[huajiao] Add new extractor

2 files changed, 51 insertions, 0 deletions

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 08bed8b0c..75e16af4e 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -372,6 +372,7 @@ from .hrti import (
     HRTiIE,
     HRTiPlaylistIE,
 )
+from .huajiao import HuajiaoIE
 from .huffpost import HuffPostIE
 from .hypem import HypemIE
 from .iconosquare import IconosquareIE
diff --git a/youtube_dl/extractor/huajiao.py b/youtube_dl/extractor/huajiao.py
new file mode 100644
index 000000000..352b48120
--- /dev/null
+++ b/youtube_dl/extractor/huajiao.py
@@ -0,0 +1,50 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from ..utils import parse_duration, parse_iso8601
+from .common import InfoExtractor
+
+
+class HuajiaoIE(InfoExtractor):
+    IE_DESC = '花椒直播'
+    _VALID_URL = r'https?://(?:www\.)?huajiao\.com/l/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.huajiao.com/l/38941232',
+        'md5': 'd08bf9ac98787d24d1e4c0283f2d372d',
+        'info_dict': {
+            'id': '38941232',
+            'ext': 'mp4',
+            'title': '#新人求关注#',
+            'description': 're:.*',
+            'duration': 2424.0,
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1475866459,
+            'upload_date': '20161007',
+            'uploader': 'Penny_余姿昀',
+            'uploader_id': '75206005',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        feed_json = self._search_regex(
+            r'var\s*feed\s*=\s*({.*})', webpage, 'feed json str')
+        feed = self._parse_json(feed_json, video_id)
+
+        description = self._html_search_meta(
+            'description', webpage, 'description', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': feed['feed']['formated_title'],
+            'description': description,
+            'duration': parse_duration(feed['feed']['duration']),
+            'thumbnail': feed['feed']['image'],
+            'timestamp': parse_iso8601(feed['creatime'], ' '),
+            'uploader': feed['author']['nickname'],
+            'uploader_id': feed['author']['uid'],
+            'formats': self._extract_m3u8_formats(
+                feed['feed']['m3u8'], video_id, 'mp4', 'm3u8_native'),
+        }