1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-05 14:47:55 +01:00
youtube-dl/youtube_dl/extractor/vidio.py

78 lines
2.8 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import re
2016-06-04 11:47:43 +02:00
from .common import InfoExtractor
from ..utils import int_or_none
class VidioIE(InfoExtractor):
2016-06-04 11:47:43 +02:00
_VALID_URL = r'https?://(?:www\.)?vidio\.com/watch/(?P<id>\d+)-(?P<display_id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015',
2016-06-04 11:47:43 +02:00
'md5': 'cd2801394afc164e9775db6a140b91fe',
'info_dict': {
'id': '165683',
2016-06-04 11:47:43 +02:00
'display_id': 'dj_ambred-booyah-live-2015',
'ext': 'mp4',
2016-06-04 11:47:43 +02:00
'title': 'DJ_AMBRED - Booyah (Live 2015)',
'description': 'md5:27dc15f819b6a78a626490881adbadf8',
'thumbnail': r're:^https?://.*\.jpg$',
2016-06-04 11:47:43 +02:00
'duration': 149,
'like_count': int,
},
2016-06-04 11:47:43 +02:00
}, {
'url': 'https://www.vidio.com/watch/77949-south-korea-test-fires-missile-that-can-strike-all-of-the-north',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id, display_id = mobj.group('id', 'display_id')
webpage = self._download_webpage(url, display_id)
2016-06-04 11:47:43 +02:00
title = self._og_search_title(webpage)
m3u8_url, duration, thumbnail = [None] * 3
2016-06-04 11:47:43 +02:00
clips = self._parse_json(
self._html_search_regex(
r'data-json-clips\s*=\s*(["\'])(?P<data>\[.+?\])\1',
webpage, 'video data', default='[]', group='data'),
display_id, fatal=False)
if clips:
clip = clips[0]
m3u8_url = clip.get('sources', [{}])[0].get('file')
duration = clip.get('clip_duration')
thumbnail = clip.get('image')
m3u8_url = m3u8_url or self._search_regex(
r'data(?:-vjs)?-clip-hls-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'hls url', group='url')
2017-04-23 06:48:51 +02:00
formats = self._extract_m3u8_formats(
m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native')
self._sort_formats(formats)
2016-06-04 11:47:43 +02:00
duration = int_or_none(duration or self._search_regex(
r'data-video-duration=(["\'])(?P<duration>\d+)\1', webpage,
'duration', fatal=False, group='duration'))
2016-06-04 11:47:43 +02:00
thumbnail = thumbnail or self._og_search_thumbnail(webpage)
like_count = int_or_none(self._search_regex(
(r'<span[^>]+data-comment-vote-count=["\'](\d+)',
r'<span[^>]+class=["\'].*?\blike(?:__|-)count\b.*?["\'][^>]*>\s*(\d+)'),
webpage, 'like count', fatal=False))
return {
'id': video_id,
2016-06-04 11:47:43 +02:00
'display_id': display_id,
'title': title,
'description': self._og_search_description(webpage),
2016-06-04 11:47:43 +02:00
'thumbnail': thumbnail,
'duration': duration,
'like_count': like_count,
'formats': formats,
}