From ada98a4dbcad8d9369b7243288e2a0c19b4595f9 Mon Sep 17 00:00:00 2001
From: rawcoder <rawcoder@fastmail.com>
Date: Fri, 20 Oct 2017 18:06:50 +0530
Subject: [PATCH] [NDTV] Added support for more sub-sites
 (food,sports,auto,doctor,movies,swirlster)

---
 youtube_dl/extractor/ndtv.py | 96 ++++++++++++++++++++++++++++--------
 1 file changed, 76 insertions(+), 20 deletions(-)

diff --git a/youtube_dl/extractor/ndtv.py b/youtube_dl/extractor/ndtv.py
index 1f624221a..2d6a1602c 100644
--- a/youtube_dl/extractor/ndtv.py
+++ b/youtube_dl/extractor/ndtv.py
@@ -6,45 +6,101 @@ from ..compat import (
     compat_urllib_parse_unquote_plus
 )
 from ..utils import (
-    int_or_none,
     remove_end,
     unified_strdate,
+    parse_duration
 )
 
 
 class NDTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|gadgets|khabar|profit)\.)?ndtv\.com/videos?/(?:[^/]+/)*[^/?^&]+-(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?ndtv\.com/(?:[^/]+/)*videos?/?(?:[^/]+/)*[^/?^&]+-(?P<id>\d+)'
 
-    _TEST = {
-        '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': r're:https?://.*\.jpg',
+    _TESTS = [
+        {
+            'url': 'https://khabar.ndtv.com/video/show/prime-time/prime-time-ill-system-and-poor-education-468818',
+            'md5': '78efcf3880ef3fd9b83d405ca94a38eb',
+            'info_dict': {
+                'id': '468818',
+                'ext': 'mp4',
+                'title': "प्राइम टाइम: सिस्टम बीमार, स्कूल बदहाल",
+                'description': 'md5:f410512f1b49672e5695dea16ef2731d',
+                'upload_date': '20170928',
+                'duration': 2218,
+                'thumbnail': r're:https?://.*\.jpg',
+            }
+        },
+        {
+            # __filename is url
+            'url': 'http://movies.ndtv.com/videos/cracker-free-diwali-wishes-from-karan-johar-kriti-sanon-other-stars-470304',
+            'md5': 'f1d709352305b44443515ac56b45aa46',
+            'info_dict': {
+                'id': '470304',
+                'ext': 'mp4',
+                'title': "Cracker-Free Diwali Wishes From Karan Johar, Kriti Sanon & Other Stars",
+                'description': 'md5:f115bba1adf2f6433fa7c1ade5feb465',
+                'upload_date': '20171019',
+                'duration': 137,
+                'thumbnail': r're:https?://.*\.jpg',
+            }
+        },
+        {
+            'url': 'https://www.ndtv.com/video/news/news/delhi-s-air-quality-status-report-after-diwali-is-very-poor-470372',
+            'only_matching': True
+        },
+        {
+            'url': 'https://auto.ndtv.com/videos/the-cnb-daily-october-13-2017-469935',
+            'only_matching': True
+        },
+        {
+            'url': 'https://sports.ndtv.com/cricket/videos/2nd-t20i-rock-thrown-at-australia-cricket-team-bus-after-win-over-india-469764',
+            'only_matching': True
+        },
+        {
+            'url': 'http://gadgets.ndtv.com/videos/uncharted-the-lost-legacy-review-465568',
+            'only_matching': True
+        },
+        {
+            'url': 'http://profit.ndtv.com/videos/news/video-indian-economy-on-very-solid-track-international-monetary-fund-chief-470040',
+            'only_matching': True
+        },
+        {
+            'url': 'http://food.ndtv.com/video-basil-seeds-coconut-porridge-419083',
+            'only_matching': True
+        },
+        {
+            'url': 'https://doctor.ndtv.com/videos/top-health-stories-of-the-week-467396',
+            'only_matching': True
+        },
+        {
+            'url': 'https://swirlster.ndtv.com/video/how-to-make-friends-at-work-469324',
+            'only_matching': True
         }
-    }
+    ]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        # '__title' does not contain extra words such as sub-site name, "Video" etc.
         title = compat_urllib_parse_unquote_plus(
-            self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title'))
+            self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title', default=None) or
+            self._og_search_title(webpage))
 
         filename = self._search_regex(
-            r"__filename\s*=\s*'([^']+)'", webpage, 'video filename')
-        video_url = 'https://ndtvod.bc-ssl.cdn.bitgravity.com/23372/ndtv/%s' % filename
+            r"(?:__)?filename\s*[:=]\s*'([^']+)'", webpage, 'video filename')
+        # in "movies" sub-site pages, filename is URL
+        video_url = 'https://ndtvod.bc-ssl.cdn.bitgravity.com/23372/ndtv/%s' % filename \
+                if not (filename.startswith('http://') or filename.startswith('https://')) else filename
 
-        duration = int_or_none(self._search_regex(
-            r"__duration\s*=\s*'([^']+)'", webpage, 'duration', fatal=False))
+        # "doctor" sub-site has MM:SS format
+        duration = parse_duration(self._search_regex(
+            r"(?:__)?duration\s*[:=]\s*'([^']+)'", webpage, 'duration', fatal=False))
 
+        # "sports", "doctor", "swirlster" sub-sites don't have 'publish-date'
         upload_date = unified_strdate(self._html_search_meta(
-            'publish-date', webpage, 'upload date', fatal=False))
+            'publish-date', webpage, 'upload date', default=None) or self._html_search_meta(
+            'uploadDate', webpage, 'upload date', default=None) or self._search_regex(
+            r'datePublished"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False))
 
         description = remove_end(self._og_search_description(webpage), ' (Read more)')