[appleconnect] Add new extractor (fixes #6189)

Closes #6190.

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index d70de76906cf12f5ee28796fea33fc4a07096bef..5033d67ed298d1c609d52d415090b3b80b4c59f9 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -19,6 +19,7 @@ from .anysex import AnySexIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aparat import AparatIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aparat import AparatIE

+from .appleconnect import AppleConnectIE

 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
 from .ard import ARDIE, ARDMediathekIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
 from .ard import ARDIE, ARDMediathekIE

diff --git a/youtube_dl/extractor/appleconnect.py b/youtube_dl/extractor/appleconnect.py
new file mode 100644 (file)
index 0000000..ea7a703
--- /dev/null
+++ b/youtube_dl/extractor/appleconnect.py
@@ -0,0 +1,50 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    str_to_int,
+    ExtractorError
+)
+
+
+class AppleConnectIE(InfoExtractor):
+    _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/idsa\.(?P<id>[\w-]+)'
+    _TEST = {
+        'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
+        'md5': '10d0f2799111df4cb1c924520ca78f98',
+        'info_dict': {
+            'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
+            'ext': 'm4v',
+            'title': 'Energy',
+            'uploader': 'Drake',
+            'thumbnail': 'http://is5.mzstatic.com/image/thumb/Video5/v4/78/61/c5/7861c5fa-ad6d-294b-1464-cf7605b911d6/source/1920x1080sr.jpg',
+            'upload_date': '20150710',
+            'timestamp': 1436545535,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        try:
+            video_json = self._html_search_regex(
+                r'class="auc-video-data">(\{.*?\})', webpage, 'json')
+        except ExtractorError:
+            raise ExtractorError('This post doesn\'t contain a video', expected=True)
+
+        video_data = self._parse_json(video_json, video_id)
+        timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
+        like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count'))
+
+        return {
+            'id': video_id,
+            'url': video_data['sslSrc'],
+            'title': video_data['title'],
+            'description': video_data['description'],
+            'uploader': video_data['artistName'],
+            'thumbnail': video_data['artworkUrl'],
+            'timestamp': timestamp,
+            'like_count': like_count,
+        }