aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2014-12-26 23:34:12 +0600
committerSergey M․ <dstftw@gmail.com>2014-12-26 23:34:12 +0600
commitbcfe9db299d957b62d61b77beb09dae8bb69dbb0 (patch)
tree9a75b81734d7317d0621081cb22606af17698b46 /youtube_dl/extractor
parentcf00ae76404d0020926f4a1ddabec864205aa34d (diff)
parent4cda41ac7be1af03cb5fc4e9bbfcbf944925ab63 (diff)
Merge branch 'alphaporno' of https://github.com/peugeot/youtube-dl into peugeot-alphaporno
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/alphaporno.py54
2 files changed, 55 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 39788712c..32d616397 100644
--- 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
index 000000000..c8eaf837f
--- /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,
+ }