From 9c2a17f2ce7b2b9dc45b603be413a943f6637498 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Sun, 17 Sep 2017 22:19:57 +0700
Subject: [PATCH] [popcorntv] Add extractor (closes #5914, closes #14211)

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/popcorntv.py  | 78 ++++++++++++++++++++++++++++++
 2 files changed, 79 insertions(+)
 create mode 100644 youtube_dl/extractor/popcorntv.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index a3a97e940..ab95c8575 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -808,6 +808,7 @@
     PolskieRadioIE,
     PolskieRadioCategoryIE,
 )
+from .popcorntv import PopcornTVIE
 from .porn91 import Porn91IE
 from .porncom import PornComIE
 from .pornflip import PornFlipIE
diff --git a/youtube_dl/extractor/popcorntv.py b/youtube_dl/extractor/popcorntv.py
new file mode 100644
index 000000000..ac901f426
--- /dev/null
+++ b/youtube_dl/extractor/popcorntv.py
@@ -0,0 +1,78 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+    int_or_none,
+    unified_timestamp,
+)
+
+
+class PopcornTVIE(InfoExtractor):
+    _VALID_URL = r'https?://[^/]+\.popcorntv\.it/guarda/(?P<display_id>[^/]+)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://animemanga.popcorntv.it/guarda/food-wars-battaglie-culinarie-episodio-01/9183',
+        'md5': '47d65a48d147caf692ab8562fe630b45',
+        'info_dict': {
+            'id': '9183',
+            'display_id': 'food-wars-battaglie-culinarie-episodio-01',
+            'ext': 'mp4',
+            'title': 'Food Wars, Battaglie Culinarie | Episodio 01',
+            'description': 'md5:b8bea378faae4651d3b34c6e112463d0',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'timestamp': 1497610857,
+            'upload_date': '20170616',
+            'duration': 1440,
+            'view_count': int,
+        },
+    }, {
+        'url': 'https://cinema.popcorntv.it/guarda/smash-cut/10433',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id, video_id = mobj.group('display_id', 'id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        m3u8_url = extract_attributes(
+            self._search_regex(
+                r'(<link[^>]+itemprop=["\'](?:content|embed)Url[^>]*>)',
+                webpage, 'content'
+            ))['href']
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+
+        title = self._search_regex(
+            r'<h1[^>]+itemprop=["\']name[^>]*>([^<]+)', webpage,
+            'title', default=None) or self._og_search_title(webpage)
+
+        description = self._html_search_regex(
+            r'(?s)<article[^>]+itemprop=["\']description[^>]*>(.+?)</article>',
+            webpage, 'description', fatal=False)
+        thumbnail = self._og_search_thumbnail(webpage)
+        timestamp = unified_timestamp(self._html_search_meta(
+            'uploadDate', webpage, 'timestamp'))
+        print(self._html_search_meta(
+            'duration', webpage))
+        duration = int_or_none(self._html_search_meta(
+            'duration', webpage), invscale=60)
+        view_count = int_or_none(self._html_search_meta(
+            'interactionCount', webpage, 'view count'))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+        }