Merge pull request #6428 from dstftw/improve-generic-smil-support

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

diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index f3a68b21d839b249112611eb62ad91f92dbd9e8f..178a7ca4c3b89ab9819fee45f1768421f32ffd27 100644 (file)
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -9,7 +9,7 @@ from ..compat import (
     compat_http_client,
     compat_str,
     compat_urllib_error,
-    compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_request,
 )
 from ..utils import (
@@ -17,6 +17,8 @@ from ..utils import (
     int_or_none,
     limit_length,
     urlencode_postdata,
+    get_element_by_id,
+    clean_html,
 )
 
 
@@ -27,7 +29,7 @@ class FacebookIE(InfoExtractor):
         (?:
             (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?)
             (?:v|video_id)=|
-            [^/]+/videos/
+            [^/]+/videos/(?:[^/]+/)?
         )
         (?P<id>[0-9]+)
         (?:.*)'''
@@ -42,6 +44,7 @@ class FacebookIE(InfoExtractor):
             'id': '637842556329505',
             'ext': 'mp4',
             'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
+            'uploader': 'Tennis on Facebook',
         }
     }, {
         'note': 'Video without discernible title',
@@ -50,13 +53,20 @@ class FacebookIE(InfoExtractor):
             'id': '274175099429670',
             'ext': 'mp4',
             'title': 'Facebook video #274175099429670',
-        }
+            'uploader': 'Asif Nawab Butt',
+        },
+        'expected_warnings': [
+            'title'
+        ]
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
         'only_matching': True,
     }, {
         'url': 'https://www.facebook.com/amogood/videos/1618742068337349/?fref=nf',
         'only_matching': True,
+    }, {
+        'url': 'https://www.facebook.com/ChristyClarkForBC/videos/vb.22819070941/10153870694020942/?type=2&theater',
+        'only_matching': True,
     }]
 
     def _login(self):
@@ -130,7 +140,7 @@ class FacebookIE(InfoExtractor):
             else:
                 raise ExtractorError('Cannot parse data')
         data = dict(json.loads(m.group(1)))
-        params_raw = compat_urllib_parse.unquote(data['params'])
+        params_raw = compat_urllib_parse_unquote(data['params'])
         params = json.loads(params_raw)
         video_data = params['video_data'][0]
 
@@ -146,15 +156,16 @@ class FacebookIE(InfoExtractor):
             raise ExtractorError('Cannot find video formats')
 
         video_title = self._html_search_regex(
-            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title',
-            fatal=False)
+            r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title',
+            default=None)
         if not video_title:
             video_title = self._html_search_regex(
                 r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
-                webpage, 'alternative title', default=None)
+                webpage, 'alternative title', fatal=False)
             video_title = limit_length(video_title, 80)
         if not video_title:
             video_title = 'Facebook video #%s' % video_id
+        uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
 
         return {
             'id': video_id,
@@ -162,4 +173,5 @@ class FacebookIE(InfoExtractor):
             'formats': formats,
             'duration': int_or_none(video_data.get('video_duration')),
             'thumbnail': video_data.get('thumbnail_src'),
+            'uploader': uploader,
         }