debian/control: Update list of extractors/supported sites.

[youtubedl] / youtube_dl / extractor / foxnews.py

diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py
index 318ac013d44b9ca8ce9de5c77d67b2cd3c9bb1e1..63613cb85d36f78c7eea9f5f03adb061bed3ac4c 100644 (file)
--- a/youtube_dl/extractor/foxnews.py
+++ b/youtube_dl/extractor/foxnews.py
@@ -3,11 +3,13 @@ from __future__ import unicode_literals
 import re
 
 from .amp import AMPIE
 import re
 
 from .amp import AMPIE

+from .common import InfoExtractor

 
 
 class FoxNewsIE(AMPIE):
 
 
 class FoxNewsIE(AMPIE):

+    IE_NAME = 'foxnews'

     IE_DESC = 'Fox News and Fox Business Video'
     IE_DESC = 'Fox News and Fox Business Video'

-    _VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
+    _VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'

     _TESTS = [
         {
             'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
     _TESTS = [
         {
             'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',


@@ -18,9 +20,9 @@ class FoxNewsIE(AMPIE):
                 'title': 'Frozen in Time',
                 'description': '16-year-old girl is size of toddler',
                 'duration': 265,
                 'title': 'Frozen in Time',
                 'description': '16-year-old girl is size of toddler',
                 'duration': 265,

-                # 'timestamp': 1304411491,
-                # 'upload_date': '20110503',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'timestamp': 1304411491,
+                'upload_date': '20110503',
+                'thumbnail': r're:^https?://.*\.jpg$',

             },
         },
         {
             },
         },
         {


@@ -32,9 +34,13 @@ class FoxNewsIE(AMPIE):
                 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
                 'description': "Congressman discusses president's plan",
                 'duration': 292,
                 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
                 'description': "Congressman discusses president's plan",
                 'duration': 292,

-                # 'timestamp': 1417662047,
-                # 'upload_date': '20141204',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'timestamp': 1417662047,
+                'upload_date': '20141204',
+                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,

             },
         },
         {
             },
         },
         {


@@ -45,8 +51,21 @@ class FoxNewsIE(AMPIE):
             'url': 'http://video.foxbusiness.com/v/4442309889001',
             'only_matching': True,
         },
             'url': 'http://video.foxbusiness.com/v/4442309889001',
             'only_matching': True,
         },

+        {
+            # From http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words
+            'url': 'http://video.insider.foxnews.com/v/video-embed.html?video_id=5099377331001&autoplay=true&share_url=http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words&share_title=Student%20Group:%20Saying%20%27Politically%20Correct,%27%20%27Trash%27%20and%20%27Lame%27%20Is%20Offensive&share=true',
+            'only_matching': True,
+        },

     ]
 
     ]
 

+    @staticmethod
+    def _extract_urls(webpage):
+        return [
+            mobj.group('url')
+            for mobj in re.finditer(
+                r'<(?:amp-)?iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//video\.foxnews\.com/v/video-embed\.html?.*?\bvideo_id=\d+.*?)\1',
+                webpage)]
+

     def _real_extract(self, url):
         host, video_id = re.match(self._VALID_URL, url).groups()
 
     def _real_extract(self, url):
         host, video_id = re.match(self._VALID_URL, url).groups()
 


@@ -54,3 +73,55 @@ class FoxNewsIE(AMPIE):
             'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
         info['id'] = video_id
         return info
             'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
         info['id'] = video_id
         return info

+
+
+class FoxNewsArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?:insider\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)'
+    IE_NAME = 'foxnews:article'
+
+    _TESTS = [{
+        # data-video-id
+        'url': 'http://www.foxnews.com/politics/2016/09/08/buzz-about-bud-clinton-camp-denies-claims-wore-earpiece-at-forum.html',
+        'md5': '83d44e1aff1433e7a29a7b537d1700b5',
+        'info_dict': {
+            'id': '5116295019001',
+            'ext': 'mp4',
+            'title': 'Trump and Clinton asked to defend positions on Iraq War',
+            'description': 'Veterans react on \'The Kelly File\'',
+            'timestamp': 1473301045,
+            'upload_date': '20160908',
+        },
+    }, {
+        # iframe embed
+        'url': 'http://www.foxnews.com/us/2018/03/09/parkland-survivor-kyle-kashuv-on-meeting-trump-his-app-to-prevent-another-school-shooting.amp.html?__twitter_impression=true',
+        'info_dict': {
+            'id': '5748266721001',
+            'ext': 'flv',
+            'title': 'Kyle Kashuv has a positive message for the Trump White House',
+            'description': 'Marjory Stoneman Douglas student disagrees with classmates.',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 229,
+            'timestamp': 1520594670,
+            'upload_date': '20180309',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._html_search_regex(
+            r'data-video-id=([\'"])(?P<id>[^\'"]+)\1',
+            webpage, 'video ID', group='id', default=None)
+        if video_id:
+            return self.url_result(
+                'http://video.foxnews.com/v/' + video_id, FoxNewsIE.ie_key())
+
+        return self.url_result(
+            FoxNewsIE._extract_urls(webpage)[0], FoxNewsIE.ie_key())