depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-25 11:41:52 +00:00
Code Issues Releases Wiki Activity

[cspan] improve info extraction(closes #27791)

Browse source
This commit is contained in:
Remita Amine 2021-01-13 09:17:43 +01:00
parent cf862771d7
commit 2408e6d26a
1 changed files with 26 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
youtube_dl/extractor/cspan.py
View file

@ -8,11 +8,14 @@ from ..utils import (
ExtractorError, ExtractorError,
extract_attributes, extract_attributes,
find_xpath_attr, find_xpath_attr,
get_element_by_attribute,
get_element_by_class, get_element_by_class,
int_or_none, int_or_none,
js_to_json, js_to_json,
merge_dicts, merge_dicts,
parse_iso8601,
smuggle_url, smuggle_url,
str_to_int,
unescapeHTML, unescapeHTML,
) )
from .senateisvp import SenateISVPIE from .senateisvp import SenateISVPIE
@ -116,8 +119,30 @@ class CSpanIE(InfoExtractor):
jwsetup, video_id, require_title=False, m3u8_id='hls', jwsetup, video_id, require_title=False, m3u8_id='hls',
base_url=url) base_url=url)
add_referer(info['formats']) add_referer(info['formats'])
for subtitles in info['subtitles'].values():
for subtitle in subtitles:
ext = determine_ext(subtitle['url'])
if ext == 'php':
ext = 'vtt'
subtitle['ext'] = ext
ld_info = self._search_json_ld(webpage, video_id, default={}) ld_info = self._search_json_ld(webpage, video_id, default={})
return merge_dicts(info, ld_info) title = get_element_by_class('video-page-title', webpage) or \
self._og_search_title(webpage)
description = get_element_by_attribute('itemprop', 'description', webpage) or \
self._html_search_meta(['og:description', 'description'], webpage)
return merge_dicts(info, ld_info, {
'title': title,
'thumbnail': get_element_by_attribute('itemprop', 'thumbnailUrl', webpage),
'description': description,
'timestamp': parse_iso8601(get_element_by_attribute('itemprop', 'uploadDate', webpage)),
'location': get_element_by_attribute('itemprop', 'contentLocation', webpage),
'duration': int_or_none(self._search_regex(
r'jwsetup\.seclength\s*=\s*(\d+);',
webpage, 'duration', fatal=False)),
'view_count': str_to_int(self._search_regex(
r"<span[^>]+class='views'[^>]*>([\d,]+)\s+Views</span>",
webpage, 'views', fatal=False)),
})
# Obsolete # Obsolete
# We first look for clipid, because clipprog always appears before # We first look for clipid, because clipprog always appears before