yt-dlp/yt_dlp/extractor/ndtv.py

108 lines
4.4 KiB
Python
Raw Normal View History

import urllib.parse
2013-12-09 19:39:41 +01:00
from .common import InfoExtractor
from ..utils import parse_duration, remove_end, unified_strdate, urljoin
2013-12-09 19:39:41 +01:00
class NDTVIE(InfoExtractor):
_WORKING = False
2017-10-22 03:32:20 +02:00
_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',
'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',
}
},
{
# __filename is url
'url': 'http://movies.ndtv.com/videos/cracker-free-diwali-wishes-from-karan-johar-kriti-sanon-other-stars-470304',
'md5': 'f1d709352305b44443515ac56b45aa46',
'info_dict': {
'id': '470304',
'ext': 'mp4',
'title': "Cracker-Free Diwali Wishes From Karan Johar, Kriti Sanon & Other Stars",
'description': 'md5:f115bba1adf2f6433fa7c1ade5feb465',
'upload_date': '20171019',
'duration': 137,
'thumbnail': r're:https?://.*\.jpg',
}
},
{
'url': 'https://www.ndtv.com/video/news/news/delhi-s-air-quality-status-report-after-diwali-is-very-poor-470372',
'only_matching': True
},
{
'url': 'https://auto.ndtv.com/videos/the-cnb-daily-october-13-2017-469935',
'only_matching': True
},
{
'url': 'https://sports.ndtv.com/cricket/videos/2nd-t20i-rock-thrown-at-australia-cricket-team-bus-after-win-over-india-469764',
'only_matching': True
},
{
'url': 'http://gadgets.ndtv.com/videos/uncharted-the-lost-legacy-review-465568',
'only_matching': True
},
{
'url': 'http://profit.ndtv.com/videos/news/video-indian-economy-on-very-solid-track-international-monetary-fund-chief-470040',
'only_matching': True
},
{
'url': 'http://food.ndtv.com/video-basil-seeds-coconut-porridge-419083',
'only_matching': True
},
{
'url': 'https://doctor.ndtv.com/videos/top-health-stories-of-the-week-467396',
'only_matching': True
},
{
'url': 'https://swirlster.ndtv.com/video/how-to-make-friends-at-work-469324',
'only_matching': True
}
]
2013-12-09 19:39:41 +01:00
def _real_extract(self, url):
2015-01-19 10:10:05 +01:00
video_id = self._match_id(url)
2013-12-09 19:39:41 +01:00
webpage = self._download_webpage(url, video_id)
2017-10-22 03:32:20 +02:00
# '__title' does not contain extra words such as sub-site name, "Video" etc.
title = urllib.parse.unquote_plus(
self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title', default=None)
or self._og_search_title(webpage))
2016-05-19 00:34:19 +02:00
2013-12-09 19:39:41 +01:00
filename = self._search_regex(
2017-10-22 03:32:20 +02:00
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('/'))
2013-12-09 19:39:41 +01:00
2017-10-22 03:32:20 +02:00
# "doctor" sub-site has MM:SS format
duration = parse_duration(self._search_regex(
r"(?:__)?duration\s*[:=]\s*'([^']+)'", webpage, 'duration', fatal=False))
2013-12-09 19:39:41 +01:00
2017-10-22 03:32:20 +02:00
# "sports", "doctor", "swirlster" sub-sites don't have 'publish-date'
2016-05-19 00:34:19 +02:00
upload_date = unified_strdate(self._html_search_meta(
2017-10-22 03:32:20 +02:00
'publish-date', webpage, 'upload date', default=None) or self._html_search_meta(
'uploadDate', webpage, 'upload date', default=None) or self._search_regex(
r'datePublished"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False))
2013-12-09 19:39:41 +01:00
2016-05-19 00:34:19 +02:00
description = remove_end(self._og_search_description(webpage), ' (Read more)')
2013-12-09 19:39:41 +01:00
return {
'id': video_id,
'url': video_url,
'title': title,
2013-12-09 19:39:41 +01:00
'description': description,
'thumbnail': self._og_search_thumbnail(webpage),
'duration': duration,
'upload_date': upload_date,
}