about summary refs log tree commit diff
path: root/youtube_dl/extractor/lenta.py
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2018-03-22 22:55:28 +0700
committerSergey M․ <dstftw@gmail.com>2018-03-22 23:07:31 +0700
commit8b7340a45eb0e3aeaa996896ff8690b6c3a32af6 (patch)
tree5bd61864c3b72d6b0aca69ce8da3d28c79c81e29 /youtube_dl/extractor/lenta.py
parent1d4a0520ba8b5fe4748ea74e1e6dda4e11f1e2f7 (diff)
downloadyoutube-dl-8b7340a45eb0e3aeaa996896ff8690b6c3a32af6.tar.gz
youtube-dl-8b7340a45eb0e3aeaa996896ff8690b6c3a32af6.tar.xz
youtube-dl-8b7340a45eb0e3aeaa996896ff8690b6c3a32af6.zip
[lenta] Add extractor (closes #15953)
Diffstat (limited to 'youtube_dl/extractor/lenta.py')
-rw-r--r--youtube_dl/extractor/lenta.py53
1 files changed, 53 insertions, 0 deletions
diff --git a/youtube_dl/extractor/lenta.py b/youtube_dl/extractor/lenta.py
new file mode 100644
index 000000000..2ebd4e577
--- /dev/null
+++ b/youtube_dl/extractor/lenta.py
@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class LentaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?lenta\.ru/[^/]+/\d+/\d+/\d+/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://lenta.ru/news/2018/03/22/savshenko_go/',
+        'info_dict': {
+            'id': '964400',
+            'ext': 'mp4',
+            'title': 'Надежду Савченко задержали',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 61,
+            'view_count': int,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # EaglePlatform iframe embed
+        'url': 'http://lenta.ru/news/2015/03/06/navalny/',
+        'info_dict': {
+            'id': '227304',
+            'ext': 'mp4',
+            'title': 'Навальный вышел на свободу',
+            'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 87,
+            'view_count': int,
+            'age_limit': 0,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r'vid\s*:\s*["\']?(\d+)', webpage, 'eagleplatform id',
+            default=None)
+        if video_id:
+            return self.url_result(
+                'eagleplatform:lentaru.media.eagleplatform.com:%s' % video_id,
+                ie='EaglePlatform', video_id=video_id)
+
+        return self.url_result(url, ie='Generic')