aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/sexu.py61
2 files changed, 62 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 21853ccf4..c15b1add8 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -324,6 +324,7 @@ from .sbs import SBSIE
from .scivee import SciVeeIE
from .screencast import ScreencastIE
from .servingsys import ServingSysIE
+from .sexu import SexuIE
from .sexykarma import SexyKarmaIE
from .shared import SharedIE
from .sharesix import ShareSixIE
diff --git a/youtube_dl/extractor/sexu.py b/youtube_dl/extractor/sexu.py
new file mode 100644
index 000000000..7002643bc
--- /dev/null
+++ b/youtube_dl/extractor/sexu.py
@@ -0,0 +1,61 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class SexuIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)'
+ _TEST = {
+ 'url': 'http://sexu.com/961791/',
+ 'md5': 'ff615aca9691053c94f8f10d96cd7884',
+ 'info_dict': {
+ 'id': '961791',
+ 'ext': 'mp4',
+ 'title': str, # NSFW
+ 'description': 'md5:c5ed8625eb386855d5a7967bd7b77a54',
+ 'categories': list, # NSFW
+ 'thumbnail': 're:https?://.*\.jpg$',
+ 'age_limit': 18,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ quality_arr = self._search_regex(r'sources:\s*\[([^\]]+)\]', webpage, 'quality formats')
+
+ formats = [{
+ 'url': fmt[0].replace('\\', ''),
+ 'format_id': fmt[1],
+ 'height': int(fmt[1][:3]),
+ } for fmt in re.findall(r'"file":"([^"]+)","label":"([^"]+)"', quality_arr)]
+ self._sort_formats(formats)
+
+ title = self._html_search_regex(
+ r'<title>([^<]+)\s*-\s*Sexu.Com</title>', webpage, 'title')
+
+ description = self._html_search_meta('description', webpage, 'description')
+
+ thumbnail = self._html_search_regex(
+ r'image:\s*"([^"]+)"',
+ 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,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'categories': categories,
+ 'formats': formats,
+ 'age_limit': 18,
+ }