From 98703c7fbfcf06348220aa63f9422cdd792cfe1a Mon Sep 17 00:00:00 2001 From: Haricharan Padmanaban Date: Sun, 14 Sep 2014 23:14:00 -0500 Subject: [PATCH] Einthusan Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/einthusan.py | 54 +++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+) create mode 100644 youtube_dl/extractor/einthusan.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index de6e8ee30f..7f0736ee82 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -77,6 +77,7 @@ from .dropbox import DropboxIE from .ebaumsworld import EbaumsWorldIE from .ehow import EHowIE from .eighttracks import EightTracksIE +from .einthusan import EinthusanIE from .eitb import EitbIE from .ellentv import ( EllenTVIE, diff --git a/youtube_dl/extractor/einthusan.py b/youtube_dl/extractor/einthusan.py new file mode 100644 index 0000000000..712368fafd --- /dev/null +++ b/youtube_dl/extractor/einthusan.py @@ -0,0 +1,54 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class EinthusanIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?einthusan\.com/movies/watch.php\?(.*)?id=(?P[0-9]+).*?' + _TESTS = [ + { + 'url': 'http://www.einthusan.com/movies/watch.php?hindimoviesonline=Ek+Villain&lang=hindi&id=2447', + 'md5': 'af244f4458cd667205e513d75da5b8b1', + 'info_dict': { + 'id': '2447', + 'ext': 'mp4', + 'title': 'Ek Villain', + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, + { + 'url': 'http://www.einthusan.com/movies/watch.php?id=1671', + 'md5': 'ef63c7a803e22315880ed182c10d1c5c', + 'info_dict': { + 'id': '1671', + 'ext': 'mp4', + 'title': 'Soodhu Kavvuum', + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + video_title = self._html_search_regex(r'''

(.*?)

''', webpage, 'title') + + video_url = self._html_search_regex( + r'''(?s)jwplayer\("mediaplayer"\)\.setup\({.*?'file': '([^']+)'.*?}\);''', webpage, 'video url') + + thumb_rel_url = self._html_search_regex( + r'''''', webpage, "thumbnail url") + thumb_abs_url = re.sub('\.\.', 'http://www.einthusan.com', thumb_rel_url) + + return { + 'id': video_id, + 'ext': 'mp4', + 'title': video_title, + 'url': video_url, + 'thumbnail': thumb_abs_url, + }