection-view-select"}):
+            collection_selector.decompose()
+
         # clean up the default notion meta tags
         for tag in [
             "description",
@@ -466,8 +475,9 @@ class Parser:
                 table_row_block_id = table_row["data-block-id"]
                 table_row_href = "/" + table_row_block_id.replace("-", "")
                 row_target_span = table_row.find("span")
+                row_target_span["style"] = row_target_span["style"].replace("pointer-events: none;","")
                 row_link_wrapper = soup.new_tag(
-                    "a", attrs={"href": table_row_href, "style": "cursor: pointer;"}
+                    "a", attrs={"href": table_row_href, "style": "cursor: pointer; color: inherit; text-decoration: none; fill: inherit;"}
                 )
                 row_target_span.wrap(row_link_wrapper)
 
@@ -557,8 +567,10 @@ class Parser:
         # find sub-pages and clean slugs / links
         sub_pages = []
         for a in soup.findAll("a"):
-            if a["href"].startswith("/"):
+            sub_page_href = a["href"]
+            if sub_page_href.startswith("/"):
                 sub_page_href = "https://www.notion.so" + a["href"]
+            if sub_page_href.startswith("https://www.notion.so/"):
                 # if the link is an anchor link,
                 # check if the page hasn't already been parsed
                 if "#" in sub_page_href: