From 0a899a1448328648927e18e43c6e2274d2706396 Mon Sep 17 00:00:00 2001 From: Vignesh Venkat Date: Sat, 9 Jan 2016 15:31:50 -0800 Subject: [PATCH] [Bigflix] Add new extractor for bigflix.com Add an IE to support bigflix.com. It uses some sort of silverlight plugin whose video url is being populated using base64 encoded flashvars. So it is quite straightforward to extract. --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/bigflix.py | 42 ++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) create mode 100644 youtube_dl/extractor/bigflix.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index a9d23b8f4..40c42d4d2 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -61,6 +61,7 @@ from .behindkink import BehindKinkIE from .beatportpro import BeatportProIE from .bet import BetIE +from .bigflix import BigflixIE from .bild import BildIE from .bilibili import BiliBiliIE from .bleacherreport import ( diff --git a/youtube_dl/extractor/bigflix.py b/youtube_dl/extractor/bigflix.py new file mode 100644 index 000000000..aeea1a002 --- /dev/null +++ b/youtube_dl/extractor/bigflix.py @@ -0,0 +1,42 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from base64 import b64decode + +from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote + + +class BigflixIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.*/(?P[0-9]+)' + _TEST = { + 'url': 'http://www.bigflix.com/Hindi-movies/Action-movies/Singham-Returns/16537', + 'md5': 'ec76aa9b1129e2e5b301a474e54fab74', + 'info_dict': { + 'id': '16537', + 'ext': 'mp4', + 'title': 'Singham Returns', + 'description': 'md5:3d2ba5815f14911d5cc6a501ae0cf65d', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r']+class=["\']pagetitle["\'][^>]*>(.+?)', + webpage, 'title') + + video_url = b64decode(compat_urllib_parse_unquote(self._search_regex( + r'file=([^&]+)', webpage, 'video url')).encode('ascii')).decode('utf-8') + + description = self._html_search_meta('description', webpage) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'description': description, + }