Imported Upstream version 2015.11.10

[youtubedl] / youtube_dl / extractor / liveleak.py

diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py
index b04be1e8cfda94addca26a1d1e3731ce61519dc1..857edfde263196d9bf2811568cc9f9de90eed92b 100644 (file)
--- a/youtube_dl/extractor/liveleak.py
+++ b/youtube_dl/extractor/liveleak.py
@@ -8,20 +8,20 @@ from ..utils import int_or_none
 
 
 class LiveLeakIE(InfoExtractor):
 
 
 class LiveLeakIE(InfoExtractor):

-    _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
+    _VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)'

     _TESTS = [{
         'url': 'http://www.liveleak.com/view?i=757_1364311680',
     _TESTS = [{
         'url': 'http://www.liveleak.com/view?i=757_1364311680',

-        'md5': '0813c2430bea7a46bf13acf3406992f4',
+        'md5': '50f79e05ba149149c1b4ea961223d5b3',

         'info_dict': {
             'id': '757_1364311680',
         'info_dict': {
             'id': '757_1364311680',

-            'ext': 'mp4',
+            'ext': 'flv',

             'description': 'extremely bad day for this guy..!',
             'uploader': 'ljfriel2',
             'title': 'Most unlucky car accident'
         }
     }, {
         'url': 'http://www.liveleak.com/view?i=f93_1390833151',
             'description': 'extremely bad day for this guy..!',
             'uploader': 'ljfriel2',
             'title': 'Most unlucky car accident'
         }
     }, {
         'url': 'http://www.liveleak.com/view?i=f93_1390833151',

-        'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
+        'md5': 'b13a29626183c9d33944e6a04f41aafc',

         'info_dict': {
             'id': 'f93_1390833151',
             'ext': 'mp4',
         'info_dict': {
             'id': 'f93_1390833151',
             'ext': 'mp4',


@@ -40,11 +40,21 @@ class LiveLeakIE(InfoExtractor):
             'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
             'age_limit': 18,
         }
             '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'
+        }

     }]
 
     def _real_extract(self, url):
     }]
 
     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()
         webpage = self._download_webpage(url, video_id)
 
         video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()


@@ -81,9 +91,22 @@ class LiveLeakIE(InfoExtractor):
         sources = json.loads(sources_json)
 
         formats = [{
         sources = json.loads(sources_json)
 
         formats = [{

+            'format_id': '%s' % i,

             'format_note': s.get('label'),
             'url': s['file'],
             '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 {
         self._sort_formats(formats)
 
         return {