MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-18 10:49:30 +01:00
Code Issues Projects Releases Wiki Activity

[ie/TV5MondePlus] Use more get_element_by_class.

Browse Source
This commit is contained in:
Alard 2024-04-13 22:56:39 +02:00
parent 1aa522dfc4
commit 24e9dab586
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
yt_dlp/extractor/tv5mondeplus.py
View File

@ -3,8 +3,10 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
clean_html,
determine_ext, determine_ext,
extract_attributes, extract_attributes,
get_element_by_class,
get_element_html_by_class, get_element_html_by_class,
int_or_none, int_or_none,
parse_duration, parse_duration,
@ -148,16 +150,13 @@ def process_video_files(v):
duration = (int_or_none(try_get(metadata, lambda x: x['content']['duration'])) duration = (int_or_none(try_get(metadata, lambda x: x['content']['duration']))
or parse_duration(self._html_search_meta('duration', webpage))) or parse_duration(self._html_search_meta('duration', webpage)))
title = episode = self._html_search_regex(r'<h1 class="main-title">([^<]+)', webpage, 'title', default=None) title = episode = clean_html(get_element_by_class('main-title', webpage))
subtitle = self._html_search_regex(r'<p class="video-subtitle">([^<]+)', webpage, 'subtitle', default=None) subtitle = clean_html(get_element_by_class('video-subtitle', webpage))
if subtitle: if subtitle:
episode = subtitle episode = subtitle
ep_summary = get_element_html_by_class('ep-summary', webpage) ep_summary = get_element_html_by_class('ep-summary', webpage)
description = clean_html(get_element_by_class('text', ep_summary))
description = self._html_search_regex(
r'<p class="text">(.+?)</p>', ep_summary,
'description', fatal=False, flags=re.DOTALL)
upload_date = self._search_regex( upload_date = self._search_regex(
r'(?:date_publication|publish_date)["\']\s*:\s*["\'](\d{4}_\d{2}_\d{2})', r'(?:date_publication|publish_date)["\']\s*:\s*["\'](\d{4}_\d{2}_\d{2})',
@ -182,6 +181,6 @@ def process_video_files(v):
'formats': formats, 'formats': formats,
'subtitles': self._extract_subtitles(self._parse_json( 'subtitles': self._extract_subtitles(self._parse_json(
traverse_obj(vpl_data, ('data-captions', {str}), default='{}'), display_id, fatal=False)), traverse_obj(vpl_data, ('data-captions', {str}), default='{}'), display_id, fatal=False)),
'series': self._html_search_regex(r'<p class="video-title">([^<]+)', webpage, 'title', default=None), 'series': clean_html(get_element_by_class('video-title', webpage)),
'episode': episode, 'episode': episode,
} }