Merge remote-tracking branch 'd912e3/golem'

[youtube-dl] / youtube_dl / extractor / pornhd.py

diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py
index c56740b8a927f7a8955a10b61eec3a9725a222b3..48ce6e7303e37463f991bb7e74241987b833297a 100644 (file)
--- a/youtube_dl/extractor/pornhd.py
+++ b/youtube_dl/extractor/pornhd.py
@@ -1,42 +1,74 @@
+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
+
 
 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+)'
     _TEST = {
-        u'id': u'1962',
-        u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
-        u'md5': u'4fe06e5108e8b524c35896f4c54c7155',
-        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',
+            'ext': 'mp4',
+            'title': 'Sierra loves doing laundry',
+            'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
+            'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group('video_id')
-        video_title = mobj.group('video_title')
-        video_extension = 'flv'
+        video_id = mobj.group('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))
 
-        self.report_extraction(video_id)
+        videos = re.findall(
+            r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage)
 
-        video_url = self._html_search_regex(
-            r'&hd=(http.+?)&', webpage, u'video URL')
-        video_url = compat_urllib_parse.unquote(video_url)
+        mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage)
+        if mobj:
+            flashvars = json.loads(mobj.group('flashvars'))
+            for key, quality in [('hashlink', 'low'), ('hd', 'high')]:
+                redirect_url = flashvars.get(key)
+                if redirect_url:
+                    videos.append(('flv', quality, redirect_url))
+            thumbnail = flashvars['urlWallpaper']
+        else:
+            thumbnail = self._og_search_thumbnail(webpage)
 
-        age_limit = 18
+        formats = []
+        for format_, quality, redirect_url in videos:
+            format_id = '%s-%s' % (format_.lower(), quality.lower())
+            video_url = self._download_webpage(
+                redirect_url, video_id, 'Downloading %s video link' % format_id, fatal=False)
+            if not video_url:
+                continue
+            formats.append({
+                'url': video_url,
+                'ext': format_.lower(),
+                'format_id': format_id,
+                'quality': 1 if quality.lower() == 'high' else 0,
+            })
+        self._sort_formats(formats)
 
         return {
-            'id':        video_id,
-            'url':       video_url,
-            'ext':       video_extension,
-            'title':     video_title,
-            'age_limit': age_limit,
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'view_count': view_count,
+            'formats': formats,
+            'age_limit': 18,
         }