Skip to content

enh: Add lxml for _fix_links.py #359

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
hoxbro wants to merge 1 commit into
base: main
Choose a base branch
from
Open

enh: Add lxml for _fix_links.py #359

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
27 changes: 12 additions & 15 deletions nbsite/scripts/_fix_links.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
from functools import partial
from pathlib import Path

from bs4 import BeautifulSoup
from lxml import html as lhtml

# TODO: holoviews specific links e.g. to reference manual...doc & generalize

Expand Down Expand Up @@ -95,43 +95,40 @@ def cleanup_links(path, inspect_links=False):
# text = text.replace(k, v)

text = component_links(text, path)
soup = BeautifulSoup(text, features="html.parser")
for a in soup.find_all('a'):
tree = lhtml.document_fromstring(text)
for a in tree.iter('a'):
href = a.get('href', '')
if '.ipynb' in href and 'http' not in href:
# for k, v in LINK_REPLACEMENTS.items():
# href = href.replace(k, v)
a['href'] = href.replace('.ipynb', '.html')
a.set('href', href.replace('.ipynb', '.html'))

# check to make sure that path exists, if not, try un-numbered version
try_path = os.path.join(os.path.dirname(path), a['href'])
try_path = os.path.join(os.path.dirname(path), a.get('href'))
if not os.path.exists(try_path):
num_name = os.path.basename(try_path)
name = re.split(r"^#?\d+( |-|_)", num_name)[-1]
new_path = try_path.replace(num_name, name)
if os.path.exists(new_path):
a['href'] = os.path.relpath(new_path, os.path.dirname(path))
a.set('href', os.path.relpath(new_path, os.path.dirname(path)))
else:
also_tried = 'Also tried: {}'.format(name) if name != num_name else ''
msg = 'Found missing link {} in: {}. {}'.format(a['href'], path, also_tried)
msg = 'Found missing link {} in: {}. {}'.format(a.get('href'), path, also_tried)
warnings.warn(msg)

if inspect_links and 'http' in a['href']:
print(a['href'])
if inspect_links and 'http' in href:
print(href)

for img in soup.find_all('img'):
for img in tree.iter('img'):
src = img.get('src', '')
if 'http' not in src and 'assets' in src:
try_path = os.path.join(os.path.dirname(path), src)
if not os.path.exists(try_path):
also_tried = os.path.join('..', src)
if os.path.exists(os.path.join(os.path.dirname(path), also_tried)):
img['src'] = also_tried
img.set('src', also_tried)
else:
msg = f'Found reference to missing image {src} in: {path}. Also tried: {also_tried}'
warnings.warn(msg)
with open(path, 'w', encoding='utf-8') as f:
f.write(str(soup))
f.write(lhtml.tostring(tree, doctype='<!DOCTYPE html>', encoding='unicode'))

def fix_links(build_dir, inspect_links=False):
files = map(os.fspath, Path(build_dir).rglob("*.html"))
Expand Down
1 change: 1 addition & 0 deletions pixi.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,7 @@ beautifulsoup4 = "*"
ipykernel = "*"
jinja2 = "*"
jupyter_client = "*"
lxml = "*"
myst-nb = ">=1.1"
myst-parser = '>=3'
nbconvert = "*"
Expand Down
1 change: 1 addition & 0 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,7 @@ dependencies = [
'sphinxext-rediraffe',
'packaging',
'requests',
'lxml',
]

[project.scripts]
Expand Down
Loading