aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/eroprofile.py
diff options
context:
space:
mode:
authorpeugeot <peugeot.com>2014-12-26 17:15:34 +0100
committerpeugeot <peugeot.com>2014-12-26 17:15:34 +0100
commit461b00f34aabf6e75e0d53419919a8e6cc9cfd7a (patch)
tree2756fef2436728b7faaad343b7b5b2dd74dcba7b /youtube_dl/extractor/eroprofile.py
parenta5424052000d6ab69412f380a96f1963f315a295 (diff)
downloadyoutube-dl-461b00f34aabf6e75e0d53419919a8e6cc9cfd7a.zip
youtube-dl-461b00f34aabf6e75e0d53419919a8e6cc9cfd7a.tar.gz
youtube-dl-461b00f34aabf6e75e0d53419919a8e6cc9cfd7a.tar.bz2
[eroprofile] new extractor
Diffstat (limited to 'youtube_dl/extractor/eroprofile.py')
-rw-r--r--youtube_dl/extractor/eroprofile.py53
1 files changed, 53 insertions, 0 deletions
diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py
new file mode 100644
index 0000000..f6745fc
--- /dev/null
+++ b/youtube_dl/extractor/eroprofile.py
@@ -0,0 +1,53 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+class EroProfileIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<display_id>[^/]+)'
+ _TEST = {
+ 'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
+ 'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
+ 'info_dict': {
+ 'id': '3733775',
+ 'ext': 'm4v',
+ 'title': 'HD MOVIES - sexy babe softcore',
+ 'description': 'md5:831ee50526c333eb4f6c1e58d382c295',
+ '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'glbUpdViews\s*\(\'\d*\',\'(\d+)\'', webpage, 'id')
+
+ video_url = self._html_search_regex(r'<source src="([^"]+)', webpage, 'video_url')
+
+ title = self._html_search_regex(
+ r'<title>([^<]+)\s*-\s*EroProfile</title>', webpage, 'title')
+
+ description = self._html_search_meta('description', webpage, 'description', fatal=False)
+
+ thumbnail = self._html_search_regex(
+ r'onclick="showVideoPlayer\(\)"><img src="([^"]+)', 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': 'm4v',
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'categories': categories,
+ 'age_limit': 18,
+ }