Merge pull request #1 from e7appew/python3

[youtubedl] / youtube_dl / extractor / vrt.py

diff --git a/youtube_dl/extractor/vrt.py b/youtube_dl/extractor/vrt.py
index 2b6bae89bd2a450c9babe1ea77e299b806b752c1..bec7ab327008803f8609ea0e78e7d70577556940 100644 (file)
--- a/youtube_dl/extractor/vrt.py
+++ b/youtube_dl/extractor/vrt.py
@@ -4,7 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..utils import float_or_none
+from ..utils import (
+    determine_ext,
+    float_or_none,
+)

 
 
 class VRTIE(InfoExtractor):
 
 
 class VRTIE(InfoExtractor):


@@ -22,7 +25,8 @@ class VRTIE(InfoExtractor):
                 'timestamp': 1414271750.949,
                 'upload_date': '20141025',
                 'duration': 929,
                 'timestamp': 1414271750.949,
                 'upload_date': '20141025',
                 'duration': 929,

-            }
+            },
+            'skip': 'HTTP Error 404: Not Found',

         },
         # sporza.be
         {
         },
         # sporza.be
         {


@@ -36,7 +40,8 @@ class VRTIE(InfoExtractor):
                 'timestamp': 1413835980.560,
                 'upload_date': '20141020',
                 'duration': 3238,
                 'timestamp': 1413835980.560,
                 'upload_date': '20141020',
                 'duration': 3238,

-            }
+            },
+            'skip': 'HTTP Error 404: Not Found',

         },
         # cobra.be
         {
         },
         # cobra.be
         {


@@ -50,11 +55,39 @@ class VRTIE(InfoExtractor):
                 'timestamp': 1413967500.494,
                 'upload_date': '20141022',
                 'duration': 661,
                 'timestamp': 1413967500.494,
                 'upload_date': '20141022',
                 'duration': 661,

-            }
+            },
+            'skip': 'HTTP Error 404: Not Found',
+        },
+        {
+            # YouTube video
+            'url': 'http://deredactie.be/cm/vrtnieuws/videozone/nieuws/cultuurenmedia/1.2622957',
+            'md5': 'b8b93da1df1cea6c8556255a796b7d61',
+            'info_dict': {
+                'id': 'Wji-BZ0oCwg',
+                'ext': 'mp4',
+                'title': 'ROGUE ONE: A STAR WARS STORY Official Teaser Trailer',
+                'description': 'md5:8e468944dce15567a786a67f74262583',
+                'uploader': 'Star Wars',
+                'uploader_id': 'starwars',
+                'upload_date': '20160407',
+            },
+            'add_ie': ['Youtube'],

         },
         {
             'url': 'http://cobra.canvas.be/cm/cobra/videozone/rubriek/film-videozone/1.2377055',
         },
         {
             'url': 'http://cobra.canvas.be/cm/cobra/videozone/rubriek/film-videozone/1.2377055',

-            'only_matching': True,
+            'md5': '',
+            'info_dict': {
+                'id': '2377055',
+                'ext': 'mp4',
+                'title': 'Cafe Derby',
+                'description': 'Lenny Van Wesemael debuteert met de langspeelfilm Café Derby. Een waar gebeurd maar ook verzonnen verhaal.',
+                'upload_date': '20150626',
+                'timestamp': 1435305240.769,
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            }

         }
     ]
 
         }
     ]
 


@@ -66,7 +99,17 @@ class VRTIE(InfoExtractor):
         video_id = self._search_regex(
             r'data-video-id="([^"]+)_[^"]+"', webpage, 'video id', fatal=False)
 
         video_id = self._search_regex(
             r'data-video-id="([^"]+)_[^"]+"', webpage, 'video id', fatal=False)
 

+        src = self._search_regex(
+            r'data-video-src="([^"]+)"', webpage, 'video src', default=None)
+
+        video_type = self._search_regex(
+            r'data-video-type="([^"]+)"', webpage, 'video type', default=None)
+
+        if video_type == 'YouTubeVideo':
+            return self.url_result(src, 'Youtube')
+

         formats = []
         formats = []

+

         mobj = re.search(
             r'data-video-iphone-server="(?P<server>[^"]+)"\s+data-video-iphone-path="(?P<path>[^"]+)"',
             webpage)
         mobj = re.search(
             r'data-video-iphone-server="(?P<server>[^"]+)"\s+data-video-iphone-path="(?P<path>[^"]+)"',
             webpage)


@@ -74,11 +117,41 @@ class VRTIE(InfoExtractor):
             formats.extend(self._extract_m3u8_formats(
                 '%s/%s' % (mobj.group('server'), mobj.group('path')),
                 video_id, 'mp4', m3u8_id='hls', fatal=False))
             formats.extend(self._extract_m3u8_formats(
                 '%s/%s' % (mobj.group('server'), mobj.group('path')),
                 video_id, 'mp4', m3u8_id='hls', fatal=False))

-        mobj = re.search(r'data-video-src="(?P<src>[^"]+)"', webpage)
-        if mobj:
-            formats.extend(self._extract_f4m_formats(
-                '%s/manifest.f4m' % mobj.group('src'),
-                video_id, f4m_id='hds', fatal=False))
+
+        if src:
+            if determine_ext(src) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    src, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+                formats.extend(self._extract_f4m_formats(
+                    src.replace('playlist.m3u8', 'manifest.f4m'),
+                    video_id, f4m_id='hds', fatal=False))
+                if 'data-video-geoblocking="true"' not in webpage:
+                    rtmp_formats = self._extract_smil_formats(
+                        src.replace('playlist.m3u8', 'jwplayer.smil'),
+                        video_id, fatal=False)
+                    formats.extend(rtmp_formats)
+                    for rtmp_format in rtmp_formats:
+                        rtmp_format_c = rtmp_format.copy()
+                        rtmp_format_c['url'] = '%s/%s' % (rtmp_format['url'], rtmp_format['play_path'])
+                        del rtmp_format_c['play_path']
+                        del rtmp_format_c['ext']
+                        http_format = rtmp_format_c.copy()
+                        http_format.update({
+                            'url': rtmp_format_c['url'].replace('rtmp://', 'http://').replace('vod.', 'download.').replace('/_definst_/', '/').replace('mp4:', ''),
+                            'format_id': rtmp_format['format_id'].replace('rtmp', 'http'),
+                            'protocol': 'http',
+                        })
+                        rtsp_format = rtmp_format_c.copy()
+                        rtsp_format.update({
+                            'url': rtsp_format['url'].replace('rtmp://', 'rtsp://'),
+                            'format_id': rtmp_format['format_id'].replace('rtmp', 'rtsp'),
+                            'protocol': 'rtsp',
+                        })
+                        formats.extend([http_format, rtsp_format])
+            else:
+                formats.extend(self._extract_f4m_formats(
+                    '%s/manifest.f4m' % src, video_id, f4m_id='hds', fatal=False))

 
         if not formats and 'data-video-geoblocking="true"' in webpage:
             self.raise_geo_restricted('This video is only available in Belgium')
 
         if not formats and 'data-video-geoblocking="true"' in webpage:
             self.raise_geo_restricted('This video is only available in Belgium')