From 9dc13a67807fd38070d95cb23deca3761476e9de Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 23 Oct 2016 18:07:56 +0700 Subject: [PATCH] [vivo] Fix extraction (closes #11003) --- youtube_dl/extractor/extractors.py | 5 +- youtube_dl/extractor/shared.py | 110 +++++++++++++++++------------ 2 files changed, 70 insertions(+), 45 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a693f8c56..6f7d9b65b 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -796,7 +796,10 @@ from .servingsys import ServingSysIE from .sexu import SexuIE from .shahid import ShahidIE -from .shared import SharedIE +from .shared import ( + SharedIE, + VivoIE, +) from .sharesix import ShareSixIE from .sina import SinaIE from .sixplay import SixPlayIE diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index d592dfeb8..89e19e927 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -10,11 +10,38 @@ ) -class SharedIE(InfoExtractor): - IE_DESC = 'shared.sx and vivo.sx' - _VALID_URL = r'https?://(?:shared|vivo)\.sx/(?P[\da-z]{10})' +class SharedBaseIE(InfoExtractor): + def _real_extract(self, url): + video_id = self._match_id(url) - _TESTS = [{ + 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 = 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)) + + 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', 'md5': '106fefed92a8a2adb8c98e6a0652f49b', 'info_dict': { @@ -23,7 +50,32 @@ class SharedIE(InfoExtractor): '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': { @@ -32,43 +84,13 @@ class SharedIE(InfoExtractor): 'title': 'Chicken', 'filesize': 528031, }, - }] + } - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage, urlh = self._download_webpage_handle(url, video_id) - - if '>File does not exist<' in webpage: - raise ExtractorError( - 'Video %s does not exist' % video_id, expected=True) - - download_form = self._hidden_inputs(webpage) - - video_page = self._download_webpage( - urlh.geturl(), video_id, 'Downloading video page', - data=urlencode_postdata(download_form), - headers={ - 'Content-Type': 'application/x-www-form-urlencoded', - 'Referer': urlh.geturl(), - }) - - video_url = self._html_search_regex( - r'data-url=(["\'])(?P(?:(?!\1).)+)\1', - video_page, 'video URL', group='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=(["\'])(?P(?:(?!\1).)+)\1', - video_page, 'thumbnail', default=None, group='url') - - return { - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'filesize': filesize, - 'title': title, - 'thumbnail': thumbnail, - } + 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]