X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fliveleak.py;h=c7de65353e616dc0d5f2ee1b0128c059d6f4f933;hb=ec85ded83cbfa652ba94cb080aab52d8b270212a;hp=b04be1e8cfda94addca26a1d1e3731ce61519dc1;hpb=2f15832f569834a37ac3ee6140a3b997407c04cd;p=youtube-dl diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py index b04be1e8c..c7de65353 100644 --- a/youtube_dl/extractor/liveleak.py +++ b/youtube_dl/extractor/liveleak.py @@ -8,26 +8,28 @@ from ..utils import int_or_none class LiveLeakIE(InfoExtractor): - _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P[\w_]+)(?:.*)' + _VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P[\w_]+)(?:.*)' _TESTS = [{ 'url': 'http://www.liveleak.com/view?i=757_1364311680', - 'md5': '0813c2430bea7a46bf13acf3406992f4', + 'md5': '50f79e05ba149149c1b4ea961223d5b3', 'info_dict': { 'id': '757_1364311680', - 'ext': 'mp4', + 'ext': 'flv', 'description': 'extremely bad day for this guy..!', 'uploader': 'ljfriel2', - 'title': 'Most unlucky car accident' + 'title': 'Most unlucky car accident', + 'thumbnail': r're:^https?://.*\.jpg$' } }, { 'url': 'http://www.liveleak.com/view?i=f93_1390833151', - 'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf', + 'md5': 'b13a29626183c9d33944e6a04f41aafc', 'info_dict': { 'id': 'f93_1390833151', 'ext': 'mp4', 'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.', 'uploader': 'ARD_Stinkt', 'title': 'German Television does first Edward Snowden Interview (ENGLISH)', + 'thumbnail': r're:^https?://.*\.jpg$' } }, { 'url': 'http://www.liveleak.com/view?i=4f7_1392687779', @@ -40,11 +42,46 @@ class LiveLeakIE(InfoExtractor): 'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck', 'age_limit': 18, } + }, { + # Covers https://github.com/rg3/youtube-dl/pull/5983 + 'url': 'http://www.liveleak.com/view?i=801_1409392012', + 'md5': '0b3bec2d888c20728ca2ad3642f0ef15', + 'info_dict': { + 'id': '801_1409392012', + 'ext': 'mp4', + 'description': 'Happened on 27.7.2014. \r\nAt 0:53 you can see people still swimming at near beach.', + 'uploader': 'bony333', + 'title': 'Crazy Hungarian tourist films close call waterspout in Croatia', + 'thumbnail': r're:^https?://.*\.jpg$' + } + }, { + # Covers https://github.com/rg3/youtube-dl/pull/10664#issuecomment-247439521 + 'url': 'http://m.liveleak.com/view?i=763_1473349649', + 'add_ie': ['Youtube'], + 'info_dict': { + 'id': '763_1473349649', + 'ext': 'mp4', + 'title': 'Reporters and public officials ignore epidemic of black on asian violence in Sacramento | Colin Flaherty', + 'description': 'Colin being the warrior he is and showing the injustice Asians in Sacramento are being subjected to.', + 'uploader': 'Ziz', + 'upload_date': '20160908', + 'uploader_id': 'UCEbta5E_jqlZmEJsriTEtnw' + }, + 'params': { + 'skip_download': True, + }, }] + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r']+src="https?://(?:\w+\.)?liveleak\.com/ll_embed\?(?:.*?)i=(?P[\w_]+)(?:.*)', + webpage) + if mobj: + return 'http://www.liveleak.com/view?i=%s' % mobj.group('id') + def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip() @@ -54,6 +91,7 @@ class LiveLeakIE(InfoExtractor): age_limit = int_or_none(self._search_regex( r'you confirm that you are ([0-9]+) years and over.', webpage, 'age limit', default=None)) + video_thumbnail = self._og_search_thumbnail(webpage) sources_raw = self._search_regex( r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None) @@ -65,7 +103,7 @@ class LiveLeakIE(InfoExtractor): else: # Maybe an embed? embed_url = self._search_regex( - r']+src="(http://www.prochan.com/embed\?[^"]+)"', + r']+src="(https?://(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"', webpage, 'embed URL') return { '_type': 'url_transparent', @@ -81,9 +119,23 @@ class LiveLeakIE(InfoExtractor): sources = json.loads(sources_json) formats = [{ + 'format_id': '%s' % i, 'format_note': s.get('label'), 'url': s['file'], - } for s in sources] + } for i, s in enumerate(sources)] + + for i, s in enumerate(sources): + # Removing '.h264_*.mp4' gives the raw video, which is essentially + # the same video without the LiveLeak logo at the top (see + # https://github.com/rg3/youtube-dl/pull/4768) + orig_url = re.sub(r'\.h264_.+?\.mp4', '', s['file']) + if s['file'] != orig_url: + formats.append({ + 'format_id': 'original-%s' % i, + 'format_note': s.get('label'), + 'url': orig_url, + 'preference': 1, + }) self._sort_formats(formats) return { @@ -93,4 +145,5 @@ class LiveLeakIE(InfoExtractor): 'uploader': video_uploader, 'formats': formats, 'age_limit': age_limit, + 'thumbnail': video_thumbnail, }