0x80
/
rsstube
1
1
Fork 0
Code Issues 6 Pull Requests Projects Releases Wiki Activity

Fix castbox extractor for channel pages.

This commit is contained in:
0x80 2022-03-27 00:00:00 +00:00
parent 1d59b5ed91
commit 51290a7203
Signed by: 0x80
GPG Key ID: 68368BCBC000EF51
1 changed files with 32 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
src/extractors/castbox.py
View File

@ -10,12 +10,37 @@ platform = os.path.basename(__file__)
if platform.endswith(".py"): if platform.endswith(".py"):
platform = platform[:(-3)] platform = platform[:(-3)]
def extract_from_page (page, verbosity): def extract_from_page (page, verbosity, url, args):
# it's like %22%2C%22rss_url%22%3A%22https%3A%2F%2Ffeeds.npr.org%2F510310%2Fpodcast.xml%22%2C%22 # if it's a chennel page, try to get an episode page
# and we have to fix the codes channel_string = "castbox.fm/channel/id"
feed = search (page, '%22%2C%22rss_url%22%3A%22', '%22%2C%22') if channel_string in url:
if not feed is None: # get channel ID
return unquote(feed) channel_id = url[url.index(channel_string)+len(channel_string):]
# strip extra arguments at end of URL
for symbol in ["/", "?", "&", ";"]:
if symbol in channel_id:
channel_id = channel_id[:channel_id.index(symbol)]
# get the first episode ID
episode_id = search (page, 'eids%22%3A%5B', '%2C')
if episode_id is None:
episode_id = search (page, 'eid%22%3A', '%2C')
if not episode_id is None:
episode_url = "https://castbox.fm/episode/id" + channel_id + "-id" + episode_id
episode_page = download (platform, episode_url, args, verbosity)
# if the original URL is an episode URL, use that page in the next step
elif "castbox.fm/episode/" in url:
episode_page = page
# if it's an episode page, get the feed from the page
if not episode_page is None:
# 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 (episode_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={}): def extract (url, page=None, network=False, verbosity=3, args={}):
# cannot get feed from URL alone # cannot get feed from URL alone
@ -23,6 +48,6 @@ def extract (url, page=None, network=False, verbosity=3, args={}):
return None return None
page = download (platform, url, args, verbosity) page = download (platform, url, args, verbosity)
feed = extract_from_page (page, verbosity) feed = extract_from_page (page, verbosity, url, args)
if not feed is None: if not feed is None:
return feed return feed