From: Sergey M․ Date: Sun, 10 Jan 2016 04:31:36 +0000 (+0600) Subject: [bigflix] Extract all formats X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=6e99d5762a844b44cad4cae144045ed0537c084b;p=youtube-dl [bigflix] Extract all formats --- diff --git a/youtube_dl/extractor/bigflix.py b/youtube_dl/extractor/bigflix.py index aeea1a002..b7e498436 100644 --- a/youtube_dl/extractor/bigflix.py +++ b/youtube_dl/extractor/bigflix.py @@ -1,15 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals -from base64 import b64decode +import base64 +import re 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 = { + _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P[0-9]+)' + _TESTS = [{ 'url': 'http://www.bigflix.com/Hindi-movies/Action-movies/Singham-Returns/16537', 'md5': 'ec76aa9b1129e2e5b301a474e54fab74', 'info_dict': { @@ -18,7 +19,20 @@ class BigflixIE(InfoExtractor): 'title': 'Singham Returns', 'description': 'md5:3d2ba5815f14911d5cc6a501ae0cf65d', } - } + }, { + # multiple formats + 'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070', + 'info_dict': { + 'id': '16070', + 'ext': 'mp4', + 'title': 'Madarasapatinam', + 'description': 'md5:63b9b8ed79189c6f0418c26d9a3452ca', + 'formats': 'mincount:2', + }, + 'params': { + 'skip_download': True, + } + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -29,14 +43,28 @@ class BigflixIE(InfoExtractor): 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') + def decode_url(quoted_b64_url): + return base64.b64decode(compat_urllib_parse_unquote( + quoted_b64_url)).encode('ascii').decode('utf-8') + + formats = [{ + 'url': decode_url(encoded_url), + 'format_id': '%sp' % height, + 'height': int(height), + } for height, encoded_url in re.findall( + r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage)] + + if not formats: + formats.append({ + 'url': decode_url(self._search_regex( + r'file=([^&]+)', webpage, 'video url')), + }) description = self._html_search_meta('description', webpage) return { 'id': video_id, 'title': title, - 'url': video_url, 'description': description, + 'formats': formats }