diff options
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 37 | ||||
| -rw-r--r-- | youtube_dl/extractor/liveleak.py | 44 |
2 files changed, 45 insertions, 36 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 983010234..bcf927252 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -36,6 +36,7 @@ from .extractor.googlesearch import GoogleSearchIE from .extractor.infoq import InfoQIE from .extractor.justintv import JustinTVIE from .extractor.keek import KeekIE +from .extractor.liveleak import LiveLeakIE from .extractor.metacafe import MetacafeIE from .extractor.mixcloud import MixcloudIE from .extractor.mtv import MTVIE @@ -92,42 +93,6 @@ from .extractor.zdf import ZDFIE -class LiveLeakIE(InfoExtractor): - - _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)' - IE_NAME = u'liveleak' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - video_id = mobj.group('video_id') - - webpage = self._download_webpage(url, video_id) - - video_url = self._search_regex(r'file: "(.*?)",', - webpage, u'video URL') - - video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"', - webpage, u'title').replace('LiveLeak.com -', '').strip() - - video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"', - webpage, u'description', fatal=False) - - video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>', - webpage, u'uploader', fatal=False) - - info = { - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': video_title, - 'description': video_description, - 'uploader': video_uploader - } - - return [info] diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py new file mode 100644 index 000000000..d4b142ea0 --- /dev/null +++ b/youtube_dl/extractor/liveleak.py @@ -0,0 +1,44 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + + +class LiveLeakIE(InfoExtractor): + + _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)' + IE_NAME = u'liveleak' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + + video_id = mobj.group('video_id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._search_regex(r'file: "(.*?)",', + webpage, u'video URL') + + video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"', + webpage, u'title').replace('LiveLeak.com -', '').strip() + + video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"', + webpage, u'description', fatal=False) + + video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>', + webpage, u'uploader', fatal=False) + + info = { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': video_title, + 'description': video_description, + 'uploader': video_uploader + } + + return [info] |