[redtube] move into own file
[youtube-dl] / youtube_dl / InfoExtractors.py
index 801fbff5eed55b141c3478dc41079e186b370ce5..c06ecbe52aad148ce036cd98c74ef1f371b27c78 100755 (executable)
@@ -48,6 +48,7 @@ from .extractor.statigram import StatigramIE
 from .extractor.photobucket import PhotobucketIE
 from .extractor.pornotube import PornotubeIE
 from .extractor.rbmaradio import RBMARadioIE
+from .extractor.redtube import RedTubeIE
 from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
 from .extractor.spiegel import SpiegelIE
 from .extractor.stanfordoc import StanfordOpenClassroomIE
@@ -55,7 +56,9 @@ from .extractor.steam import SteamIE
 from .extractor.ted import TEDIE
 from .extractor.tumblr import TumblrIE
 from .extractor.ustream import UstreamIE
+from .extractor.vbox7 import Vbox7IE
 from .extractor.vimeo import VimeoIE
+from .extractor.vine import VineIE
 from .extractor.worldstarhiphop import WorldStarHipHopIE
 from .extractor.xnxx import XNXXIE
 from .extractor.xvideos import XVideosIE
@@ -100,34 +103,6 @@ from .extractor.zdf import ZDFIE
 
 
 
-class RedTubeIE(InfoExtractor):
-    """Information Extractor for redtube"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
-
-    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('id')
-        video_extension = 'mp4'        
-        webpage = self._download_webpage(url, video_id)
-
-        self.report_extraction(video_id)
-
-        video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">',
-            webpage, u'video URL')
-
-        video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
-            webpage, u'title')
-
-        return [{
-            'id':       video_id,
-            'url':      video_url,
-            'ext':      video_extension,
-            'title':    video_title,
-        }]
-        
 class InaIE(InfoExtractor):
     """Information Extractor for Ina.fr"""
     _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
@@ -189,39 +164,6 @@ class HowcastIE(InfoExtractor):
             'thumbnail': thumbnail,
         }]
 
-class VineIE(InfoExtractor):
-    """Information Extractor for Vine.co"""
-    _VALID_URL = r'(?:https?://)?(?:www\.)?vine\.co/v/(?P<id>\w+)'
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group('id')
-        webpage_url = 'https://vine.co/v/' + video_id
-        webpage = self._download_webpage(webpage_url, video_id)
-
-        self.report_extraction(video_id)
-
-        video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
-            webpage, u'video URL')
-
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
-            webpage, u'title')
-
-        thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)(\?.*?)?"',
-            webpage, u'thumbnail', fatal=False)
-
-        uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
-            webpage, u'uploader', fatal=False, flags=re.DOTALL)
-
-        return [{
-            'id':        video_id,
-            'url':       video_url,
-            'ext':       'mp4',
-            'title':     video_title,
-            'thumbnail': thumbnail,
-            'uploader':  uploader,
-        }]
 
 class FlickrIE(InfoExtractor):
     """Information Extractor for Flickr videos"""
@@ -413,41 +355,6 @@ class HypemIE(InfoExtractor):
             'artist':   artist,
         }]
 
-class Vbox7IE(InfoExtractor):
-    """Information Extractor for Vbox7"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)'
-
-    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(1)
-
-        redirect_page, urlh = self._download_webpage_handle(url, video_id)
-        new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
-        redirect_url = urlh.geturl() + new_location
-        webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
-
-        title = self._html_search_regex(r'<title>(.*)</title>',
-            webpage, u'title').split('/')[0].strip()
-
-        ext = "flv"
-        info_url = "http://vbox7.com/play/magare.do"
-        data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id})
-        info_request = compat_urllib_request.Request(info_url, data)
-        info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage')
-        if info_response is None:
-            raise ExtractorError(u'Unable to extract the media url')
-        (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
-
-        return [{
-            'id':        video_id,
-            'url':       final_url,
-            'ext':       ext,
-            'title':     title,
-            'thumbnail': thumbnail_url,
-        }]
 
 
 def gen_extractors():