From d2e522de09ed2f2a73b41b6e1fc73c537667e897 Mon Sep 17 00:00:00 2001
From: Laura Liberda <laura@selfisekai.rocks>
Date: Mon, 25 Jan 2021 15:45:55 +0100
Subject: [PATCH] wp.pl extractor

---
 haruhi_dl/extractor/extractors.py |  1 +
 haruhi_dl/extractor/wppl.py       | 61 +++++++++++++++++++++++++++++++
 2 files changed, 62 insertions(+)
 create mode 100644 haruhi_dl/extractor/wppl.py

diff --git a/haruhi_dl/extractor/extractors.py b/haruhi_dl/extractor/extractors.py
index 0b8eb1202..a68090c79 100644
--- a/haruhi_dl/extractor/extractors.py
+++ b/haruhi_dl/extractor/extractors.py
@@ -1465,6 +1465,7 @@ from .weibo import (
 from .weiqitv import WeiqiTVIE
 from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
+from .wppl import WpPlIE
 from .wsj import (
     WSJIE,
     WSJArticleIE,
diff --git a/haruhi_dl/extractor/wppl.py b/haruhi_dl/extractor/wppl.py
new file mode 100644
index 000000000..b299f2d07
--- /dev/null
+++ b/haruhi_dl/extractor/wppl.py
@@ -0,0 +1,61 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+)
+
+
+class WpPlIE(InfoExtractor):
+    _VALID_URL = r'https://(?:[^/]+\.)?wp\.pl/[^/]+-(?P<id>\d+v)'
+    IE_NAME = 'wp.pl'
+    IE_DESC = 'Wirtualna Polska'
+    _TESTS = [{
+        'url': 'https://wiadomosci.wp.pl/piotr-wawrzyk-na-rpo-dzieki-psl-to-byloby-trzesienie-ziemi-w-polskiej-polityce-6600013103609985v',
+        'info_dict': {
+            'id': '2062884',
+            'ext': 'mp4',
+            'title': 'Piotr Wawrzyk na RPO dzięki PSL? "To byłoby trzęsienie ziemi w polskiej polityce"',
+            'description': 'md5:c9b41dce48678c605cedf3f3fe5282c5',
+        },
+    }]
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, page_id)
+        video_id = self._search_regex(r'<div\b[^>]+\bid="video-player-(\d+)', webpage, 'video id')
+
+        video_data = self._download_json('https://wideo.wp.pl/api/v2/embed/%s/secured' % video_id, video_id)['clip']
+
+        formats = []
+        for fmt in video_data['url']:
+            ext = determine_ext(fmt['url'])
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(fmt['url'], video_id, m3u8_id=fmt['type']))
+            elif ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(fmt['url'], video_id, mpd_id=fmt['type']))
+            else:
+                mobj = re.match(r'(\d+)x(\d+)', fmt['resolution'])
+                width, height = mobj.group(1, 2)
+                formats.append({
+                    'url': fmt['url'],
+                    'ext': ext,
+                    'format_id': '%s-%s' % (fmt['type'], fmt['quality']),
+                    'width': int(width),
+                    'height': int(height),
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': video_data['title'],
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('screenshot'),
+            'duration': video_data.get('duration'),
+            'age_limit': video_data.get('minimalAge'),
+        }