X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/5ea61d104de9ca8a7d19d63d83173eb7391081d2..ce7bc3aa7fcf5bc302342428c41df23fa8ce2887:/youtube_dl/extractor/shared.py diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index 9f3e944..b2250af 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -1,57 +1,30 @@ from __future__ import unicode_literals -import re -import base64 - from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_b64decode from ..utils import ( ExtractorError, int_or_none, + urlencode_postdata, ) -class SharedIE(InfoExtractor): - _VALID_URL = r'http://shared\.sx/(?P[\da-z]{10})' - - _TEST = { - 'url': 'http://shared.sx/0060718775', - 'md5': '106fefed92a8a2adb8c98e6a0652f49b', - 'info_dict': { - 'id': '0060718775', - 'ext': 'mp4', - 'title': 'Bmp4', - }, - } - +class SharedBaseIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - if '>File does not exist<' in webpage: + webpage, urlh = self._download_webpage_handle(url, video_id) + + if self._FILE_NOT_FOUND in webpage: raise ExtractorError( 'Video %s does not exist' % video_id, expected=True) - download_form = dict(re.findall( - r'[\da-z]{10})' + _FILE_NOT_FOUND = '>File does not exist<' + + _TEST = { + 'url': 'http://shared.sx/0060718775', + 'md5': '106fefed92a8a2adb8c98e6a0652f49b', + 'info_dict': { + 'id': '0060718775', + 'ext': 'mp4', + 'title': 'Bmp4', + 'filesize': 1720110, + }, + } + + def _extract_video_url(self, webpage, video_id, url): + download_form = self._hidden_inputs(webpage) + + video_page = self._download_webpage( + url, video_id, 'Downloading video page', + data=urlencode_postdata(download_form), + headers={ + 'Content-Type': 'application/x-www-form-urlencoded', + 'Referer': url, + }) + + video_url = self._html_search_regex( + r'data-url=(["\'])(?P(?:(?!\1).)+)\1', + video_page, 'video URL', group='url') + + return video_url + + +class VivoIE(SharedBaseIE): + IE_DESC = 'vivo.sx' + _VALID_URL = r'https?://vivo\.sx/(?P[\da-z]{10})' + _FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed' + + _TEST = { + 'url': 'http://vivo.sx/d7ddda0e78', + 'md5': '15b3af41be0b4fe01f4df075c2678b2c', + 'info_dict': { + 'id': 'd7ddda0e78', + 'ext': 'mp4', + 'title': 'Chicken', + 'filesize': 528031, + }, + } + + def _extract_video_url(self, webpage, video_id, *args): + return self._parse_json( + self._search_regex( + r'InitializeStream\s*\(\s*(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'stream', group='url'), + video_id, + transform_source=lambda x: compat_b64decode(x).decode('utf-8'))[0]