- Refactor codebase into src/ (preprocessing, translation, assembly) - Add pipeline/ scripts for individual stages - Externalize configuration to config/config.yaml - Fix Cover Image preservation - Update documentation and manuals
37 lines
1010 B
Python
37 lines
1010 B
Python
import json
|
|
from bs4 import BeautifulSoup
|
|
|
|
path = ".work/Gambling Man/book_structure.json"
|
|
target_file = "e9781668070765/xhtml/ch08.xhtml"
|
|
target_id = "uuid-100309c1-0643-4aa1-8ffb-1d2bfbd0e376"
|
|
|
|
try:
|
|
with open(path, 'r') as f:
|
|
data = json.load(f)
|
|
|
|
target_res = None
|
|
for item_id, res in data['resources'].items():
|
|
if "ch08.xhtml" in res.get('href', ''):
|
|
print(f"Found resource with ID: {item_id}, href: {res.get('href')}")
|
|
target_res = res
|
|
break
|
|
|
|
if not target_res:
|
|
print(f"Resource {target_file} not found by href search.")
|
|
exit(1)
|
|
|
|
content = target_res['content']
|
|
soup = BeautifulSoup(content, 'html.parser')
|
|
element = soup.find(id=target_id)
|
|
|
|
if element:
|
|
print(f"--- HTML for {target_id} ---")
|
|
print(element.prettify())
|
|
print("--- Raw ---")
|
|
print(str(element))
|
|
else:
|
|
print("Element not found")
|
|
|
|
except Exception as e:
|
|
print(e)
|