feat: implement dynamic training course tab system and modular PDF data migration scripts
This commit is contained in:
@@ -0,0 +1,25 @@
|
||||
import re
|
||||
from bs4 import BeautifulSoup
|
||||
import json
|
||||
import os
|
||||
|
||||
with open('/home/x79/.gemini/antigravity-ide/brain/53991324-2cf9-45f5-8177-0e9acab31498/.system_generated/steps/939/content.md', 'r') as f:
|
||||
html = f.read()
|
||||
|
||||
soup = BeautifulSoup(html, 'html.parser')
|
||||
content = soup.find('div', class_='entry-content')
|
||||
|
||||
if not content:
|
||||
print('entry-content not found.')
|
||||
exit(1)
|
||||
|
||||
# we want to get the raw HTML string of the inner contents
|
||||
inner_html = ""
|
||||
for child in content.children:
|
||||
inner_html += str(child)
|
||||
|
||||
# Let's save this raw HTML to a temp file
|
||||
with open('html_snippets/content_main_blocks/temp_agenda', 'w') as f:
|
||||
f.write(inner_html)
|
||||
|
||||
print("Saved extracted HTML to temp_agenda. Length:", len(inner_html))
|
||||
Reference in New Issue
Block a user