X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/0cf0312991a54458a07e903da2e47e9f3c8855ae..27375a0e586f091b3366c9963a15304fee569a05:/youtube_dl/extractor/fourtube.py

diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py
index b22ce2a..ad273a0 100644
--- a/youtube_dl/extractor/fourtube.py
+++ b/youtube_dl/extractor/fourtube.py
@@ -3,93 +3,221 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
-    compat_urllib_request,
-    unified_strdate,
-    str_to_int,
     parse_duration,
-    clean_html,
+    parse_iso8601,
+    str_to_int,
 )
 
 
-class FourTubeIE(InfoExtractor):
-    IE_NAME = '4tube'
-    _VALID_URL = r'https?://(?:www\.)?4tube\.com/videos/(?P<id>\d+)'
-
-    _TEST = {
-        'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
-        'md5': '6516c8ac63b03de06bc8eac14362db4f',
-        'info_dict': {
-            'id': '209733',
-            'ext': 'mp4',
-            'title': 'Hot Babe Holly Michaels gets her ass stuffed by black',
-            'uploader': 'WCP Club',
-            'uploader_id': 'wcp-club',
-            'upload_date': '20131031',
-            'duration': 583,
-        }
-    }
-
+class FourTubeBaseIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        kind, video_id, display_id = mobj.group('kind', 'id', 'display_id')
 
-        video_id = mobj.group('id')
-        webpage_url = 'http://www.4tube.com/videos/' + video_id
-        webpage = self._download_webpage(webpage_url, video_id)
-
-        self.report_extraction(video_id)
-
-        playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist')
-        media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id')
-        sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',')
-        title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title')
-        thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False)
-
-        uploader_str = self._search_regex(r'<span>Uploaded by</span>(.*?)<span>', webpage, 'uploader', fatal=False)
-        mobj = re.search(r'<a href="/sites/(?P<id>[^"]+)"><strong>(?P<name>[^<]+)</strong></a>', uploader_str)
-        (uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None)
-
-        upload_date = None
-        view_count = None
-        duration = None
-        description = self._html_search_meta('description', webpage, 'description')
-        if description:
-            upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date',
-                                             fatal=False)
-            if upload_date:
-                upload_date = unified_strdate(upload_date)
-            view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False)
-            if view_count:
-                view_count = str_to_int(view_count)
-            duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False))
-
-        token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources))
-        headers = {
-            b'Content-Type': b'application/x-www-form-urlencoded',
-            b'Origin': b'http://www.4tube.com',
-        }
-        token_req = compat_urllib_request.Request(token_url, b'{}', headers)
-        tokens = self._download_json(token_req, video_id)
+        if kind == 'm' or not display_id:
+            url = self._URL_TEMPLATE % video_id
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_meta('name', webpage)
+        timestamp = parse_iso8601(self._html_search_meta(
+            'uploadDate', webpage))
+        thumbnail = self._html_search_meta('thumbnailUrl', webpage)
+        uploader_id = self._html_search_regex(
+            r'<a class="item-to-subscribe" href="[^"]+/(?:channel|user)s?/([^/"]+)" title="Go to [^"]+ page">',
+            webpage, 'uploader id', fatal=False)
+        uploader = self._html_search_regex(
+            r'<a class="item-to-subscribe" href="[^"]+/(?:channel|user)s?/[^/"]+" title="Go to ([^"]+) page">',
+            webpage, 'uploader', fatal=False)
+
+        categories_html = self._search_regex(
+            r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="[^"]*?list[^"]*?">(.*?)</ul>',
+            webpage, 'categories', fatal=False)
+        categories = None
+        if categories_html:
+            categories = [
+                c.strip() for c in re.findall(
+                    r'(?s)<li><a.*?>(.*?)</a>', categories_html)]
+
+        view_count = str_to_int(self._search_regex(
+            r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([0-9,]+)">',
+            webpage, 'view count', default=None))
+        like_count = str_to_int(self._search_regex(
+            r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserLikes:([0-9,]+)">',
+            webpage, 'like count', default=None))
+        duration = parse_duration(self._html_search_meta('duration', webpage))
 
+        media_id = self._search_regex(
+            r'<button[^>]+data-id=(["\'])(?P<id>\d+)\1[^>]+data-quality=', webpage,
+            'media id', default=None, group='id')
+        sources = [
+            quality
+            for _, quality in re.findall(r'<button[^>]+data-quality=(["\'])(.+?)\1', webpage)]
+        if not (media_id and sources):
+            player_js = self._download_webpage(
+                self._search_regex(
+                    r'<script[^>]id=(["\'])playerembed\1[^>]+src=(["\'])(?P<url>.+?)\2',
+                    webpage, 'player JS', group='url'),
+                video_id, 'Downloading player JS')
+            params_js = self._search_regex(
+                r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)',
+                player_js, 'initialization parameters')
+            params = self._parse_json('[%s]' % params_js, video_id)
+            media_id = params[0]
+            sources = ['%s' % p for p in params[2]]
+
+        token_url = 'https://tkn.kodicdn.com/{0}/desktop/{1}'.format(
+            media_id, '+'.join(sources))
+
+        parsed_url = compat_urlparse.urlparse(url)
+        tokens = self._download_json(token_url, video_id, data=b'', headers={
+            'Origin': '%s://%s' % (parsed_url.scheme, parsed_url.hostname),
+            'Referer': url,
+        })
         formats = [{
             'url': tokens[format]['token'],
             'format_id': format + 'p',
             'resolution': format + 'p',
             'quality': int(format),
         } for format in sources]
-
         self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': title,
             'formats': formats,
-            'thumbnail': thumbnail_url,
+            'categories': categories,
+            'thumbnail': thumbnail,
             'uploader': uploader,
             'uploader_id': uploader_id,
-            'upload_date': upload_date,
+            'timestamp': timestamp,
+            'like_count': like_count,
             'view_count': view_count,
             'duration': duration,
             'age_limit': 18,
-            'webpage_url': webpage_url,
         }
+
+
+class FourTubeIE(FourTubeBaseIE):
+    IE_NAME = '4tube'
+    _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?4tube\.com/(?:videos|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
+    _URL_TEMPLATE = 'https://www.4tube.com/videos/%s/video'
+    _TESTS = [{
+        'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
+        'md5': '6516c8ac63b03de06bc8eac14362db4f',
+        'info_dict': {
+            'id': '209733',
+            'ext': 'mp4',
+            'title': 'Hot Babe Holly Michaels gets her ass stuffed by black',
+            'uploader': 'WCP Club',
+            'uploader_id': 'wcp-club',
+            'upload_date': '20131031',
+            'timestamp': 1383263892,
+            'duration': 583,
+            'view_count': int,
+            'like_count': int,
+            'categories': list,
+            'age_limit': 18,
+        },
+    }, {
+        'url': 'http://www.4tube.com/embed/209733',
+        'only_matching': True,
+    }, {
+        'url': 'http://m.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
+        'only_matching': True,
+    }]
+
+
+class FuxIE(FourTubeBaseIE):
+    _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?fux\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
+    _URL_TEMPLATE = 'https://www.fux.com/video/%s/video'
+    _TESTS = [{
+        'url': 'https://www.fux.com/video/195359/awesome-fucking-kitchen-ends-cum-swallow',
+        'info_dict': {
+            'id': '195359',
+            'ext': 'mp4',
+            'title': 'Awesome fucking in the kitchen ends with cum swallow',
+            'uploader': 'alenci2342',
+            'uploader_id': 'alenci2342',
+            'upload_date': '20131230',
+            'timestamp': 1388361660,
+            'duration': 289,
+            'view_count': int,
+            'like_count': int,
+            'categories': list,
+            'age_limit': 18,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.fux.com/embed/195359',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.fux.com/video/195359/awesome-fucking-kitchen-ends-cum-swallow',
+        'only_matching': True,
+    }]
+
+
+class PornTubeIE(FourTubeBaseIE):
+    _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?porntube\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)'
+    _URL_TEMPLATE = 'https://www.porntube.com/videos/video_%s'
+    _TESTS = [{
+        'url': 'https://www.porntube.com/videos/teen-couple-doing-anal_7089759',
+        'info_dict': {
+            'id': '7089759',
+            'ext': 'mp4',
+            'title': 'Teen couple doing anal',
+            'uploader': 'Alexy',
+            'uploader_id': 'Alexy',
+            'upload_date': '20150606',
+            'timestamp': 1433595647,
+            'duration': 5052,
+            'view_count': int,
+            'like_count': int,
+            'categories': list,
+            'age_limit': 18,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.porntube.com/embed/7089759',
+        'only_matching': True,
+    }, {
+        'url': 'https://m.porntube.com/videos/teen-couple-doing-anal_7089759',
+        'only_matching': True,
+    }]
+
+
+class PornerBrosIE(FourTubeBaseIE):
+    _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?pornerbros\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)'
+    _URL_TEMPLATE = 'https://www.pornerbros.com/videos/video_%s'
+    _TESTS = [{
+        'url': 'https://www.pornerbros.com/videos/skinny-brunette-takes-big-cock-down-her-anal-hole_181369',
+        'md5': '6516c8ac63b03de06bc8eac14362db4f',
+        'info_dict': {
+            'id': '181369',
+            'ext': 'mp4',
+            'title': 'Skinny brunette takes big cock down her anal hole',
+            'uploader': 'PornerBros HD',
+            'uploader_id': 'pornerbros-hd',
+            'upload_date': '20130130',
+            'timestamp': 1359527401,
+            'duration': 1224,
+            'view_count': int,
+            'categories': list,
+            'age_limit': 18,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.pornerbros.com/embed/181369',
+        'only_matching': True,
+    }, {
+        'url': 'https://m.pornerbros.com/videos/skinny-brunette-takes-big-cock-down-her-anal-hole_181369',
+        'only_matching': True,
+    }]