From: remitamine <remitamine@gmail.com>
Date: Fri, 25 Dec 2015 00:59:56 +0000 (+0100)
Subject: [hotstar] Add new extractor
X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=fb8e402ad252bebc54c36c5acca1b7ef05416c9b;p=youtube-dl

[hotstar] Add new extractor
---

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 365c0b86f..dd7e23d80 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -253,6 +253,7 @@ from .history import HistoryIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hornbunny import HornBunnyIE
 from .hotnewhiphop import HotNewHipHopIE
+from .hotstar import HotStarIE
 from .howcast import HowcastIE
 from .howstuffworks import HowStuffWorksIE
 from .huffpost import HuffPostIE
diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py
new file mode 100644
index 000000000..05d27e75d
--- /dev/null
+++ b/youtube_dl/extractor/hotstar.py
@@ -0,0 +1,79 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    determine_ext,
+    int_or_none,
+)
+
+
+class HotStarIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hotstar\.com/.*?[/-](?P<id>\d{10})'
+    _TEST = {
+        'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273',
+        'info_dict': {
+            'id': '1000076273',
+            'ext': 'mp4',
+            'title': 'On Air With AIB - English',
+            'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
+            'timestamp': 1447227000,
+            'upload_date': '20151111',
+            'duration': 381,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }
+
+    _GET_CONTENT_TEMPLATE = 'http://account.hotstar.com/AVS/besc?action=GetAggregatedContentDetails&channel=PCTV&contentId=%s'
+    _GET_CDN_TEMPLATE = 'http://getcdn.hotstar.com/AVS/besc?action=GetCDN&asJson=Y&channel=%s&id=%s&type=%s'
+
+    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True):
+        json_data = super(HotStarIE, self)._download_json(url_or_request, video_id, note, fatal=fatal)
+        if json_data['resultCode'] != 'OK':
+            if fatal:
+                raise ExtractorError(json_data['errorDescription'])
+            return None
+        return json_data['resultObj']
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_json(
+            self._GET_CONTENT_TEMPLATE % video_id,
+            video_id)['contentInfo'][0]
+
+        formats = []
+        # PCTV for extracting f4m manifest
+        for f in ('TABLET',):
+            format_data = self._download_json(
+                self._GET_CDN_TEMPLATE % (f, video_id, 'VOD'),
+                video_id, 'Downloading %s JSON metadata' % f, fatal=False)
+            if format_data:
+                format_url = format_data['src']
+                ext = determine_ext(format_url)
+                if ext == 'm3u8':
+                    m3u8_formats = self._extract_m3u8_formats(format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+                    if m3u8_formats:
+                        formats.extend(m3u8_formats)
+                elif ext == 'f4m':
+                    # produce broken files
+                    continue
+                else:
+                    formats.append({
+                        'url': format_url,
+                        'width': int_or_none(format_data.get('width')),
+                        'height': int_or_none(format_data.get('height')),
+                    })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_data['episodeTitle'],
+            'description': video_data.get('description'),
+            'duration': int_or_none(video_data.get('duration')),
+            'timestamp': int_or_none(video_data.get('broadcastDate')),
+            'formats': formats,
+        }