CodeMirror/ArchiveBox
1
0
Fork 0
mirror of synced 2024-06-28 11:00:35 +12:00
Code Issues Projects Releases Wiki Activity

add rudimentary method to parse back html index into urls

Browse source
This commit is contained in:
Nick Sweeting 2019-04-24 11:37:51 -04:00
parent 3825ddc095
commit e91cdfbc88
1 changed files with 13 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
archivebox/legacy/storage/html.py
View file

@ -3,7 +3,7 @@ __package__ = 'archivebox.legacy.storage'
import os
from datetime import datetime
from typing import List, Optional
from typing import List, Optional, Iterator
from ..schema import Link
from ..config import (
@ -39,6 +39,18 @@ TITLE_LOADING_MSG = 'Not yet archived...'
### Main Links Index
@enforce_types
def parse_html_main_index(out_dir: str=OUTPUT_DIR) -> Iterator[str]:
"""parse an archive index html file and return the list of urls"""
index_path = os.path.join(out_dir, HTML_INDEX_FILENAME)
if os.path.exists(index_path):
with open(index_path, 'r', encoding='utf-8') as f:
for line in f:
if 'class="link-url"' in line:
yield line.split('"')[1]
return ()
@enforce_types
def write_html_main_index(links: List[Link], out_dir: str=OUTPUT_DIR, finished: bool=False) -> None:
"""write the html link index to a given path"""