Update changelog.

[youtubedl] / youtube_dl / extractor / generic.py

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 7d0edf09c6a2e8428b84b3e7ebf787738db1bfaa..2a9c3e2dea0f397bc24b783550216ea42a582283 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -22,6 +22,8 @@ from ..utils import (
     HEADRequest,
     is_html,
     js_to_json,
     HEADRequest,
     is_html,
     js_to_json,

+    KNOWN_EXTENSIONS,
+    mimetype2ext,

     orderedSet,
     sanitized_Request,
     smuggle_url,
     orderedSet,
     sanitized_Request,
     smuggle_url,


@@ -99,6 +101,7 @@ from .mediaset import MediasetIE
 from .joj import JojIE
 from .megaphone import MegaphoneIE
 from .vzaar import VzaarIE
 from .joj import JojIE
 from .megaphone import MegaphoneIE
 from .vzaar import VzaarIE

+from .channel9 import Channel9IE

 
 
 class GenericIE(InfoExtractor):
 
 
 class GenericIE(InfoExtractor):


@@ -1088,7 +1091,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'upload_date': '20150212',
                 'uploader': 'The National Archives UK',
                 'ext': 'mp4',
                 'upload_date': '20150212',
                 'uploader': 'The National Archives UK',

-                'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
+                'description': 'md5:8078af856dca76edc42910b61273dbbf',

                 'uploader_id': 'NationalArchives08',
                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
             },
                 'uploader_id': 'NationalArchives08',
                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
             },


@@ -1104,7 +1107,8 @@ class GenericIE(InfoExtractor):
             },
             'params': {
                 'skip_download': True,
             },
             'params': {
                 'skip_download': True,

-            }
+            },
+            'skip': 'does not contain a video anymore',

         },
         # Complex jwplayer
         {
         },
         # Complex jwplayer
         {


@@ -1113,6 +1117,7 @@ class GenericIE(InfoExtractor):
                 'id': 'videos',
                 'ext': 'mp4',
                 'title': 'king machine trailer 1',
                 'id': 'videos',
                 'ext': 'mp4',
                 'title': 'king machine trailer 1',

+                'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',

                 'thumbnail': r're:^https?://.*\.jpg$',
             },
         },
                 'thumbnail': r're:^https?://.*\.jpg$',
             },
         },


@@ -1130,13 +1135,42 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             }
         },
                 'skip_download': True,
             }
         },

+        {
+            # Video.js embed, multiple formats
+            'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
+            'info_dict': {
+                'id': 'yygqldloqIk',
+                'ext': 'mp4',
+                'title': 'SolidWorks. Урок 6 Настройка чертежа',
+                'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
+                'upload_date': '20130314',
+                'uploader': 'PROстое3D',
+                'uploader_id': 'PROstoe3D',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            # Video.js embed, single format
+            'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
+            'info_dict': {
+                'id': 'watch',
+                'ext': 'mp4',
+                'title': 'Step 1 -  Good Foundation',
+                'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },

         # rtl.nl embed
         {
             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
             'playlist_mincount': 5,
             'info_dict': {
                 'id': 'aanslagen-kopenhagen',
         # rtl.nl embed
         {
             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
             'playlist_mincount': 5,
             'info_dict': {
                 'id': 'aanslagen-kopenhagen',

-                'title': 'Aanslagen Kopenhagen | RTL Nieuws',
+                'title': 'Aanslagen Kopenhagen',

             }
         },
         # Zapiks embed
             }
         },
         # Zapiks embed


@@ -1268,6 +1302,7 @@ class GenericIE(InfoExtractor):
             'params': {
                 'skip_download': True,
             },
             'params': {
                 'skip_download': True,
             },

+            'skip': 'This video is unavailable.',

         },
         # Pladform embed
         {
         },
         # Pladform embed
         {


@@ -1281,6 +1316,7 @@ class GenericIE(InfoExtractor):
                 'duration': 694,
                 'age_limit': 0,
             },
                 'duration': 694,
                 'age_limit': 0,
             },

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

         },
         # Playwire embed
         {
         },
         # Playwire embed
         {


@@ -1301,6 +1337,14 @@ class GenericIE(InfoExtractor):
                 'id': '518726732',
                 'ext': 'mp4',
                 'title': 'Facebook Creates "On This Day" | Crunch Report',
                 'id': '518726732',
                 'ext': 'mp4',
                 'title': 'Facebook Creates "On This Day" | Crunch Report',

+                'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
+                'timestamp': 1427237531,
+                'uploader': 'Crunch Report',
+                'upload_date': '20150324',
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,

             },
         },
         # SVT embed
             },
         },
         # SVT embed


@@ -1352,16 +1396,20 @@ class GenericIE(InfoExtractor):
                 'upload_date': '20140107',
                 'timestamp': 1389118457,
             },
                 'upload_date': '20140107',
                 'timestamp': 1389118457,
             },

+            'skip': 'Invalid Page URL',

         },
         # NBC News embed
         {
             'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
             'md5': '1aa589c675898ae6d37a17913cf68d66',
             'info_dict': {
         },
         # NBC News embed
         {
             'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
             'md5': '1aa589c675898ae6d37a17913cf68d66',
             'info_dict': {

-                'id': '701714499682',
+                'id': 'x_dtl_oa_LettermanliftPR_160608',

                 'ext': 'mp4',
                 'ext': 'mp4',

-                'title': 'PREVIEW: On Assignment: David Letterman',
+                'title': 'David Letterman: A Preview',

                 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
                 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',

+                'upload_date': '20160609',
+                'timestamp': 1465431544,
+                'uploader': 'NBCU-NEWS',

             },
         },
         # UDN embed
             },
         },
         # UDN embed


@@ -1378,6 +1426,7 @@ class GenericIE(InfoExtractor):
                 # m3u8 download
                 'skip_download': True,
             },
                 # m3u8 download
                 'skip_download': True,
             },

+            'expected_warnings': ['Failed to parse JSON Expecting value'],

         },
         # Ooyala embed
         {
         },
         # Ooyala embed
         {


@@ -1385,7 +1434,7 @@ class GenericIE(InfoExtractor):
             'info_dict': {
                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
                 'ext': 'mp4',
             'info_dict': {
                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
                 'ext': 'mp4',

-                'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
+                'description': 'Index/Match versus VLOOKUP.',

                 'title': 'This is what separates the Excel masters from the wannabes',
                 'duration': 191.933,
             },
                 'title': 'This is what separates the Excel masters from the wannabes',
                 'duration': 191.933,
             },


@@ -1423,7 +1472,8 @@ class GenericIE(InfoExtractor):
                 'upload_date': '20150622',
                 'uploader': 'Public Sénat',
                 'uploader_id': 'xa9gza',
                 'upload_date': '20150622',
                 'uploader': 'Public Sénat',
                 'uploader_id': 'xa9gza',

-            }
+            },
+            'skip': 'File not found.',

         },
         # OnionStudios embed
         {
         },
         # OnionStudios embed
         {


@@ -1581,22 +1631,6 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['BrightcoveLegacy'],
         },
             },
             'add_ie': ['BrightcoveLegacy'],
         },

-        # Nexx embed
-        {
-            'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
-            'info_dict': {
-                'id': '247746',
-                'ext': 'mp4',
-                'title': "Yesterday's Jam (OV)",
-                'description': 'md5:09bc0984723fed34e2581624a84e05f0',
-                'timestamp': 1492594816,
-                'upload_date': '20170419',
-            },
-            'params': {
-                'format': 'bestvideo',
-                'skip_download': True,
-            },
-        },

         # Facebook <iframe> embed
         {
             'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
         # Facebook <iframe> embed
         {
             'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',


@@ -2175,7 +2209,7 @@ class GenericIE(InfoExtractor):
         # And then there are the jokers who advertise that they use RTA,
         # but actually don't.
         AGE_LIMIT_MARKERS = [
         # And then there are the jokers who advertise that they use RTA,
         # but actually don't.
         AGE_LIMIT_MARKERS = [

-            r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
+            r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',

         ]
         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
             age_limit = 18
         ]
         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
             age_limit = 18


@@ -2237,7 +2271,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded rtl.nl player
         matches = re.findall(
 
         # Look for embedded rtl.nl player
         matches = re.findall(

-            r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
+            r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',

             webpage)
         if matches:
             return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
             webpage)
         if matches:
             return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')


@@ -2636,7 +2670,7 @@ class GenericIE(InfoExtractor):
 
         # Look for UDN embeds
         mobj = re.search(
 
         # Look for UDN embeds
         mobj = re.search(

-            r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
+            r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)

         if mobj is not None:
             return self.url_result(
                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
         if mobj is not None:
             return self.url_result(
                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')


@@ -2840,6 +2874,11 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
 
             return self.playlist_from_matches(
                 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
 

+        channel9_urls = Channel9IE._extract_urls(webpage)
+        if channel9_urls:
+            return self.playlist_from_matches(
+                channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
+

         def merge_dicts(dict1, dict2):
             merged = {}
             for k, v in dict1.items():
         def merge_dicts(dict1, dict2):
             merged = {}
             for k, v in dict1.items():


@@ -2880,6 +2919,46 @@ class GenericIE(InfoExtractor):
                 jwplayer_data, video_id, require_title=False, base_url=url)
             return merge_dicts(info, info_dict)
 
                 jwplayer_data, video_id, require_title=False, base_url=url)
             return merge_dicts(info, info_dict)
 

+        # Video.js embed
+        mobj = re.search(
+            r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
+            webpage)
+        if mobj is not None:
+            sources = self._parse_json(
+                mobj.group(1), video_id, transform_source=js_to_json,
+                fatal=False) or []
+            if not isinstance(sources, list):
+                sources = [sources]
+            formats = []
+            for source in sources:
+                src = source.get('src')
+                if not src or not isinstance(src, compat_str):
+                    continue
+                src = compat_urlparse.urljoin(url, src)
+                src_type = source.get('type')
+                if isinstance(src_type, compat_str):
+                    src_type = src_type.lower()
+                ext = determine_ext(src).lower()
+                if src_type == 'video/youtube':
+                    return self.url_result(src, YoutubeIE.ie_key())
+                if src_type == 'application/dash+xml' or ext == 'mpd':
+                    formats.extend(self._extract_mpd_formats(
+                        src, video_id, mpd_id='dash', fatal=False))
+                elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        src, video_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id='hls', fatal=False))
+                else:
+                    formats.append({
+                        'url': src,
+                        'ext': (mimetype2ext(src_type) or
+                                ext if ext in KNOWN_EXTENSIONS else 'mp4'),
+                    })
+            if formats:
+                self._sort_formats(formats)
+                info_dict['formats'] = formats
+                return info_dict
+

         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')


@@ -2973,7 +3052,7 @@ class GenericIE(InfoExtractor):
             # be supported by youtube-dl thus this is checked the very last (see
             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
             embed_url = self._html_search_meta('twitter:player', webpage, default=None)
             # be supported by youtube-dl thus this is checked the very last (see
             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
             embed_url = self._html_search_meta('twitter:player', webpage, default=None)

-            if embed_url:
+            if embed_url and embed_url != url:

                 return self.url_result(embed_url)
 
         if not found:
                 return self.url_result(embed_url)
 
         if not found: