New upstream version 2016.12.01

[youtubedl] / youtube_dl / extractor / ndtv.py

diff --git a/youtube_dl/extractor/ndtv.py b/youtube_dl/extractor/ndtv.py
index d81df3c10668492383c11b03cf30db7d797f7c90..96528f6499d1e02c5208e61fe8abd1f606b29392 100644 (file)
--- a/youtube_dl/extractor/ndtv.py
+++ b/youtube_dl/extractor/ndtv.py
@@ -1,62 +1,52 @@
-import re
+from __future__ import unicode_literals

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

-from ..utils import month_by_name
+from ..utils import (
+    int_or_none,
+    remove_end,
+    unified_strdate,
+)

 
 
 class NDTVIE(InfoExtractor):
 
 
 class NDTVIE(InfoExtractor):

-    _VALID_URL = r'^https?://(?:www\.)?ndtv\.com/video/player/[^/]*/[^/]*/(?P<id>[a-z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?ndtv\.com/video/(?:[^/]+/)+[^/?^&]+-(?P<id>\d+)'

 
     _TEST = {
 
     _TEST = {

-        u"url": u"http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710",
-        u"file": u"300710.mp4",
-        u"md5": u"39f992dbe5fb531c395d8bbedb1e5e88",
-        u"info_dict": {
-            u"title": u"NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
-            u"description": u"In an exclusive interview to NDTV, Aam Aadmi Party's Arvind Kejriwal says it makes no difference to him that Rahul Gandhi said the Congress needs to learn from his party.",
-            u"upload_date": u"20131208",
-            u"duration": 1327,
-            u"thumbnail": u"http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg",
+        'url': 'http://www.ndtv.com/video/news/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal-300710',
+        'md5': '39f992dbe5fb531c395d8bbedb1e5e88',
+        'info_dict': {
+            'id': '300710',
+            'ext': 'mp4',
+            'title': "NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
+            'description': 'md5:ab2d4b4a6056c5cb4caa6d729deabf02',
+            'upload_date': '20131208',
+            'duration': 1327,
+            'thumbnail': 're:https?://.*\.jpg',

         },
     }
 
     def _real_extract(self, url):
         },
     }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)

         webpage = self._download_webpage(url, video_id)
 
         webpage = self._download_webpage(url, video_id)
 

+        title = remove_end(self._og_search_title(webpage), ' - NDTV')
+

         filename = self._search_regex(
         filename = self._search_regex(

-            r"__filename='([^']+)'", webpage, u'video filename')
-        video_url = (u'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' %
-                     filename)
+            r"__filename='([^']+)'", webpage, 'video filename')
+        video_url = 'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' % filename

 
 

-        duration_str = filename = self._search_regex(
-            r"__duration='([^']+)'", webpage, u'duration', fatal=False)
-        duration = None if duration_str is None else int(duration_str)
+        duration = int_or_none(self._search_regex(
+            r"__duration='([^']+)'", webpage, 'duration', fatal=False))

 
 

-        date_m = re.search(r'''(?x)
-            <p\s+class="vod_dateline">\s*
-                Published\s+On:\s*
-                (?P<monthname>[A-Za-z]+)\s+(?P<day>[0-9]+),\s*(?P<year>[0-9]+)
-            ''', webpage)
-        upload_date = None
-        assert date_m
-        if date_m is not None:
-            month = month_by_name(date_m.group('monthname'))
-            if month is not None:
-                upload_date = '%s%02d%02d' % (
-                    date_m.group('year'), month, int(date_m.group('day')))
+        upload_date = unified_strdate(self._html_search_meta(
+            'publish-date', webpage, 'upload date', fatal=False))

 
 

-        description = self._og_search_description(webpage)
-        READ_MORE = u' (Read more)'
-        if description.endswith(READ_MORE):
-            description = description[:-len(READ_MORE)]
+        description = remove_end(self._og_search_description(webpage), ' (Read more)')

 
         return {
             'id': video_id,
             'url': video_url,
 
         return {
             'id': video_id,
             'url': video_url,

-            'title': self._og_search_title(webpage),
+            'title': title,

             'description': description,
             'thumbnail': self._og_search_thumbnail(webpage),
             'duration': duration,
             'description': description,
             'thumbnail': self._og_search_thumbnail(webpage),
             'duration': duration,