Prepare to release.

[youtubedl] / youtube_dl / extractor / liveleak.py

diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py
index b04be1e8cfda94addca26a1d1e3731ce61519dc1..c54519636d064ea7a0d9b0ac543c5ec190f60306 100644 (file)
--- a/youtube_dl/extractor/liveleak.py
+++ b/youtube_dl/extractor/liveleak.py
@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import json

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor


@@ -8,7 +7,7 @@ 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',
         'md5': '0813c2430bea7a46bf13acf3406992f4',
     _TESTS = [{
         'url': 'http://www.liveleak.com/view?i=757_1364311680',
         'md5': '0813c2430bea7a46bf13acf3406992f4',


@@ -17,7 +16,8 @@ class LiveLeakIE(InfoExtractor):
             'ext': 'mp4',
             'description': 'extremely bad day for this guy..!',
             'uploader': 'ljfriel2',
             'ext': 'mp4',
             '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',
         }
     }, {
         'url': 'http://www.liveleak.com/view?i=f93_1390833151',


@@ -28,8 +28,10 @@ class LiveLeakIE(InfoExtractor):
             '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)',
             '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$'

         }
     }, {
         }
     }, {

+        # Prochan embed

         'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
         'md5': '42c6d97d54f1db107958760788c5f48f',
         'info_dict': {
         'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
         'md5': '42c6d97d54f1db107958760788c5f48f',
         'info_dict': {


@@ -39,12 +41,49 @@ class LiveLeakIE(InfoExtractor):
             'uploader': 'CapObveus',
             'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
             'age_limit': 18,
             'uploader': 'CapObveus',
             'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
             'age_limit': 18,

+        },
+        'skip': 'Video is dead',
+    }, {
+        # Covers https://github.com/rg3/youtube-dl/pull/5983
+        # Multiple resolutions
+        'url': 'http://www.liveleak.com/view?i=801_1409392012',
+        'md5': 'c3a449dbaca5c0d1825caecd52a57d7b',
+        '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'<iframe[^>]+src="https?://(?:\w+\.)?liveleak\.com/ll_embed\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)',
+            webpage)
+        if mobj:
+            return 'http://www.liveleak.com/view?i=%s' % mobj.group('id')
+

     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()


@@ -54,43 +93,40 @@ 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))
         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)
+
+        entries = self._parse_html5_media_entries(url, webpage, video_id)
+        if not entries:
+            # Maybe an embed?
+            embed_url = self._search_regex(
+                r'<iframe[^>]+src="((?:https?:)?//(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"',
+                webpage, 'embed URL')
+            return {
+                '_type': 'url_transparent',
+                'url': embed_url,
+                'id': video_id,
+                'title': video_title,
+                'description': video_description,
+                'uploader': video_uploader,
+                'age_limit': age_limit,
+            }

 
 

-        sources_raw = self._search_regex(
-            r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
-        if sources_raw is None:
-            alt_source = self._search_regex(
-                r'(file: ".*?"),', webpage, 'video URL', default=None)
-            if alt_source:
-                sources_raw = '[{ %s}]' % alt_source
-            else:
-                # Maybe an embed?
-                embed_url = self._search_regex(
-                    r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"',
-                    webpage, 'embed URL')
-                return {
-                    '_type': 'url_transparent',
-                    'url': embed_url,
-                    'id': video_id,
-                    'title': video_title,
-                    'description': video_description,
-                    'uploader': video_uploader,
-                    'age_limit': age_limit,
-                }
+        info_dict = entries[0]

 
 

-        sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
-        sources = json.loads(sources_json)
+        for a_format in info_dict['formats']:
+            if not a_format.get('height'):
+                a_format['height'] = self._search_regex(
+                    r'([0-9]+)p\.mp4', a_format['url'], 'height label', default=None)

 
 

-        formats = [{
-            'format_note': s.get('label'),
-            'url': s['file'],
-        } for s in sources]
-        self._sort_formats(formats)
+        self._sort_formats(info_dict['formats'])

 
 

-        return {
+        info_dict.update({

             'id': video_id,
             'title': video_title,
             'description': video_description,
             'uploader': video_uploader,
             'id': video_id,
             'title': video_title,
             'description': video_description,
             'uploader': video_uploader,

-            'formats': formats,

             'age_limit': age_limit,
             'age_limit': age_limit,

-        }
+            'thumbnail': video_thumbnail,
+        })
+
+        return info_dict