Miroirs/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2025-02-08 08:46:31 +01:00
Code Issues Projects Releases Packages Wiki Activity

refined code as per coding guidelines

Browse source
This commit is contained in:
subrat-lima 2024-08-18 21:32:37 +05:30
parent 9a235dd6f9
commit db4b19eaff
1 changed files with 21 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

31
yt_dlp/extractor/ndtv.py
View file

@ -137,26 +137,37 @@ class NDTVIE(InfoExtractor):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = clean_html(self._html_search_meta('taboola:title', webpage, 'title', default=None) or self._html_search_meta('name', webpage, 'title', default=None) or self._og_search_title(webpage)) title = clean_html(
self._html_search_meta('taboola:title', webpage, 'title', default=None)
or self._html_search_meta('name', webpage, 'title', default=None)
or self._og_search_title(webpage))
# in "movies" sub-site pages, filename is URL # in "movies" sub-site pages, filename is URL
# in "food" sub-site pages, url string contains escape characters # in "food" sub-site pages, url string contains escape characters
video_url = (self._html_search_meta('contentUrl', webpage, 'video-url', default=None) video_url = (self._html_search_meta('contentUrl', webpage, 'video-url', default=None)
or self._search_regex(r'\"media_mp4\"\s*:\s*\"([^\"]+)\"', webpage, 'video-url')).replace('\\/', '/') or self._search_regex(r'"media_mp4"\s*:\s*"([^"]+)', webpage, 'video-url'))
if video_url is not None:
video_url = video_url.replace('\\/', '/')
# "doctor" sub-site has MM:SS format # "doctor" sub-site has MM:SS format
duration = parse_duration(self._html_search_meta('video:duration', webpage, 'duration', default=None) or self._search_regex(r'\"dur\"\s*:\s*\"([^\"]+)\"', webpage, 'duration')) duration = parse_duration(
self._html_search_meta('video:duration', webpage, 'duration', default=None)
or self._search_regex(r'"dur"\s*:\s*"([^"]+)', webpage, 'duration', fatal=False, default=None))
# "sports", "doctor", "swirlster" sub-sites don't have 'publish-date' # "sports", "doctor", "swirlster" sub-sites don't have 'publish-date'
upload_date = unified_strdate(self._html_search_meta( upload_date = unified_strdate(
'publish-date', webpage, 'upload date', default=None) or self._html_search_meta( self._html_search_meta('publish-date', webpage, 'upload date', default=None)
'uploadDate', webpage, 'upload date', default=None) or self._search_regex( or self._html_search_meta('uploadDate', webpage, 'upload date', default=None)
r'datePublished"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False)) or self._search_regex(r'datePublished"\s*:\s*"([^"]+)', webpage, 'upload date', fatal=False, default=None))
description = clean_html(self._html_search_meta('description', webpage, 'description', default=None) description = clean_html(
or remove_end(self._og_search_description(webpage), ' (Read more)')) self._html_search_meta('description', webpage, 'description', default=None)
or remove_end(self._og_search_description(webpage, default=None), ' (Read more)'))
thumbnail = (self._html_search_meta('thumbnailUrl', webpage, 'thumbnail', default=None) or self._search_regex(r'\"image\"\s*:\s*\"([^\"]+)\"', webpage, 'thumbnail')).replace('\\/', '/') thumbnail = (self._html_search_meta('thumbnailUrl', webpage, 'thumbnail', default=None)
or self._search_regex(r'"image"\s*:\s*"([^\"]+)', webpage, 'thumbnail', fatal=False, default=None))
if thumbnail is not None:
thumbnail = thumbnail.replace('\\/', '/')
return { return {
'id': video_id, 'id': video_id,