[utils] `clean_podcast_url`: Handle more trackers (#7556)

Authored by: mabdelfattah, bashonly
Closes #7544
pull/7571/head
Mahmoud Abdel-Fattah 1 year ago committed by GitHub
parent 325191d0c9
commit 2af4eeb772
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -1835,6 +1835,8 @@ Line 1
def test_clean_podcast_url(self): def test_clean_podcast_url(self):
self.assertEqual(clean_podcast_url('https://www.podtrac.com/pts/redirect.mp3/chtbl.com/track/5899E/traffic.megaphone.fm/HSW7835899191.mp3'), 'https://traffic.megaphone.fm/HSW7835899191.mp3') self.assertEqual(clean_podcast_url('https://www.podtrac.com/pts/redirect.mp3/chtbl.com/track/5899E/traffic.megaphone.fm/HSW7835899191.mp3'), 'https://traffic.megaphone.fm/HSW7835899191.mp3')
self.assertEqual(clean_podcast_url('https://play.podtrac.com/npr-344098539/edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3'), 'https://edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3') self.assertEqual(clean_podcast_url('https://play.podtrac.com/npr-344098539/edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3'), 'https://edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3')
self.assertEqual(clean_podcast_url('https://pdst.fm/e/2.gum.fm/chtbl.com/track/chrt.fm/track/34D33/pscrb.fm/rss/p/traffic.megaphone.fm/ITLLC7765286967.mp3?updated=1687282661'), 'https://traffic.megaphone.fm/ITLLC7765286967.mp3?updated=1687282661')
self.assertEqual(clean_podcast_url('https://pdst.fm/e/https://mgln.ai/e/441/www.buzzsprout.com/1121972/13019085-ep-252-the-deep-life-stack.mp3'), 'https://www.buzzsprout.com/1121972/13019085-ep-252-the-deep-life-stack.mp3')
def test_LazyList(self): def test_LazyList(self):
it = list(range(10)) it = list(range(10))

@ -5123,14 +5123,18 @@ def clean_podcast_url(url):
(?: (?:
chtbl\.com/track| chtbl\.com/track|
media\.blubrry\.com| # https://create.blubrry.com/resources/podcast-media-download-statistics/getting-started/ media\.blubrry\.com| # https://create.blubrry.com/resources/podcast-media-download-statistics/getting-started/
play\.podtrac\.com play\.podtrac\.com|
)/[^/]+| chrt\.fm/track|
mgln\.ai/e
)(?:/[^/.]+)?|
(?:dts|www)\.podtrac\.com/(?:pts/)?redirect\.[0-9a-z]{3,4}| # http://analytics.podtrac.com/how-to-measure (?:dts|www)\.podtrac\.com/(?:pts/)?redirect\.[0-9a-z]{3,4}| # http://analytics.podtrac.com/how-to-measure
flex\.acast\.com| flex\.acast\.com|
pd(?: pd(?:
cn\.co| # https://podcorn.com/analytics-prefix/ cn\.co| # https://podcorn.com/analytics-prefix/
st\.fm # https://podsights.com/docs/ st\.fm # https://podsights.com/docs/
)/e )/e|
[0-9]\.gum\.fm|
pscrb\.fm/rss/p
)/''', '', url) )/''', '', url)
return re.sub(r'^\w+://(\w+://)', r'\1', url) return re.sub(r'^\w+://(\w+://)', r'\1', url)

Loading…
Cancel
Save