yt_dlp/extractor/ndtv.py

   1 import urllib.parse
   2
   3 from .common import InfoExtractor
   4 from ..utils import parse_duration, remove_end, unified_strdate, urljoin
   5
   6
   7 class NDTVIE(InfoExtractor):
   8     _WORKING = False
   9     _VALID_URL = r'https?://(?:[^/]+\.)?ndtv\.com/(?:[^/]+/)*videos?/?(?:[^/]+/)*[^/?^&]+-(?P<id>\d+)'
  10
  11     _TESTS = [
  12         {
  13             'url': 'https://khabar.ndtv.com/video/show/prime-time/prime-time-ill-system-and-poor-education-468818',
  14             'md5': '78efcf3880ef3fd9b83d405ca94a38eb',
  15             'info_dict': {
  16                 'id': '468818',
  17                 'ext': 'mp4',
  18                 'title': 'प्राइम टाइम: सिस्टम बीमार, स्कूल बदहाल',
  19                 'description': 'md5:f410512f1b49672e5695dea16ef2731d',
  20                 'upload_date': '20170928',
  21                 'duration': 2218,
  22                 'thumbnail': r're:https?://.*\.jpg',
  23             },
  24         },
  25         {
  26             # __filename is url
  27             'url': 'http://movies.ndtv.com/videos/cracker-free-diwali-wishes-from-karan-johar-kriti-sanon-other-stars-470304',
  28             'md5': 'f1d709352305b44443515ac56b45aa46',
  29             'info_dict': {
  30                 'id': '470304',
  31                 'ext': 'mp4',
  32                 'title': 'Cracker-Free Diwali Wishes From Karan Johar, Kriti Sanon & Other Stars',
  33                 'description': 'md5:f115bba1adf2f6433fa7c1ade5feb465',
  34                 'upload_date': '20171019',
  35                 'duration': 137,
  36                 'thumbnail': r're:https?://.*\.jpg',
  37             },
  38         },
  39         {
  40             'url': 'https://www.ndtv.com/video/news/news/delhi-s-air-quality-status-report-after-diwali-is-very-poor-470372',
  41             'only_matching': True,
  42         },
  43         {
  44             'url': 'https://auto.ndtv.com/videos/the-cnb-daily-october-13-2017-469935',
  45             'only_matching': True,
  46         },
  47         {
  48             'url': 'https://sports.ndtv.com/cricket/videos/2nd-t20i-rock-thrown-at-australia-cricket-team-bus-after-win-over-india-469764',
  49             'only_matching': True,
  50         },
  51         {
  52             'url': 'http://gadgets.ndtv.com/videos/uncharted-the-lost-legacy-review-465568',
  53             'only_matching': True,
  54         },
  55         {
  56             'url': 'http://profit.ndtv.com/videos/news/video-indian-economy-on-very-solid-track-international-monetary-fund-chief-470040',
  57             'only_matching': True,
  58         },
  59         {
  60             'url': 'http://food.ndtv.com/video-basil-seeds-coconut-porridge-419083',
  61             'only_matching': True,
  62         },
  63         {
  64             'url': 'https://doctor.ndtv.com/videos/top-health-stories-of-the-week-467396',
  65             'only_matching': True,
  66         },
  67         {
  68             'url': 'https://swirlster.ndtv.com/video/how-to-make-friends-at-work-469324',
  69             'only_matching': True,
  70         },
  71     ]
  72
  73     def _real_extract(self, url):
  74         video_id = self._match_id(url)
  75         webpage = self._download_webpage(url, video_id)
  76
  77         # '__title' does not contain extra words such as sub-site name, "Video" etc.
  78         title = urllib.parse.unquote_plus(
  79             self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title', default=None)
  80             or self._og_search_title(webpage))
  81
  82         filename = self._search_regex(
  83             r"(?:__)?filename\s*[:=]\s*'([^']+)'", webpage, 'video filename')
  84         # in "movies" sub-site pages, filename is URL
  85         video_url = urljoin('https://ndtvod.bc-ssl.cdn.bitgravity.com/23372/ndtv/', filename.lstrip('/'))
  86
  87         # "doctor" sub-site has MM:SS format
  88         duration = parse_duration(self._search_regex(
  89             r"(?:__)?duration\s*[:=]\s*'([^']+)'", webpage, 'duration', fatal=False))
  90
  91         # "sports", "doctor", "swirlster" sub-sites don't have 'publish-date'
  92         upload_date = unified_strdate(self._html_search_meta(
  93             'publish-date', webpage, 'upload date', default=None) or self._html_search_meta(
  94             'uploadDate', webpage, 'upload date', default=None) or self._search_regex(
  95             r'datePublished"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False))
  96
  97         description = remove_end(self._og_search_description(webpage), ' (Read more)')
  98
  99         return {
 100             'id': video_id,
 101             'url': video_url,
 102             'title': title,
 103             'description': description,
 104             'thumbnail': self._og_search_thumbnail(webpage),
 105             'duration': duration,
 106             'upload_date': upload_date,
 107         }