ravenscroftj
/
brainsteam.co.uk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

implement title getter for bookmarks

This commit is contained in:
James Ravenscroft 2024-09-08 12:09:41 +01:00
parent 3354021cbd
commit 7376dc4dc9
1 changed files with 32 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
bstools/bstools.py
View File

@ -53,14 +53,12 @@ def cli():
dotenv.load_dotenv() dotenv.load_dotenv()
pass pass
@cli.command() @cli.command()
@click.option("--folder", type=click.Path(dir_okay=True, file_okay=False), required=True) @click.option("--folder", type=click.Path(dir_okay=True, file_okay=False), required=True)
def fetch_link_titles(folder): def fetch_link_titles(folder):
"""Fetch titles for reply and bookmark links""" """Fetch titles for reply and bookmark links"""
for root, _, files in os.walk(folder): for root, _, files in os.walk(folder):
for file in files: for file in files:
if file.endswith(".md"): if file.endswith(".md"):
full_path = os.path.join(root, file) full_path = os.path.join(root, file)
@ -68,26 +66,44 @@ def fetch_link_titles(folder):
print(f"Analysing... {full_path}") print(f"Analysing... {full_path}")
reply_data = data.get('in-reply-to') properties_to_check = ['in-reply-to', 'bookmark-of']
updated = False
if 'twitter.com' in reply_data: for property_name in properties_to_check:
print("Not grabbing title for tweet")
continue
if type(reply_data) == str: property_data = data.get(property_name)
title = get_html_title(reply_data)
if title is not None: if property_data:
print(f"Found in-reply-to title: '{title}'") if isinstance(property_data, str):
data['in-reply-to'] = {"url": reply_data, if 'twitter.com' in property_data:
"title": str(title)} print(f"Not grabbing title for tweet in {property_name}")
continue
print(f"Updating in-reply-to data... {full_path}") title = get_html_title(property_data)
with open(full_path, 'wb') as f: if title is not None:
frontmatter.dump(data, f) print(f"Found {property_name} title: '{title}'")
data[property_name] = {"url": property_data, "title": str(title)}
updated = True
# parse the response and extract the title elif isinstance(property_data, dict) and 'url' in property_data:
if 'twitter.com' in property_data['url']:
print(f"Not grabbing title for tweet in {property_name}")
continue
if 'title' not in property_data:
title = get_html_title(property_data['url'])
if title is not None:
print(f"Found {property_name} title: '{title}'")
property_data['title'] = str(title)
data[property_name] = property_data
updated = True
if updated:
print(f"Updating data... {full_path}")
with open(full_path, 'wb') as f:
frontmatter.dump(data, f)
@cli.command() @cli.command()