1
0
Fork 0
mirror of https://github.com/blackjack4494/yt-dlc.git synced 2024-12-27 18:29:01 +00:00
yt-dlc/youtube_dl/extractor/videomega.py
Philipp Hagemeister 1cc79574fc Fix imports and general cleanup
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail.
· Use _match_id consistently whenever possible
· Fix some outdated tests
· Use consistent valid URL (always match the whole protocol, no ^ at start required)
· Use modern test definitions
2014-12-13 12:35:45 +01:00

55 lines
1.6 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
)
from ..utils import (
remove_start,
)
class VideoMegaIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://
(?:www\.)?videomega\.tv/
(?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
'''
_TEST = {
'url': 'http://videomega.tv/?ref=GKeGPVedBe',
'md5': '240fb5bcf9199961f48eb17839b084d6',
'info_dict': {
'id': 'GKeGPVedBe',
'ext': 'mp4',
'title': 'XXL - All Sports United',
'thumbnail': 're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id)
webpage = self._download_webpage(url, video_id)
escaped_data = self._search_regex(
r'unescape\("([^"]+)"\)', webpage, 'escaped data')
playlist = compat_urllib_parse.unquote(escaped_data)
thumbnail = self._search_regex(
r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False)
url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL')
title = remove_start(self._html_search_regex(
r'<title>(.*?)</title>', webpage, 'title'), 'VideoMega.tv - ')
formats = [{
'format_id': 'sd',
'url': url,
}]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
}