yt-dlp/youtube_dl/extractor/openload.py

# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    ExtractorError,
    get_element_by_id,
    PhantomJSwrapper,
)


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,
    }]

    _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'

    @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)
        url = 'https://openload.co/embed/%s/' % video_id
        headers = {
            'User-Agent': self._USER_AGENT,
        }

        phantom = PhantomJSwrapper(self)
        webpage, _ = phantom.get(url, video_id=video_id, headers=headers)

        if 'File not found' in webpage or 'deleted by the owner' in webpage:
            raise ExtractorError('File not found', expected=True, video_id=video_id)

        decoded_id = get_element_by_id('streamurl', webpage)

        video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id

        title = self._og_search_title(webpage, default=None) or self._search_regex(
            r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
            'title', default=None) or self._html_search_meta(
            'description', webpage, 'title', fatal=True)

        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,
            'http_headers': headers,
        }
        return info_dict