X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgeneric.py;h=76852f9dc82b046bf319d075ae7ca67c58b7d205;hb=54fc90aabfb71968f28af68dfe3f7a3544cc2f0b;hp=e3cb5c5ce51de5d5fc4aac16c64443b60e91b478;hpb=069937151e429a2127569910d204c03eec167f0d;p=youtube-dl

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index e3cb5c5ce..76852f9dc 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -23,6 +23,7 @@ from ..utils import (
     is_html,
     js_to_json,
     KNOWN_EXTENSIONS,
+    merge_dicts,
     mimetype2ext,
     orderedSet,
     sanitized_Request,
@@ -106,6 +107,7 @@ from .springboardplatform import SpringboardPlatformIE
 from .yapfiles import YapFilesIE
 from .vice import ViceIE
 from .xfileshare import XFileShareIE
+from .cloudflarestream import CloudflareStreamIE
 
 
 class GenericIE(InfoExtractor):
@@ -190,6 +192,16 @@ class GenericIE(InfoExtractor):
                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
             }
         },
+        # RSS feed with enclosures and unsupported link URLs
+        {
+            'url': 'http://www.hellointernet.fm/podcast?format=rss',
+            'info_dict': {
+                'id': 'http://www.hellointernet.fm/podcast?format=rss',
+                'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
+                'title': 'Hello Internet',
+            },
+            'playlist_mincount': 100,
+        },
         # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
         {
             'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
@@ -1220,7 +1232,7 @@ class GenericIE(InfoExtractor):
                 'title': '35871',
                 'timestamp': 1355743100,
                 'upload_date': '20121217',
-                'uploader_id': 'batchUser',
+                'uploader_id': 'cplapp@learn360.com',
             },
             'add_ie': ['Kaltura'],
         },
@@ -1271,6 +1283,39 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Kaltura'],
         },
+        {
+            # Kaltura iframe embed, more sophisticated
+            'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
+            'info_dict': {
+                'id': '1_9gzouybz',
+                'ext': 'mp4',
+                'title': 'lecture-05sep2017',
+                'description': 'md5:40f347d91fd4ba047e511c5321064b49',
+                'upload_date': '20170913',
+                'uploader_id': 'eps2',
+                'timestamp': 1505340777,
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'add_ie': ['Kaltura'],
+        },
+        {
+            # meta twitter:player
+            'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
+            'info_dict': {
+                'id': '0_01b42zps',
+                'ext': 'mp4',
+                'title': 'Main Twerk (Video)',
+                'upload_date': '20171208',
+                'uploader_id': 'sebastian.salinas@thechive.com',
+                'timestamp': 1512713057,
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'add_ie': ['Kaltura'],
+        },
         # referrer protected EaglePlatform embed
         {
             'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
@@ -1427,21 +1472,6 @@ class GenericIE(InfoExtractor):
             },
             'expected_warnings': ['Failed to parse JSON Expecting value'],
         },
-        # Ooyala embed
-        {
-            'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
-            'info_dict': {
-                'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
-                'ext': 'mp4',
-                'description': 'Index/Match versus VLOOKUP.',
-                'title': 'This is what separates the Excel masters from the wannabes',
-                'duration': 191.933,
-            },
-            'params': {
-                # m3u8 downloads
-                'skip_download': True,
-            }
-        },
         # Brightcove URL in single quotes
         {
             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
@@ -1969,6 +1999,19 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            # CloudflareStream embed
+            'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
+            'info_dict': {
+                'id': '31c9291ab41fac05471db4e73aa11717',
+                'ext': 'mp4',
+                'title': '31c9291ab41fac05471db4e73aa11717',
+            },
+            'add_ie': [CloudflareStreamIE.ie_key()],
+            'params': {
+                'skip_download': True,
+            },
+        },
         {
             'url': 'http://share-videos.se/auto/video/83645793?uid=13',
             'md5': 'b68d276de422ab07ee1d49388103f457',
@@ -2009,13 +2052,15 @@ class GenericIE(InfoExtractor):
 
         entries = []
         for it in doc.findall('./channel/item'):
-            next_url = xpath_text(it, 'link', fatal=False)
+            next_url = None
+            enclosure_nodes = it.findall('./enclosure')
+            for e in enclosure_nodes:
+                next_url = e.attrib.get('url')
+                if next_url:
+                    break
+
             if not next_url:
-                enclosure_nodes = it.findall('./enclosure')
-                for e in enclosure_nodes:
-                    next_url = e.attrib.get('url')
-                    if next_url:
-                        break
+                next_url = xpath_text(it, 'link', fatal=False)
 
             if not next_url:
                 continue
@@ -2979,6 +3024,11 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
 
+        cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
+        if cloudflarestream_urls:
+            return self.playlist_from_matches(
+                cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
+
         sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
             r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
             webpage)]
@@ -2986,21 +3036,6 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 sharevideos_urls, video_id, video_title)
 
-        def merge_dicts(dict1, dict2):
-            merged = {}
-            for k, v in dict1.items():
-                if v is not None:
-                    merged[k] = v
-            for k, v in dict2.items():
-                if v is None:
-                    continue
-                if (k not in merged or
-                        (isinstance(v, compat_str) and v and
-                            isinstance(merged[k], compat_str) and
-                            not merged[k])):
-                    merged[k] = v
-            return merged
-
         # Look for HTML5 media
         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
         if entries: