29 lines
791 B
Python
29 lines
791 B
Python
|
#!/usr/bin/python3
|
||
|
|
|
||
|
|
from utils import *
|
||
|
|
from download_page import download
|
||
|
|
from urllib.parse import unquote
|
||
|
|
|
||
|
|
# portable code to get filename
|
||
|
|
import os
|
||
|
|
platform = os.path.basename(__file__)
|
||
|
|
if platform.endswith(".py"):
|
||
|
|
platform = platform[:(-3)]
|
||
|
|
|
||
|
|
def extract_from_page (page, verbosity):
|
||
|
|
# it's like %22%2C%22rss_url%22%3A%22https%3A%2F%2Ffeeds.npr.org%2F510310%2Fpodcast.xml%22%2C%22
|
||
|
|
# and we have to fix the codes
|
||
|
|
feed = search (page, '%22%2C%22rss_url%22%3A%22', '%22%2C%22')
|
||
|
|
if not feed is None:
|
||
|
|
return unquote(feed)
|
||
|
|
|
||
|
|
def extract (url, page=None, network=False, verbosity=3, args={}):
|
||
|
|
# cannot get feed from URL alone
|
||
|
|
if not network:
|
||
|
|
return None
|
||
|
|
|
||
|
|
page = download (platform, url, args, verbosity)
|
||
|
|
feed = extract_from_page (page, verbosity)
|
||
|
|
if not feed is None:
|
||
|
|
return feed
|