From aab6f8439c96fb14ec62cbf72c55d0fc376abab8 Mon Sep 17 00:00:00 2001
From: Jakub Wilk <jwilk@jwilk.net>
Date: Thu, 11 Apr 2019 17:11:57 +0200
Subject: [PATCH 01/10] [tvn24] Strip ".html" suffix from video id

---
 youtube_dl/extractor/tvn24.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py
index 6590e1fd0..acded1662 100644
--- a/youtube_dl/extractor/tvn24.py
+++ b/youtube_dl/extractor/tvn24.py
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
+    remove_end,
     unescapeHTML,
 )
 
@@ -36,6 +37,7 @@ class TVN24IE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        video_id = remove_end(video_id, '.html')
 
         webpage = self._download_webpage(url, video_id)
 

From f50d1c6a65b75af6341b698908ee5a3da7585d7b Mon Sep 17 00:00:00 2001
From: Jakub Wilk <jwilk@jwilk.net>
Date: Fri, 12 Apr 2019 13:53:03 +0200
Subject: [PATCH 02/10] [tvn24] Update description in test video

---
 youtube_dl/extractor/tvn24.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py
index acded1662..71c61ac11 100644
--- a/youtube_dl/extractor/tvn24.py
+++ b/youtube_dl/extractor/tvn24.py
@@ -18,7 +18,7 @@ class TVN24IE(InfoExtractor):
             'id': '1584444',
             'ext': 'mp4',
             'title': '"Święta mają być wesołe, dlatego, ludziska, wszyscy pod jemiołę"',
-            'description': 'Wyjątkowe orędzie Artura Andrusa, jednego z gości "Szkła kontaktowego".',
+            'description': 'Wyjątkowe orędzie Artura Andrusa, jednego z gości Szkła kontaktowego.',
             'thumbnail': 're:https?://.*[.]jpeg',
         }
     }, {

From 1e2483ac0f398187f867ff225888e92a1104cb28 Mon Sep 17 00:00:00 2001
From: Jakub Wilk <jwilk@jwilk.net>
Date: Wed, 17 Apr 2019 18:29:10 +0200
Subject: [PATCH 03/10] [tvn24] Extract all parts of Superwizjer videos

---
 youtube_dl/extractor/tvn24.py | 122 ++++++++++++++++++++++++----------
 1 file changed, 87 insertions(+), 35 deletions(-)

diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py
index 71c61ac11..a984b9c31 100644
--- a/youtube_dl/extractor/tvn24.py
+++ b/youtube_dl/extractor/tvn24.py
@@ -1,6 +1,9 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import itertools
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -21,6 +24,22 @@ class TVN24IE(InfoExtractor):
             'description': 'Wyjątkowe orędzie Artura Andrusa, jednego z gości Szkła kontaktowego.',
             'thumbnail': 're:https?://.*[.]jpeg',
         }
+    }, {
+        'url': 'https://www.tvn24.pl/superwizjer-w-tvn24,149,m/farma-trolli-zarabiaja-na-falszywych-informacjach-i-hejcie,923108.html',
+        'md5': 'fbdec753d7bc29d96036808275f2130c',
+        'info_dict': {
+            'title': '"Ludzie to jest, jakby nie patrzeć, też pieniądz". Farmy trolli zarabiają na fake newsach i hejcie',
+            'description': 'Ponad połowa Polaków wierzy w informacje, które znajduje w mediach społecznościowych. Ten fakt wykorzystują anonimowi twórcy tak zwanych fake newsów, czyli...',
+        },
+        'playlist_count': 4,
+        'playlist': [{
+            'md5': '8b1001e576a81e22fbb605a9e5ca9d65',
+            'info_dict': {
+                'id': '1831060',
+                'ext': 'mp4',
+                'title': 'Farma trolli. Pierwsza część reportażu',
+            },
+        }],
     }, {
         'url': 'http://fakty.tvn24.pl/ogladaj-online,60/53-konferencja-bezpieczenstwa-w-monachium,716431.html',
         'only_matching': True,
@@ -36,46 +55,79 @@ class TVN24IE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        video_id = remove_end(video_id, '.html')
+        page_id = self._match_id(url)
+        page_id = remove_end(page_id, '.html')
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, page_id)
 
-        title = self._og_search_title(webpage)
+        VIDEO_ELT_REGEX = r'(?P<video><div\b[^>]+\bclass="[^"]*\bvideoPlayer\b[^"]*"[^>]+>)'
 
-        def extract_json(attr, name, fatal=True):
-            return self._parse_json(
-                self._search_regex(
-                    r'\b%s=(["\'])(?P<json>(?!\1).+?)\1' % attr, webpage,
-                    name, group='json', fatal=fatal) or '{}',
-                video_id, transform_source=unescapeHTML, fatal=fatal)
+        def extract_videos(regex=VIDEO_ELT_REGEX, single=False):
 
-        quality_data = extract_json('data-quality', 'formats')
+            def extract_value(attr, name, fatal=True):
+                return self._html_search_regex(
+                    r'\bdata-%s=(["\'])(?P<val>(?!\1).+?)\1' % attr, video_elt,
+                    name, group='val', fatal=fatal)
 
-        formats = []
-        for format_id, url in quality_data.items():
-            formats.append({
-                'url': url,
-                'format_id': format_id,
-                'height': int_or_none(format_id.rstrip('p')),
-            })
-        self._sort_formats(formats)
+            def extract_json(attr, name, fatal=True):
+                value = extract_value(attr, name, fatal=fatal) or '{}'
+                return self._parse_json(value, video_id or page_id, fatal=fatal)
 
-        description = self._og_search_description(webpage)
-        thumbnail = self._og_search_thumbnail(
-            webpage, default=None) or self._html_search_regex(
-            r'\bdata-poster=(["\'])(?P<url>(?!\1).+?)\1', webpage,
-            'thumbnail', group='url')
+            entries = []
+            iterator = re.finditer(regex, webpage)
+            if single:
+                iterator = itertools.islice(iterator, 0, 1)
+            for match in iterator:
+                video_elt = match.group('video')
+                video_id = None
+                share_params = extract_json('share-params', 'share params', fatal=False)
+                if share_params:
+                    video_id = share_params['id']
+                else:
+                    video_id = extract_value('video-id', 'video id')
+                try:
+                    title = match.group('title')
+                except IndexError:
+                    title = None
+                title = unescapeHTML(title)
+                thumbnail = extract_value('poster', 'thumbnail', fatal=False)
+                quality_data = extract_json('quality', 'formats')
+                formats = []
+                for format_id, url in quality_data.items():
+                    formats.append({
+                        'url': url,
+                        'format_id': format_id,
+                        'height': int_or_none(format_id.rstrip('p')),
+                    })
+                self._sort_formats(formats)
+                entries.append({
+                    'id': video_id,
+                    'thumbnail': thumbnail,
+                    'formats': formats,
+                    'title': title,
+                })
+            if not entries:
+                # provoke RegexNotFoundError
+                self._search_regex('x', '', 'video elements')
+            return entries
 
-        share_params = extract_json(
-            'data-share-params', 'share params', fatal=False)
-        if isinstance(share_params, dict):
-            video_id = share_params.get('id') or video_id
+        if '/superwizjer-w-tvn24,' in url:
+            regex = r'<a\b[^>]*\btitle="(?P<title>[^"]+)"[^>]*\bclass="playVideo">\s*</a>\s*(<[^/][^>]*>\s*)+' + VIDEO_ELT_REGEX
+            entries = extract_videos(regex=regex)
+        else:
+            entries = extract_videos(single=True)
 
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'formats': formats,
-        }
+        if len(entries) == 1:
+            info = entries[0]
+        else:
+            info = {
+                'video_id': page_id,
+                '_type': 'multi_video',
+                'entries': entries,
+            }
+
+        if not info.get('title'):
+            info['title'] = self._og_search_title(webpage)
+        info['description'] = self._og_search_description(webpage)
+
+        return info

From 2f16501b8d5a1232ae6c01b728537a20ccb0e8db Mon Sep 17 00:00:00 2001
From: Jakub Wilk <jwilk@jwilk.net>
Date: Wed, 24 Apr 2019 10:31:41 +0200
Subject: [PATCH 04/10] [tvn24] Add support for toteraz.pl

---
 youtube_dl/extractor/tvn24.py | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py
index a984b9c31..b0829e232 100644
--- a/youtube_dl/extractor/tvn24.py
+++ b/youtube_dl/extractor/tvn24.py
@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class TVN24IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:[^/]+)\.)?tvn24(?:bis)?\.pl/(?:[^/]+/)*(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:(?:[^/]+)\.)?(?:toteraz|tvn24(?:bis)?)\.pl/(?:[^/]+/)*(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'http://www.tvn24.pl/wiadomosci-z-kraju,3/oredzie-artura-andrusa,702428.html',
         'md5': 'fbdec753d7bc29d96036808275f2130c',
@@ -40,6 +40,15 @@ class TVN24IE(InfoExtractor):
                 'title': 'Farma trolli. Pierwsza część reportażu',
             },
         }],
+    }, {
+        'url': 'https://toteraz.pl/zakaz-wyprowadzania-psow-nielegalny-decyzja-sadu-administracyjnego,1838704.html',
+        'md5': '46d127c478834e942b196d584b3ed747',
+        'info_dict': {
+            'id': '1838704',
+            'ext': 'mp4',
+            'title': 'Zakaz wyprowadzania psów nielegalny. Decyzja Sądu Administracyjnego',
+            'description': 'Okazuje się, że zakaz wprowadzania psów jest nielegalny i należy go traktować wyłącznie w kategoriach prośby.',
+        }
     }, {
         'url': 'http://fakty.tvn24.pl/ogladaj-online,60/53-konferencja-bezpieczenstwa-w-monachium,716431.html',
         'only_matching': True,
@@ -83,7 +92,10 @@ class TVN24IE(InfoExtractor):
                 share_params = extract_json('share-params', 'share params', fatal=False)
                 if share_params:
                     video_id = share_params['id']
-                else:
+                    if video_id == '[id]':
+                        # toteraz.pl videos have bogus share-params
+                        video_id = None
+                if video_id is None:
                     video_id = extract_value('video-id', 'video id')
                 try:
                     title = match.group('title')

From 27d70ea99ee34bc6afb21a61f0bd1b56841e3d04 Mon Sep 17 00:00:00 2001
From: Jakub Wilk <jwilk@jwilk.net>
Date: Sat, 27 Apr 2019 22:23:24 +0200
Subject: [PATCH 05/10] [tvn24] Extract video id from the data-video-id
 attribute

Extracting video identifier from the data-share-params attribute has proven to
be brittle: the attribute is bogus for some videos and completely missing for
some others.

Extract the identifier from the numeric part of the data-video-id attribute
instead.
---
 youtube_dl/extractor/tvn24.py | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py
index b0829e232..b113b990a 100644
--- a/youtube_dl/extractor/tvn24.py
+++ b/youtube_dl/extractor/tvn24.py
@@ -88,15 +88,9 @@ class TVN24IE(InfoExtractor):
                 iterator = itertools.islice(iterator, 0, 1)
             for match in iterator:
                 video_elt = match.group('video')
-                video_id = None
-                share_params = extract_json('share-params', 'share params', fatal=False)
-                if share_params:
-                    video_id = share_params['id']
-                    if video_id == '[id]':
-                        # toteraz.pl videos have bogus share-params
-                        video_id = None
-                if video_id is None:
-                    video_id = extract_value('video-id', 'video id')
+                video_id = self._search_regex(
+                    r'^(\d{6,})($|_)',
+                    extract_value('video-id', 'video id'), 'video id')
                 try:
                     title = match.group('title')
                 except IndexError:

From 2d220ad87596103040024f7e29a0b78392ef4d7a Mon Sep 17 00:00:00 2001
From: Jakub Wilk <jwilk@jwilk.net>
Date: Sat, 27 Apr 2019 22:28:29 +0200
Subject: [PATCH 06/10] [tvn24] Fall back to <title> when OpenGraph title is
 missing

---
 youtube_dl/extractor/tvn24.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py
index b113b990a..2691cbace 100644
--- a/youtube_dl/extractor/tvn24.py
+++ b/youtube_dl/extractor/tvn24.py
@@ -133,7 +133,8 @@ class TVN24IE(InfoExtractor):
             }
 
         if not info.get('title'):
-            info['title'] = self._og_search_title(webpage)
+            info['title'] = (self._og_search_title(webpage, default=None) or
+                             self._html_search_regex(r'<title>([^<]+)', webpage, 'title'))
         info['description'] = self._og_search_description(webpage)
 
         return info

From 213e3db8d8ded8917fa56351948ce409babb76c2 Mon Sep 17 00:00:00 2001
From: Jakub Wilk <jwilk@jwilk.net>
Date: Sat, 27 Apr 2019 22:32:17 +0200
Subject: [PATCH 07/10] [tvn24] Don't warn about missing OpenGraph description

The OpenGraph description is missing on some pages.
---
 youtube_dl/extractor/tvn24.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py
index 2691cbace..d5f9aa6d3 100644
--- a/youtube_dl/extractor/tvn24.py
+++ b/youtube_dl/extractor/tvn24.py
@@ -135,6 +135,7 @@ class TVN24IE(InfoExtractor):
         if not info.get('title'):
             info['title'] = (self._og_search_title(webpage, default=None) or
                              self._html_search_regex(r'<title>([^<]+)', webpage, 'title'))
-        info['description'] = self._og_search_description(webpage)
+
+        info['description'] = self._og_search_description(webpage, default=None)
 
         return info

From 34d72db0404a6d07bccb462ae001b2b8aa300298 Mon Sep 17 00:00:00 2001
From: Jakub Wilk <jwilk@jwilk.net>
Date: Sat, 27 Apr 2019 22:35:49 +0200
Subject: [PATCH 08/10] [tvn24] Add another test

---
 youtube_dl/extractor/tvn24.py | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py
index d5f9aa6d3..07dc22d72 100644
--- a/youtube_dl/extractor/tvn24.py
+++ b/youtube_dl/extractor/tvn24.py
@@ -40,6 +40,15 @@ class TVN24IE(InfoExtractor):
                 'title': 'Farma trolli. Pierwsza część reportażu',
             },
         }],
+    }, {
+        # no OpenGraph title or description
+        'url': 'https://tvnmeteo.tvn24.pl/magazyny/maja-w-ogrodzie,13/odcinki-online,1,1,1,0/zielona-wstazka-wsrod-pagorkow-odc-705-hgtv-odc-5-serii-2019,1831029.html',
+        'md5': '6fc1cdb118e429dd05c7111305caee83',
+        'info_dict': {
+            'id': '1831029',
+            'ext': 'mp4',
+            'title': 'Zielona wstążka wśród pagórków (odc. 705 /HGTV odc. 5 serii 2019) - Maja w Ogrodzie',
+        }
     }, {
         'url': 'https://toteraz.pl/zakaz-wyprowadzania-psow-nielegalny-decyzja-sadu-administracyjnego,1838704.html',
         'md5': '46d127c478834e942b196d584b3ed747',

From 488f54abc24f9635022c77f21bf60fda92ec7c3a Mon Sep 17 00:00:00 2001
From: Jakub Wilk <jwilk@jwilk.net>
Date: Mon, 29 Apr 2019 13:14:19 +0200
Subject: [PATCH 09/10] [tvn24] Fall back to data-src when data-quality is
 missing

---
 youtube_dl/extractor/tvn24.py | 41 +++++++++++++++++++++++++----------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py
index 07dc22d72..567fde961 100644
--- a/youtube_dl/extractor/tvn24.py
+++ b/youtube_dl/extractor/tvn24.py
@@ -49,6 +49,16 @@ class TVN24IE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Zielona wstążka wśród pagórków (odc. 705 /HGTV odc. 5 serii 2019) - Maja w Ogrodzie',
         }
+    }, {
+        # no data-quality
+        'url': 'https://tvnmeteo.tvn24.pl/informacje-pogoda/swiat,27/kotka-przyjela-cztery-wiewiorki-zaczely-po-niej-biegac-i-skakac,289746,1,0.html',
+        'md5': '691d604adc807a84c769c487762fc1ea',
+        'info_dict': {
+            'id': '1840073',
+            'ext': 'mp4',
+            'title': 'Kotka przyjęła cztery wiewiórki. "Zaczęły po niej biegać i skakać"',
+            'description': 'Kotka o imieniu Pusza, żyjąca w Parku Miniatur w krymskim mieście Bakczysaraj to idealny przykład na to, że matczyna miłość nie zna granic. Zwierzę zao...',
+        }
     }, {
         'url': 'https://toteraz.pl/zakaz-wyprowadzania-psow-nielegalny-decyzja-sadu-administracyjnego,1838704.html',
         'md5': '46d127c478834e942b196d584b3ed747',
@@ -107,20 +117,29 @@ class TVN24IE(InfoExtractor):
                 title = unescapeHTML(title)
                 thumbnail = extract_value('poster', 'thumbnail', fatal=False)
                 quality_data = extract_json('quality', 'formats')
-                formats = []
-                for format_id, url in quality_data.items():
-                    formats.append({
-                        'url': url,
-                        'format_id': format_id,
-                        'height': int_or_none(format_id.rstrip('p')),
-                    })
-                self._sort_formats(formats)
-                entries.append({
+                info = {
                     'id': video_id,
                     'thumbnail': thumbnail,
-                    'formats': formats,
                     'title': title,
-                })
+                }
+                if quality_data:
+                    info['formats'] = formats = []
+                    for format_id, url in quality_data.items():
+                        formats.append({
+                            'url': url,
+                            'format_id': format_id,
+                            'height': int_or_none(format_id.rstrip('p')),
+                        })
+                    self._sort_formats(formats)
+                else:
+                    info['url'] = url = extract_value('src', 'video URL')
+                    height = self._search_regex('-([0-9]+)p[.]', url, 'format id', default=None)
+                    if height:
+                        info.update({
+                            'format_id': height + 'p',
+                            'height': int_or_none(height),
+                        })
+                entries.append(info)
             if not entries:
                 # provoke RegexNotFoundError
                 self._search_regex('x', '', 'video elements')

From 37cbc63e44dea67af2d9570b48514f01126dd49f Mon Sep 17 00:00:00 2001
From: Jakub Wilk <jwilk@jwilk.net>
Date: Sat, 4 May 2019 22:19:33 +0200
Subject: [PATCH 10/10] =?UTF-8?q?[tvn24]=20Extract=20all=20parts=20of=20"S?=
 =?UTF-8?q?zk=C5=82o=20kontaktowe"=20videos?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 youtube_dl/extractor/tvn24.py | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py
index 567fde961..2b92d901a 100644
--- a/youtube_dl/extractor/tvn24.py
+++ b/youtube_dl/extractor/tvn24.py
@@ -59,6 +59,29 @@ class TVN24IE(InfoExtractor):
             'title': 'Kotka przyjęła cztery wiewiórki. "Zaczęły po niej biegać i skakać"',
             'description': 'Kotka o imieniu Pusza, żyjąca w Parku Miniatur w krymskim mieście Bakczysaraj to idealny przykład na to, że matczyna miłość nie zna granic. Zwierzę zao...',
         }
+    }, {
+        'url': 'https://szklokontaktowe.tvn24.pl/lenin-czyli-kto,932164.html',
+        'info_dict': {
+            'title': 'Lenin, czyli kto?',
+            'description': 'Jarosław Kaczyński zdradził w Nowym Sączu pewną tajemnicę. Teraz już wszyscy wiemy, na którego z przedstawicieli PiS ludzie są tak źli na niego, że go nazy...',
+        },
+        'playlist_count': 3,
+        'playlist': [{
+            'md5': '014222e9a6261b424cd3474fd94ffeeb',
+            'info_dict': {
+                'id': '1841329',
+                'ext': 'mp4',
+                'title': 'Lenin, czyli kto? - część 1',
+            },
+        }],
+    }, {
+        'url': 'https://szklokontaktowe.tvn24.pl/rumba-szuka-domu,931617.html',
+        'info_dict': {
+            'id': '1840681',
+            'ext': 'mp4',
+            'title': 'Rumba szuka domu',
+            'description': 'RUMBA - wspaniała, ok czteroletnia suczka w typie owczarka uratowana z paskudnego schroniska wypatruje domu. Odznacza się wielką inteligencją i bardzo pozy...',
+        }
     }, {
         'url': 'https://toteraz.pl/zakaz-wyprowadzania-psow-nielegalny-decyzja-sadu-administracyjnego,1838704.html',
         'md5': '46d127c478834e942b196d584b3ed747',
@@ -148,6 +171,13 @@ class TVN24IE(InfoExtractor):
         if '/superwizjer-w-tvn24,' in url:
             regex = r'<a\b[^>]*\btitle="(?P<title>[^"]+)"[^>]*\bclass="playVideo">\s*</a>\s*(<[^/][^>]*>\s*)+' + VIDEO_ELT_REGEX
             entries = extract_videos(regex=regex)
+        elif '//szklokontaktowe.tvn24.pl/' in url:
+            regex = VIDEO_ELT_REGEX + r'(\s*</div>)+\s*<figcaption>'
+            entries = extract_videos(regex=regex)
+            if len(entries) > 1:
+                title = self._og_search_title(webpage)
+                for n, entry in enumerate(entries, start=1):
+                    entry['title'] = '{title} - część {n}'.format(title=title, n=n)
         else:
             entries = extract_videos(single=True)