From 093717a750b22310b7ec573da109930e9c9e76bd Mon Sep 17 00:00:00 2001 From: rawcoder Date: Wed, 18 Oct 2017 17:38:00 +0530 Subject: [PATCH] [NDTV] Added support for sub-sites (gadgets,khabar,profit) --- youtube_dl/extractor/ndtv.py | 81 ++++++++++++++++++++++++++++-------- 1 file changed, 64 insertions(+), 17 deletions(-) diff --git a/youtube_dl/extractor/ndtv.py b/youtube_dl/extractor/ndtv.py index 255f60878..683b39501 100644 --- a/youtube_dl/extractor/ndtv.py +++ b/youtube_dl/extractor/ndtv.py @@ -1,6 +1,10 @@ +# coding: utf-8 from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse_unquote_plus +) from ..utils import ( int_or_none, remove_end, @@ -9,34 +13,77 @@ from ..utils import ( class NDTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?ndtv\.com/video/(?:[^/]+/)+[^/?^&]+-(?P\d+)' + _VALID_URL = r'https?://(?:(?:www|gadgets|khabar|profit)\.)?ndtv\.com/videos?/(?:[^/]+/)*[^/?^&]+-(?P\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': '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', + }, }, - } + { + 'url': 'http://gadgets.ndtv.com/videos/uncharted-the-lost-legacy-review-465568', + 'md5': '1169bb2c0b288d65da4f4832a32e4489', + 'info_dict': { + 'id': '465568', + 'ext': 'mp4', + 'title': "Uncharted: The Lost Legacy Review", + 'description': 'md5:f8299743bc50c4cbd0dd307a3830fcb0', + 'upload_date': '20170816', + 'duration': 168, + 'thumbnail': r're:https?://.*\.jpg', + } + }, + { + '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', + } + }, + { + 'url': 'http://profit.ndtv.com/videos/news/video-indian-economy-on-very-solid-track-international-monetary-fund-chief-470040', + 'md5': '16f192bb61ae8721770ca82554a125e6', + 'info_dict': { + 'id': '470040', + 'ext': 'mp4', + 'title': "Indian Economy On 'Very Solid Track': International Monetary Fund Chief", + 'description': 'md5:e84e6b93a9ece5573df6344626fb6df7', + 'upload_date': '20171015', + 'duration': 137, + 'thumbnail': r're:https?://.*\.jpg', + } + } + ] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = remove_end(self._og_search_title(webpage), ' - NDTV') + title = compat_urllib_parse_unquote_plus( + self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title') or + self._og_search_title(webpage)) filename = self._search_regex( - r"__filename='([^']+)'", webpage, 'video filename') - video_url = 'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' % filename + r"__filename\s*=\s*'([^']+)'", webpage, 'video filename') + video_url = 'https://ndtvod.bc-ssl.cdn.bitgravity.com/23372/ndtv/%s' % filename duration = int_or_none(self._search_regex( - r"__duration='([^']+)'", webpage, 'duration', fatal=False)) + r"__duration\s*=\s*'([^']+)'", webpage, 'duration', fatal=False)) upload_date = unified_strdate(self._html_search_meta( 'publish-date', webpage, 'upload date', fatal=False))