yt-dlp/yt_dlp/extractor/izlesene.py
sepro add96eb9f8
[cleanup] Add more ruff rules (#10149)
Authored by: seproDev

Reviewed-by: bashonly <88596187+bashonly@users.noreply.github.com>
Reviewed-by: Simon Sawicki <contact@grub4k.xyz>
2024-06-12 01:09:58 +02:00

111 lines
3.9 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import urllib.parse
from .common import InfoExtractor
from ..utils import (
determine_ext,
float_or_none,
get_element_by_id,
int_or_none,
parse_iso8601,
str_to_int,
)
class IzleseneIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://(?:(?:www|m)\.)?izlesene\.com/
(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
'''
_TESTS = [
{
'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
'md5': '4384f9f0ea65086734b881085ee05ac2',
'info_dict': {
'id': '7599694',
'ext': 'mp4',
'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
'description': 'md5:253753e2655dde93f59f74b572454f6d',
'thumbnail': r're:^https?://.*\.jpg',
'uploader_id': 'pelikzzle',
'timestamp': int,
'upload_date': '20140702',
'duration': 95.395,
'age_limit': 0,
},
},
{
'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
'md5': '97f09b6872bffa284cb7fa4f6910cb72',
'info_dict': {
'id': '17997',
'ext': 'mp4',
'title': 'Tarkan Dortmund 2006 Konseri',
'thumbnail': r're:^https://.*\.jpg',
'uploader_id': 'parlayankiz',
'timestamp': int,
'upload_date': '20061112',
'duration': 253.666,
'age_limit': 0,
},
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(f'http://www.izlesene.com/video/{video_id}', video_id)
video = self._parse_json(
self._search_regex(
r'videoObj\s*=\s*({.+?})\s*;\s*\n', webpage, 'streams'),
video_id)
title = video.get('videoTitle') or self._og_search_title(webpage)
formats = []
for stream in video['media']['level']:
source_url = stream.get('source')
if not source_url or not isinstance(source_url, str):
continue
ext = determine_ext(url, 'mp4')
quality = stream.get('value')
height = int_or_none(quality)
formats.append({
'format_id': f'{quality}p' if quality else 'sd',
'url': urllib.parse.unquote(source_url),
'ext': ext,
'height': height,
})
description = self._og_search_description(webpage, default=None)
thumbnail = video.get('posterURL') or self._proto_relative_url(
self._og_search_thumbnail(webpage), scheme='http:')
uploader = self._html_search_regex(
r"adduserUsername\s*=\s*'([^']+)';",
webpage, 'uploader', fatal=False)
timestamp = parse_iso8601(self._html_search_meta(
'uploadDate', webpage, 'upload date'))
duration = float_or_none(video.get('duration') or self._html_search_regex(
r'videoduration["\']?\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
webpage, 'duration', fatal=False, group='value'), scale=1000)
view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
comment_count = self._html_search_regex(
r'comment_count\s*=\s*\'([^\']+)\';',
webpage, 'comment_count', fatal=False)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader_id': uploader,
'timestamp': timestamp,
'duration': duration,
'view_count': int_or_none(view_count),
'comment_count': int_or_none(comment_count),
'age_limit': self._family_friendly_search(webpage),
'formats': formats,
}