diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 21:10:21 +0200 | 
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 21:10:21 +0200 | 
| commit | 7beb36a52974a2cf7c8b00ba1da339f4f3de3abc (patch) | |
| tree | 76fa90f548feae90457d1ac25dc18731d953ecc3 /youtube_dl/InfoExtractors.py | |
| parent | 153697660dfbc5f510f756e22e30d1ac86d9e612 (diff) | |
Move Collegehumor IE into its own file
Diffstat (limited to 'youtube_dl/InfoExtractors.py')
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 91 | 
1 files changed, 1 insertions, 90 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 1edafb43c..789fd147c 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -22,6 +22,7 @@ from .extractor.ard import ARDIE  from .extractor.arte import ArteTvIE  from .extractor.bliptv import BlipTVIE, BlipTVUserIE  from .extractor.comedycentral import ComedyCentralIE +from .extractor.collegehumor import CollegeHumorIE  from .extractor.dailymotion import DailymotionIE  from .extractor.depositfiles import DepositFilesIE  from .extractor.escapist import EscapistIE @@ -41,96 +42,6 @@ from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, Yo  from .extractor.zdf import ZDFIE - - - - - - - - - - - - - - - - - - - - - - - - - - - -class CollegeHumorIE(InfoExtractor): -    """Information extractor for collegehumor.com""" - -    _WORKING = False -    _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$' -    IE_NAME = u'collegehumor' - -    def report_manifest(self, video_id): -        """Report information extraction.""" -        self.to_screen(u'%s: Downloading XML manifest' % video_id) - -    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('videoid') - -        info = { -            'id': video_id, -            'uploader': None, -            'upload_date': None, -        } - -        self.report_extraction(video_id) -        xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id -        try: -            metaXml = compat_urllib_request.urlopen(xmlUrl).read() -        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: -            raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err)) - -        mdoc = xml.etree.ElementTree.fromstring(metaXml) -        try: -            videoNode = mdoc.findall('./video')[0] -            info['description'] = videoNode.findall('./description')[0].text -            info['title'] = videoNode.findall('./caption')[0].text -            info['thumbnail'] = videoNode.findall('./thumbnail')[0].text -            manifest_url = videoNode.findall('./file')[0].text -        except IndexError: -            raise ExtractorError(u'Invalid metadata XML file') - -        manifest_url += '?hdcore=2.10.3' -        self.report_manifest(video_id) -        try: -            manifestXml = compat_urllib_request.urlopen(manifest_url).read() -        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: -            raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err)) - -        adoc = xml.etree.ElementTree.fromstring(manifestXml) -        try: -            media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] -            node_id = media_node.attrib['url'] -            video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text -        except IndexError as err: -            raise ExtractorError(u'Invalid manifest file') - -        url_pr = compat_urllib_parse_urlparse(manifest_url) -        url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1' - -        info['url'] = url -        info['ext'] = 'f4f' -        return [info] - -  class XVideosIE(InfoExtractor):      """Information extractor for xvideos.com"""  | 
