youtube_dl/extractor/ndtv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_urllib_parse_unquote_plus
   7 )
   8 from ..utils import (
   9     parse_duration,
  10     remove_end,
  11     unified_strdate,
  12     urljoin
  13 )
  14
  15
  16 class NDTVIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:[^/]+\.)?ndtv\.com/(?:[^/]+/)*videos?/?(?:[^/]+/)*[^/?^&]+-(?P<id>\d+)'
  18
  19     _TESTS = [
  20         {
  21             'url': 'https://khabar.ndtv.com/video/show/prime-time/prime-time-ill-system-and-poor-education-468818',
  22             'md5': '78efcf3880ef3fd9b83d405ca94a38eb',
  23             'info_dict': {
  24                 'id': '468818',
  25                 'ext': 'mp4',
  26                 'title': "प्राइम टाइम: सिस्टम बीमार, स्कूल बदहाल",
  27                 'description': 'md5:f410512f1b49672e5695dea16ef2731d',
  28                 'upload_date': '20170928',
  29                 'duration': 2218,
  30                 'thumbnail': r're:https?://.*\.jpg',
  31             }
  32         },
  33         {
  34             # __filename is url
  35             'url': 'http://movies.ndtv.com/videos/cracker-free-diwali-wishes-from-karan-johar-kriti-sanon-other-stars-470304',
  36             'md5': 'f1d709352305b44443515ac56b45aa46',
  37             'info_dict': {
  38                 'id': '470304',
  39                 'ext': 'mp4',
  40                 'title': "Cracker-Free Diwali Wishes From Karan Johar, Kriti Sanon & Other Stars",
  41                 'description': 'md5:f115bba1adf2f6433fa7c1ade5feb465',
  42                 'upload_date': '20171019',
  43                 'duration': 137,
  44                 'thumbnail': r're:https?://.*\.jpg',
  45             }
  46         },
  47         {
  48             'url': 'https://www.ndtv.com/video/news/news/delhi-s-air-quality-status-report-after-diwali-is-very-poor-470372',
  49             'only_matching': True
  50         },
  51         {
  52             'url': 'https://auto.ndtv.com/videos/the-cnb-daily-october-13-2017-469935',
  53             'only_matching': True
  54         },
  55         {
  56             'url': 'https://sports.ndtv.com/cricket/videos/2nd-t20i-rock-thrown-at-australia-cricket-team-bus-after-win-over-india-469764',
  57             'only_matching': True
  58         },
  59         {
  60             'url': 'http://gadgets.ndtv.com/videos/uncharted-the-lost-legacy-review-465568',
  61             'only_matching': True
  62         },
  63         {
  64             'url': 'http://profit.ndtv.com/videos/news/video-indian-economy-on-very-solid-track-international-monetary-fund-chief-470040',
  65             'only_matching': True
  66         },
  67         {
  68             'url': 'http://food.ndtv.com/video-basil-seeds-coconut-porridge-419083',
  69             'only_matching': True
  70         },
  71         {
  72             'url': 'https://doctor.ndtv.com/videos/top-health-stories-of-the-week-467396',
  73             'only_matching': True
  74         },
  75         {
  76             'url': 'https://swirlster.ndtv.com/video/how-to-make-friends-at-work-469324',
  77             'only_matching': True
  78         }
  79     ]
  80
  81     def _real_extract(self, url):
  82         video_id = self._match_id(url)
  83         webpage = self._download_webpage(url, video_id)
  84
  85         # '__title' does not contain extra words such as sub-site name, "Video" etc.
  86         title = compat_urllib_parse_unquote_plus(
  87             self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title', default=None)
  88             or self._og_search_title(webpage))
  89
  90         filename = self._search_regex(
  91             r"(?:__)?filename\s*[:=]\s*'([^']+)'", webpage, 'video filename')
  92         # in "movies" sub-site pages, filename is URL
  93         video_url = urljoin('https://ndtvod.bc-ssl.cdn.bitgravity.com/23372/ndtv/', filename.lstrip('/'))
  94
  95         # "doctor" sub-site has MM:SS format
  96         duration = parse_duration(self._search_regex(
  97             r"(?:__)?duration\s*[:=]\s*'([^']+)'", webpage, 'duration', fatal=False))
  98
  99         # "sports", "doctor", "swirlster" sub-sites don't have 'publish-date'
 100         upload_date = unified_strdate(self._html_search_meta(
 101             'publish-date', webpage, 'upload date', default=None) or self._html_search_meta(
 102             'uploadDate', webpage, 'upload date', default=None) or self._search_regex(
 103             r'datePublished"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False))
 104
 105         description = remove_end(self._og_search_description(webpage), ' (Read more)')
 106
 107         return {
 108             'id': video_id,
 109             'url': video_url,
 110             'title': title,
 111             'description': description,
 112             'thumbnail': self._og_search_thumbnail(webpage),
 113             'duration': duration,
 114             'upload_date': upload_date,
 115         }