Merge e640e1fae3 into be3579aaf0

changes made
1. updated the extractor
2. added test cases

yt_dlp/extractor/ndtv.py

@@ -1,31 +1,31 @@
-import urllib.parse
 
 from .common import InfoExtractor
-from ..utils import parse_duration, remove_end, unified_strdate, urljoin
+from ..utils import clean_html, determine_ext, parse_duration, traverse_obj, unescapeHTML, unified_strdate
 
 
 class NDTVIE(InfoExtractor):
-    _WORKING = False
+    _WORKING = True
     _VALID_URL = r'https?://(?:[^/]+\.)?ndtv\.com/(?:[^/]+/)*videos?/?(?:[^/]+/)*[^/?^&]+-(?P<id>\d+)'
 
     _TESTS = [
         {
             'url': 'https://khabar.ndtv.com/video/show/prime-time/prime-time-ill-system-and-poor-education-468818',
-            'md5': '78efcf3880ef3fd9b83d405ca94a38eb',
+            'md5': '5237500d57c8af47a519c4af9e2fd9c0',
             'info_dict': {
                 'id': '468818',
                 'ext': 'mp4',
                 'title': 'प्राइम टाइम: सिस्टम बीमार, स्कूल बदहाल',
-                'description': 'md5:f410512f1b49672e5695dea16ef2731d',
+                'description': 'md5:de6008f2439005344c1c0c686032b43a',
                 'upload_date': '20170928',
                 'duration': 2218,
                 'thumbnail': r're:https?://.*\.jpg',
+                'categories': 'shows',
+                'channel_id': '2',
             },
         },
         {
-            # __filename is url
             'url': 'http://movies.ndtv.com/videos/cracker-free-diwali-wishes-from-karan-johar-kriti-sanon-other-stars-470304',
-            'md5': 'f1d709352305b44443515ac56b45aa46',
+            'md5': 'b7ef90f55e63885aef59c59cf2e44e81',
             'info_dict': {
                 'id': '470304',
                 'ext': 'mp4',
@@ -34,6 +34,83 @@ class NDTVIE(InfoExtractor):
                 'upload_date': '20171019',
                 'duration': 137,
                 'thumbnail': r're:https?://.*\.jpg',
+                'categories': 'entertainment',
+                'channel_id': '1',
+            },
+        },
+        {
+            'url': 'https://www.ndtv.com/video/ndtv-jai-jawan-dnd-john-abraham-is-busy-watching-soldiers-fitness-routine-826286',
+            'md5': '19d9a96480a8dac0e03a42efce27350f',
+            'info_dict': {
+                'id': '826286',
+                'ext': 'mp4',
+                'title': 'NDTV Jai Jawan: DND, John Abraham Is Busy Watching Soldiers\' Fitness Routine',
+                'description': 'md5:ad700713b10702555555e6a01a25442a',
+                'upload_date': '20240818',
+                'duration': 220,
+                'thumbnail': 'https://c.ndtvimg.com/2024-08/be8djnjc_jai-jawan_640x480_18_August_24.jpg',
+                'categories': 'entertainment',
+                'channel_id': '1',
+            },
+        },
+        {
+            'url': 'https://www.ndtv.com/video/cancer-can-be-prevented-cured-with-lifestyle-changes-expert-to-ndtv-827194',
+            'md5': '72734ed9226e200454100ffe7dfae2b6',
+            'info_dict': {
+                'id': '827194',
+                'ext': 'mp4',
+                'title': '"Cancer Can Be Prevented, Cured With Lifestyle Changes": Expert To NDTV',
+                'description': 'md5:cbecc6372e33370014748db9ad2b5df0',
+                'upload_date': '20240818',
+                'duration': 931,
+                'thumbnail': 'https://c.ndtvimg.com/2024-08/hh48aduk_dr-sameer-kaul_640x480_18_August_24.jpg',
+                'categories': 'news',
+                'channel_id': '1',
+            },
+        },
+        {
+            'url': 'https://sports.ndtv.com/cricket/videos/ex-india-captain-ms-dhoni-spotted-at-airport-820044',
+            'md5': '9f3442f49aa660623e8925c0fc7606a4',
+            'info_dict': {
+                'id': '820044',
+                'ext': 'mp4',
+                'title': 'Ex-India Captain MS Dhoni Spotted At Airport',
+                'description': 'md5:7be70dbb543bb647f83dbd6e7b8f16a0',
+                'upload_date': '20240730',
+                'duration': 45,
+                'thumbnail': 'https://c.ndtvimg.com/2024-07/itrg8ilo_msdhoni_640x480_31_July_24.jpg',
+                'categories': 'fangully',
+                'channel_id': '',
+            },
+        },
+        {
+            'url': 'https://doctor.ndtv.com/videos/attack-the-heart-attack-a-public-awareness-initiative-by-medtronics-822292',
+            'md5': 'a13ad8bbb45eec4405a45f9bd7ed0356',
+            'info_dict': {
+                'id': '822292',
+                'ext': 'mp4',
+                'title': 'Attack The Heart Attack - A Public Awareness Initiative By Medtronics',
+                'description': 'md5:31b876e23795b4d7ef91797f88b22730',
+                'upload_date': '20240805',
+                'duration': 1304,
+                'thumbnail': 'https://c.ndtvimg.com/2024-08/kh67tomo_heartattack_640x480_05_August_24.jpg',
+                'categories': 'Health',
+                'channel_id': '1',
+            },
+        },
+        {
+            'url': 'https://food.ndtv.com/video-watch-ndtv-food-awards-2024-on-ndtv-24x7-on-saturday-9th-march-2024-767098',
+            'md5': '78ddea4f057115e84952563749c6b94c',
+            'info_dict': {
+                'id': '767098',
+                'ext': 'mp4',
+                'title': 'Watch NDTV Food Awards 2024 On NDTV 24x7 On Saturday 9th March, 2024',
+                'description': 'md5:11948e8404b058cd0a9d174aa1e88e84',
+                'upload_date': '20240307',
+                'duration': 35,
+                'thumbnail': 'https://c.ndtvimg.com/2024-03/2eianfs_food-awards_640x480_08_March_24.jpg',
+                'categories': 'food',
+                'channel_id': '1',
             },
         },
         {
@@ -74,34 +151,46 @@ class NDTVIE(InfoExtractor):
         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.
+        # required for removing unwanted js expression in the json data
-        title = urllib.parse.unquote_plus(
+        # found this expression in one article
-            self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title', default=None)
+        # will update this json data handler more generic if more of similar patterns found
-            or self._og_search_title(webpage))
+        webpage = webpage.replace('true / false', 'true')
 
-        filename = self._search_regex(
+        data = self._search_json(r'__html5playerdata\s*=\s*', webpage, 'json_data', video_id)
-            r"(?:__)?filename\s*[:=]\s*'([^']+)'", webpage, 'video filename')
-        # in "movies" sub-site pages, filename is URL
-        video_url = urljoin('https://ndtvod.bc-ssl.cdn.bitgravity.com/23372/ndtv/', filename.lstrip('/'))
 
-        # "doctor" sub-site has MM:SS format
+        title = clean_html(unescapeHTML(traverse_obj(data, ('title'))))
-        duration = parse_duration(self._search_regex(
+        duration = parse_duration(traverse_obj(data, ('dur')))
-            r"(?:__)?duration\s*[:=]\s*'([^']+)'", webpage, 'duration', fatal=False))
+        upload_date = unified_strdate(traverse_obj(data, ('date')))
+        video_m3u8 = traverse_obj(data, ('media'))
+        video_mp4 = traverse_obj(data, ('media_mp4'))
+        video_webm = traverse_obj(data, ('media_webm'))
+        description = clean_html(unescapeHTML(traverse_obj(data, ('description'))))
+        thumbnail = traverse_obj(data, ('image'))
+        channel_id = traverse_obj(data, ('channel'))
+        categories = traverse_obj(data, ('category'))
 
-        # "sports", "doctor", "swirlster" sub-sites don't have 'publish-date'
+        formats = []
-        upload_date = unified_strdate(self._html_search_meta(
+        if video_mp4:
-            'publish-date', webpage, 'upload date', default=None) or self._html_search_meta(
+            formats.append({'url': video_mp4, 'ext': determine_ext(video_mp4)})
-            'uploadDate', webpage, 'upload date', default=None) or self._search_regex(
+        if video_webm:
-            r'datePublished"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False))
+            formats.append({'url': video_webm, 'ext': determine_ext(video_webm)})
-
+        if video_m3u8:
-        description = remove_end(self._og_search_description(webpage), ' (Read more)')
+            m3u8_data = self._extract_m3u8_formats(video_m3u8, video_id)
+            formats.extend(m3u8_data)
+            # here, making the assumption that mp4 video available is always the highest quality
+            # will update if any deviation found
+            formats[0]['width'] = m3u8_data[-1]['width']
+            formats[0]['height'] = m3u8_data[-1]['height']
+            formats[0]['tbr'] = m3u8_data[-1]['tbr']
 
         return {
             'id': video_id,
-            'url': video_url,
+            'formats': formats,
             'title': title,
             'description': description,
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'thumbnail': thumbnail,
             'duration': duration,
             'upload_date': upload_date,
+            'categories': categories,
+            'channel_id': channel_id,
         }