mirror/archivebox
1
0
Fork 0
mirror of https://github.com/pirate/ArchiveBox.git synced 2025-08-23 14:44:21 +02:00
Code Issues Releases Wiki Activity

Merge pull request #822 from overhacked/bug_pinboard_rss

Browse Source 
Fix Pinboard RSS parsing valid links as `None`
This commit is contained in:
Nick Sweeting
2021-08-04 12:23:40 -04:00
committed by GitHub
parent 3d54b1321b f6cf35a45d
commit 2e5937d9e1
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
archivebox/parsers/pinboard_rss.py
View File

@@ -21,13 +21,18 @@ def parse_pinboard_rss_export(rss_file: IO[str], **_kwargs) -> Iterable[Link]:
root = ElementTree.parse(rss_file).getroot()
items = root.findall("{http://purl.org/rss/1.0/}item")
for item in items:
find = lambda p: item.find(p).text.strip() if item.find(p) else None # type: ignore
find = lambda p: item.find(p).text.strip() if item.find(p) is not None else None # type: ignore
url = find("{http://purl.org/rss/1.0/}link")
tags = find("{http://purl.org/dc/elements/1.1/}subject")
title = find("{http://purl.org/rss/1.0/}title")
ts_str = find("{http://purl.org/dc/elements/1.1/}date")
if url is None:
# Yielding a Link with no URL will
# crash on a URL validation assertion
continue
# Pinboard includes a colon in its date stamp timezone offsets, which
# Python can't parse. Remove it:
if ts_str and ts_str[-3:-2] == ":":