xZero707/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 06:10:12 +01:00
Code Issues Packages Projects Releases Wiki Activity

updated extractor to a simpler process

Browse Source
This commit is contained in:
subrat-lima 2024-08-22 13:52:33 +05:30
parent db4b19eaff
commit dbb1b746d4
1 changed files with 49 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

82
yt_dlp/extractor/ndtv.py
View File

@ -1,6 +1,6 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import clean_html, parse_duration, remove_end, unified_strdate from ..utils import clean_html, determine_ext, parse_duration, traverse_obj, unescapeHTML, unified_strdate
class NDTVIE(InfoExtractor): class NDTVIE(InfoExtractor):
@ -10,7 +10,7 @@ class NDTVIE(InfoExtractor):
_TESTS = [ _TESTS = [
{ {
'url': 'https://khabar.ndtv.com/video/show/prime-time/prime-time-ill-system-and-poor-education-468818', 'url': 'https://khabar.ndtv.com/video/show/prime-time/prime-time-ill-system-and-poor-education-468818',
'md5': '78efcf3880ef3fd9b83d405ca94a38eb', 'md5': '5237500d57c8af47a519c4af9e2fd9c0',
'info_dict': { 'info_dict': {
'id': '468818', 'id': '468818',
'ext': 'mp4', 'ext': 'mp4',
@ -19,11 +19,13 @@ class NDTVIE(InfoExtractor):
'upload_date': '20170928', 'upload_date': '20170928',
'duration': 2218, 'duration': 2218,
'thumbnail': r're:https?://.*\.jpg', 'thumbnail': r're:https?://.*\.jpg',
'categories': 'shows',
'channel_id': '2',
}, },
}, },
{ {
'url': 'http://movies.ndtv.com/videos/cracker-free-diwali-wishes-from-karan-johar-kriti-sanon-other-stars-470304', 'url': 'http://movies.ndtv.com/videos/cracker-free-diwali-wishes-from-karan-johar-kriti-sanon-other-stars-470304',
'md5': 'f1d709352305b44443515ac56b45aa46', 'md5': 'b7ef90f55e63885aef59c59cf2e44e81',
'info_dict': { 'info_dict': {
'id': '470304', 'id': '470304',
'ext': 'mp4', 'ext': 'mp4',
@ -32,6 +34,8 @@ class NDTVIE(InfoExtractor):
'upload_date': '20171019', 'upload_date': '20171019',
'duration': 137, 'duration': 137,
'thumbnail': r're:https?://.*\.jpg', 'thumbnail': r're:https?://.*\.jpg',
'categories': 'entertainment',
'channel_id': '1',
}, },
}, },
{ {
@ -45,6 +49,8 @@ class NDTVIE(InfoExtractor):
'upload_date': '20240818', 'upload_date': '20240818',
'duration': 220, 'duration': 220,
'thumbnail': 'https://c.ndtvimg.com/2024-08/be8djnjc_jai-jawan_640x480_18_August_24.jpg', 'thumbnail': 'https://c.ndtvimg.com/2024-08/be8djnjc_jai-jawan_640x480_18_August_24.jpg',
'categories': 'entertainment',
'channel_id': '1',
}, },
}, },
{ {
@ -58,6 +64,8 @@ class NDTVIE(InfoExtractor):
'upload_date': '20240818', 'upload_date': '20240818',
'duration': 931, 'duration': 931,
'thumbnail': 'https://c.ndtvimg.com/2024-08/hh48aduk_dr-sameer-kaul_640x480_18_August_24.jpg', 'thumbnail': 'https://c.ndtvimg.com/2024-08/hh48aduk_dr-sameer-kaul_640x480_18_August_24.jpg',
'categories': 'news',
'channel_id': '1',
}, },
}, },
{ {
@ -71,6 +79,8 @@ class NDTVIE(InfoExtractor):
'upload_date': '20240730', 'upload_date': '20240730',
'duration': 45, 'duration': 45,
'thumbnail': 'https://c.ndtvimg.com/2024-07/itrg8ilo_msdhoni_640x480_31_July_24.jpg', 'thumbnail': 'https://c.ndtvimg.com/2024-07/itrg8ilo_msdhoni_640x480_31_July_24.jpg',
'categories': 'fangully',
'channel_id': '',
}, },
}, },
{ {
@ -84,6 +94,8 @@ class NDTVIE(InfoExtractor):
'upload_date': '20240805', 'upload_date': '20240805',
'duration': 1304, 'duration': 1304,
'thumbnail': 'https://c.ndtvimg.com/2024-08/kh67tomo_heartattack_640x480_05_August_24.jpg', 'thumbnail': 'https://c.ndtvimg.com/2024-08/kh67tomo_heartattack_640x480_05_August_24.jpg',
'categories': 'Health',
'channel_id': '1',
}, },
}, },
{ {
@ -93,10 +105,12 @@ class NDTVIE(InfoExtractor):
'id': '767098', 'id': '767098',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Watch NDTV Food Awards 2024 On NDTV 24x7 On Saturday 9th March, 2024', 'title': 'Watch NDTV Food Awards 2024 On NDTV 24x7 On Saturday 9th March, 2024',
'description': 'md5:4a8831a038ab50dc5ea76b1fad4b51d0', 'description': 'md5:11948e8404b058cd0a9d174aa1e88e84',
'upload_date': '20240307', 'upload_date': '20240307',
'duration': 35, 'duration': 35,
'thumbnail': 'https://c.ndtvimg.com/2024-03/2eianfs_food-awards_640x480_08_March_24.jpg', 'thumbnail': 'https://c.ndtvimg.com/2024-03/2eianfs_food-awards_640x480_08_March_24.jpg',
'categories': 'food',
'channel_id': '1',
}, },
}, },
{ {
@ -137,44 +151,46 @@ def _real_extract(self, url):
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( # required for removing unwanted js expression in the json data
self._html_search_meta('taboola:title', webpage, 'title', default=None) # found this expression in one article
or self._html_search_meta('name', webpage, 'title', default=None) # will update this json data handler more generic if more of similar patterns found
or self._og_search_title(webpage)) webpage = webpage.replace('true / false', 'true')
# in "movies" sub-site pages, filename is URL data = self._search_json(r'__html5playerdata\s*=\s*', webpage, 'json_data', video_id)
# in "food" sub-site pages, url string contains escape characters
video_url = (self._html_search_meta('contentUrl', webpage, 'video-url', default=None)
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 title = clean_html(unescapeHTML(traverse_obj(data, ('title'))))
duration = parse_duration( duration = parse_duration(traverse_obj(data, ('dur')))
self._html_search_meta('video:duration', webpage, 'duration', default=None) upload_date = unified_strdate(traverse_obj(data, ('date')))
or self._search_regex(r'"dur"\s*:\s*"([^"]+)', webpage, 'duration', fatal=False, default=None)) video_m3u8 = traverse_obj(data, ('media'))
video_mp4 = traverse_obj(data, ('media_mp4'))
video_webm = traverse_obj(data, ('media_webm'))
description = clean_html(unescapeHTML(traverse_obj(data, ('description'))))
thumbnail = traverse_obj(data, ('image'))
channel_id = traverse_obj(data, ('channel'))
categories = traverse_obj(data, ('category'))
# "sports", "doctor", "swirlster" sub-sites don't have 'publish-date' formats = []
upload_date = unified_strdate( if video_mp4:
self._html_search_meta('publish-date', webpage, 'upload date', default=None) formats.append({'url': video_mp4, 'ext': determine_ext(video_mp4)})
or self._html_search_meta('uploadDate', webpage, 'upload date', default=None) if video_webm:
or self._search_regex(r'datePublished"\s*:\s*"([^"]+)', webpage, 'upload date', fatal=False, default=None)) formats.append({'url': video_webm, 'ext': determine_ext(video_webm)})
if video_m3u8:
description = clean_html( m3u8_data = self._extract_m3u8_formats(video_m3u8, video_id)
self._html_search_meta('description', webpage, 'description', default=None) formats.extend(m3u8_data)
or remove_end(self._og_search_description(webpage, default=None), ' (Read more)')) # here, making the assumption that mp4 video available is always the highest quality
# will update if any deviation found
thumbnail = (self._html_search_meta('thumbnailUrl', webpage, 'thumbnail', default=None) formats[0]['width'] = m3u8_data[-1]['width']
or self._search_regex(r'"image"\s*:\s*"([^\"]+)', webpage, 'thumbnail', fatal=False, default=None)) formats[0]['height'] = m3u8_data[-1]['height']
if thumbnail is not None: formats[0]['tbr'] = m3u8_data[-1]['tbr']
thumbnail = thumbnail.replace('\\/', '/')
return { return {
'id': video_id, 'id': video_id,
'url': video_url, 'formats': formats,
'title': title, 'title': title,
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'duration': duration, 'duration': duration,
'upload_date': upload_date, 'upload_date': upload_date,
'categories': categories,
'channel_id': channel_id,
} }