From: Sergey M․ Date: Wed, 11 Nov 2015 16:58:39 +0000 (+0600) Subject: [gorillavid] Rename to xfileshare X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=031ec536f00af5dc4ec034d3adb7d5fe3cc02453;p=youtube-dl [gorillavid] Rename to xfileshare --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 0a90da73c..06d25ef40 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -221,7 +221,6 @@ from .goldenmoustache import GoldenMoustacheIE from .golem import GolemIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE -from .gorillavid import GorillaVidIE from .goshgay import GoshgayIE from .groupon import GrouponIE from .hark import HarkIE @@ -786,6 +785,7 @@ from .wrzuta import WrzutaIE from .wsj import WSJIE from .xbef import XBefIE from .xboxclips import XboxClipsIE +from .xfileshare import XFileShareIE from .xhamster import ( XHamsterIE, XHamsterEmbedIE, diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py deleted file mode 100644 index 8c982d8e9..000000000 --- a/youtube_dl/extractor/gorillavid.py +++ /dev/null @@ -1,138 +0,0 @@ -# -*- 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, - encode_dict, - int_or_none, -) - - -class GorillaVidIE(InfoExtractor): - IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me' - _VALID_URL = r'''(?x) - https?://(?P(?:www\.)? - (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto.\me))/ - (?:embed-)?(?P[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)? - ''' - - _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<' - - _TESTS = [{ - 'url': 'http://gorillavid.in/06y9juieqpmi', - 'md5': '5ae4a3580620380619678ee4875893ba', - 'info_dict': { - 'id': '06y9juieqpmi', - 'ext': 'flv', - 'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ', - 'thumbnail': 're:http://.*\.jpg', - }, - }, { - 'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html', - 'only_matching': True, - }, { - 'url': 'http://daclips.in/3rso4kdn6f9m', - 'md5': '1ad8fd39bb976eeb66004d3a4895f106', - 'info_dict': { - 'id': '3rso4kdn6f9m', - 'ext': 'mp4', - 'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc', - 'thumbnail': 're:http://.*\.jpg', - } - }, { - # video with countdown timeout - 'url': 'http://fastvideo.in/1qmdn1lmsmbw', - 'md5': '8b87ec3f6564a3108a0e8e66594842ba', - 'info_dict': { - 'id': '1qmdn1lmsmbw', - 'ext': 'mp4', - 'title': 'Man of Steel - Trailer', - 'thumbnail': 're:http://.*\.jpg', - }, - }, { - 'url': 'http://realvid.net/ctn2y6p2eviw', - 'md5': 'b2166d2cf192efd6b6d764c18fd3710e', - 'info_dict': { - 'id': 'ctn2y6p2eviw', - 'ext': 'flv', - 'title': 'rdx 1955', - 'thumbnail': 're:http://.*\.jpg', - }, - }, { - 'url': 'http://movpod.in/0wguyyxi1yca', - 'only_matching': True, - }, { - 'url': 'http://filehoot.com/3ivfabn7573c.html', - 'info_dict': { - 'id': '3ivfabn7573c', - 'ext': 'mp4', - 'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4', - 'thumbnail': 're:http://.*\.jpg', - } - }, { - 'url': 'http://vidto.me/ku5glz52nqe1.html', - 'info_dict': { - 'id': 'ku5glz52nqe1', - 'ext': 'mp4', - 'title': 'test' - } - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - url = 'http://%s/%s' % (mobj.group('host'), video_id) - webpage = self._download_webpage(url, video_id) - - if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None: - raise ExtractorError('Video %s does not exist' % video_id, expected=True) - - fields = self._hidden_inputs(webpage) - - if fields['op'] == 'download1': - countdown = int_or_none(self._search_regex( - r'(?:[Ww]ait)?\s*(\d+)\s*(?:seconds?)?', - webpage, 'countdown', default=None)) - if countdown: - self._sleep(countdown, video_id) - - post = compat_urllib_parse.urlencode(encode_dict(fields)) - - req = compat_urllib_request.Request(url, post) - req.add_header('Content-type', 'application/x-www-form-urlencoded') - - webpage = self._download_webpage(req, video_id, 'Downloading video page') - - title = (self._search_regex( - [r'style="z-index: [0-9]+;">([^<]+)', - r'([^<]+)', - r'>Watch (.+) ', - r'

([^<]+)

'], - webpage, 'title', default=None) or self._og_search_title(webpage)).strip() - video_url = self._search_regex( - [r'file\s*:\s*["\'](http[^"\']+)["\'],', - r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'], - webpage, 'file url') - thumbnail = self._search_regex( - r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None) - - formats = [{ - 'format_id': 'sd', - 'url': video_url, - 'quality': 1, - }] - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'formats': formats, - } diff --git a/youtube_dl/extractor/xfileshare.py b/youtube_dl/extractor/xfileshare.py new file mode 100644 index 000000000..7610dc627 --- /dev/null +++ b/youtube_dl/extractor/xfileshare.py @@ -0,0 +1,138 @@ +# 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, + encode_dict, + int_or_none, +) + + +class XFileShareIE(InfoExtractor): + IE_DESC = 'XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me' + _VALID_URL = r'''(?x) + https?://(?P(?:www\.)? + (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto.\me))/ + (?:embed-)?(?P[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)? + ''' + + _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<' + + _TESTS = [{ + 'url': 'http://gorillavid.in/06y9juieqpmi', + 'md5': '5ae4a3580620380619678ee4875893ba', + 'info_dict': { + 'id': '06y9juieqpmi', + 'ext': 'flv', + 'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html', + 'only_matching': True, + }, { + 'url': 'http://daclips.in/3rso4kdn6f9m', + 'md5': '1ad8fd39bb976eeb66004d3a4895f106', + 'info_dict': { + 'id': '3rso4kdn6f9m', + 'ext': 'mp4', + 'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc', + 'thumbnail': 're:http://.*\.jpg', + } + }, { + # video with countdown timeout + 'url': 'http://fastvideo.in/1qmdn1lmsmbw', + 'md5': '8b87ec3f6564a3108a0e8e66594842ba', + 'info_dict': { + 'id': '1qmdn1lmsmbw', + 'ext': 'mp4', + 'title': 'Man of Steel - Trailer', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://realvid.net/ctn2y6p2eviw', + 'md5': 'b2166d2cf192efd6b6d764c18fd3710e', + 'info_dict': { + 'id': 'ctn2y6p2eviw', + 'ext': 'flv', + 'title': 'rdx 1955', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://movpod.in/0wguyyxi1yca', + 'only_matching': True, + }, { + 'url': 'http://filehoot.com/3ivfabn7573c.html', + 'info_dict': { + 'id': '3ivfabn7573c', + 'ext': 'mp4', + 'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4', + 'thumbnail': 're:http://.*\.jpg', + } + }, { + 'url': 'http://vidto.me/ku5glz52nqe1.html', + 'info_dict': { + 'id': 'ku5glz52nqe1', + 'ext': 'mp4', + 'title': 'test' + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://%s/%s' % (mobj.group('host'), video_id) + webpage = self._download_webpage(url, video_id) + + if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + + fields = self._hidden_inputs(webpage) + + if fields['op'] == 'download1': + countdown = int_or_none(self._search_regex( + r'(?:[Ww]ait)?\s*(\d+)\s*(?:seconds?)?', + webpage, 'countdown', default=None)) + if countdown: + self._sleep(countdown, video_id) + + post = compat_urllib_parse.urlencode(encode_dict(fields)) + + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + + webpage = self._download_webpage(req, video_id, 'Downloading video page') + + title = (self._search_regex( + [r'style="z-index: [0-9]+;">([^<]+)', + r'([^<]+)', + r'>Watch (.+) ', + r'

([^<]+)

'], + webpage, 'title', default=None) or self._og_search_title(webpage)).strip() + video_url = self._search_regex( + [r'file\s*:\s*["\'](http[^"\']+)["\'],', + r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'], + webpage, 'file url') + thumbnail = self._search_regex( + r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None) + + formats = [{ + 'format_id': 'sd', + 'url': video_url, + 'quality': 1, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + }