Merge pull request #2282 from dstftw/lifenews

[lifenews] Add support for lifenews.ru and fix og content extraction regex

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index e89b5cf9def65965f525b1e706bb7fb691a67228..7b71b9c701d02660aeec3a74bad2e1f1a211a881 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -110,6 +110,7 @@ from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
 from .la7 import LA7IE
+from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
 from .livestream import LivestreamIE, LivestreamOriginalIE
 from .lynda import (

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 70ba9eaba3f1e4cc32207867ba3dc6a4ed0d2b10..2c0c75604b96cfd08a283c0d93ef36f85b525922 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -399,7 +399,7 @@ class InfoExtractor(object):
     # Helper functions for extracting OpenGraph info
     @staticmethod
     def _og_regexes(prop):
-        content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')'
+        content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')'
         property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
         template = r'<meta[^>]+?%s[^>]+?%s'
         return [

diff --git a/youtube_dl/extractor/lifenews.py b/youtube_dl/extractor/lifenews.py
new file mode 100644 (file)
index 0000000..4e4035b
--- /dev/null
+++ b/youtube_dl/extractor/lifenews.py
@@ -0,0 +1,63 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class LifeNewsIE(InfoExtractor):
+    IE_NAME = 'lifenews'
+    IE_DESC = 'LIFE | NEWS'
+    _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
+    
+    _TEST = {
+        'url': 'http://lifenews.ru/news/126342',
+        'file': '126342.mp4',
+        'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
+        'info_dict': {
+            'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
+            'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
+            'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg',
+            'upload_date': '20140130',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage('http://lifenews.ru/mobile/news/%s' % video_id, video_id, 'Downloading page')
+
+        video_url = self._html_search_regex(
+            r'<video.*?src="([^"]+)"></video>', webpage, 'video URL')
+        
+        thumbnail = self._html_search_regex(
+            r'<video.*?poster="([^"]+)".*?"></video>', webpage, 'video thumbnail')
+
+        title = self._og_search_title(webpage)
+        TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS'
+        if title.endswith(TITLE_SUFFIX):
+            title = title[:-len(TITLE_SUFFIX)]
+
+        description = self._og_search_description(webpage)
+
+        view_count = self._html_search_regex(
+            r'<div class=\'views\'>(\d+)</div>', webpage, 'view count')
+        comment_count = self._html_search_regex(
+            r'<div class=\'comments\'>(\d+)</div>', webpage, 'comment count')
+
+        upload_date = self._html_search_regex(
+            r'<time datetime=\'([^\']+)\'>', webpage, 'upload date')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'title': title,
+            'description': description,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'upload_date': unified_strdate(upload_date),
+        }
\ No newline at end of file