mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-13 14:44:29 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Replaced os.path in html.py

Browse source
This commit is contained in:
Angel Rey 2020-09-30 14:30:53 -05:00 • committed by Cristian Vargas
parent 8b03c37fbb
commit 78f7062761
1 changed files with 12 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

27
archivebox/index/html.py
View file

@ -1,7 +1,5 @@
__package__ = 'archivebox.index'
import os
from string import Template
from datetime import datetime
from typing import List, Optional, Iterator, Mapping
@ -30,11 +28,10 @@ from ..config import (
FAVICON_FILENAME,
)
join = lambda *paths: os.path.join(*paths)
MAIN_INDEX_TEMPLATE = join(TEMPLATES_DIR, 'main_index.html')
MINIMAL_INDEX_TEMPLATE = join(TEMPLATES_DIR, 'main_index_minimal.html')
MAIN_INDEX_ROW_TEMPLATE = join(TEMPLATES_DIR, 'main_index_row.html')
LINK_DETAILS_TEMPLATE = join(TEMPLATES_DIR, 'link_details.html')
MAIN_INDEX_TEMPLATE = str(Path(TEMPLATES_DIR) / 'main_index.html')
MINIMAL_INDEX_TEMPLATE = str(Path(TEMPLATES_DIR) / 'main_index_minimal.html')
MAIN_INDEX_ROW_TEMPLATE = str(Path(TEMPLATES_DIR) / 'main_index_row.html')
LINK_DETAILS_TEMPLATE = str(Path(TEMPLATES_DIR) / 'link_details.html')
TITLE_LOADING_MSG = 'Not yet archived...'
@ -44,8 +41,8 @@ TITLE_LOADING_MSG = 'Not yet archived...'
def parse_html_main_index(out_dir: Path=OUTPUT_DIR) -> Iterator[str]:
"""parse an archive index html file and return the list of urls"""
index_path = join(out_dir, HTML_INDEX_FILENAME)
if os.path.exists(index_path):
index_path = Path(out_dir) / HTML_INDEX_FILENAME
if index_path.exists():
with open(index_path, 'r', encoding='utf-8') as f:
for line in f:
if 'class="link-url"' in line:
@ -56,12 +53,12 @@ def parse_html_main_index(out_dir: Path=OUTPUT_DIR) -> Iterator[str]:
def write_html_main_index(links: List[Link], out_dir: Path=OUTPUT_DIR, finished: bool=False) -> None:
"""write the html link index to a given path"""
copy_and_overwrite(join(TEMPLATES_DIR, FAVICON_FILENAME), join(out_dir, FAVICON_FILENAME))
copy_and_overwrite(join(TEMPLATES_DIR, ROBOTS_TXT_FILENAME), join(out_dir, ROBOTS_TXT_FILENAME))
copy_and_overwrite(join(TEMPLATES_DIR, STATIC_DIR_NAME), join(out_dir, STATIC_DIR_NAME))
copy_and_overwrite(str(Path(TEMPLATES_DIR) / FAVICON_FILENAME), str(out_dir / FAVICON_FILENAME))
copy_and_overwrite(str(Path(TEMPLATES_DIR) / ROBOTS_TXT_FILENAME), str(out_dir / ROBOTS_TXT_FILENAME))
copy_and_overwrite(str(Path(TEMPLATES_DIR) / STATIC_DIR_NAME), str(out_dir / STATIC_DIR_NAME))
rendered_html = main_index_template(links, finished=finished)
atomic_write(join(out_dir, HTML_INDEX_FILENAME), rendered_html)
atomic_write(str(out_dir / HTML_INDEX_FILENAME), rendered_html)
@enforce_types
@ -100,7 +97,7 @@ def main_index_row_template(link: Link) -> str:
# before pages are finished archiving, show fallback loading favicon
'favicon_url': (
join(ARCHIVE_DIR_NAME, link.timestamp, 'favicon.ico')
str(Path(ARCHIVE_DIR_NAME) / link.timestamp / 'favicon.ico')
# if link['is_archived'] else 'data:image/gif;base64,R0lGODlhAQABAAD/ACwAAAAAAQABAAACADs='
),
@ -119,7 +116,7 @@ def write_html_link_details(link: Link, out_dir: Optional[str]=None) -> None:
out_dir = out_dir or link.link_dir
rendered_html = link_details_template(link)
atomic_write(join(out_dir, HTML_INDEX_FILENAME), rendered_html)
atomic_write(str(Path(out_dir) / HTML_INDEX_FILENAME), rendered_html)
@enforce_types