__package__ = 'archivebox.parsers' from typing import IO, Iterable from datetime import datetime from ..index.schema import Link from ..util import ( htmldecode, enforce_types, str_between, ) @enforce_types def parse_shaarli_rss_export(rss_file: IO[str]) -> Iterable[Link]: """Parse Shaarli-specific RSS XML-format files into links""" rss_file.seek(0) entries = rss_file.read().split('')[1:] for entry in entries: # example entry: # # Aktuelle Trojaner-Welle: Emotet lauert in gefälschten Rechnungsmails | heise online # # https://demo.shaarli.org/?cEV4vw # 2019-01-30T06:06:01+00:00 # 2019-01-30T06:06:01+00:00 #

Permalink

]]>
#
trailing_removed = entry.split('
', 1)[0] leading_removed = trailing_removed.strip() rows = leading_removed.split('\n') def get_row(key): return [r.strip() for r in rows if r.strip().startswith('<{}'.format(key))][0] title = str_between(get_row('title'), '', '').strip() url = str_between(get_row('link'), '') ts_str = str_between(get_row('published'), '', '') time = datetime.strptime(ts_str, "%Y-%m-%dT%H:%M:%S%z") yield Link( url=htmldecode(url), timestamp=str(time.timestamp()), title=htmldecode(title) or None, tags=None, sources=[rss_file.name], )