New upstream version 2019.06.08

[youtubedl] / youtube_dl / extractor / ccc.py

diff --git a/youtube_dl/extractor/ccc.py b/youtube_dl/extractor/ccc.py
index 8f7f09e22dad6eda3ca08edfbf9edc118146e893..36e6dff72c9f4bf62b59b864091a7b3a0d17ba5b 100644 (file)
--- a/youtube_dl/extractor/ccc.py
+++ b/youtube_dl/extractor/ccc.py
@@ -1,9 +1,12 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     parse_iso8601,
+    try_get,
+    url_or_none,
 )
 
 
@@ -18,11 +21,13 @@ class CCCIE(InfoExtractor):
             'id': '1839',
             'ext': 'mp4',
             'title': 'Introduction to Processor Design',
+            'creator': 'byterazor',
             'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20131228',
             'timestamp': 1388188800,
             'duration': 3710,
+            'tags': list,
         }
     }, {
         'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
@@ -32,7 +37,7 @@ class CCCIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        event_id = self._search_regex("data-id='(\d+)'", webpage, 'event id')
+        event_id = self._search_regex(r"data-id='(\d+)'", webpage, 'event id')
         event_data = self._download_json('https://media.ccc.de/public/events/%s' % event_id, event_id)
 
         formats = []
@@ -68,6 +73,7 @@ class CCCIE(InfoExtractor):
             'id': event_id,
             'display_id': display_id,
             'title': event_data['title'],
+            'creator': try_get(event_data, lambda x: ', '.join(x['persons'])),
             'description': event_data.get('description'),
             'thumbnail': event_data.get('thumb_url'),
             'timestamp': parse_iso8601(event_data.get('date')),
@@ -75,3 +81,31 @@ class CCCIE(InfoExtractor):
             'tags': event_data.get('tags'),
             'formats': formats,
         }
+
+
+class CCCPlaylistIE(InfoExtractor):
+    IE_NAME = 'media.ccc.de:lists'
+    _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/c/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://media.ccc.de/c/30c3',
+        'info_dict': {
+            'title': '30C3',
+            'id': '30c3',
+        },
+        'playlist_count': 135,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url).lower()
+
+        conf = self._download_json(
+            'https://media.ccc.de/public/conferences/' + playlist_id,
+            playlist_id)
+
+        entries = []
+        for e in conf['events']:
+            event_url = url_or_none(e.get('frontend_link'))
+            if event_url:
+                entries.append(self.url_result(event_url, ie=CCCIE.ie_key()))
+
+        return self.playlist_result(entries, playlist_id, conf.get('title'))