alex/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2026-03-31 04:12:23 +10:00
Code Issues Packages Projects Releases Wiki Activity

fix RSS parser bailing out when lines have whitespace before tags

Browse Source
This commit is contained in:
Nick Sweeting
2019-02-19 02:31:53 -05:00
parent 3571ef24e4
commit eff0100971
2 changed files with 2 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
archivebox/parse.py
View File

@@ -161,7 +161,7 @@ def parse_rss_export(rss_file):
rows = leading_removed.split('\n')
def get_row(key):
return [r for r in rows if r.startswith('<{}>'.format(key))][0]
return [r for r in rows if r.strip().startswith('<{}>'.format(key))][0]
title = str_between(get_row('title'), '<![CDATA[', ']]').strip()
url = str_between(get_row('link'), '<link>', '</link>')
@@ -209,7 +209,6 @@ def parse_shaarli_rss_export(rss_file):
ts_str = str_between(get_row('published'), '<published>', '</published>')
time = datetime.strptime(ts_str, "%Y-%m-%dT%H:%M:%S%z")
info = {
'url': url,
'domain': domain(url),