Prepare to upload.

[youtubedl] / youtube_dl / extractor / facebook.py

diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index 8a9ed96c264ae37c5de2af472eca4c0ff1f4fa86..74954049dc79e6e9d0682a73550c52a4d010a06d 100644 (file)
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -20,6 +20,7 @@ from ..utils import (
     int_or_none,
     js_to_json,
     limit_length,
     int_or_none,
     js_to_json,
     limit_length,

+    parse_count,

     sanitized_Request,
     try_get,
     urlencode_postdata,
     sanitized_Request,
     try_get,
     urlencode_postdata,


@@ -56,7 +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'
+    _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',


@@ -75,7 +76,7 @@ class FacebookIE(InfoExtractor):
         'info_dict': {
             'id': '274175099429670',
             'ext': 'mp4',
         'info_dict': {
             'id': '274175099429670',
             'ext': 'mp4',

-            'title': 'Asif Nawab Butt posted a video to his Timeline.',
+            '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,


@@ -133,7 +134,7 @@ class FacebookIE(InfoExtractor):
     }, {
         # 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',


@@ -142,6 +143,7 @@ class FacebookIE(InfoExtractor):
             'upload_date': '20161030',
             'uploader': 'CNN',
             'thumbnail': r're:^https?://.*',
             'upload_date': '20161030',
             'uploader': 'CNN',
             'thumbnail': r're:^https?://.*',

+            'view_count': int,

         },
     }, {
         # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
         },
     }, {
         # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall


@@ -149,7 +151,7 @@ class FacebookIE(InfoExtractor):
         'info_dict': {
             'id': '1417995061575415',
             'ext': 'mp4',
         'info_dict': {
             'id': '1417995061575415',
             'ext': 'mp4',

-            'title': 'md5:a7b86ca673f51800cd54687b7f4012fe',
+            'title': 'md5:1db063d6a8c13faa8da727817339c857',

             'timestamp': 1486648217,
             'upload_date': '20170209',
             'uploader': 'Yaroslav Korpan',
             'timestamp': 1486648217,
             'upload_date': '20170209',
             'uploader': 'Yaroslav Korpan',


@@ -176,7 +178,7 @@ class FacebookIE(InfoExtractor):
         'info_dict': {
             'id': '1396382447100162',
             'ext': 'mp4',
         'info_dict': {
             'id': '1396382447100162',
             'ext': 'mp4',

-            'title': 'md5:e2d2700afdf84e121f5d0f999bad13a3',
+            'title': 'md5:19a428bbde91364e3de815383b54a235',

             'timestamp': 1486035494,
             'upload_date': '20170202',
             'uploader': 'Elisabeth Ahtn',
             'timestamp': 1486035494,
             'upload_date': '20170202',
             'uploader': 'Elisabeth Ahtn',


@@ -353,7 +355,6 @@ class FacebookIE(InfoExtractor):
             tahoe_data = self._download_webpage(
                 self._VIDEO_PAGE_TAHOE_TEMPLATE % video_id, video_id,
                 data=urlencode_postdata({
             tahoe_data = self._download_webpage(
                 self._VIDEO_PAGE_TAHOE_TEMPLATE % video_id, video_id,
                 data=urlencode_postdata({

-                    '__user': 0,

                     '__a': 1,
                     '__pc': self._search_regex(
                         r'pkg_cohort["\']\s*:\s*["\'](.+?)["\']', webpage,
                     '__a': 1,
                     '__pc': self._search_regex(
                         r'pkg_cohort["\']\s*:\s*["\'](.+?)["\']', webpage,


@@ -361,6 +362,9 @@ class FacebookIE(InfoExtractor):
                     '__rev': self._search_regex(
                         r'client_revision["\']\s*:\s*(\d+),', webpage,
                         'client revision', default='3944515'),
                     '__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',
                 }),
                 headers={
                     'Content-Type': 'application/x-www-form-urlencoded',


@@ -426,6 +430,10 @@ class FacebookIE(InfoExtractor):
             'timestamp', default=None))
         thumbnail = self._og_search_thumbnail(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,
             'title': video_title,
         info_dict = {
             'id': video_id,
             'title': video_title,


@@ -433,6 +441,7 @@ class FacebookIE(InfoExtractor):
             'uploader': uploader,
             'timestamp': timestamp,
             'thumbnail': thumbnail,
             'uploader': uploader,
             'timestamp': timestamp,
             'thumbnail': thumbnail,

+            'view_count': view_count,

         }
 
         return webpage, info_dict
         }
 
         return webpage, info_dict