Merge tag 'upstream/2014.12.01'

[youtubedl] / youtube_dl / extractor / pornhd.py

diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py
index 71abd5013bf272ffbb2812a87a6838fd3aeedd7e..bac484c67dbb01bbafa319c117b7c6d152b7dd5d 100644 (file)
--- a/youtube_dl/extractor/pornhd.py
+++ b/youtube_dl/extractor/pornhd.py
@@ -1,38 +1,66 @@
+from __future__ import unicode_literals
+
 import re
+import json
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_parse
+from ..utils import (
+    int_or_none,
+    js_to_json,
+    qualities,
+    determine_ext,
+)
 
 
 class PornHdIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
+    _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
     _TEST = {
-        u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
-        u'file': u'1962.flv',
-        u'md5': u'35272469887dca97abd30abecc6cdf75',
-        u'info_dict': {
-            u"title": u"sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
-            u"age_limit": 18,
+        'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
+        'md5': '956b8ca569f7f4d8ec563e2c41598441',
+        'info_dict': {
+            'id': '1962',
+            'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
+            'ext': 'mp4',
+            'title': 'Sierra loves doing laundry',
+            'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'view_count': int,
+            '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')
 
-        video_id = mobj.group('video_id')
-        video_title = mobj.group('video_title')
+        webpage = self._download_webpage(url, display_id or video_id)
 
-        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_regex(
+            r'<title>(.+) porn HD.+?</title>', webpage, 'title')
+        description = self._html_search_regex(
+            r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
+        view_count = int_or_none(self._html_search_regex(
+            r'(\d+) views\s*</span>', webpage, 'view count', fatal=False))
+        thumbnail = self._search_regex(
+            r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
 
-        video_url = self._html_search_regex(
-            r'&hd=(http.+?)&', webpage, u'video URL')
-        video_url = compat_urllib_parse.unquote(video_url)
-        age_limit = 18
+        quality = qualities(['SD', 'HD'])
+        formats = [{
+            'url': source['file'],
+            'format_id': '%s-%s' % (source['label'], determine_ext(source['file'])),
+            'quality': quality(source['label']),
+        } for source in json.loads(js_to_json(self._search_regex(
+            r"(?s)'sources'\s*:\s*(\[.+?\])", webpage, 'sources')))]
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'flv',
-            'title': video_title,
-            'age_limit': age_limit,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'view_count': view_count,
+            'formats': formats,
+            'age_limit': 18,
         }