Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions substack_scraper.py
Original file line number Diff line number Diff line change
Expand Up @@ -261,12 +261,12 @@ def extract_post_data(self, soup: BeautifulSoup) -> Tuple[str, str, str, str, st
title = title_element.text.strip() if title_element else "Untitled"

# Subtitle
subtitle_element = soup.select_one("h3.subtitle")
subtitle_element = soup.select_one("h3.subtitle, div.subtitle-HEEcLo")
subtitle = subtitle_element.text.strip() if subtitle_element else ""

# Date — try CSS selector first
date = ""
date_element = soup.select_one("div.pencraft.pc-reset.color-pub-secondary-text-hGQ02T")
date_element = soup.select_one("div.meta-EgzBVA")
if date_element and date_element.text.strip():
date = date_element.text.strip()

Expand All @@ -287,7 +287,7 @@ def extract_post_data(self, soup: BeautifulSoup) -> Tuple[str, str, str, str, st
date = "Date not found"

# Like count
like_count_element = soup.select_one("a.post-ufi-button .label")
like_count_element = soup.select_one('div.like-button-container button div.label')
like_count = (
like_count_element.text.strip()
if like_count_element and like_count_element.text.strip().isdigit()
Expand Down