youtube-dl

commit 94388f50b39e750f81e9baeb9fea0354f209d4e9
parent a4446482027156c8221351d677bed8927d74e231
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Mon,  1 Sep 2014 23:17:27 +0200

Merge remote-tracking branch 'peugeot/drtuber'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/drtuber.py
 | 
48
++++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 49 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -70,6 +70,7 @@ from .daum import DaumIE
 from .dfb import DFBIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
+from .drtuber import DrTuberIE
 from .drtv import DRTVIE
 from .dump import DumpIE
 from .defense import DefenseGouvFrIE
diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py
@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class DrTuberIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<title_dash>[\w-]+)'
+    _TEST = {
+        'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
+        'md5': '93e680cf2536ad0dfb7e74d94a89facd',
+        'info_dict': {
+            'id': '1740434',
+            'ext': 'mp4',
+            'title': 'Hot Perky Blonde Naked Golf',
+            'categories': list,  # NSFW
+            'thumbnail': 're:https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._html_search_regex(
+            r'<source src="([^"]+)"', webpage, 'video URL')
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)\s*-\s*Free', webpage, 'title')
+
+        thumbnail = self._html_search_regex(
+            r'poster="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        categories_str = self._html_search_regex(
+            r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
+        categories = categories_str.split(' ')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'categories': categories,
+        }