X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fliveleak.py;h=0a700d663215df27f3553100862e9805e2c9f6ea;hb=1824b4816974bbd8d026ed44185ad888e6fb6d70;hp=dd062a14e736ba84b3aacb9d3bf426bca4c8f86f;hpb=66400c470c36a5cdceec531ebd2cfc52e02d6c53;p=youtube-dl diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py index dd062a14e..0a700d663 100644 --- a/youtube_dl/extractor/liveleak.py +++ b/youtube_dl/extractor/liveleak.py @@ -1,52 +1,63 @@ +from __future__ import unicode_literals + +import json import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) class LiveLeakIE(InfoExtractor): - - _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P[\w_]+)(?:.*)' - IE_NAME = u'liveleak' - _TEST = { - u'url': u'http://www.liveleak.com/view?i=757_1364311680', - u'file': u'757_1364311680.mp4', - u'md5': u'0813c2430bea7a46bf13acf3406992f4', - u'info_dict': { - u"description": u"extremely bad day for this guy..!", - u"uploader": u"ljfriel2", - u"title": u"Most unlucky car accident" + _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P[\w_]+)(?:.*)' + _TESTS = [{ + 'url': 'http://www.liveleak.com/view?i=757_1364311680', + 'file': '757_1364311680.mp4', + 'md5': '0813c2430bea7a46bf13acf3406992f4', + 'info_dict': { + 'description': 'extremely bad day for this guy..!', + 'uploader': 'ljfriel2', + 'title': 'Most unlucky car accident' } - } + }, + { + 'url': 'http://www.liveleak.com/view?i=f93_1390833151', + 'file': 'f93_1390833151.mp4', + 'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf', + 'info_dict': { + 'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.', + 'uploader': 'ARD_Stinkt', + 'title': 'German Television does first Edward Snowden Interview (ENGLISH)', + } + }] 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('video_id') - webpage = self._download_webpage(url, video_id) + sources_raw = self._search_regex( + r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None) + if sources_raw is None: + sources_raw = '[{ %s}]' % ( + self._search_regex(r'(file: ".*?"),', webpage, 'video URL')) - video_url = self._search_regex(r'file: "(.*?)",', - webpage, u'video URL') + sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw) + sources = json.loads(sources_json) - video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip() + formats = [{ + 'format_note': s.get('label'), + 'url': s['file'], + } for s in sources] + self._sort_formats(formats) + video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip() video_description = self._og_search_description(webpage) + video_uploader = self._html_search_regex( + r'By:.*?(\w+)', webpage, 'uploader', fatal=False) - video_uploader = self._html_search_regex(r'By:.*?(\w+)', - webpage, u'uploader', fatal=False) - - info = { - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', + return { + 'id': video_id, 'title': video_title, 'description': video_description, - 'uploader': video_uploader + 'uploader': video_uploader, + 'formats': formats, } - - return [info]