0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-14 01:05:06 +00:00
yt-dlp/yt_dlp/extractor/snotr.py
pukkandan 86e5f3ed2e
[cleanup] Upgrade syntax
Using https://github.com/asottile/pyupgrade

1. `__future__` imports and `coding: utf-8` were removed
2. Files were rewritten with `pyupgrade --py36-plus --keep-percent-format`
3. f-strings were cherry-picked from `pyupgrade --py36-plus`

Extractors are left untouched (except removing header) to avoid unnecessary merge conflicts
2022-04-12 05:32:51 +05:30

68 lines
2.4 KiB
Python

from .common import InfoExtractor
from ..utils import (
parse_duration,
parse_filesize,
str_to_int,
)
class SnotrIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?snotr\.com/video/(?P<id>\d+)/([\w]+)'
_TESTS = [{
'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks',
'info_dict': {
'id': '13708',
'ext': 'mp4',
'title': 'Drone flying through fireworks!',
'duration': 248,
'filesize_approx': 40700000,
'description': 'A drone flying through Fourth of July Fireworks',
'thumbnail': r're:^https?://.*\.jpg$',
},
'expected_warnings': ['description'],
}, {
'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10',
'info_dict': {
'id': '530',
'ext': 'mp4',
'title': 'David Letteman - George W. Bush Top 10',
'duration': 126,
'filesize_approx': 8500000,
'description': 'The top 10 George W. Bush moments, brought to you by David Letterman!',
'thumbnail': r're:^https?://.*\.jpg$',
}
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
info_dict = self._parse_html5_media_entries(
url, webpage, video_id, m3u8_entry_protocol='m3u8_native')[0]
view_count = str_to_int(self._html_search_regex(
r'<p[^>]*>\s*<strong[^>]*>Views:</strong>\s*<span[^>]*>([\d,\.]+)',
webpage, 'view count', fatal=False))
duration = parse_duration(self._html_search_regex(
r'<p[^>]*>\s*<strong[^>]*>Length:</strong>\s*<span[^>]*>([\d:]+)',
webpage, 'duration', fatal=False))
filesize_approx = parse_filesize(self._html_search_regex(
r'<p[^>]*>\s*<strong[^>]*>Filesize:</strong>\s*<span[^>]*>([^<]+)',
webpage, 'filesize', fatal=False))
info_dict.update({
'id': video_id,
'description': description,
'title': title,
'view_count': view_count,
'duration': duration,
'filesize_approx': filesize_approx,
})
return info_dict