X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9ed7fe4fe4c445eb7d9f3197bb300d0db8f1807a..d9d7cd0e85dc712461d9185db9df9d6c900a573b:/youtube_dl/extractor/shared.py diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index 8eda3c8..89e19e9 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -3,62 +3,29 @@ from __future__ import unicode_literals import base64 from .common import InfoExtractor -from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, int_or_none, - sanitized_Request, + urlencode_postdata, ) -class SharedIE(InfoExtractor): - IE_DESC = 'shared.sx and vivo.sx' - _VALID_URL = r'http://(?:shared|vivo)\.sx/(?P[\da-z]{10})' - - _TESTS = [{ - 'url': 'http://shared.sx/0060718775', - 'md5': '106fefed92a8a2adb8c98e6a0652f49b', - 'info_dict': { - 'id': '0060718775', - 'ext': 'mp4', - 'title': 'Bmp4', - 'filesize': 1720110, - }, - }, { - 'url': 'http://vivo.sx/d7ddda0e78', - 'md5': '15b3af41be0b4fe01f4df075c2678b2c', - 'info_dict': { - 'id': 'd7ddda0e78', - 'ext': 'mp4', - 'title': 'Chicken', - 'filesize': 528031, - }, - }] - +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 = self._hidden_inputs(webpage) - request = sanitized_Request( - url, compat_urllib_parse.urlencode(download_form)) - request.add_header('Content-Type', 'application/x-www-form-urlencoded') + video_url = self._extract_video_url(webpage, video_id, url) - video_page = self._download_webpage( - request, video_id, 'Downloading video page') - - 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) return { 'id': video_id, @@ -66,5 +33,64 @@ class SharedIE(InfoExtractor): 'ext': 'mp4', 'filesize': filesize, 'title': title, - 'thumbnail': thumbnail, } + + +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', + '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: base64.b64decode( + x.encode('ascii')).decode('utf-8'))[0]