indymedia
/
epicyon
mirror of https://gitlab.com/bashrc2/epicyon
7
4
Fork 1
Code Issues 14 Releases Wiki Activity

Tidying

main
Bob Mottram 2022-01-12 14:23:07 +00:00
parent 13dbfba96b
commit 1186c39512
1 changed files with 31 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

85
newswire.py
View File

@ -468,6 +468,31 @@ def xml_podcast_to_dict(xml_str: str) -> {}:
return podcast_properties return podcast_properties
def _get_link_from_rss_item(rss_item: str) -> str:
"""Extracts rss link from rss item string
"""
link = None
if '<enclosure ' in rss_item:
# get link from audio or video enclosure
enclosure = rss_item.split('<enclosure ')[1]
if '>' in enclosure:
enclosure = enclosure.split('>')[0]
if 'url="' in enclosure and \
('"audio/' in enclosure or '"video/' in enclosure):
link_str = enclosure.split('url="')[1]
if '"' in link_str:
link_str = link_str.split('"')[0]
if '://' in link_str:
link = link_str
if not link:
link = rss_item.split('<link>')[1]
link = link.split('</link>')[0]
if '://' not in link:
return None
return link
def _xml2str_to_dict(base_dir: str, domain: str, xml_str: str, def _xml2str_to_dict(base_dir: str, domain: str, xml_str: str,
moderated: bool, mirrored: bool, moderated: bool, mirrored: bool,
max_posts_per_source: int, max_posts_per_source: int,
@ -523,25 +548,9 @@ def _xml2str_to_dict(base_dir: str, domain: str, xml_str: str,
description = description.split('</media:description>')[0] description = description.split('</media:description>')[0]
description = remove_html(description) description = remove_html(description)
link = None link = _get_link_from_rss_item(rss_item)
if '<enclosure ' in rss_item:
# get link from audio or video enclosure
enclosure = rss_item.split('<enclosure ')[1]
if '>' in enclosure:
enclosure = enclosure.split('>')[0]
if 'url="' in enclosure and \
('"audio/' in enclosure or '"video/' in enclosure):
link_str = enclosure.split('url="')[1]
if '"' in link_str:
link_str = link_str.split('"')[0]
if '://' in link_str:
link = link_str
if not link: if not link:
link = rss_item.split('<link>')[1] continue
link = link.split('</link>')[0]
if '://' not in link:
continue
item_domain = link.split('://')[1] item_domain = link.split('://')[1]
if '/' in item_domain: if '/' in item_domain:
@ -631,25 +640,9 @@ def _xml1str_to_dict(base_dir: str, domain: str, xml_str: str,
description = description.split('</media:description>')[0] description = description.split('</media:description>')[0]
description = remove_html(description) description = remove_html(description)
link = None link = _get_link_from_rss_item(rss_item)
if '<enclosure ' in rss_item:
# get link from audio or video enclosure
enclosure = rss_item.split('<enclosure ')[1]
if '>' in enclosure:
enclosure = enclosure.split('>')[0]
if 'url="' in enclosure and \
('"audio/' in enclosure or '"video/' in enclosure):
link_str = enclosure.split('url="')[1]
if '"' in link_str:
link_str = link_str.split('"')[0]
if '://' in link_str:
link = link_str
if not link: if not link:
link = rss_item.split('<link>')[1] continue
link = link.split('</link>')[0]
if '://' not in link:
continue
item_domain = link.split('://')[1] item_domain = link.split('://')[1]
if '/' in item_domain: if '/' in item_domain:
@ -727,25 +720,9 @@ def _atom_feed_to_dict(base_dir: str, domain: str, xml_str: str,
description = description.split('</media:description>')[0] description = description.split('</media:description>')[0]
description = remove_html(description) description = remove_html(description)
link = None link = _get_link_from_rss_item(atom_item)
if '<enclosure ' in atom_item:
# get link from audio or video enclosure
enclosure = atom_item.split('<enclosure ')[1]
if '>' in enclosure:
enclosure = enclosure.split('>')[0]
if 'url="' in enclosure and \
('"audio/' in enclosure or '"video/' in enclosure):
link_str = enclosure.split('url="')[1]
if '"' in link_str:
link_str = link_str.split('"')[0]
if '://' in link_str:
link = link_str
if not link: if not link:
link = atom_item.split('<link>')[1] continue
link = link.split('</link>')[0]
if '://' not in link:
continue
item_domain = link.split('://')[1] item_domain = link.split('://')[1]
if '/' in item_domain: if '/' in item_domain: