From de691a498dd334ee5f8d237a4fc7ced314d86f44 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 25 Jan 2016 22:18:34 +0600 Subject: [PATCH] [facebook:post] Add extractor (Closes #8321) --- youtube_dl/extractor/__init__.py | 5 ++++- youtube_dl/extractor/facebook.py | 30 ++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 245e4d044..532be7e4c 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -196,7 +196,10 @@ from .exfm import ExfmIE from .expotv import ExpoTVIE from .extremetube import ExtremeTubeIE -from .facebook import FacebookIE +from .facebook import ( + FacebookIE, + FacebookPostIE, +) from .faz import FazIE from .fc2 import FC2IE from .fczenit import FczenitIE diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index f9fd8ed4e..cb5dd57fb 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -199,3 +199,33 @@ def _real_extract(self, url): 'formats': formats, 'uploader': uploader, } + + +class FacebookPostIE(InfoExtractor): + IE_NAME = 'facebook:post' + _VALID_URL = r'https?://(?:\w+\.)?facebook\.com/[^/]+/posts/(?P\d+)' + _TEST = { + 'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570', + 'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6', + 'info_dict': { + 'id': '544765982287235', + 'ext': 'mp4', + 'title': '"What are you doing running in the snow?"', + 'uploader': 'FailArmy', + } + } + + def _real_extract(self, url): + post_id = self._match_id(url) + + webpage = self._download_webpage(url, post_id) + + entries = [ + self.url_result('facebook:%s' % video_id, FacebookIE.ie_key()) + for video_id in self._parse_json( + self._search_regex( + r'(["\'])video_ids\1\s*:\s*(?P\[.+?\])', + webpage, 'video ids', group='ids'), + post_id)] + + return self.playlist_result(entries, post_id)