Fix some regexes

[youtube-dl] / youtube_dl / extractor / generic.py

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 7d0edf09c6a2e8428b84b3e7ebf787738db1bfaa..68b6338396dc84277792273db277154fe3cc4995 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,
+    KNOWN_EXTENSIONS,
+    mimetype2ext,
     orderedSet,
     sanitized_Request,
     smuggle_url,
@@ -1130,6 +1132,35 @@ class GenericIE(InfoExtractor):
                 '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',
@@ -2175,7 +2206,7 @@ class GenericIE(InfoExtractor):
         # 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
@@ -2880,6 +2911,46 @@ class GenericIE(InfoExtractor):
                 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')
@@ -2973,7 +3044,7 @@ 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)
-            if embed_url:
+            if embed_url and embed_url != url:
                 return self.url_result(embed_url)
 
         if not found: