]> git.bitcoin.ninja Git - youtube-dl/commitdiff
[xxxymovies] new ectractor
authorpeugeot <peugeot.com>
Mon, 29 Dec 2014 10:31:22 +0000 (11:31 +0100)
committerpeugeot <peugeot.com>
Mon, 29 Dec 2014 10:31:22 +0000 (11:31 +0100)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/xxxymovies.py [new file with mode: 0644]

index fd0ebffe3ef15d0f7f2e4095be9a71de8cc4dc37..c8a77616e24fff789f11422a0ab46d71c0592eca 100644 (file)
@@ -512,6 +512,7 @@ from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xvideos import XVideosIE
 from .xtube import XTubeUserIE, XTubeIE
+from .xxxymovies import XXXYMoviesIE
 from .yahoo import (
     YahooIE,
     YahooSearchIE,
diff --git a/youtube_dl/extractor/xxxymovies.py b/youtube_dl/extractor/xxxymovies.py
new file mode 100644 (file)
index 0000000..4a91446
--- /dev/null
@@ -0,0 +1,63 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+)
+
+
+class XXXYMoviesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?xxxymovies\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)'
+    _TEST = {
+        'url': 'http://xxxymovies.com/videos/138669/ecstatic-orgasm-sofcore/',
+        'md5': '810b1bdbbffff89dd13bdb369fe7be4b',
+        'info_dict': {
+            'id': '138669',
+            'display_id': 'ecstatic-orgasm-sofcore',
+            'ext': 'mp4',
+            'title': 'Ecstatic Orgasm Sofcore',
+            'duration': 931,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._html_search_regex(
+            r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
+
+        title = self._html_search_regex(
+            r'<title>(.*?)\s*-\s*XXXYMovies.com</title>', webpage, 'title')
+
+        thumbnail = self._html_search_regex(
+            r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
+
+        categories = self._html_search_meta(
+            'keywords', webpage, 'categories', default='').split(',')
+
+        duration = parse_duration(self._search_regex(
+            r'<span>Duration:</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
+
+        view_count = int_or_none(self._html_search_regex(
+            r'<div class="video_views">\s*(\d+)', webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'duration': duration,
+            'view_count': view_count,
+            'age_limit': 18,
+        }