diff --git a/yt_dlp/extractor/ndtv.py b/yt_dlp/extractor/ndtv.py index ec4c898753..c2ad462482 100644 --- a/yt_dlp/extractor/ndtv.py +++ b/yt_dlp/extractor/ndtv.py @@ -1,11 +1,19 @@ - from .common import InfoExtractor -from ..utils import clean_html, determine_ext, parse_duration, traverse_obj, unescapeHTML, unified_strdate +from ..utils import ( + clean_html, + parse_duration, + str_or_none, + traverse_obj, + unescapeHTML, + unified_timestamp, + url_or_none, +) class NDTVIE(InfoExtractor): _WORKING = True - _VALID_URL = r'https?://(?:[^/]+\.)?ndtv\.com/(?:[^/]+/)*videos?/?(?:[^/]+/)*[^/?^&]+-(?P\d+)' + IE_NAME = 'ndtv:video' + _VALID_URL = r'https?://(?:[^/]+\.)?ndtv\.com/(?:[^#/]+/)*videos?/?(?:[^#/]+/)*[^/?^&]+-(?P\d+)' _TESTS = [ { @@ -17,9 +25,10 @@ class NDTVIE(InfoExtractor): 'title': 'प्राइम टाइम: सिस्टम बीमार, स्कूल बदहाल', 'description': 'md5:de6008f2439005344c1c0c686032b43a', 'upload_date': '20170928', + 'timestamp': 1506612600.0, 'duration': 2218, 'thumbnail': r're:https?://.*\.jpg', - 'categories': 'shows', + 'categories': ['shows'], 'channel_id': '2', }, }, @@ -31,70 +40,75 @@ class NDTVIE(InfoExtractor): 'ext': 'mp4', 'title': 'Cracker-Free Diwali Wishes From Karan Johar, Kriti Sanon & Other Stars', 'description': 'md5:f115bba1adf2f6433fa7c1ade5feb465', - 'upload_date': '20171019', + 'upload_date': '20171018', + 'timestamp': 1508352987.0, 'duration': 137, 'thumbnail': r're:https?://.*\.jpg', - 'categories': 'entertainment', + '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', + 'md5': '443cbf0b7dd82089f5ebb11804fbc892', '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', + 'timestamp': 1723964765.0, 'duration': 220, - 'thumbnail': 'https://c.ndtvimg.com/2024-08/be8djnjc_jai-jawan_640x480_18_August_24.jpg', - 'categories': 'entertainment', + 'thumbnail': r're:https?://.*\.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', + 'md5': '3bb5e431246a5d6431affc0e26cec4a0', 'info_dict': { 'id': '827194', 'ext': 'mp4', 'title': '"Cancer Can Be Prevented, Cured With Lifestyle Changes": Expert To NDTV', 'description': 'md5:cbecc6372e33370014748db9ad2b5df0', 'upload_date': '20240818', + 'timestamp': 1723970085.0, 'duration': 931, - 'thumbnail': 'https://c.ndtvimg.com/2024-08/hh48aduk_dr-sameer-kaul_640x480_18_August_24.jpg', - 'categories': 'news', + 'thumbnail': r're:https?://.*\.jpg', + 'categories': ['news'], 'channel_id': '1', }, }, { 'url': 'https://sports.ndtv.com/cricket/videos/ex-india-captain-ms-dhoni-spotted-at-airport-820044', - 'md5': '9f3442f49aa660623e8925c0fc7606a4', + 'md5': '57ef9cee36e0178ef1b67a879300eee1', 'info_dict': { 'id': '820044', 'ext': 'mp4', 'title': 'Ex-India Captain MS Dhoni Spotted At Airport', 'description': 'md5:7be70dbb543bb647f83dbd6e7b8f16a0', 'upload_date': '20240730', + 'timestamp': 1722336305.0, 'duration': 45, - 'thumbnail': 'https://c.ndtvimg.com/2024-07/itrg8ilo_msdhoni_640x480_31_July_24.jpg', - 'categories': 'fangully', + 'thumbnail': r're:https?://.*\.jpg', + 'categories': ['fangully'], 'channel_id': '', }, }, { 'url': 'https://doctor.ndtv.com/videos/attack-the-heart-attack-a-public-awareness-initiative-by-medtronics-822292', - 'md5': 'a13ad8bbb45eec4405a45f9bd7ed0356', + 'md5': '74c9715df47630dd9abbcb64ec3c988f', 'info_dict': { 'id': '822292', 'ext': 'mp4', 'title': 'Attack The Heart Attack - A Public Awareness Initiative By Medtronics', 'description': 'md5:31b876e23795b4d7ef91797f88b22730', 'upload_date': '20240805', + 'timestamp': 1722816000, 'duration': 1304, - 'thumbnail': 'https://c.ndtvimg.com/2024-08/kh67tomo_heartattack_640x480_05_August_24.jpg', - 'categories': 'Health', + 'thumbnail': r're:https?://.*\.jpg', + 'categories': ['Health'], 'channel_id': '1', }, }, @@ -107,9 +121,10 @@ class NDTVIE(InfoExtractor): 'title': 'Watch NDTV Food Awards 2024 On NDTV 24x7 On Saturday 9th March, 2024', 'description': 'md5:11948e8404b058cd0a9d174aa1e88e84', 'upload_date': '20240307', + 'timestamp': 1709799526.0, 'duration': 35, - 'thumbnail': 'https://c.ndtvimg.com/2024-03/2eianfs_food-awards_640x480_08_March_24.jpg', - 'categories': 'food', + 'thumbnail': r're:https?://.*\.jpg', + 'categories': ['food'], 'channel_id': '1', }, }, @@ -155,42 +170,29 @@ def _real_extract(self, url): # found this expression in one article # will update this json data handler more generic if more of similar patterns found webpage = webpage.replace('true / false', 'true') + json_data = self._search_json(r'__html5playerdata\s*=\s*', webpage, 'json_data', video_id) - data = self._search_json(r'__html5playerdata\s*=\s*', webpage, 'json_data', video_id) - - title = clean_html(unescapeHTML(traverse_obj(data, ('title')))) - duration = parse_duration(traverse_obj(data, ('dur'))) - 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')) + video_data = traverse_obj(json_data, { + 'id': ('id', {str_or_none}), + 'title': ('title', {unescapeHTML}, {clean_html}), + 'description': ('description', {unescapeHTML}, {clean_html}), + 'duration': ('dur', {parse_duration}), + 'thumbnail': ('image', {url_or_none}), + 'categories': ('category', {str}, all), + 'timestamp': ('date', {unified_timestamp}), + 'channel_id': ('channel', {str}), + }) formats = [] + video_m3u8 = traverse_obj(json_data, ('media', {url_or_none})) + video_mp4 = traverse_obj(json_data, ('media_mp4', {url_or_none})) + video_webm = traverse_obj(json_data, ('media_webm', {url_or_none})) if video_mp4: - formats.append({'url': video_mp4, 'ext': determine_ext(video_mp4)}) + formats.append({'url': video_mp4}) if video_webm: - formats.append({'url': video_webm, 'ext': determine_ext(video_webm)}) + formats.append({'url': video_webm}) if video_m3u8: - 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'] + formats.extend(self._extract_m3u8_formats(video_m3u8, video_id)) + video_data['formats'] = formats - return { - 'id': video_id, - 'formats': formats, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'upload_date': upload_date, - 'categories': categories, - 'channel_id': channel_id, - } + return video_data