Merge pull request #2813 from dstftw/test-real-download-improvement

Improve download mechanism when Range HTTP header is ignored

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index e389acc6abe086f9a1253c0f39d13a2b62a48a65..4b53bef5c93694b23c0f9c2c00fdc9a710b0cc66 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -210,6 +210,7 @@ from .ringtv import RingTVIE
 from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
+from .rtbf import RTBFIE
 from .rtlnow import RTLnowIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE

diff --git a/youtube_dl/extractor/fivemin.py b/youtube_dl/extractor/fivemin.py
index b596bf587b77045c1b16bba932df3e3823b9ebef..3a50bab5c9bd04c9d176a88be080033368fe46c7 100644 (file)
--- a/youtube_dl/extractor/fivemin.py
+++ b/youtube_dl/extractor/fivemin.py
@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     compat_str,
     compat_urllib_parse,
+    ExtractorError,
 )
 
 
@@ -58,9 +59,17 @@ class FiveMinIE(InfoExtractor):
             'isPlayerSeed': 'true',
             'url': embed_url,
         })
-        info = self._download_json(
+        response = self._download_json(
             'https://syn.5min.com/handlers/SenseHandler.ashx?' + query,
-            video_id)['binding'][0]
+            video_id)
+        if not response['success']:
+            err_msg = response['errorMessage']
+            if err_msg == 'ErrorVideoUserNotGeo':
+                msg = 'Video not available from your location'
+            else:
+                msg = 'Aol said: %s' % err_msg
+            raise ExtractorError(msg, expected=True, video_id=video_id)
+        info = response['binding'][0]
 
         second_id = compat_str(int(video_id[:-2]) + 1)
         formats = []

diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py
new file mode 100644 (file)
index 0000000..205f8a1
--- /dev/null
+++ b/youtube_dl/extractor/rtbf.py
@@ -0,0 +1,49 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class RTBFIE(InfoExtractor):
+    _VALID_URL = r'https?://www.rtbf.be/video/[^\?]+\?id=(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
+        'md5': '799f334ddf2c0a582ba80c44655be570',
+        'info_dict': {
+            'id': '1921274',
+            'ext': 'mp4',
+            'title': 'Les Diables au coeur (épisode 2)',
+            'description': 'Football - Diables Rouges',
+            'duration': 3099,
+            'timestamp': 1398456336,
+            'upload_date': '20140425',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id)
+
+        data = json.loads(self._html_search_regex(
+            r'<div class="js-player-embed" data-video="([^"]+)"', page, 'data video'))['data']
+
+        video_url = data.get('downloadUrl') or data.get('url')
+
+        if data['provider'].lower() == 'youtube':
+            return self.url_result(video_url, 'Youtube')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': data['title'],
+            'description': data.get('description') or data.get('subtitle'),
+            'thumbnail': data['thumbnail']['large'],
+            'duration': data.get('duration') or data.get('realDuration'),
+            'timestamp': data['created'],
+            'view_count': data['viewCount'],
+        }

diff --git a/youtube_dl/extractor/scivee.py b/youtube_dl/extractor/scivee.py
index 609a5ec994002ab17fb40f1ec970e53d1e9d3b28..33a78759a5ad37e8a6cbb6397c74317f34092385 100644 (file)
--- a/youtube_dl/extractor/scivee.py
+++ b/youtube_dl/extractor/scivee.py
@@ -11,13 +11,17 @@ class SciVeeIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.scivee.tv/node/62352',
-        'md5': 'b16699b74c9e6a120f6772a44960304f',
+        #'md5': 'b16699b74c9e6a120f6772a44960304f',
         'info_dict': {
             'id': '62352',
             'ext': 'mp4',
             'title': 'Adam Arkin at the 2014 DOE JGI Genomics of Energy & Environment Meeting',
             'description': 'md5:81f1710638e11a481358fab1b11059d7',
-        }
+        },
+        'params': {
+            # Range HTTP header is ignored
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):