Prepare for release.

[youtubedl] / youtube_dl / extractor / facebook.py

diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index 82dc27bc6ff3ed2edd3b318f3ed3d14e360ef22d..fd854411b554185708d4edeeb338897e0a0da890 100644 (file)
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -9,14 +9,15 @@ from ..compat import (
     compat_http_client,
     compat_str,
     compat_urllib_error,
     compat_http_client,
     compat_str,
     compat_urllib_error,

-    compat_urllib_parse,
-    compat_urllib_request,
+    compat_urllib_parse_unquote,

 )
 from ..utils import (
     ExtractorError,
 )
 from ..utils import (
     ExtractorError,

-    int_or_none,

     limit_length,
     limit_length,

+    sanitized_Request,

     urlencode_postdata,
     urlencode_postdata,

+    get_element_by_id,
+    clean_html,

 )
 
 
 )
 
 


@@ -42,6 +43,7 @@ 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',
             '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',
         }
     }, {
         'note': 'Video without discernible title',


@@ -50,6 +52,7 @@ class FacebookIE(InfoExtractor):
             'id': '274175099429670',
             'ext': 'mp4',
             'title': 'Facebook video #274175099429670',
             'id': '274175099429670',
             'ext': 'mp4',
             'title': 'Facebook video #274175099429670',

+            'uploader': 'Asif Nawab Butt',

         },
         'expected_warnings': [
             'title'
         },
         'expected_warnings': [
             'title'


@@ -70,7 +73,7 @@ class FacebookIE(InfoExtractor):
         if useremail is None:
             return
 
         if useremail is None:
             return
 

-        login_page_req = compat_urllib_request.Request(self._LOGIN_URL)
+        login_page_req = sanitized_Request(self._LOGIN_URL)

         login_page_req.add_header('Cookie', 'locale=en_US')
         login_page = self._download_webpage(login_page_req, None,
                                             note='Downloading login page',
         login_page_req.add_header('Cookie', 'locale=en_US')
         login_page = self._download_webpage(login_page_req, None,
                                             note='Downloading login page',


@@ -91,7 +94,7 @@ class FacebookIE(InfoExtractor):
             'timezone': '-60',
             'trynum': '1',
         }
             'timezone': '-60',
             'trynum': '1',
         }

-        request = compat_urllib_request.Request(self._LOGIN_URL, urlencode_postdata(login_form))
+        request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form))

         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         try:
             login_results = self._download_webpage(request, None,
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         try:
             login_results = self._download_webpage(request, None,


@@ -106,7 +109,7 @@ class FacebookIE(InfoExtractor):
                     r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'),
                 'name_action_selected': 'dont_save',
             }
                     r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'),
                 'name_action_selected': 'dont_save',
             }

-            check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
+            check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))

             check_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
             check_response = self._download_webpage(check_req, None,
                                                     note='Confirming login')
             check_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
             check_response = self._download_webpage(check_req, None,
                                                     note='Confirming login')


@@ -136,18 +139,22 @@ class FacebookIE(InfoExtractor):
             else:
                 raise ExtractorError('Cannot parse data')
         data = dict(json.loads(m.group(1)))
             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)
         params = json.loads(params_raw)

-        video_data = params['video_data'][0]

 
         formats = []
 
         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,
-                })
+        for format_id, f in params['video_data'].items():
+            if not f or not isinstance(f, list):
+                continue
+            for quality in ('sd', 'hd'):
+                for src_type in ('src', 'src_no_ratelimit'):
+                    src = f[0].get('%s_%s' % (quality, src_type))
+                    if src:
+                        formats.append({
+                            'format_id': '%s_%s_%s' % (format_id, quality, src_type),
+                            'url': src,
+                            'preference': -10 if format_id == 'progressive' else 0,
+                        })

         if not formats:
             raise ExtractorError('Cannot find video formats')
 
         if not formats:
             raise ExtractorError('Cannot find video formats')
 


@@ -161,11 +168,11 @@ class FacebookIE(InfoExtractor):
             video_title = limit_length(video_title, 80)
         if not video_title:
             video_title = 'Facebook video #%s' % video_id
             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,
             'title': video_title,
             'formats': formats,
 
         return {
             'id': video_id,
             'title': video_title,
             'formats': formats,

-            'duration': int_or_none(video_data.get('video_duration')),
-            'thumbnail': video_data.get('thumbnail_src'),
+            'uploader': uploader,

         }
         }