Change to using Podchaser's API for data retrieval
I've temporarily removed the `podchaser.com/creators/creator-<creatorid>` path from _VALID_URL, because I haven't figured out how to get a Creator's 4 or 5 digit numeric ID from the alphanumeric ID in the URL--at least not without downloading the page's HTML, which looks tricky atm with cloudflare
This commit is contained in:
Conner
parent
6ddf44e2f3
commit
94c633d58a
@ -1,8 +1,8 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
import json
|
||||
import re
|
||||
from datetime import datetime
|
||||
from ..utils import float_or_none, try_get, str_to_int, unified_timestamp
|
||||
from ..utils import float_or_none, try_get, str_to_int, unified_timestamp, merge_dicts
|
||||
from ..compat import compat_str
|
||||
from .common import InfoExtractor
|
||||
|
||||
@ -10,10 +10,8 @@ from .common import InfoExtractor
|
||||
class PodchaserIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?podchaser\.com/
|
||||
(?:(?:podcasts)|(?:creators))
|
||||
/[\w-]+-
|
||||
(?:
|
||||
(?P<creator_id>[\d]+[\w]+)|(?P<podcast_id>[\d]+))
|
||||
(?:podcasts/[\w-]+-(?P<podcast_id>[\d]+)))
|
||||
(?:/episodes/[\w\-]+-
|
||||
(?P<id>[\d]+))?'''
|
||||
|
||||
@ -26,6 +24,7 @@ class PodchaserIE(InfoExtractor):
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'ext': 'mp3',
|
||||
'categories': ['Comedy'],
|
||||
'tags': ['comedy', 'dark humor'],
|
||||
'series': 'Cum Town',
|
||||
'duration': 3708,
|
||||
'timestamp': 1636531259,
|
||||
@ -36,63 +35,80 @@ class PodchaserIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '28853',
|
||||
'title': 'The Bone Zone',
|
||||
'description': 'md5:c39acd897170a8bf3ad94fc45dc25060',
|
||||
'description': 'Podcast by The Bone Zone',
|
||||
},
|
||||
'playlist_count': 6
|
||||
}, {
|
||||
'url': 'https://www.podchaser.com/creators/todd-glass-107ZzkFiEQ',
|
||||
'info_dict': {
|
||||
'id': '107ZzkFiEQ',
|
||||
'title': 'Todd Glass',
|
||||
'description': 'md5:0771e81d879f304f11254e5a56a97a58',
|
||||
},
|
||||
'playlist_mincount': 48
|
||||
'playlist_count': 275
|
||||
}, {
|
||||
'url': 'https://www.podchaser.com/podcasts/sean-carrolls-mindscape-scienc-699349/episodes',
|
||||
'info_dict': {
|
||||
'id': '699349',
|
||||
'title': "Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas",
|
||||
'description': 'md5:8692ce0c50cb900c5e4eb27b437dd67b'
|
||||
'description': 'md5:2cbd8f4749891a84dc8235342e0b5ff1'
|
||||
},
|
||||
'playlist_count': 25
|
||||
'playlist_mincount': 199
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
audio_id, podcast_id, creator_id = mobj.group('id'), \
|
||||
mobj.group('podcast_id'), mobj.group('creator_id')
|
||||
webpage = self._download_webpage(url, audio_id)
|
||||
page_title = self._html_search_meta(['title', 'og:title', 'twitter:title'], webpage, default=None) \
|
||||
or self._search_regex(
|
||||
r'<h1[^>]*>(.+?)</h1>', webpage, 'title', fatal=False, default="Podchaser Podcast")
|
||||
page_description = self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage, default=None)
|
||||
audio_id, podcast_id = mobj.group('id'), mobj.group('podcast_id')
|
||||
|
||||
data = self._search_regex(
|
||||
r'window.__APP_STATE__\s*=\s*(["\']?{.+?}["\']?);</script>', webpage, 'app state')
|
||||
# If one episode
|
||||
if audio_id:
|
||||
episodes = [self._download_json("https://api.podchaser.com/episodes/%s" % audio_id, audio_id)]
|
||||
|
||||
while isinstance(data, compat_str):
|
||||
data = self._parse_json(data, audio_id)
|
||||
# Else get every episode available
|
||||
else:
|
||||
total_episode_count = self._download_json(
|
||||
"https://api.podchaser.com/list/episode", podcast_id,
|
||||
headers={'Content-Type': 'application/json;charset=utf-8'},
|
||||
data=json.dumps({
|
||||
"filters": {"podcast_id": podcast_id}
|
||||
}).encode()).get('total')
|
||||
episodes = []
|
||||
print(total_episode_count)
|
||||
for i in range(total_episode_count // 100 + 1):
|
||||
curr_episodes_data = self._download_json(
|
||||
"https://api.podchaser.com/list/episode", podcast_id,
|
||||
headers={'Content-Type': 'application/json;charset=utf-8'},
|
||||
data=json.dumps({
|
||||
"start": i * 100,
|
||||
"count": (i + 1) * 100,
|
||||
"sort_order": "SORT_ORDER_RECENT",
|
||||
"filters": {
|
||||
"podcast_id": podcast_id
|
||||
}, "options": {}
|
||||
}).encode())
|
||||
curr_episodes = curr_episodes_data.get('entities') or []
|
||||
if len(curr_episodes) + len(episodes) <= total_episode_count:
|
||||
episodes.extend(curr_episodes)
|
||||
|
||||
episodes = try_get(data, lambda x: x['podcast']['episodes']['entities'], dict) or {}
|
||||
episode_list = [(episodes.get(episode_id), episode_id) for episode_id in episodes]
|
||||
podcast_data = merge_dicts(
|
||||
self._download_json("https://api.podchaser.com/podcasts/%s" % podcast_id, audio_id or podcast_id) or {},
|
||||
episodes[0].get('podcast') or {} if episodes else {})
|
||||
|
||||
entries = [{
|
||||
'id': episode_id,
|
||||
'id': compat_str(episode.get('id')),
|
||||
'title': episode.get('title'),
|
||||
'description': episode.get('description'),
|
||||
'url': episode.get('audio_url'),
|
||||
'thumbnail': try_get(episode, lambda x: x['podcast']['image_url']),
|
||||
'thumbnail': episode.get('image_url'),
|
||||
'duration': str_to_int(episode.get('length')),
|
||||
'timestamp': unified_timestamp(episode.get('air_date')),
|
||||
'rating': float_or_none(episode.get('rating')),
|
||||
'categories': [x['text'] for x in try_get(episode, lambda x: x['podcast']['categories'], list) or []],
|
||||
'tags': [tag['text'] for tag in episode.get('tags') or []],
|
||||
'series': try_get(episode, lambda x: x['podcast']['title'], compat_str),
|
||||
} for episode, episode_id in episode_list]
|
||||
'categories': [
|
||||
x.get('text') for x in
|
||||
podcast_data.get('categories')
|
||||
or try_get(podcast_data, lambda x: x['summary']['categories'], list) or []],
|
||||
'tags': [tag.get('text') for tag in podcast_data.get('tags') or []],
|
||||
'series': podcast_data.get('title'),
|
||||
} for episode in episodes]
|
||||
|
||||
if len(entries) > 1:
|
||||
# Return playlist
|
||||
return self.playlist_result(
|
||||
entries, playlist_id=(creator_id or podcast_id), playlist_title=page_title,
|
||||
playlist_description=page_description)
|
||||
entries, playlist_id=compat_str(podcast_data.get('id')),
|
||||
playlist_title=podcast_data.get('title'),
|
||||
playlist_description=podcast_data.get('description'))
|
||||
|
||||
# Return episode
|
||||
return entries[0]
|
||||
|
||||
Loading…
Reference in New Issue
Block a user