Merge branch 'fix.25.12.2018'

youtube_dl/downloader/external.py

@@ -243,8 +243,6 @@ class FFmpegFD(ExternalFD):
             # http://trac.ffmpeg.org/ticket/6125#comment:10
             args += ['-seekable', '1' if seekable else '0']
 
-        args += self._configuration_args()
-
         # start_time = info_dict.get('start_time') or 0
         # if start_time:
         #     args += ['-ss', compat_str(start_time)]
@@ -312,6 +310,8 @@ class FFmpegFD(ExternalFD):
 
         args += ['-i', url, '-c', 'copy']
         
+        args += self._configuration_args()
+
         if self.params.get('test', False):
             args += ['-fs', compat_str(self._TEST_FILE_SIZE)]
 

youtube_dl/extractor/common.py

@@ -2816,7 +2816,7 @@ class InfoExtractor(object):
         """ Return a compat_cookies.SimpleCookie with the cookies for the url """
         req = sanitized_Request(url)
         self._downloader.cookiejar.add_cookie_header(req)
-        return compat_cookies.SimpleCookie(req.get_header('Cookie'))
+        return compat_cookies.SimpleCookie(str(req.get_header('Cookie')))
 
     def _apply_first_set_cookie_header(self, url_handle, cookie):
         """

youtube_dl/extractor/facebook.py

@@ -431,6 +431,8 @@ class FacebookIE(InfoExtractor):
             video_title = self._html_search_regex(
                 r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
                 webpage, 'alternative title', default=None)
+        if not video_title:
+            video_title = self._og_search_title(webpage, default=None)
         if not video_title:
             video_title = self._html_search_meta(
                 'description', webpage, 'title', default=None)
@@ -438,12 +440,13 @@ class FacebookIE(InfoExtractor):
             video_title = limit_length(video_title, 80)
         else:
             video_title = 'Facebook video #%s' % video_id
+
         uploader = clean_html(get_element_by_id(
             'fbPhotoPageAuthorName', webpage)) or self._search_regex(
             r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader',default=None) or \
-                   self._og_search_title(webpage, default=None) or self._search_regex(
+                   self._search_regex(
                         r'\"ownerName\":"(.+?)"', tahoe_data.secondary,
-                        'uploader_id', fatal=False)
+                        'uploader_id', fatal=False) or self._og_search_title(webpage, default=None)
 
 
         timestamp = int_or_none(self._search_regex(
@@ -457,18 +460,12 @@ class FacebookIE(InfoExtractor):
             'uploader_id', default=None) or self._search_regex(
             r'[\'\"]ownerid[\'\"]\s*:\s*[\'\"](\d+)[\'\"]', tahoe_data.secondary,
             'uploader_id', fatal=False)
+
         thumbnail = self._og_search_thumbnail(webpage)
 
-        view_count = parse_count(self._search_regex(
+        view_count = parse_count(self._extract_meta_count(['postViewCount', 'viewCount'], webpage, tahoe_data, 'likes'))
-            r'\bpostViewCount\s*:\s*["\']([\d,.]+)', webpage, 'view count',
+        likes_count = parse_count(self._extract_likes(webpage, tahoe_data))
-            default=None) or self._search_regex(
+        shares_count = parse_count(self._extract_meta_count(['sharecount'], webpage, tahoe_data, 'shares'))
-            r'[\'\"]postViewCount[\'\"]\s*:\s*(\d+)', tahoe_data.secondary, 'view count',
-            default=None) or self._search_regex(
-            r'\bviewCount\s*:\s*["\']([\d,.]+)', webpage, 'view count',
-            default=None) or self._search_regex(
-            r'[\'\"]viewCount[\'\"]\s*:\s*(\d+)', tahoe_data.secondary, 'view count',
-            default=None)
-        )
 
         info_dict = {
             'id': video_id,
@@ -480,11 +477,42 @@ class FacebookIE(InfoExtractor):
             'view_count': view_count,
             'uploader_id': uploader_id,
             'is_live': is_live,
-            'live_status': live_status
+            'live_status': live_status,
+            'like_count': likes_count,
+            'share_count': shares_count
         }
 
         return webpage, info_dict
 
+    def _extract_meta_count(self, fields, webpage, tahoe_data, name, ):
+        value = None
+
+        for f in fields:
+            if value:
+                break
+            value = self._search_regex(
+                    r'\b%s\s*:\s*["\']([\d,.]+)' % f, webpage, name,
+                    default=None
+            )
+            if value:
+                break
+
+            value = self._search_regex(
+                r'[\'\"]%s[\'\"]\s*:\s*(\d+)' % f, tahoe_data.secondary, name,
+                default=None)
+
+        return value
+
+    def _extract_likes(self, webpage, tahoe_data):
+        values = re.findall(r'\blikecount\s*:\s*["\']([\d,.]+)', webpage)
+        if values:
+            return values[-1]
+
+
+        values = re.findall(r'[\'\"]\blikecount[\'\"]\s*:\s*(\d+)', tahoe_data.secondary)
+        if values:
+            return values[-1]
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

youtube_dl/extractor/twitter.py

@@ -14,6 +14,7 @@ from ..utils import (
     remove_end,
     try_get,
     xpath_text,
+    parse_count
 )
 
 from .periscope import PeriscopeIE
@@ -165,6 +166,7 @@ class TwitterCardIE(TwitterBaseIE):
         config = None
         formats = []
         duration = None
+        view_count = None
 
         urls = [url]
         if path.startswith('cards/'):
@@ -239,12 +241,18 @@ class TwitterCardIE(TwitterBaseIE):
             ct0 = self._get_cookies(url).get('ct0')
             if ct0:
                 headers['csrf_token'] = ct0.value
-            guest_token = self._download_json(
+            guest_token_c = self._get_cookies('http://api.twitter.com/').get('gt')
-                '%s/guest/activate.json' % self._API_BASE, video_id,
+            if not guest_token_c:
-                'Downloading guest token', data=b'',
+                guest_token = self._download_json(
-                headers=headers)['guest_token']
+                    '%s/guest/activate.json' % self._API_BASE, video_id,
+                    'Downloading guest token', data=b'',
+                    headers=headers)['guest_token']
+                self._set_cookie('api.twitter.com', 'gt', guest_token)
+            else:
+                guest_token = guest_token_c.value
+
             headers['x-guest-token'] = guest_token
-            self._set_cookie('api.twitter.com', 'gt', guest_token)
+
             config = self._download_json(
                 '%s/videos/tweet/config/%s.json' % (self._API_BASE, video_id),
                 video_id, headers=headers)
@@ -265,6 +273,7 @@ class TwitterCardIE(TwitterBaseIE):
             title = 'Twitter web player'
             thumbnail = config.get('posterImage')
             duration = float_or_none(track.get('durationMs'), scale=1000)
+            view_count = parse_count(track.get('viewCount'))
 
         self._remove_duplicate_formats(formats)
         self._sort_formats(formats)
@@ -275,6 +284,7 @@ class TwitterCardIE(TwitterBaseIE):
             'thumbnail': thumbnail,
             'duration': duration,
             'formats': formats,
+            'view_count': view_count
         }
 
 

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = 'vc.2019.06.08'
+__version__ = 'vc.2019.06.19'