debian/control: Update list of extractors.

[youtubedl] / youtube_dl / extractor / xhamster.py

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 0f1feeffd777ccc152b1ea1c4bb15dc00dc6b494..279f75e7a1f5b860e81d955c33bb58fcea092cbc 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -3,48 +3,67 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
-
+    unescapeHTML,
+    determine_ext,
     ExtractorError,
 )
 
 
 class XHamsterIE(InfoExtractor):
     """Information Extractor for xHamster"""
-    _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
-    _TEST = {
+    _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
+    _TESTS = [{
         u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
         u'file': u'1509445.flv',
         u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa',
         u'info_dict': {
             u"upload_date": u"20121014", 
             u"uploader_id": u"Ruseful2011", 
-            u"title": u"FemaleAgent Shy beauty takes the bait"
+            u"title": u"FemaleAgent Shy beauty takes the bait",
+            u"age_limit": 18,
+        }
+    },
+    {
+        u'url': u'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
+        u'file': u'2221348.flv',
+        u'md5': u'970a94178ca4118c5aa3aaea21211b81',
+        u'info_dict': {
+            u"upload_date": u"20130914",
+            u"uploader_id": u"jojo747400",
+            u"title": u"Britney Spears  Sexy Booty",
+            u"age_limit": 18,
         }
-    }
+    }]
 
     def _real_extract(self,url):
+        def extract_video_url(webpage):
+            mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
+            if mobj is None:
+                raise ExtractorError(u'Unable to extract media URL')
+            if len(mobj.group('server')) == 0:
+                return compat_urllib_parse.unquote(mobj.group('file'))
+            else:
+                return mobj.group('server')+'/key='+mobj.group('file')
+
+        def is_hd(webpage):
+            return webpage.find('<div class=\'icon iconHD\'>') != -1
+
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
-        mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
+        seo = mobj.group('seo')
+        mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
         webpage = self._download_webpage(mrss_url, video_id)
 
-        mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract media URL')
-        if len(mobj.group('server')) == 0:
-            video_url = compat_urllib_parse.unquote(mobj.group('file'))
-        else:
-            video_url = mobj.group('server')+'/key='+mobj.group('file')
-        video_extension = video_url.split('.')[-1]
-
         video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
             webpage, u'title')
 
-        # Can't see the description anywhere in the UI
-        # video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
-        #     webpage, u'description', fatal=False)
-        # if video_description: video_description = unescapeHTML(video_description)
+        # Only a few videos have an description
+        mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
+        if mobj:
+            video_description = unescapeHTML(mobj.group('description'))
+        else:
+            video_description = None
 
         mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
         if mobj:
@@ -59,13 +78,34 @@ class XHamsterIE(InfoExtractor):
         video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
             webpage, u'thumbnail', fatal=False)
 
-        return [{
-            'id':       video_id,
-            'url':      video_url,
-            'ext':      video_extension,
-            'title':    video_title,
-            # 'description': video_description,
+        age_limit = self._rta_search(webpage)
+
+        video_url = extract_video_url(webpage)
+        hd = is_hd(webpage)
+        formats = [{
+            'url': video_url,
+            'ext': determine_ext(video_url),
+            'format': 'hd' if hd else 'sd',
+            'format_id': 'hd' if hd else 'sd',
+        }]
+        if not hd:
+            webpage = self._download_webpage(mrss_url+'?hd', video_id)
+            if is_hd(webpage):
+                video_url = extract_video_url(webpage)
+                formats.append({
+                    'url': video_url,
+                    'ext': determine_ext(video_url),
+                    'format': 'hd',
+                    'format_id': 'hd',
+                })
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'formats': formats,
+            'description': video_description,
             'upload_date': video_upload_date,
             'uploader_id': video_uploader_id,
-            'thumbnail': video_thumbnail
-        }]
+            'thumbnail': video_thumbnail,
+            'age_limit': age_limit,
+        }