# coding: utf-8 from __future__ import unicode_literals import re from .common import InfoExtractor from ..compat import ( compat_urllib_parse, compat_urllib_request, ) from ..utils import ( ExtractorError, ) class FiredriveIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?firedrive\.com/' + \ '(?:file|embed)/(?P[0-9a-zA-Z]+)' _FILE_DELETED_REGEX = r'
' _TESTS = [{ 'url': 'https://www.firedrive.com/file/FEB892FA160EBD01', 'md5': 'd5d4252f80ebeab4dc2d5ceaed1b7970', 'info_dict': { 'id': 'FEB892FA160EBD01', 'ext': 'flv', 'title': 'bbb_theora_486kbit.flv', 'thumbnail': 're:^http://.*\.jpg$', }, }] def _real_extract(self, url): video_id = self._match_id(url) url = 'http://firedrive.com/file/%s' % video_id webpage = self._download_webpage(url, video_id) if re.search(self._FILE_DELETED_REGEX, webpage) is not None: raise ExtractorError('Video %s does not exist' % video_id, expected=True) fields = dict(re.findall(r'''(?x)(.+)
', webpage, 'title') thumbnail = self._search_regex(r'image:\s?"(//[^\"]+)', webpage, 'thumbnail', fatal=False) if thumbnail is not None: thumbnail = 'http:' + thumbnail ext = self._search_regex(r'type:\s?\'([^\']+)\',', webpage, 'extension', fatal=False) video_url = self._search_regex( r'file:\s?loadURL\(\'(http[^\']+)\'\),', webpage, 'file url') formats = [{ 'format_id': 'sd', 'url': video_url, 'ext': ext, }] return { 'id': video_id, 'title': title, 'thumbnail': thumbnail, 'formats': formats, }