114 lines
3.9 KiB
Python
114 lines
3.9 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import compat_chr
|
|
from ..utils import (
|
|
determine_ext,
|
|
ExtractorError,
|
|
)
|
|
|
|
|
|
class OpenloadIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
|
|
|
|
_TESTS = [{
|
|
'url': 'https://openload.co/f/kUEfGclsU9o',
|
|
'md5': 'bf1c059b004ebc7a256f89408e65c36e',
|
|
'info_dict': {
|
|
'id': 'kUEfGclsU9o',
|
|
'ext': 'mp4',
|
|
'title': 'skyrim_no-audio_1080.mp4',
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
|
},
|
|
}, {
|
|
'url': 'https://openload.co/embed/rjC09fkPLYs',
|
|
'info_dict': {
|
|
'id': 'rjC09fkPLYs',
|
|
'ext': 'mp4',
|
|
'title': 'movie.mp4',
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
|
'subtitles': {
|
|
'en': [{
|
|
'ext': 'vtt',
|
|
}],
|
|
},
|
|
},
|
|
'params': {
|
|
'skip_download': True, # test subtitles only
|
|
},
|
|
}, {
|
|
'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
|
|
'only_matching': True,
|
|
}, {
|
|
'url': 'https://openload.io/f/ZAn6oz-VZGE/',
|
|
'only_matching': True,
|
|
}, {
|
|
'url': 'https://openload.co/f/_-ztPaZtMhM/',
|
|
'only_matching': True,
|
|
}, {
|
|
# unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
|
|
# for title and ext
|
|
'url': 'https://openload.co/embed/Sxz5sADo82g/',
|
|
'only_matching': True,
|
|
}, {
|
|
'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
|
|
'only_matching': True,
|
|
}]
|
|
|
|
_API_URL = 'https://api.openload.co/1'
|
|
_PAIR_INFO_URL = _API_URL + '/streaming/info'
|
|
_GET_VIDEO_URL = _API_URL + '/streaming/get?file={0}'
|
|
|
|
_PAIR_NEEDED = 'Open this url: {0}, solve captcha, click "Pair" button and try again'
|
|
|
|
@staticmethod
|
|
def _extract_urls(webpage):
|
|
return re.findall(
|
|
r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
|
|
webpage)
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
webpage = self._download_webpage('https://openload.co/embed/{0}/'.format(video_id), video_id)
|
|
|
|
if 'File not found' in webpage or 'deleted by the owner' in webpage:
|
|
raise ExtractorError('File not found', expected=True, video_id=video_id)
|
|
|
|
get_info = self._download_json(self._GET_VIDEO_URL.format(video_id), video_id)
|
|
status = get_info.get('status')
|
|
if status == 200:
|
|
result = get_info.get('result', {})
|
|
title = result.get('name')
|
|
video_url = result.get('url')
|
|
elif status == 403:
|
|
pair_info = self._download_json(self._PAIR_INFO_URL, video_id,
|
|
note='Downloading pair info')
|
|
if pair_info.get('status') == 200:
|
|
pair_url = pair_info.get('result', {}).get('auth_url')
|
|
if pair_url:
|
|
raise ExtractorError(self._PAIR_NEEDED.format(pair_url), expected=True)
|
|
else:
|
|
raise ExtractorError('Pair URL not found')
|
|
else:
|
|
raise ExtractorError('Error loading pair info')
|
|
else:
|
|
raise ExtractorError('Error loading JSON metadata', video_id=video_id)
|
|
|
|
entries = self._parse_html5_media_entries(url, webpage, video_id)
|
|
entry = entries[0] if entries else {}
|
|
subtitles = entry.get('subtitles')
|
|
|
|
info_dict = {
|
|
'id': video_id,
|
|
'title': title,
|
|
'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None),
|
|
'url': video_url,
|
|
# Seems all videos have extensions in their titles
|
|
'ext': determine_ext(title, 'mp4'),
|
|
'subtitles': subtitles,
|
|
}
|
|
return info_dict
|