youtube-dl

commit 8e7020daef5477a05e6f02c3b59b0bd04b315eb6
parent a26bcc61c177470606a1b5e8fd74469e894745b2
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date:   Mon, 11 Jul 2016 13:19:25 +0800

[rudo] Add new extractor

Used in biobiochile.tv

Diffstat:
M
youtube_dl/extractor/extractors.py
 | 
1
+
A
youtube_dl/extractor/rudo.py
 | 
53
+++++++++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 54 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -691,6 +691,7 @@ from .rtp import RTPIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
 from .rtvnh import RTVNHIE
+from .rudo import RudoIE
 from .ruhd import RUHDIE
 from .ruleporn import RulePornIE
 from .rutube import (
diff --git a/youtube_dl/extractor/rudo.py b/youtube_dl/extractor/rudo.py
@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .jwplatform import JWPlatformBaseIE
+from ..utils import (
+    js_to_json,
+    get_element_by_class,
+    unified_strdate,
+)
+
+
+class RudoIE(JWPlatformBaseIE):
+    _VALID_URL = r'https?://rudo\.video/vod/(?P<id>[0-9a-zA-Z]+)'
+
+    _TEST = {
+        'url': 'http://rudo.video/vod/oTzw0MGnyG',
+        'md5': '2a03a5b32dd90a04c83b6d391cf7b415',
+        'info_dict': {
+            'id': 'oTzw0MGnyG',
+            'ext': 'mp4',
+            'title': 'Comentario Tomás Mosciatti',
+            'upload_date': '20160617',
+        },
+    }
+
+    @classmethod
+    def _extract_url(self, webpage):
+        mobj = re.search(
+            '<iframe[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)',
+            webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id, encoding='iso-8859-1')
+
+        jwplayer_data = self._parse_json(self._search_regex(
+            r'(?s)playerInstance\.setup\(({.+?})\)', webpage, 'jwplayer data'), video_id,
+            transform_source=lambda s: js_to_json(re.sub(r'encodeURI\([^)]+\)', '""', s)))
+
+        info_dict = self._parse_jwplayer_data(
+            jwplayer_data, video_id, require_title=False, m3u8_id='hls')
+
+        info_dict.update({
+            'title': self._og_search_title(webpage),
+            'upload_date': unified_strdate(get_element_by_class('date', webpage)),
+        })
+
+        return info_dict