From 3898c8a7b2835b1632ef0e34481bdf5e006cee2b Mon Sep 17 00:00:00 2001 From: yac Date: Fri, 7 Nov 2014 23:19:26 +0100 Subject: [PATCH] [FreeVideo] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/freevideo.py | 49 +++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+) create mode 100644 youtube_dl/extractor/freevideo.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 3c1807f158..db76e88708 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -127,6 +127,7 @@ ) from .freesound import FreesoundIE from .freespeech import FreespeechIE +from .freevideo import FreeVideoIE from .funnyordie import FunnyOrDieIE from .gamekings import GamekingsIE from .gameone import ( diff --git a/youtube_dl/extractor/freevideo.py b/youtube_dl/extractor/freevideo.py new file mode 100644 index 0000000000..f9716c4c82 --- /dev/null +++ b/youtube_dl/extractor/freevideo.py @@ -0,0 +1,49 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + + +class FreeVideoIE(InfoExtractor): + _VALID_URL = r'^http://www.freevideo.cz/vase-videa/(?P[^.]+)\.html$' + + _TEST = { + 'url': 'http://www.freevideo.cz/vase-videa/vysukany-zadecek-22033.html', + 'file': 'vysukany-zadecek-22033.mp4', + 'info_dict': { + "title": "vysukany-zadecek-22033", + "age_limit": 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError('Invalid search query "%s"' % query) + + video_id = mobj.group('videoid') + + # Get webpage content + webpage = self._download_webpage(url, video_id) + + age_limit = self._rta_search(webpage) + if age_limit == 0: + # interpret 0 as mis-detection since this site is adult-content only. + # However, if we get non-0, assume the rtalabel started giving proper + # results + age_limit = 18 + + url = re.search(r'\s+url: "(http://[a-z0-9-]+.cdn.freevideo.cz/stream/.*/video.mp4)"', webpage) + if url is None: + raise ExtractorError('ERROR: unable to extract video url') + + return { + 'id': video_id, + 'url': url.groups()[0], + 'title': video_id, + 'age_limit': age_limit, + }