From cbf46c737c3f4156dee019b70521dcd3194877ac Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 21:11:47 +0200 Subject: [PATCH] Move XVideos IE into its own file (and simplify it a bit) --- youtube_dl/InfoExtractors.py | 44 +-------------------------------- youtube_dl/extractor/xvideos.py | 43 ++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+), 43 deletions(-) create mode 100644 youtube_dl/extractor/xvideos.py diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 789fd147c5..8fcd19ca21 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -37,54 +37,12 @@ from .extractor.statigram import StatigramIE from .extractor.photobucket import PhotobucketIE from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE from .extractor.vimeo import VimeoIE +from .extractor.xvideos import XVideosIE from .extractor.yahoo import YahooIE, YahooSearchIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE from .extractor.zdf import ZDFIE -class XVideosIE(InfoExtractor): - """Information extractor for xvideos.com""" - - _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' - IE_NAME = u'xvideos' - - 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) - - webpage = self._download_webpage(url, video_id) - - self.report_extraction(video_id) - - # Extract video URL - video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&', - webpage, u'video URL')) - - # Extract title - video_title = self._html_search_regex(r'(.*?)\s+-\s+XVID', - webpage, u'title') - - # Extract video thumbnail - video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', - webpage, u'thumbnail', fatal=False) - - info = { - 'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': None, - 'title': video_title, - 'ext': 'flv', - 'thumbnail': video_thumbnail, - 'description': None, - } - - return [info] - - - class InfoQIE(InfoExtractor): """Information extractor for infoq.com""" diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py new file mode 100644 index 0000000000..8b3cb3930d --- /dev/null +++ b/youtube_dl/extractor/xvideos.py @@ -0,0 +1,43 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, +) + + +class XVideosIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1) + + webpage = self._download_webpage(url, video_id) + + self.report_extraction(video_id) + + # Extract video URL + video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&', + webpage, u'video URL')) + + # Extract title + video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID', + webpage, u'title') + + # Extract video thumbnail + video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', + webpage, u'thumbnail', fatal=False) + + info = { + 'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': 'flv', + 'thumbnail': video_thumbnail, + 'description': None, + } + + return [info]