From 68b5101b487159e1e59ced60ab389654a592e95d Mon Sep 17 00:00:00 2001
From: Surkal <>
Date: Sun, 6 Sep 2020 18:43:14 +0200
Subject: [PATCH 1/3] [Lumni] Add new extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/lumni.py      | 74 ++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+)
 create mode 100644 youtube_dl/extractor/lumni.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 9564465a0..420f1be40 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -580,6 +580,7 @@ from .lnkgo import LnkGoIE
 from .localnews8 import LocalNews8IE
 from .lovehomeporn import LoveHomePornIE
 from .lrt import LRTIE
+from .lumni import LumniIE, LumniPlaylistIE
 from .lynda import (
     LyndaIE,
     LyndaCourseIE
diff --git a/youtube_dl/extractor/lumni.py b/youtube_dl/extractor/lumni.py
new file mode 100644
index 000000000..748306e59
--- /dev/null
+++ b/youtube_dl/extractor/lumni.py
@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .francetv import FranceTVIE
+from ..utils import orderedSet
+
+
+class LumniIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?lumni\.fr/video/(?P<id>[0-9a-z-]+)'
+    _TEST = {
+        'url': 'https://www.lumni.fr/video/la-guerre-froide',
+        'md5': '31158a5b300083ba373f4fc85dd88272',
+        'info_dict': {
+            'id': '302dbf40-b0df-4847-926b-99fdf4f10162',
+            'ext': 'mp4',
+            'timestamp': 1585754978,
+            'upload_date': '20200401',
+            'title': 'La guerre froide (1er avril)',
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r'data-factoryid="([^"]+)',
+            webpage, 'video id')
+        full_id = 'francetv:%s' % video_id
+
+        return self.url_result(full_id,
+                               ie=FranceTVIE.ie_key(),
+                               video_id=video_id)
+
+
+class LumniPlaylistIE(InfoExtractor):
+    _VALID_URL = r'''https?://
+                        (?:www\.)?lumni\.fr/
+                        (?:dossier|programme|serie)/
+                        (?P<id>[0-9a-z-]+)
+                    '''
+    _TESTS = [{
+        'url': 'https://www.lumni.fr/dossier/les-fondamentaux-vocabulaire',
+        'info_dict': {
+            'id': 'les-fondamentaux-vocabulaire',
+            'title': 'Les Fondamentaux : Vocabulaire',
+        },
+        'playlist_mincount': 39
+    }, {
+        'url': 'https://www.lumni.fr/programme/the-rich-morning-show',
+        'only_matching': True
+    }, {
+        'url': 'https://www.lumni.fr/serie/la-maison-lumni-college',
+        'only_matching': True
+    }
+    ]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [self.url_result(
+            'https://lumni.fr/video/%s' % video_id,
+            ie=LumniIE.ie_key(), video_id=video_id)
+            for video_id in orderedSet(re.findall(
+                r'<a[^>]+\bhref=["\']/video/([0-9a-z-]+)', webpage))]
+
+        playlist_title = self._og_search_title(webpage)
+
+        return self.playlist_result(entries, playlist_id, playlist_title)

From 9d037f4f1dbf9cdb0abe2617b3b806203c875fea Mon Sep 17 00:00:00 2001
From: Surkal <>
Date: Sun, 6 Sep 2020 19:00:26 +0200
Subject: [PATCH 2/3] fix regex

---
 youtube_dl/extractor/lumni.py | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/youtube_dl/extractor/lumni.py b/youtube_dl/extractor/lumni.py
index 748306e59..68f6f0bd1 100644
--- a/youtube_dl/extractor/lumni.py
+++ b/youtube_dl/extractor/lumni.py
@@ -37,11 +37,7 @@ class LumniIE(InfoExtractor):
 
 
 class LumniPlaylistIE(InfoExtractor):
-    _VALID_URL = r'''https?://
-                        (?:www\.)?lumni\.fr/
-                        (?:dossier|programme|serie)/
-                        (?P<id>[0-9a-z-]+)
-                    '''
+    _VALID_URL = r'https?://(?:www\.)?lumni\.fr/(?:dossier|programme|serie)/(?P<id>[0-9a-z-]+)'
     _TESTS = [{
         'url': 'https://www.lumni.fr/dossier/les-fondamentaux-vocabulaire',
         'info_dict': {

From e062ec875d402a13117754dd7f7a4542353082eb Mon Sep 17 00:00:00 2001
From: Surkal <>
Date: Mon, 7 Sep 2020 12:24:28 +0200
Subject: [PATCH 3/3] split regex

---
 youtube_dl/extractor/lumni.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/lumni.py b/youtube_dl/extractor/lumni.py
index 68f6f0bd1..05146ab72 100644
--- a/youtube_dl/extractor/lumni.py
+++ b/youtube_dl/extractor/lumni.py
@@ -37,7 +37,12 @@ class LumniIE(InfoExtractor):
 
 
 class LumniPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?lumni\.fr/(?:dossier|programme|serie)/(?P<id>[0-9a-z-]+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?lumni\.fr/
+                        (?:dossier|programme|serie)/
+                        (?P<id>[0-9a-z-]+)
+                    '''
     _TESTS = [{
         'url': 'https://www.lumni.fr/dossier/les-fondamentaux-vocabulaire',
         'info_dict': {