]> git.bitcoin.ninja Git - youtube-dl/commitdiff
[eroprofile] new extractor
authorpeugeot <peugeot.com>
Fri, 26 Dec 2014 16:15:34 +0000 (17:15 +0100)
committerpeugeot <peugeot.com>
Fri, 26 Dec 2014 16:15:34 +0000 (17:15 +0100)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/eroprofile.py [new file with mode: 0644]

index fd0ebffe3ef15d0f7f2e4095be9a71de8cc4dc37..39788712cf888fd97d20e84132d6fb8cfd6576a4 100644 (file)
@@ -108,6 +108,7 @@ from .elpais import ElPaisIE
 from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
 from .eporner import EpornerIE
+from .eroprofile import EroProfileIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py
new file mode 100644 (file)
index 0000000..f6745fc
--- /dev/null
@@ -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,
+        }