mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-13 22:54:27 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix rss parsing when items have newlines between them

Browse source
This commit is contained in:
Nick Sweeting 2019-03-25 16:27:50 -04:00
parent c48b1bbb3c
commit 58c9b47d43
1 changed files with 3 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

5
archivebox/parse.py
View file

@ -154,7 +154,8 @@ def parse_rss_export(rss_file):
"""Parse RSS XML-format files into links""" """Parse RSS XML-format files into links"""
rss_file.seek(0) rss_file.seek(0)
items = rss_file.read().split('</item>\n<item>') items = rss_file.read().split('<item>')
items = items[1:] if items else []
for item in items: for item in items:
# example item: # example item:
# <item> # <item>
@ -166,7 +167,7 @@ def parse_rss_export(rss_file):
# </item> # </item>
trailing_removed = item.split('</item>', 1)[0] trailing_removed = item.split('</item>', 1)[0]
leading_removed = trailing_removed.split('<item>', 1)[-1] leading_removed = trailing_removed.split('<item>', 1)[-1].strip()
rows = leading_removed.split('\n') rows = leading_removed.split('\n')
def get_row(key): def get_row(key):