X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/0652569e481a8cf0995a00635ef62143fa779add..89bb9e23b34f43c6563524917f7dffb9841a972e:/youtube_dl/extractor/shared.py diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index a076776..931a0f7 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -1,20 +1,45 @@ from __future__ import unicode_literals -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, + url_or_none, + urlencode_postdata, ) -class SharedIE(InfoExtractor): - _VALID_URL = r'http://shared\.sx/(?P[\da-z]{10})' +class SharedBaseIE(InfoExtractor): + def _real_extract(self, url): + video_id = self._match_id(url) + + 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) + + video_url = self._extract_video_url(webpage, video_id, url) + + title = compat_b64decode(self._html_search_meta( + 'full:title', webpage, 'title')).decode('utf-8') + filesize = int_or_none(self._html_search_meta( + 'full:size', webpage, 'file size', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'filesize': filesize, + 'title': title, + } + + +class SharedIE(SharedBaseIE): + IE_DESC = 'shared.sx' + _VALID_URL = r'https?://shared\.sx/(?P[\da-z]{10})' + _FILE_NOT_FOUND = '>File does not exist<' _TEST = { 'url': 'http://shared.sx/0060718775', @@ -23,39 +48,55 @@ class SharedIE(InfoExtractor): 'id': '0060718775', 'ext': 'mp4', 'title': 'Bmp4', + 'filesize': 1720110, }, } - 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: - raise ExtractorError( - 'Video %s does not exist' % video_id, expected=True) - + def _extract_video_url(self, webpage, video_id, url): download_form = self._hidden_inputs(webpage) - request = compat_urllib_request.Request( - url, compat_urllib_parse.urlencode(download_form)) - request.add_header('Content-Type', 'application/x-www-form-urlencoded') video_page = self._download_webpage( - request, video_id, 'Downloading video page') + 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="([^"]+)"', video_page, 'video URL') - title = base64.b64decode(self._html_search_meta( - 'full:title', webpage, 'title').encode('utf-8')).decode('utf-8') - filesize = int_or_none(self._html_search_meta( - 'full:size', webpage, 'file size', fatal=False)) - thumbnail = self._html_search_regex( - r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None) + r'data-url=(["\'])(?P(?:(?!\1).)+)\1', + video_page, 'video URL', group='url') - return { - 'id': video_id, - 'url': video_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', - 'filesize': filesize, - 'title': title, - 'thumbnail': thumbnail, - } + 'title': 'Chicken', + 'filesize': 528031, + }, + } + + def _extract_video_url(self, webpage, video_id, *args): + def decode_url(encoded_url): + return compat_b64decode(encoded_url).decode('utf-8') + + stream_url = url_or_none(decode_url(self._search_regex( + r'data-stream\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'stream url', default=None, group='url'))) + if stream_url: + return stream_url + return self._parse_json( + self._search_regex( + r'InitializeStream\s*\(\s*(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'stream', group='url'), + video_id, transform_source=decode_url)[0]