from __future__ import unicode_literals import json import re import socket from .common import InfoExtractor from ..utils import ( compat_http_client, compat_str, compat_urllib_error, compat_urllib_parse, compat_urllib_request, ExtractorError, ) class FacebookIE(InfoExtractor): """Information Extractor for Facebook""" _VALID_URL = r'''(?x) (?:https?://)?(?:\w+\.)?facebook\.com/ (?:[^#?]*\#!/)? (?:video/video\.php|photo\.php|video/embed)\?(?:.*?) (?:v|video_id)=(?P[0-9]+) (?:.*)''' _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1' _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1' _NETRC_MACHINE = 'facebook' IE_NAME = 'facebook' _TEST = { 'url': 'https://www.facebook.com/photo.php?v=120708114770723', 'md5': '48975a41ccc4b7a581abd68651c1a5a8', 'info_dict': { 'id': '120708114770723', 'ext': 'mp4', u"duration": 279, u"title": u"PEOPLE ARE AWESOME 2013" } } def report_login(self): """Report attempt to log in.""" self.to_screen('Logging in') def _login(self): (useremail, password) = self._get_login_info() if useremail is None: return login_page_req = compat_urllib_request.Request(self._LOGIN_URL) login_page_req.add_header('Cookie', 'locale=en_US') self.report_login() login_page = self._download_webpage(login_page_req, None, note=False, errnote='Unable to download login page') lsd = self._search_regex( r'', login_results) is not None: self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') return check_form = { 'fb_dtsg': self._search_regex(r'"fb_dtsg":"(.*?)"', login_results, 'fb_dtsg'), 'nh': self._search_regex(r'name="nh" value="(\w*?)"', login_results, 'nh'), 'name_action_selected': 'dont_save', 'submit[Continue]': self._search_regex(r'
(.*?)
', webpage) if m_msg is not None: raise ExtractorError( 'The video is not available, Facebook said: "%s"' % m_msg.group(1), expected=True) else: raise ExtractorError('Cannot parse data') data = dict(json.loads(m.group(1))) params_raw = compat_urllib_parse.unquote(data['params']) params = json.loads(params_raw) video_data = params['video_data'][0] video_url = video_data.get('hd_src') if not video_url: video_url = video_data['sd_src'] if not video_url: raise ExtractorError('Cannot find video URL') video_duration = int(video_data['video_duration']) thumbnail = video_data['thumbnail_src'] video_title = self._html_search_regex( r'

([^<]*)

', webpage, 'title') info = { 'id': video_id, 'title': video_title, 'url': video_url, 'ext': 'mp4', 'duration': video_duration, 'thumbnail': thumbnail, } return [info]