debian/copyright: Update my copyright years.

[youtubedl] / youtube_dl / extractor / facebook.py

diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index 2139f68aa3cb16facdc45b5fd9e014621e1c6674..f0e575320015d435889b1bd610b4871dbd84ae21 100644 (file)
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -13,9 +13,10 @@ from ..compat import (
     compat_urllib_request,
 )
 from ..utils import (
     compat_urllib_request,
 )
 from ..utils import (

-    urlencode_postdata,

     ExtractorError,
     ExtractorError,

+    int_or_none,

     limit_length,
     limit_length,

+    urlencode_postdata,

 )
 
 
 )
 
 


@@ -36,7 +37,6 @@ class FacebookIE(InfoExtractor):
         'info_dict': {
             'id': '637842556329505',
             'ext': 'mp4',
         'info_dict': {
             'id': '637842556329505',
             'ext': 'mp4',

-            'duration': 38,

             'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
         }
     }, {
             'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
         }
     }, {


@@ -107,9 +107,7 @@ class FacebookIE(InfoExtractor):
         self._login()
 
     def _real_extract(self, url):
         self._login()
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)

         url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
         webpage = self._download_webpage(url, video_id)
 
         url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
         webpage = self._download_webpage(url, video_id)
 


@@ -128,11 +126,17 @@ class FacebookIE(InfoExtractor):
         params_raw = compat_urllib_parse.unquote(data['params'])
         params = json.loads(params_raw)
         video_data = params['video_data'][0]
         params_raw = compat_urllib_parse.unquote(data['params'])
         params = json.loads(params_raw)
         video_data = params['video_data'][0]

-        video_url = video_data.get('hd_src')
-        if not video_url:
-            video_url = video_data['sd_src']
-        if not video_url:
-            raise ExtractorError('Cannot find video URL')
+
+        formats = []
+        for quality in ['sd', 'hd']:
+            src = video_data.get('%s_src' % quality)
+            if src is not None:
+                formats.append({
+                    'format_id': quality,
+                    'url': src,
+                })
+        if not formats:
+            raise ExtractorError('Cannot find video formats')

 
         video_title = self._html_search_regex(
             r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title',
 
         video_title = self._html_search_regex(
             r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title',


@@ -148,7 +152,7 @@ class FacebookIE(InfoExtractor):
         return {
             'id': video_id,
             'title': video_title,
         return {
             'id': video_id,
             'title': video_title,

-            'url': video_url,
-            'duration': int(video_data['video_duration']),
-            'thumbnail': video_data['thumbnail_src'],
+            'formats': formats,
+            'duration': int_or_none(video_data.get('video_duration')),
+            'thumbnail': video_data.get('thumbnail_src'),

         }
         }