aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/xxxymovies.py
diff options
context:
space:
mode:
authorpeugeot <peugeot.com>2014-12-29 11:31:22 +0100
committerpeugeot <peugeot.com>2014-12-29 11:31:22 +0100
commit0cc4f8e3850e41dc5e3f237315a20eac5eb99f46 (patch)
treec260503baadb77cae5fb8e5db42f4f53bfcbedbd /youtube_dl/extractor/xxxymovies.py
parenta5424052000d6ab69412f380a96f1963f315a295 (diff)
[xxxymovies] new ectractor
Diffstat (limited to 'youtube_dl/extractor/xxxymovies.py')
-rw-r--r--youtube_dl/extractor/xxxymovies.py63
1 files changed, 63 insertions, 0 deletions
diff --git a/youtube_dl/extractor/xxxymovies.py b/youtube_dl/extractor/xxxymovies.py
new file mode 100644
index 000000000..4a9144661
--- /dev/null
+++ b/youtube_dl/extractor/xxxymovies.py
@@ -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,
+ }