X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/b238854ce845f3796daac74edab2e8a373e8ba1a..3cd33af594d34a8809318ebd0be4d606d212a7a0:/youtube_dl/extractor/xhamster.py

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 279f75e..36a8c98 100644
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -1,111 +1,197 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urllib_parse,
-    unescapeHTML,
-    determine_ext,
-    ExtractorError,
+    dict_get,
+    int_or_none,
+    parse_duration,
+    unified_strdate,
 )
 
 
 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'(?P<proto>https?)://(?:.+?\.)?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"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,
-        }
+        'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
+        'md5': '8281348b8d3c53d39fffb377d24eac4e',
+        'info_dict': {
+            'id': '1509445',
+            'ext': 'mp4',
+            'title': 'FemaleAgent Shy beauty takes the bait',
+            'upload_date': '20121014',
+            'uploader': 'Ruseful2011',
+            'duration': 893,
+            'age_limit': 18,
+        },
+    }, {
+        'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
+        'info_dict': {
+            'id': '2221348',
+            'ext': 'mp4',
+            'title': 'Britney Spears  Sexy Booty',
+            'upload_date': '20130914',
+            'uploader': 'jojo747400',
+            'duration': 200,
+            'age_limit': 18,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # empty seo
+        'url': 'http://xhamster.com/movies/5667973/.html',
+        'info_dict': {
+            'id': '5667973',
+            'ext': 'mp4',
+            'title': '....',
+            'upload_date': '20160208',
+            'uploader': 'parejafree',
+            'duration': 72,
+            'age_limit': 18,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
+        'only_matching': True,
     }]
 
-    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 _real_extract(self, url):
+        def extract_video_url(webpage, name):
+            return self._search_regex(
+                [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
+                 r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
+                 r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
+                webpage, name, group='mp4')
 
         def is_hd(webpage):
-            return webpage.find('<div class=\'icon iconHD\'>') != -1
+            return '<div class=\'icon iconHD\'' in webpage
 
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
         seo = mobj.group('seo')
-        mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
+        proto = mobj.group('proto')
+        mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
         webpage = self._download_webpage(mrss_url, video_id)
 
-        video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
-            webpage, u'title')
+        title = self._html_search_regex(
+            [r'<h1[^>]*>([^<]+)</h1>',
+             r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
+             r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
+            webpage, 'title')
 
         # 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'<span>Description: </span>([^<]+)', webpage)
+        description = mobj.group(1) if mobj else None
+
+        upload_date = unified_strdate(self._search_regex(
+            r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
+            webpage, 'upload date', fatal=False))
+
+        uploader = self._html_search_regex(
+            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P<uploader>.+?)</a>',
+            webpage, 'uploader', default='anonymous')
+
+        thumbnail = self._search_regex(
+            [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
+             r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
+            webpage, 'thumbnail', fatal=False, group='thumbnail')
 
-        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:
-            video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
-        else:
-            video_upload_date = None
-            self._downloader.report_warning(u'Unable to extract upload date')
+        duration = parse_duration(self._search_regex(
+            r'Runtime:\s*</span>\s*([\d:]+)', webpage,
+            'duration', fatal=False))
 
-        video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
-            webpage, u'uploader id', default=u'anonymous')
+        view_count = int_or_none(self._search_regex(
+            r'content=["\']User(?:View|Play)s:(\d+)',
+            webpage, 'view count', fatal=False))
 
-        video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
-            webpage, u'thumbnail', fatal=False)
+        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)
 
-        video_url = extract_video_url(webpage)
         hd = is_hd(webpage)
+
+        format_id = 'hd' if hd else 'sd'
+
+        video_url = extract_video_url(webpage, format_id)
         formats = [{
             'url': video_url,
-            'ext': determine_ext(video_url),
-            'format': 'hd' if hd else 'sd',
             'format_id': 'hd' if hd else 'sd',
+            'preference': 1,
         }]
+
         if not hd:
-            webpage = self._download_webpage(mrss_url+'?hd', video_id)
+            mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
+            webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
             if is_hd(webpage):
-                video_url = extract_video_url(webpage)
+                video_url = extract_video_url(webpage, 'hd')
                 formats.append({
                     'url': video_url,
-                    'ext': determine_ext(video_url),
-                    'format': 'hd',
                     'format_id': 'hd',
+                    'preference': 2,
                 })
 
+        self._sort_formats(formats)
+
         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,
+            'title': title,
+            'description': description,
+            'upload_date': upload_date,
+            'uploader': uploader,
+            'thumbnail': 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,
+        }
+
+
+class XHamsterEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://xhamster.com/xembed.php?video=3328539',
+        'info_dict': {
+            'id': '3328539',
+            'ext': 'mp4',
+            'title': 'Pen Masturbation',
+            'upload_date': '20140728',
+            'uploader_id': 'anonymous',
+            'duration': 5,
+            'age_limit': 18,
         }
+    }
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [url for _, url in re.findall(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
+            webpage)]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(
+            r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id,
+            webpage, 'xhamster url', default=None)
+
+        if not video_url:
+            vars = self._parse_json(
+                self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
+                video_id)
+            video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
+
+        return self.url_result(video_url, 'XHamster')