[alphaporno] new extractor

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index fd0ebffe3ef15d0f7f2e4095be9a71de8cc4dc37..3fd0240c37f3a7f75dc5c52108b42034416ea865 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -7,6 +7,7 @@ from .adobetv import AdobeTVIE
 from .adultswim import AdultSwimIE
 from .aftonbladet import AftonbladetIE
 from .aljazeera import AlJazeeraIE
+from .alphaporno import AlphaPornoIE
 from .anitube import AnitubeIE
 from .anysex import AnySexIE
 from .aol import AolIE

diff --git a/youtube_dl/extractor/alphaporno.py b/youtube_dl/extractor/alphaporno.py
new file mode 100644 (file)
index 0000000..c8eaf83
--- /dev/null
+++ b/youtube_dl/extractor/alphaporno.py
@@ -0,0 +1,54 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+class AlphaPornoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<display_id>[^/]+)'
+    _TEST = {
+        'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/',
+        'md5': 'feb6d3bba8848cd54467a87ad34bd38e',
+        'info_dict': {
+            'id': '258807',
+            'ext': 'mp4',
+            'title': 'Sensual striptease porn with Samantha Alexandra - Striptease Porn',
+            'description': 'md5:c4447dc80e5be4c5f2711f7806e45424',
+            'categories': list,  # NSFW
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, 'main')
+
+        video_id = self._html_search_regex(r'video_id:\s*\'([^\']+)\'', webpage, 'id')
+
+        video_url = self._html_search_regex(r'video_url:\s*\'([^\']+)\'', webpage, 'video_url')
+
+        ext = self._html_search_meta('encodingFormat', webpage, 'ext')[1:]
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title')
+
+        description = self._html_search_meta('description', webpage, 'description', fatal=False)
+
+        thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail', fatal=False)
+
+        categories_str = self._html_search_meta(
+            'keywords', webpage, 'categories', fatal=False)
+        categories = (
+            None if categories_str is None
+            else categories_str.split(','))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'ext': ext,
+            'description': description,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'age_limit': 18,
+        }