From 8d9b9022435abcc24790b5dcce8d323b167d7954 Mon Sep 17 00:00:00 2001
From: mzbaulhaque <11481344+mzbaulhaque@users.noreply.github.com>
Date: Tue, 20 Jul 2021 00:16:21 +0600
Subject: [PATCH] [pornflip] Add new extractor (#523)

Authored-by: mzbaulhaque
---
 yt_dlp/extractor/extractors.py |  1 +
 yt_dlp/extractor/pornflip.py   | 82 ++++++++++++++++++++++++++++++++++
 2 files changed, 83 insertions(+)
 create mode 100644 yt_dlp/extractor/pornflip.py

diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py
index 694be9e57..ded5989bf 100644
--- a/yt_dlp/extractor/extractors.py
+++ b/yt_dlp/extractor/extractors.py
@@ -1015,6 +1015,7 @@ from .popcorntimes import PopcorntimesIE
 from .popcorntv import PopcornTVIE
 from .porn91 import Porn91IE
 from .porncom import PornComIE
+from .pornflip import PornFlipIE
 from .pornhd import PornHdIE
 from .pornhub import (
     PornHubIE,
diff --git a/yt_dlp/extractor/pornflip.py b/yt_dlp/extractor/pornflip.py
new file mode 100644
index 000000000..d0aefa2dd
--- /dev/null
+++ b/yt_dlp/extractor/pornflip.py
@@ -0,0 +1,82 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    parse_iso8601
+)
+
+
+class PornFlipIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:(embed|sv|v)/)?(?P<id>[^/]+)'
+    _TESTS = [
+        {
+            'url': 'https://www.pornflip.com/dzv9Mtw1qj2/sv/brazzers-double-dare-two-couples-fucked-jenna-reid-maya-bijou',
+            'info_dict': {
+                'id': 'dzv9Mtw1qj2',
+                'ext': 'mp4',
+                'title': 'Brazzers - Double Dare Two couples fucked Jenna Reid Maya Bijou',
+                'description': 'md5:d2b69e6cc743c5fd158e162aa7f05821',
+                'duration': 476,
+                'like_count': int,
+                'dislike_count': int,
+                'view_count': int,
+                'timestamp': 1617846819,
+                'upload_date': '20210408',
+                'uploader': 'Brazzers',
+                'age_limit': 18,
+            },
+            'params': {
+                'format': 'bestvideo',
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'https://www.pornflip.com/v/IrJEC40i21L',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://www.pornflip.com/Z3jzbChC5-P/sexintaxi-e-sereyna-gomez-czech-naked-couple',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://www.pornflip.com/embed/bLcDFxnrZnU',
+            'only_matching': True,
+        },
+    ]
+    _HOST = 'www.pornflip.com'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(
+            'https://{}/sv/{}'.format(self._HOST, video_id), video_id, headers={'host': self._HOST})
+        description = self._html_search_regex(r'&p\[summary\]=(.*?)\s*&p', webpage, 'description', fatal=False)
+        duration = self._search_regex(r'"duration":\s+"([^"]+)",', webpage, 'duration', fatal=False)
+        view_count = self._search_regex(r'"interactionCount":\s+"([^"]+)"', webpage, 'view_count', fatal=False)
+        title = self._html_search_regex(r'id="mediaPlayerTitleLink"[^>]*>(.+)</a>', webpage, 'title', fatal=False)
+        uploader = self._html_search_regex(r'class="title-chanel"[^>]*>[^<]*<a[^>]*>([^<]+)<', webpage, 'uploader', fatal=False)
+        upload_date = self._search_regex(r'"uploadDate":\s+"([^"]+)",', webpage, 'upload_date', fatal=False)
+        likes = self._html_search_regex(
+            r'class="btn btn-up-rating[^>]*>[^<]*<i[^>]*>[^<]*</i>[^>]*<span[^>]*>[^0-9]*([0-9]+)[^<0-9]*<', webpage, 'like_count', fatal=False)
+        dislikes = self._html_search_regex(
+            r'class="btn btn-down-rating[^>]*>[^<]*<i[^>]*>[^<]*</i>[^>]*<span[^>]*>[^0-9]*([0-9]+)[^<0-9]*<', webpage, 'dislike_count', fatal=False)
+        mpd_url = self._search_regex(r'"([^"]+userscontent.net/dash/[0-9]+/manifest.mpd[^"]*)"', webpage, 'mpd_url').replace('&amp;', '&')
+        formats = self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash')
+        self._sort_formats(formats)
+
+        return {
+            'age_limit': 18,
+            'description': description,
+            'dislike_count': int_or_none(dislikes),
+            'duration': parse_duration(duration),
+            'formats': formats,
+            'id': video_id,
+            'like_count': int_or_none(likes),
+            'timestamp': parse_iso8601(upload_date),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'title': title,
+            'uploader': uploader,
+            'view_count': int_or_none(view_count),
+        }