Merge tag 'upstream/2016.02.22'

[youtubedl] / youtube_dl / extractor / nytimes.py

diff --git a/youtube_dl/extractor/nytimes.py b/youtube_dl/extractor/nytimes.py
index 7bf105d38178a5d59339d81262649b40fa57a46e..7f254b867da66f70a79ff7aac5d81eb6f37bd997 100644 (file)
--- a/youtube_dl/extractor/nytimes.py
+++ b/youtube_dl/extractor/nytimes.py
@@ -1,39 +1,22 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

-from ..utils import parse_iso8601
-
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+)

 
 

-class NYTimesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nytimes\.com/video/(?:[^/]+/)+(?P<id>\d+)'
-
-    _TEST = {
-        '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,
-        }
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')

 
 

+class NYTimesBaseIE(InfoExtractor):
+    def _extract_video_from_id(self, video_id):

         video_data = self._download_json(
         video_data = self._download_json(

-            'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id, video_id, 'Downloading video JSON')
+            'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id,
+            video_id, 'Downloading video JSON')

 
         title = video_data['headline']
 
         title = video_data['headline']

-        description = video_data['summary']
-        duration = video_data['duration'] / 1000.0
+        description = video_data.get('summary')
+        duration = float_or_none(video_data.get('duration'), 1000)

 
         uploader = video_data['byline']
         timestamp = parse_iso8601(video_data['publication_date'][:-8])
 
         uploader = video_data['byline']
         timestamp = parse_iso8601(video_data['publication_date'][:-8])


@@ -49,11 +32,11 @@ class NYTimesIE(InfoExtractor):
         formats = [
             {
                 'url': video['url'],
         formats = [
             {
                 'url': video['url'],

-                'format_id': video['type'],
-                'vcodec': video['video_codec'],
-                'width': video['width'],
-                'height': video['height'],
-                'filesize': get_file_size(video['fileSize']),
+                'format_id': video.get('type'),
+                'vcodec': video.get('video_codec'),
+                'width': int_or_none(video.get('width')),
+                'height': int_or_none(video.get('height')),
+                'filesize': get_file_size(video.get('fileSize')),

             } for video in video_data['renditions']
         ]
         self._sort_formats(formats)
             } for video in video_data['renditions']
         ]
         self._sort_formats(formats)


@@ -61,7 +44,8 @@ class NYTimesIE(InfoExtractor):
         thumbnails = [
             {
                 'url': 'http://www.nytimes.com/%s' % image['url'],
         thumbnails = [
             {
                 'url': 'http://www.nytimes.com/%s' % image['url'],

-                'resolution': '%dx%d' % (image['width'], image['height']),
+                'width': int_or_none(image.get('width')),
+                'height': int_or_none(image.get('height')),

             } for image in video_data['images']
         ]
 
             } for image in video_data['images']
         ]
 


@@ -74,4 +58,60 @@ class NYTimesIE(InfoExtractor):
             'duration': duration,
             'formats': formats,
             'thumbnails': thumbnails,
             'duration': duration,
             'formats': formats,
             'thumbnails': thumbnails,

-        }
\ No newline at end of file
+        }
+
+
+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/(.(?<!video))*?/(?:[^/]+/)*(?P<id>[^.]+)(?:\.html)?'
+    _TESTS = [{
+        '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',
+        }
+    }, {
+        'url': 'http://www.nytimes.com/news/minute/2014/03/17/times-minute-whats-next-in-crimea/?_php=true&_type=blogs&_php=true&_type=blogs&_r=1',
+        'only_matching': True,
+    }]
+
+    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)