Update upstream source from tag 'upstream/2019.06.08'

[youtubedl] / youtube_dl / extractor / facebook.py

diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index b4d38e5c258b830e192bcfa2639f2074d9217434..789dd79d5474ea8f7c9d18df244c686076e3e646 100644 (file)
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -1,3 +1,4 @@
+# coding: utf-8

 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re


@@ -12,14 +13,17 @@ from ..compat import (
     compat_urllib_parse_unquote_plus,
 )
 from ..utils import (
     compat_urllib_parse_unquote_plus,
 )
 from ..utils import (

+    clean_html,

     error_to_compat_str,
     ExtractorError,
     error_to_compat_str,
     ExtractorError,

+    get_element_by_id,

     int_or_none,
     int_or_none,

+    js_to_json,

     limit_length,
     limit_length,

+    parse_count,

     sanitized_Request,
     sanitized_Request,

+    try_get,

     urlencode_postdata,
     urlencode_postdata,

-    get_element_by_id,
-    clean_html,

 )
 
 
 )
 
 


@@ -27,7 +31,7 @@ class FacebookIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                 (?:
                     https?://
     _VALID_URL = r'''(?x)
                 (?:
                     https?://

-                        (?:[\w-]+\.)?facebook\.com/
+                        (?:[\w-]+\.)?(?:facebook\.com|facebookcorewwwi\.onion)/

                         (?:[^#]*?\#!/)?
                         (?:
                             (?:
                         (?:[^#]*?\#!/)?
                         (?:
                             (?:


@@ -53,6 +57,7 @@ class FacebookIE(InfoExtractor):
     _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36'
 
     _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s'
     _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36'
 
     _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s'

+    _VIDEO_PAGE_TAHOE_TEMPLATE = 'https://www.facebook.com/video/tahoe/async/%s/?chain=true&isvideo=true&payloadtype=primary'

 
     _TESTS = [{
         'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
 
     _TESTS = [{
         'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',


@@ -64,17 +69,18 @@ class FacebookIE(InfoExtractor):
             'uploader': 'Tennis on Facebook',
             'upload_date': '20140908',
             'timestamp': 1410199200,
             'uploader': 'Tennis on Facebook',
             'upload_date': '20140908',
             'timestamp': 1410199200,

-        }
+        },
+        'skip': 'Requires logging in',

     }, {
     }, {

-        'note': 'Video without discernible title',

         'url': 'https://www.facebook.com/video.php?v=274175099429670',
         'info_dict': {
             'id': '274175099429670',
             'ext': 'mp4',
         'url': 'https://www.facebook.com/video.php?v=274175099429670',
         'info_dict': {
             'id': '274175099429670',
             'ext': 'mp4',

-            'title': 'Facebook video #274175099429670',
+            'title': 're:^Asif Nawab Butt posted a video',

             'uploader': 'Asif Nawab Butt',
             'upload_date': '20140506',
             'timestamp': 1399398998,
             'uploader': 'Asif Nawab Butt',
             'upload_date': '20140506',
             'timestamp': 1399398998,

+            'thumbnail': r're:^https?://.*',

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


@@ -91,6 +97,7 @@ class FacebookIE(InfoExtractor):
             'upload_date': '20160110',
             'timestamp': 1452431627,
         },
             'upload_date': '20160110',
             'timestamp': 1452431627,
         },

+        'skip': 'Requires logging in',

     }, {
         'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
         'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6',
     }, {
         'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
         'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6',


@@ -118,19 +125,66 @@ class FacebookIE(InfoExtractor):
         'info_dict': {
             'id': '10153664894881749',
             'ext': 'mp4',
         'info_dict': {
             'id': '10153664894881749',
             'ext': 'mp4',

-            'title': 'Facebook video #10153664894881749',
+            'title': 'Average time to confirm recent Supreme Court nominees: 67 days Longest it\'s t...',
+            'thumbnail': r're:^https?://.*',
+            'timestamp': 1456259628,
+            'upload_date': '20160223',
+            'uploader': 'Barack Obama',

         },
     }, {
         # have 1080P, but only up to 720p in swf params
         'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',
         },
     }, {
         # have 1080P, but only up to 720p in swf params
         'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',

-        'md5': '0d9813160b146b3bc8744e006027fcc6',
+        'md5': '9571fae53d4165bbbadb17a94651dcdc',

         'info_dict': {
             'id': '10155529876156509',
             'ext': 'mp4',
         'info_dict': {
             'id': '10155529876156509',
             'ext': 'mp4',

-            'title': 'Holocaust survivor becomes US citizen',
+            'title': 'She survived the holocaust — and years later, she’s getting her citizenship s...',

             'timestamp': 1477818095,
             'upload_date': '20161030',
             'uploader': 'CNN',
             'timestamp': 1477818095,
             'upload_date': '20161030',
             'uploader': 'CNN',

+            'thumbnail': r're:^https?://.*',
+            'view_count': int,
+        },
+    }, {
+        # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
+        'url': 'https://www.facebook.com/yaroslav.korpan/videos/1417995061575415/',
+        'info_dict': {
+            'id': '1417995061575415',
+            'ext': 'mp4',
+            'title': 'md5:1db063d6a8c13faa8da727817339c857',
+            'timestamp': 1486648217,
+            'upload_date': '20170209',
+            'uploader': 'Yaroslav Korpan',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.facebook.com/LaGuiaDelVaron/posts/1072691702860471',
+        'info_dict': {
+            'id': '1072691702860471',
+            'ext': 'mp4',
+            'title': 'md5:ae2d22a93fbb12dad20dc393a869739d',
+            'timestamp': 1477305000,
+            'upload_date': '20161024',
+            'uploader': 'La Guía Del Varón',
+            'thumbnail': r're:^https?://.*',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.facebook.com/groups/1024490957622648/permalink/1396382447100162/',
+        'info_dict': {
+            'id': '1396382447100162',
+            'ext': 'mp4',
+            'title': 'md5:19a428bbde91364e3de815383b54a235',
+            'timestamp': 1486035494,
+            'upload_date': '20170202',
+            'uploader': 'Elisabeth Ahtn',
+        },
+        'params': {
+            'skip_download': True,

         },
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
         },
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',


@@ -150,25 +204,43 @@ class FacebookIE(InfoExtractor):
     }, {
         'url': 'https://zh-hk.facebook.com/peoplespower/videos/1135894589806027/',
         'only_matching': True,
     }, {
         'url': 'https://zh-hk.facebook.com/peoplespower/videos/1135894589806027/',
         'only_matching': True,

+    }, {
+        'url': 'https://www.facebookcorewwwi.onion/video.php?v=274175099429670',
+        'only_matching': True,
+    }, {
+        # no title
+        'url': 'https://www.facebook.com/onlycleverentertainment/videos/1947995502095005/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.facebook.com/WatchESLOne/videos/359649331226507/',
+        'info_dict': {
+            'id': '359649331226507',
+            'ext': 'mp4',
+            'title': '#ESLOne VoD - Birmingham Finals Day#1 Fnatic vs. @Evil Geniuses',
+            'uploader': 'ESL One Dota 2',
+        },
+        'params': {
+            'skip_download': True,
+        },

     }]
 
     @staticmethod
     }]
 
     @staticmethod

-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
-        if mobj is not None:
-            return mobj.group('url')
-
+    def _extract_urls(webpage):
+        urls = []
+        for mobj in re.finditer(
+                r'<iframe[^>]+?src=(["\'])(?P<url>https?://www\.facebook\.com/(?:video/embed|plugins/video\.php).+?)\1',
+                webpage):
+            urls.append(mobj.group('url'))

         # Facebook API embed
         # see https://developers.facebook.com/docs/plugins/embedded-video-player
         # Facebook API embed
         # see https://developers.facebook.com/docs/plugins/embedded-video-player

-        mobj = re.search(r'''(?x)<div[^>]+
+        for mobj in re.finditer(r'''(?x)<div[^>]+

                 class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+
                 class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+

-                data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''', webpage)
-        if mobj is not None:
-            return mobj.group('url')
+                data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''', webpage):
+            urls.append(mobj.group('url'))
+        return urls

 
     def _login(self):
 
     def _login(self):

-        (useremail, password) = self._get_login_info()
+        useremail, password = self._get_login_info()

         if useremail is None:
             return
 
         if useremail is None:
             return
 


@@ -240,12 +312,32 @@ class FacebookIE(InfoExtractor):
 
         video_data = None
 
 
         video_data = None
 

+        def extract_video_data(instances):
+            for item in instances:
+                if item[1][0] == 'VideoConfig':
+                    video_item = item[2][0]
+                    if video_item.get('video_id'):
+                        return video_item['videoData']
+

         server_js_data = self._parse_json(self._search_regex(
         server_js_data = self._parse_json(self._search_regex(

-            r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id)
-        for item in server_js_data.get('instances', []):
-            if item[1][0] == 'VideoConfig':
-                video_data = item[2][0]['videoData']
-                break
+            r'handleServerJS\(({.+})(?:\);|,")', webpage,
+            'server js data', default='{}'), video_id, fatal=False)
+
+        if server_js_data:
+            video_data = extract_video_data(server_js_data.get('instances', []))
+
+        def extract_from_jsmods_instances(js_data):
+            if js_data:
+                return extract_video_data(try_get(
+                    js_data, lambda x: x['jsmods']['instances'], list) or [])
+
+        if not video_data:
+            server_js_data = self._parse_json(
+                self._search_regex(
+                    r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall|permalink_video_pagelet)',
+                    webpage, 'js data', default='{}'),
+                video_id, transform_source=js_to_json, fatal=False)
+            video_data = extract_from_jsmods_instances(server_js_data)

 
         if not video_data:
             if not fatal_if_no_video:
 
         if not video_data:
             if not fatal_if_no_video:


@@ -255,8 +347,37 @@ class FacebookIE(InfoExtractor):
                 raise ExtractorError(
                     'The video is not available, Facebook said: "%s"' % m_msg.group(1),
                     expected=True)
                 raise ExtractorError(
                     'The video is not available, Facebook said: "%s"' % m_msg.group(1),
                     expected=True)

-            else:
-                raise ExtractorError('Cannot parse data')
+            elif '>You must log in to continue' in webpage:
+                self.raise_login_required()
+
+            # Video info not in first request, do a secondary request using
+            # tahoe player specific URL
+            tahoe_data = self._download_webpage(
+                self._VIDEO_PAGE_TAHOE_TEMPLATE % video_id, video_id,
+                data=urlencode_postdata({
+                    '__a': 1,
+                    '__pc': self._search_regex(
+                        r'pkg_cohort["\']\s*:\s*["\'](.+?)["\']', webpage,
+                        'pkg cohort', default='PHASED:DEFAULT'),
+                    '__rev': self._search_regex(
+                        r'client_revision["\']\s*:\s*(\d+),', webpage,
+                        'client revision', default='3944515'),
+                    'fb_dtsg': self._search_regex(
+                        r'"DTSGInitialData"\s*,\s*\[\]\s*,\s*{\s*"token"\s*:\s*"([^"]+)"',
+                        webpage, 'dtsg token', default=''),
+                }),
+                headers={
+                    'Content-Type': 'application/x-www-form-urlencoded',
+                })
+            tahoe_js_data = self._parse_json(
+                self._search_regex(
+                    r'for\s+\(\s*;\s*;\s*\)\s*;(.+)', tahoe_data,
+                    'tahoe js data', default='{}'),
+                video_id, fatal=False)
+            video_data = extract_from_jsmods_instances(tahoe_js_data)
+
+        if not video_data:
+            raise ExtractorError('Cannot parse data')

 
         formats = []
         for f in video_data:
 
         formats = []
         for f in video_data:


@@ -287,19 +408,31 @@ class FacebookIE(InfoExtractor):
         self._sort_formats(formats)
 
         video_title = self._html_search_regex(
         self._sort_formats(formats)
 
         video_title = self._html_search_regex(

-            r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title',
-            default=None)
+            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)
         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)

-            video_title = limit_length(video_title, 80)

         if not video_title:
         if not video_title:

+            video_title = self._html_search_meta(
+                'description', webpage, 'title', default=None)
+        if video_title:
+            video_title = limit_length(video_title, 80)
+        else:

             video_title = 'Facebook video #%s' % video_id
             video_title = 'Facebook video #%s' % video_id

-        uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
+        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, fatal=False)

         timestamp = int_or_none(self._search_regex(
             r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
             'timestamp', default=None))
         timestamp = int_or_none(self._search_regex(
             r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
             'timestamp', default=None))

+        thumbnail = self._og_search_thumbnail(webpage)
+
+        view_count = parse_count(self._search_regex(
+            r'\bviewCount\s*:\s*["\']([\d,.]+)', webpage, 'view count',
+            default=None))

 
         info_dict = {
             'id': video_id,
 
         info_dict = {
             'id': video_id,


@@ -307,6 +440,8 @@ class FacebookIE(InfoExtractor):
             'formats': formats,
             'uploader': uploader,
             'timestamp': timestamp,
             'formats': formats,
             'uploader': uploader,
             'timestamp': timestamp,

+            'thumbnail': thumbnail,
+            'view_count': view_count,

         }
 
         return webpage, info_dict
         }
 
         return webpage, info_dict