youtube-dl

commit 50aa43b3ae074781bb7c7ad55a85f54b1fd84146
parent a90552663e555c89638706141c31b0022a9ba27b
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date:   Mon,  4 May 2015 22:32:57 +0800

[nytimes] Implement extracting videos from articles (closes  #5436)

Diffstat:
M
youtube_dl/extractor/nytimes.py
 | 
79
+++++++++++++++++++++++++++++++++++++++++++++++++++++++------------------------

1 file changed, 55 insertions(+), 24 deletions(-)
diff --git a/youtube_dl/extractor/nytimes.py b/youtube_dl/extractor/nytimes.py
@@ -8,30 +8,8 @@ from ..utils import (
 )
 
 
-class NYTimesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
-
-    _TESTS = [{
-        'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
-        'md5': '18a525a510f942ada2720db5f31644c0',
-        'info_dict': {
-            'id': '100000002847155',
-            'ext': 'mov',
-            'title': 'Verbatim: What Is a Photocopier?',
-            'description': 'md5:93603dada88ddbda9395632fdc5da260',
-            'timestamp': 1398631707,
-            'upload_date': '20140427',
-            'uploader': 'Brett Weiner',
-            'duration': 419,
-        }
-    }, {
-        'url': 'http://www.nytimes.com/video/travel/100000003550828/36-hours-in-dubai.html',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
+class NYTimesBaseIE(InfoExtractor):
+    def _extract_video_from_id(self, video_id):
         video_data = self._download_json(
             'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id,
             video_id, 'Downloading video JSON')
@@ -81,3 +59,56 @@ class NYTimesIE(InfoExtractor):
             'formats': formats,
             'thumbnails': thumbnails,
         }
+
+
+class NYTimesIE(NYTimesBaseIE):
+    _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
+        'md5': '18a525a510f942ada2720db5f31644c0',
+        'info_dict': {
+            'id': '100000002847155',
+            'ext': 'mov',
+            'title': 'Verbatim: What Is a Photocopier?',
+            'description': 'md5:93603dada88ddbda9395632fdc5da260',
+            'timestamp': 1398631707,
+            'upload_date': '20140427',
+            'uploader': 'Brett Weiner',
+            'duration': 419,
+        }
+    }, {
+        'url': 'http://www.nytimes.com/video/travel/100000003550828/36-hours-in-dubai.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        return self._extract_video_from_id(video_id)
+
+
+class NYTimesArticleIE(NYTimesBaseIE):
+    _VALID_URL = r'https?://(?:www)?\.nytimes\.com/\d{4}/\d{2}/\d{2}/(?:[^/]+/)*(?P<id>[^.]+)\.html'
+    _TEST = {
+        'url': 'http://www.nytimes.com/2015/04/14/business/owner-of-gravity-payments-a-credit-card-processor-is-setting-a-new-minimum-wage-70000-a-year.html?_r=0',
+        'md5': 'e2076d58b4da18e6a001d53fd56db3c9',
+        'info_dict': {
+            'id': '100000003628438',
+            'ext': 'mov',
+            'title': 'New Minimum Wage: $70,000 a Year',
+            'description': 'Dan Price, C.E.O. of Gravity Payments, surprised his 120-person staff by announcing that he planned over the next three years to raise the salary of every employee to $70,000 a year.',
+            'timestamp': 1429033037,
+            'upload_date': '20150414',
+            'uploader': 'Matthew Williams',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_id = self._html_search_regex(r'data-videoid="(\d+)"', webpage, 'video id')
+
+        return self._extract_video_from_id(video_id)