From bb1cd2bea1aa36bdcc0a194ba546ccc62757d4c5 Mon Sep 17 00:00:00 2001 From: Sergey M Date: Tue, 4 Feb 2014 20:40:27 +0700 Subject: [PATCH 1/2] [mooshare] Add support for mooshare.biz (Closes #2149) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/mooshare.py | 114 +++++++++++++++++++++++++++++++ 2 files changed, 115 insertions(+) create mode 100644 youtube_dl/extractor/mooshare.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index a8d5a9cb8..ae702240b 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -127,6 +127,7 @@ from .mixcloud import MixcloudIE from .mpora import MporaIE from .mofosex import MofosexIE +from .mooshare import MooshareIE from .mtv import ( MTVIE, MTVIggyIE, diff --git a/youtube_dl/extractor/mooshare.py b/youtube_dl/extractor/mooshare.py new file mode 100644 index 000000000..909d21a99 --- /dev/null +++ b/youtube_dl/extractor/mooshare.py @@ -0,0 +1,114 @@ +from __future__ import unicode_literals + +import re +import time + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_request, + compat_urllib_parse, +) + + +class MooshareIE(InfoExtractor): + IE_NAME = 'mooshare' + IE_DESC = 'Mooshare.biz' + _VALID_URL = r'http://mooshare\.biz/(?P[\da-z]{12})' + + _TESTS = [ + { + 'url': 'http://mooshare.biz/8dqtk4bjbp8g', + 'md5': '4e14f9562928aecd2e42c6f341c8feba', + 'info_dict': { + 'id': '8dqtk4bjbp8g', + 'ext': 'mp4', + 'title': 'Comedy Football 2011 - (part 1-2)', + 'duration': 893, + }, + }, + { + 'url': 'http://mooshare.biz/aipjtoc4g95j', + 'info_dict': { + 'id': 'aipjtoc4g95j', + 'ext': 'mp4', + 'title': 'Orange Caramel Dashing Through the Snow', + 'duration': 212, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage(url, video_id, 'Downloading page') + + if re.search(r'>Video Not Found or Deleted<', page) is not None: + raise ExtractorError(u'Video %s does not exist' % video_id, expected=True) + + hash_key = self._html_search_regex(r'', page, 'hash') + title = self._html_search_regex(r'(?m)
\s*

Watch ([^<]+)

', page, 'title') + + download_form = { + 'op': 'download1', + 'id': video_id, + 'hash': hash_key, + } + + request = compat_urllib_request.Request( + 'http://mooshare.biz/8dqtk4bjbp8g', compat_urllib_parse.urlencode(download_form)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + + self.to_screen('%s: Waiting for timeout' % video_id) + time.sleep(5) + + video_page = self._download_webpage(request, video_id, 'Downloading video page') + + thumbnail = self._html_search_regex(r'image:\s*"([^"]+)",', video_page, 'thumbnail', fatal=False) + duration_str = self._html_search_regex(r'duration:\s*"(\d+)",', video_page, 'duration', fatal=False) + duration = int(duration_str) if duration_str is not None else None + + formats = [] + + # SD video + mobj = re.search(r'(?m)file:\s*"(?P[^"]+)",\s*provider:', video_page) + if mobj is not None: + formats.append({ + 'url': mobj.group('url'), + 'format_id': 'sd', + 'format': 'SD', + }) + + # HD video + mobj = re.search(r'\'hd-2\': { file: \'(?P[^\']+)\' },', video_page) + if mobj is not None: + formats.append({ + 'url': mobj.group('url'), + 'format_id': 'hd', + 'format': 'HD', + }) + + # rtmp video + mobj = re.search(r'(?m)file: "(?P[^"]+)",\s*streamer: "(?Prtmp://[^"]+)",', video_page) + if mobj is not None: + formats.append({ + 'url': mobj.group('rtmpurl'), + 'play_path': mobj.group('playpath'), + 'rtmp_live': False, + 'ext': 'mp4', + 'format_id': 'rtmp', + 'format': 'HD', + }) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + } From 3c493256584fa5563df1e7963a40cb82ba1d1d01 Mon Sep 17 00:00:00 2001 From: "Sergey M." Date: Tue, 4 Feb 2014 21:31:25 +0700 Subject: [PATCH 2/2] [lifenews] Fix video URL extraction (Closes #2302) --- youtube_dl/extractor/lifenews.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/lifenews.py b/youtube_dl/extractor/lifenews.py index 4e4035b76..051259857 100644 --- a/youtube_dl/extractor/lifenews.py +++ b/youtube_dl/extractor/lifenews.py @@ -31,7 +31,7 @@ def _real_extract(self, url): webpage = self._download_webpage('http://lifenews.ru/mobile/news/%s' % video_id, video_id, 'Downloading page') video_url = self._html_search_regex( - r'', webpage, 'video URL') + r'', webpage, 'video URL') thumbnail = self._html_search_regex( r'', webpage, 'video thumbnail')