[xhamster] Fix and improve

youtube_dl/extractor/xhamster.py

@@ -4,51 +4,51 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urllib_parse,
     ExtractorError,
+    unified_strdate,
+    str_to_int,
+    int_or_none,
+    parse_duration,
 )
 
 
 class XHamsterIE(InfoExtractor):
     """Information Extractor for xHamster"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
+    _VALID_URL = r'http://(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
-    _TESTS = [{
+    _TESTS = [
+        {
             'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
-        'file': '1509445.mp4',
             'md5': '8281348b8d3c53d39fffb377d24eac4e',
             'info_dict': {
-            "upload_date": "20121014",
+                'id': '1509445',
-            "uploader_id": "Ruseful2011",
+                'ext': 'mp4',
-            "title": "FemaleAgent Shy beauty takes the bait",
+                'title': 'FemaleAgent Shy beauty takes the bait',
-            "age_limit": 18,
+                'upload_date': '20121014',
+                'uploader_id': 'Ruseful2011',
+                'duration': 893,
+                'age_limit': 18,
             }
         },
         {
             'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
-        'file': '2221348.flv',
+            'md5': '4cbd8d56708ecb4fb4124c23e4acb81a',
-        'md5': 'e767b9475de189320f691f49c679c4c7',
             'info_dict': {
-            "upload_date": "20130914",
+                'id': '2221348',
-            "uploader_id": "jojo747400",
+                'ext': 'mp4',
-            "title": "Britney Spears  Sexy Booty",
+                'title': 'Britney Spears  Sexy Booty',
-            "age_limit": 18,
+                'upload_date': '20130914',
+                'uploader_id': 'jojo747400',
+                'duration': 200,
+                '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)
+            mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
-            if mobj is None:
-                raise ExtractorError('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 extract_mp4_video_url(webpage):
-            mp4 = re.search(r'<a href=\"(.+?)\" class=\"mp4Play\"',webpage)
             if mp4 is None:
-                return None
+                raise ExtractorError('Unable to extract media URL')
             else:
                 return mp4.group(1)
 
@@ -62,50 +62,48 @@ class XHamsterIE(InfoExtractor):
         mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
         webpage = self._download_webpage(mrss_url, video_id)
 
-        video_title = self._html_search_regex(
+        title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
-            r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
 
         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
-        video_description = mobj.group(1) if mobj else None
+        description = mobj.group(1) if mobj else 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)
+        upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
-        if mobj:
+            webpage, 'upload date', fatal=False)
-            video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
+        if upload_date:
-        else:
+            upload_date = unified_strdate(upload_date)
-            video_upload_date = None
-            self._downloader.report_warning('Unable to extract upload date')
 
-        video_uploader_id = self._html_search_regex(
+        uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
-            r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
             webpage, 'uploader id', default='anonymous')
 
-        video_thumbnail = self._search_regex(
+        thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
-            r'\'image\':\'(?P<thumbnail>[^\']+)\'',
+
-            webpage, 'thumbnail', fatal=False)
+        duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
+            webpage, 'duration', fatal=False))
+
+        view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
+        if view_count:
+            view_count = str_to_int(view_count)
+
+        mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
+        (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
+
+        mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
+        comment_count = mobj.group('commentcount') if mobj else 0
 
         age_limit = self._rta_search(webpage)
 
         hd = is_hd(webpage)
+
         video_url = extract_video_url(webpage)
         formats = [{
             'url': video_url,
             'format_id': 'hd' if hd else 'sd',
-            'preference': 0,
-        }]
-
-        video_mp4_url = extract_mp4_video_url(webpage)
-        if video_mp4_url is not None:
-            formats.append({
-                'url': video_mp4_url,
-                'ext': 'mp4',
-                'format_id': 'mp4-hd' if hd else 'mp4-sd',
             'preference': 1,
-            })
+        }]
 
         if not hd:
-            webpage = self._download_webpage(
+            webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
-                mrss_url + '?hd', video_id, note='Downloading HD webpage')
             if is_hd(webpage):
                 video_url = extract_video_url(webpage)
                 formats.append({
@@ -118,11 +116,16 @@ class XHamsterIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': video_title,
+            'title': title,
-            'formats': formats,
+            'description': description,
-            'description': video_description,
+            'upload_date': upload_date,
-            'upload_date': video_upload_date,
+            'uploader_id': uploader_id,
-            'uploader_id': video_uploader_id,
+            'thumbnail': thumbnail,
-            'thumbnail': video_thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': int_or_none(like_count),
+            'dislike_count': int_or_none(dislike_count),
+            'comment_count': int_or_none(comment_count),
             'age_limit': age_limit,
+            'formats': formats,
         }