From 1306767d3662cb2fc78c59ff8a4d8ee9eb130946 Mon Sep 17 00:00:00 2001
From: JChris246 <43832407+JChris246@users.noreply.github.com>
Date: Sat, 2 Feb 2019 13:32:34 -0400
Subject: [PATCH 1/2] Delete vporn.py

---
 youtube_dl/extractor/vporn.py | 113 ----------------------------------
 1 file changed, 113 deletions(-)
 delete mode 100644 youtube_dl/extractor/vporn.py

diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py
deleted file mode 100644
index 9a11ebfc0..000000000
--- a/youtube_dl/extractor/vporn.py
+++ /dev/null
@@ -1,113 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    parse_duration,
-    parse_resolution,
-    str_to_int,
-)
-
-
-class VpornIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)'
-    _TESTS = [
-        {
-            'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
-            'md5': 'facf37c1b86546fa0208058546842c55',
-            'info_dict': {
-                'id': '497944',
-                'display_id': 'violet-on-her-th-birthday',
-                'ext': 'mp4',
-                'title': 'Violet on her 19th birthday',
-                'description': 'Violet dances in front of the camera which is sure to get you horny.',
-                'thumbnail': r're:^https?://.*\.jpg$',
-                'uploader': 'kileyGrope',
-                'categories': ['Masturbation', 'Teen'],
-                'duration': 393,
-                'age_limit': 18,
-                'view_count': int,
-            },
-            'skip': 'video removed',
-        },
-        {
-            'url': 'http://www.vporn.com/female/hana-shower/523564/',
-            'md5': 'ced35a4656198a1664cf2cda1575a25f',
-            'info_dict': {
-                'id': '523564',
-                'display_id': 'hana-shower',
-                'ext': 'mp4',
-                'title': 'Hana Shower',
-                'description': 'Hana showers at the bathroom.',
-                'thumbnail': r're:^https?://.*\.jpg$',
-                'uploader': 'Hmmmmm',
-                'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female', '720p'],
-                'duration': 588,
-                'age_limit': 18,
-                'view_count': int,
-            }
-        },
-    ]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
-
-        webpage = self._download_webpage(url, display_id)
-
-        errmsg = 'This video has been deleted due to Copyright Infringement or by the account owner!'
-        if errmsg in webpage:
-            raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
-
-        title = self._html_search_regex(
-            r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
-
-        description = self._search_regex(r'[^>]*class="(?:sidebar-box)"[^>]*>[\n]<p>(.*?)</p>',
-                                         webpage, 'description', fatal=False)
-
-        thumbnail = self._search_regex(r'<video[^>]+poster="([^"])"', webpage, 'thumbnail', default=None) or self._search_regex(r'posterurl\s=\s\'([^\']+)', webpage, 'thumbnail', fatal=False)
-
-        uploader = self._search_regex(r'class="avatarname">(.*?)</span>',
-                                      webpage, 'uploader', fatal=False)
-
-        categories = re.findall(r'<a[^>]*class="tags links"[^>]*>([^<]+)</a>', webpage)
-
-        duration = parse_duration(self._search_regex(
-            r'class="durat-img"[^>]*>\s*(\d+ min \d+ sec)',
-            webpage, 'duration', fatal=False))
-
-        view_count = str_to_int(self._search_regex(
-            r'class="view-count">[\n]([\d,\.]+) [Vv]iews[\n]<',
-            webpage, 'view count', fatal=False))
-
-        comment_count = str_to_int(self._html_search_regex(
-            r"'Comments \(([\d,\.]+)\)'",
-            webpage, 'comment count', default=None))
-
-        formats = []
-        for mobj in re.finditer(r'<source[^>]+src="([^"]+)"[^>]+label="([^"]+)[^>]*>', webpage):
-            f = parse_resolution(mobj.group(2))
-            f.update({
-                'url': mobj.group(1),
-                'format_id': mobj.group(2),
-            })
-            formats.append(f)
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'uploader': uploader,
-            'categories': categories,
-            'duration': duration,
-            'view_count': view_count,
-            'comment_count': comment_count,
-            'age_limit': 18,
-            'formats': formats,
-        }

From ba6f2017240c977ce6dfcc5856516299cb977947 Mon Sep 17 00:00:00 2001
From: JChris246 <43832407+JChris246@users.noreply.github.com>
Date: Sat, 2 Feb 2019 13:33:13 -0400
Subject: [PATCH 2/2] fixed tag parsing

---
 youtube_dl/extractor/pornhub.py | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index be93d5d48..1804ba15d 100644
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -307,10 +307,13 @@ class PornHubIE(PornHubBaseIE):
             r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
             webpage, 'page parameters', group='data', default='{}'),
             video_id, transform_source=js_to_json, fatal=False)
-        tags = categories = None
+        tags = None
         if page_params:
             tags = page_params.get('tags', '').split(',')
-            categories = page_params.get('categories', '').split(',')
+
+        categories = []
+        for mobj in re.finditer(r'<a href=[^>]+Category[^>]*>([^<]+)', webpage):
+            categories.append(mobj.group(1))
 
         return {
             'id': video_id,