Merge branch 'master' of https://github.com/DarkstaIkers/youtube-dl into DarkstaIkers...

[youtube-dl] / youtube_dl / extractor / acast.py

diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py
index c2719ca32cfdc6b0e8cda1683dcc4c7157b7991e..94ce88c834f5ce1575b36f839f02fdf43f96e046 100644 (file)
--- a/youtube_dl/extractor/acast.py
+++ b/youtube_dl/extractor/acast.py
@@ -2,36 +2,36 @@
 from __future__ import unicode_literals
 
 import re
+import functools
 
 from .common import InfoExtractor
 from ..compat import compat_str
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    OnDemandPagedList,
+)
 
 
-class ACastBaseIE(InfoExtractor):
-    _API_BASE_URL = 'https://www.acast.com/api/'
-
-
-class ACastIE(ACastBaseIE):
+class ACastIE(InfoExtractor):
     IE_NAME = 'acast'
     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
     _TEST = {
-        'url': 'https://www.acast.com/gardenersquestiontime/liverpool',
-        'md5': '9e9cd59c3a8a7d8d5407605f51093050',
+        'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
+        'md5': 'ada3de5a1e3a2a381327d749854788bb',
         'info_dict': {
-            'id': '43da2262-ade7-420c-8564-f6367da7c010',
+            'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
             'ext': 'mp3',
-            'title': 'Liverpool',
-            'timestamp': 1446163200000,
-            'description': 'md5:170432c9956eec0670d7080a75000d5b',
-            'duration': 2520,
+            'title': '"Where Are You?": Taipei 101, Taiwan',
+            'timestamp': 1196172000000,
+            'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
+            'duration': 211,
         }
     }
 
     def _real_extract(self, url):
         channel, display_id = re.match(self._VALID_URL, url).groups()
-        cast_data = self._download_json(self._API_BASE_URL + 'channels/%s/acasts/%s/playback' % (channel, display_id), display_id)
-
+        cast_data = self._download_json(
+            'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
         return {
             'id': compat_str(cast_data['id']),
             'display_id': display_id,
@@ -44,23 +44,39 @@ class ACastIE(ACastBaseIE):
         }
 
 
-class ACastChannelIE(ACastBaseIE):
+class ACastChannelIE(InfoExtractor):
     IE_NAME = 'acast:channel'
     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
     _TEST = {
-        'url': 'https://www.acast.com/gardenersquestiontime',
+        'url': 'https://www.acast.com/condenasttraveler',
         'info_dict': {
-            'id': '9d8f6f73-6b9d-4d16-9399-52bf88f8f611',
-            'title': 'Gardeners\' Question Time',
-            'description': 'md5:c7ef18049da6a52b63d371b3edccce90',
+            'id': '50544219-29bb-499e-a083-6087f4cb7797',
+            'title': 'Condé Nast Traveler Podcast',
+            'description': 'md5:98646dee22a5b386626ae31866638fbd',
         },
-        'playlist_mincount': 5,
+        'playlist_mincount': 20,
     }
+    _API_BASE_URL = 'https://www.acast.com/api/'
+    _PAGE_SIZE = 10
 
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id)
-        casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id)
-        entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts]
+    @classmethod
+    def suitable(cls, url):
+        return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
 
-        return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description'))
+    def _fetch_page(self, channel_slug, page):
+        casts = self._download_json(
+            self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
+            channel_slug, note='Download page %d of channel data' % page)
+        for cast in casts:
+            yield self.url_result(
+                'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
+                'ACast', cast['id'])
+
+    def _real_extract(self, url):
+        channel_slug = self._match_id(url)
+        channel_data = self._download_json(
+            self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
+        entries = OnDemandPagedList(functools.partial(
+            self._fetch_page, channel_slug), self._PAGE_SIZE)
+        return self.playlist_result(entries, compat_str(
+            channel_data['id']), channel_data['name'], channel_data.get('description'))