From 1183b85f50478f6e57e51d2af06e0f6730bb6cb1 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 22:13:32 +0200 Subject: [PATCH] [pornotube] move into own file --- youtube_dl/InfoExtractors.py | 35 +------------------------- youtube_dl/extractor/pornotube.py | 41 +++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+), 34 deletions(-) create mode 100644 youtube_dl/extractor/pornotube.py diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 51b3a0fad..73b3825a0 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -41,6 +41,7 @@ from .extractor.nba import NBAIE from .extractor.statigram import StatigramIE from .extractor.photobucket import PhotobucketIE +from .extractor.pornotube import PornotubeIE from .extractor.rbmaradio import RBMARadioIE from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE from .extractor.stanfordoc import StanfordOpenClassroomIE @@ -79,40 +80,6 @@ -class PornotubeIE(InfoExtractor): - """Information extractor for pornotube.com.""" - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P[0-9]+))?(/m/(?P[0-9]+))(/(?P.+))$' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - video_id = mobj.group('videoid') - video_title = mobj.group('title') - - # Get webpage content - webpage = self._download_webpage(url, video_id) - - # Get the video URL - VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' - video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url') - video_url = compat_urllib_parse.unquote(video_url) - - #Get the uploaded date - VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' - upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False) - if upload_date: upload_date = unified_strdate(upload_date) - - info = {'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': upload_date, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv'} - - return [info] class YouJizzIE(InfoExtractor): """Information extractor for youjizz.com.""" diff --git a/youtube_dl/extractor/pornotube.py b/youtube_dl/extractor/pornotube.py new file mode 100644 index 000000000..0adb40db0 --- /dev/null +++ b/youtube_dl/extractor/pornotube.py @@ -0,0 +1,41 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + + unified_strdate, +) + + +class PornotubeIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + + video_id = mobj.group('videoid') + video_title = mobj.group('title') + + # Get webpage content + webpage = self._download_webpage(url, video_id) + + # Get the video URL + VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' + video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url') + video_url = compat_urllib_parse.unquote(video_url) + + #Get the uploaded date + VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' + upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False) + if upload_date: upload_date = unified_strdate(upload_date) + + info = {'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': upload_date, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv'} + + return [info]